diff --git a/.github/workflows/build-and-test.yml b/.github/workflows/build-and-test.yml index f94a3123..8c9b1a1c 100644 --- a/.github/workflows/build-and-test.yml +++ b/.github/workflows/build-and-test.yml @@ -2,6 +2,9 @@ name: Compile the app and run tests on: push: + branches-ignore: + - main + - dev jobs: sanity-check: @@ -21,6 +24,9 @@ jobs: - name: Install dependencies run: python -m pip install --upgrade pip && python -m pip install -r requirements-dev.txt + - name: Lint with ruff + run: python -m ruff check --output-format=github . + - name: Build app run: python -m compileall api core database services scripts web_server.py wsgi.py beatport_unified_scraper.py diff --git a/.github/workflows/cleanup-dev-images.yml b/.github/workflows/cleanup-dev-images.yml new file mode 100644 index 00000000..19597992 --- /dev/null +++ b/.github/workflows/cleanup-dev-images.yml @@ -0,0 +1,24 @@ +name: Cleanup old dev images + +on: + schedule: + # Weekly on Sunday at 6 AM UTC + - cron: '0 6 * * 0' + workflow_dispatch: + +jobs: + cleanup: + runs-on: ubuntu-latest + permissions: + packages: write + + steps: + - name: Delete old dev image tags + uses: actions/delete-package-versions@v5 + with: + package-name: soulsync + package-type: container + min-versions-to-keep: 10 + delete-only-pre-release-versions: false + # Only prune tags matching the dev nightly pattern (keep rolling + version tags) + ignore-versions: '^(dev|nightly|latest|\\d+\\.\\d+)$' diff --git a/.github/workflows/dev-nightly.yml b/.github/workflows/dev-nightly.yml new file mode 100644 index 00000000..d5312d29 --- /dev/null +++ b/.github/workflows/dev-nightly.yml @@ -0,0 +1,103 @@ +name: Dev Nightly Build + +on: + # Nightly at 4:00 AM UTC ā€” only if dev branch has new commits + schedule: + - cron: '0 4 * * *' + # Also build on every push to dev for immediate feedback + push: + branches: + - dev + # Manual trigger for testing + workflow_dispatch: + +jobs: + nightly: + runs-on: ubuntu-latest + # Skip scheduled runs if dev branch has no new commits in the last 24h + # (pushes and manual triggers always run) + permissions: + contents: read + packages: write + + steps: + - name: Checkout dev branch + uses: actions/checkout@v6 + with: + ref: dev + + - name: Set lowercase owner + run: echo "OWNER=${GITHUB_REPOSITORY_OWNER,,}" >> "$GITHUB_ENV" + + - name: Check for recent commits (scheduled only) + if: github.event_name == 'schedule' + id: recent + run: | + LAST_COMMIT=$(git log -1 --format=%ct) + NOW=$(date +%s) + DIFF=$(( NOW - LAST_COMMIT )) + if [ "$DIFF" -gt 86400 ]; then + echo "No commits in the last 24h, skipping build" + echo "skip=true" >> "$GITHUB_OUTPUT" + else + echo "skip=false" >> "$GITHUB_OUTPUT" + fi + + - name: Set up Python + if: steps.recent.outputs.skip != 'true' + uses: actions/setup-python@v6 + with: + python-version: "3.11" + cache: pip + cache-dependency-path: requirements-dev.txt + + - name: Install dependencies and run tests + if: steps.recent.outputs.skip != 'true' + env: + PYTHONPATH: ${{ github.workspace }} + run: | + python -m pip install --upgrade pip + python -m pip install -r requirements-dev.txt + python -m ruff check --output-format=github . + python -m compileall api core database services scripts web_server.py wsgi.py beatport_unified_scraper.py + python -m pytest + + - name: Set up QEMU + if: steps.recent.outputs.skip != 'true' + uses: docker/setup-qemu-action@v4 + + - name: Set up Docker Buildx + if: steps.recent.outputs.skip != 'true' + uses: docker/setup-buildx-action@v4 + + - name: Log in to GHCR + if: steps.recent.outputs.skip != 'true' + uses: docker/login-action@v4 + with: + registry: ghcr.io + username: ${{ env.OWNER }} + password: ${{ secrets.GITHUB_TOKEN }} + + - name: Generate build tag + if: steps.recent.outputs.skip != 'true' + id: tag + run: | + echo "date=$(date -u +%Y%m%d)" >> "$GITHUB_OUTPUT" + echo "short_sha=${GITHUB_SHA::7}" >> "$GITHUB_OUTPUT" + + - name: Build and push to GHCR + if: steps.recent.outputs.skip != 'true' + uses: docker/build-push-action@v7 + with: + context: . + platforms: linux/amd64,linux/arm64 + push: true + pull: true + cache-from: type=gha + cache-to: type=gha,mode=max + build-args: | + COMMIT_SHA=${{ github.sha }} + tags: | + ghcr.io/${{ env.OWNER }}/soulsync:dev + ghcr.io/${{ env.OWNER }}/soulsync:dev-${{ steps.tag.outputs.date }}-${{ steps.tag.outputs.short_sha }} + ${{ github.event_name == 'schedule' && format('ghcr.io/{0}/soulsync:nightly', env.OWNER) || '' }} diff --git a/.github/workflows/docker-publish.yml b/.github/workflows/docker-publish.yml index f12467cf..b18d1b26 100644 --- a/.github/workflows/docker-publish.yml +++ b/.github/workflows/docker-publish.yml @@ -1,6 +1,11 @@ name: Build and Push Docker Image on: + # Auto-build :latest on every push to main + push: + branches: + - main + # Manual trigger for tagged releases (e.g. 2.33) workflow_dispatch: inputs: version_tag: @@ -12,10 +17,17 @@ jobs: build-and-push: runs-on: ubuntu-latest + permissions: + contents: read + packages: write + steps: - name: Checkout code uses: actions/checkout@v6 + - name: Set lowercase owner + run: echo "OWNER=${GITHUB_REPOSITORY_OWNER,,}" >> "$GITHUB_ENV" + - name: Set up QEMU uses: docker/setup-qemu-action@v4 @@ -28,22 +40,32 @@ jobs: username: ${{ secrets.DOCKERHUB_USERNAME }} password: ${{ secrets.DOCKERHUB_TOKEN }} + - name: Log in to GHCR + uses: docker/login-action@v4 + with: + registry: ghcr.io + username: ${{ env.OWNER }} + password: ${{ secrets.GITHUB_TOKEN }} + - name: Build and push uses: docker/build-push-action@v7 with: context: . platforms: linux/amd64,linux/arm64 push: true - no-cache: true pull: true + cache-from: type=gha + cache-to: type=gha,mode=max build-args: | COMMIT_SHA=${{ github.sha }} tags: | boulderbadgedad/soulsync:latest - boulderbadgedad/soulsync:${{ inputs.version_tag }} + ghcr.io/${{ env.OWNER }}/soulsync:latest + ${{ inputs.version_tag && format('boulderbadgedad/soulsync:{0}', inputs.version_tag) || '' }} + ${{ inputs.version_tag && format('ghcr.io/{0}/soulsync:{1}', env.OWNER, inputs.version_tag) || '' }} - name: Announce release to Discord - if: success() + if: success() && inputs.version_tag env: DISCORD_WEBHOOK: ${{ secrets.DISCORD_ANNOUNCEMENTS_WEBHOOK }} run: | diff --git a/.gitignore b/.gitignore index 59d00f35..8266b83b 100644 --- a/.gitignore +++ b/.gitignore @@ -25,3 +25,5 @@ bin/ # Development compose/config files *.dev.yml +# Any hidden folders +**/.*/ diff --git a/Support/README-Docker.md b/Support/README-Docker.md index d52a4205..77d0f2d8 100644 --- a/Support/README-Docker.md +++ b/Support/README-Docker.md @@ -63,6 +63,7 @@ environment: - FLASK_ENV=production # Flask environment - PYTHONPATH=/app # Python path - SOULSYNC_CONFIG_PATH=/app/config/config.json # Config file location + - SOULSYNC_LOG_LEVEL=INFO # Optional startup log level override, takes precedence over the UI-configured log level - TZ=America/New_York # Timezone ``` @@ -268,4 +269,4 @@ services: - [ ] Configure firewall rules - [ ] Set up backup strategy - [ ] Test health checks -- [ ] Verify external service connectivity \ No newline at end of file +- [ ] Verify external service connectivity diff --git a/api/playlists.py b/api/playlists.py index 75754e85..369ba72d 100644 --- a/api/playlists.py +++ b/api/playlists.py @@ -138,7 +138,7 @@ def register_routes(bp): try: # Forward to the internal sync endpoint import requests as http_requests - internal_url = f"http://127.0.0.1:8008/api/sync/start" + internal_url = "http://127.0.0.1:8008/api/sync/start" resp = http_requests.post(internal_url, json={ "playlist_id": playlist_id, "playlist_name": playlist_name, diff --git a/beatport_unified_scraper.py b/beatport_unified_scraper.py index eced8d24..67daf909 100644 --- a/beatport_unified_scraper.py +++ b/beatport_unified_scraper.py @@ -7,6 +7,8 @@ Focused on extracting clean artist and track names for virtual playlists import requests from bs4 import BeautifulSoup import json +import logging +import os import time import re from urllib.parse import urljoin @@ -14,6 +16,39 @@ from typing import Dict, List, Optional import concurrent.futures from threading import Lock +from utils.logging_config import get_logger + + +logger = get_logger("beatport_scraper") +_BEATPORT_LOGGING_ENABLED = os.environ.get("SOULSYNC_BEATPORT_SCRAPER_LOGS", "").lower() in ("1", "true", "yes", "on") +if _BEATPORT_LOGGING_ENABLED: + logger.setLevel(logging.DEBUG) +else: + logger.setLevel(logging.CRITICAL + 1) + +def _beatport_log(message: str): + """Route scraper output through logging when explicitly enabled.""" + if not _BEATPORT_LOGGING_ENABLED: + return + + text = str(message) + stripped = text.strip() + + if not stripped: + return + + lowered = stripped.lower() + level = logging.DEBUG + + if lowered.startswith("error") or " exception" in lowered or lowered.startswith("failed") or " failed" in lowered: + level = logging.ERROR + elif lowered.startswith("could not") or lowered.startswith("couldn't"): + level = logging.WARNING + elif lowered.startswith("no ") and "found" not in lowered: + level = logging.WARNING + + logger.log(level, text) + class BeatportUnifiedScraper: def __init__(self): self.base_url = "https://beatport.com" @@ -127,7 +162,7 @@ class BeatportUnifiedScraper: response.raise_for_status() return BeautifulSoup(response.content, 'html.parser') except requests.RequestException as e: - print(f"Error fetching {url}: {e}") + _beatport_log(f"Error fetching {url}: {e}") return None def clean_artist_track_data(self, raw_artist: str, raw_title: str) -> Dict[str, str]: @@ -171,12 +206,12 @@ class BeatportUnifiedScraper: def discover_genres_from_homepage(self) -> List[Dict]: """Dynamically discover all genres from Beatport homepage dropdown""" - print("Discovering genres from Beatport homepage...") + _beatport_log("Discovering genres from Beatport homepage...") try: soup = self.get_page(self.base_url) if not soup: - print("Could not fetch homepage") + _beatport_log("Could not fetch homepage") return self.fallback_genres genres = [] @@ -185,14 +220,14 @@ class BeatportUnifiedScraper: genres_dropdown = soup.find('div', {'id': 'genres-dropdown-menu'}) if genres_dropdown: - print("Found genres-dropdown-menu") + _beatport_log("Found genres-dropdown-menu") # Look for the two main div containers as described genre_containers = genres_dropdown.find_all('div', recursive=False) - print(f"Found {len(genre_containers)} top-level containers in dropdown") + _beatport_log(f"Found {len(genre_containers)} top-level containers in dropdown") for container_idx, container in enumerate(genre_containers): - print(f"Processing container {container_idx + 1}") + _beatport_log(f"Processing container {container_idx + 1}") # Look specifically for .dropdown_menu classes dropdown_menus = container.find_all(class_='dropdown_menu') @@ -202,17 +237,17 @@ class BeatportUnifiedScraper: dropdown_menus = container.find_all(class_=re.compile(r'dropdown.*menu', re.I)) if not dropdown_menus: - print(f"No .dropdown_menu found in container {container_idx + 1}") + _beatport_log(f"No .dropdown_menu found in container {container_idx + 1}") continue for menu_idx, menu in enumerate(dropdown_menus): - print(f"Processing dropdown_menu {menu_idx + 1} in container {container_idx + 1}") + _beatport_log(f"Processing dropdown_menu {menu_idx + 1} in container {container_idx + 1}") # Look for
  • elements first, then elements within them list_items = menu.find_all('li') if list_items: - print(f"Found {len(list_items)} list items in menu") + _beatport_log(f"Found {len(list_items)} list items in menu") for li in list_items: # Find anchor tag within the list item @@ -239,16 +274,16 @@ class BeatportUnifiedScraper: 'id': genre_id, 'url': urljoin(self.base_url, href) }) - print(f" Added: {name} ({slug}/{genre_id})") + _beatport_log(f" Added: {name} ({slug}/{genre_id})") else: - print(f" Filtered out: '{name}' (appears to be a section title)") + _beatport_log(f" Filtered out: '{name}' (appears to be a section title)") else: # Fallback: try the old method if no
  • elements found - print(f"No
  • elements found, trying direct search...") + _beatport_log("No
  • elements found, trying direct search...") genre_links = menu.find_all('a', href=re.compile(r'/genre/[^/]+/\d+')) if genre_links: - print(f"Found {len(genre_links)} genre links in menu (fallback method)") + _beatport_log(f"Found {len(genre_links)} genre links in menu (fallback method)") for link in genre_links: href = link.get('href', '') name_text = link.get_text(strip=True) @@ -266,16 +301,16 @@ class BeatportUnifiedScraper: 'id': genre_id, 'url': urljoin(self.base_url, href) }) - print(f" Added: {name} ({slug}/{genre_id})") + _beatport_log(f" Added: {name} ({slug}/{genre_id})") else: - print(f"No genre links found in dropdown_menu {menu_idx + 1}") + _beatport_log(f"No genre links found in dropdown_menu {menu_idx + 1}") if genres: - print(f"Successfully extracted {len(genres)} genres from dropdown menu") + _beatport_log(f"Successfully extracted {len(genres)} genres from dropdown menu") else: - print("No genre links found in dropdown menu structure") + _beatport_log("No genre links found in dropdown menu structure") else: - print("Could not find genres-dropdown-menu, trying fallback methods...") + _beatport_log("Could not find genres-dropdown-menu, trying fallback methods...") # Fallback: Look for other potential dropdown structures potential_dropdowns = [ @@ -289,11 +324,11 @@ class BeatportUnifiedScraper: for dropdown in potential_dropdowns: if dropdown: - print(f"Found fallback dropdown: {dropdown.name} with class {dropdown.get('class')}") + _beatport_log(f"Found fallback dropdown: {dropdown.name} with class {dropdown.get('class')}") genre_links = dropdown.find_all('a', href=re.compile(r'/genre/[^/]+/\d+')) if genre_links: - print(f"Found {len(genre_links)} genre links in fallback dropdown") + _beatport_log(f"Found {len(genre_links)} genre links in fallback dropdown") for link in genre_links: href = link.get('href', '') name_text = link.get_text(strip=True) @@ -313,14 +348,14 @@ class BeatportUnifiedScraper: }) if genres: - print(f"Successfully extracted {len(genres)} genres from fallback dropdown") + _beatport_log(f"Successfully extracted {len(genres)} genres from fallback dropdown") break # Method 2: Look for any genre links on the page if not genres: - print("Dropdown not found, searching for genre links...") + _beatport_log("Dropdown not found, searching for genre links...") all_genre_links = soup.find_all('a', href=re.compile(r'/genre/[^/]+/\d+')) - print(f"Found {len(all_genre_links)} potential genre links on page") + _beatport_log(f"Found {len(all_genre_links)} potential genre links on page") seen_genres = set() for link in all_genre_links: @@ -343,18 +378,18 @@ class BeatportUnifiedScraper: # Method 3: Try to find a genres page link and scrape from there if not genres: - print("Searching for genres page...") + _beatport_log("Searching for genres page...") genres_page_link = soup.find('a', href=re.compile(r'/genres$')) or \ soup.find('a', href=re.compile(r'/browse.*genre', re.I)) if genres_page_link: genres_page_url = urljoin(self.base_url, genres_page_link['href']) - print(f"Found genres page: {genres_page_url}") + _beatport_log(f"Found genres page: {genres_page_url}") genres_soup = self.get_page(genres_page_url) if genres_soup: genre_links = genres_soup.find_all('a', href=re.compile(r'/genre/[^/]+/\d+')) - print(f"Found {len(genre_links)} genre links on genres page") + _beatport_log(f"Found {len(genre_links)} genre links on genres page") seen_genres = set() for link in genre_links: @@ -386,19 +421,19 @@ class BeatportUnifiedScraper: final_genres = list(unique_genres.values()) final_genres.sort(key=lambda x: x['name']) - print(f"Discovered {len(final_genres)} unique genres from homepage") + _beatport_log(f"Discovered {len(final_genres)} unique genres from homepage") return final_genres else: - print("No genres found, using fallback list") + _beatport_log("No genres found, using fallback list") return self.fallback_genres except Exception as e: - print(f"Error discovering genres: {e}") + _beatport_log(f"Error discovering genres: {e}") return self.fallback_genres def discover_chart_sections(self) -> Dict[str, List[Dict]]: """Dynamically discover chart sections from homepage""" - print("Discovering chart sections from Beatport homepage...") + _beatport_log("Discovering chart sections from Beatport homepage...") soup = self.get_page(self.base_url) if not soup: @@ -411,7 +446,7 @@ class BeatportUnifiedScraper: } # Method 1: Find H2 section headings - print(" Finding H2 section headings...") + _beatport_log(" Finding H2 section headings...") h2_headings = soup.find_all('h2') for heading in h2_headings: @@ -426,10 +461,10 @@ class BeatportUnifiedScraper: # Categorize into our three main groups category = self._categorize_chart_section(text) chart_sections[category].append(section_info) - print(f" Found: '{text}' -> {category}") + _beatport_log(f" Found: '{text}' -> {category}") # Method 2: Find specific chart links - print(" Finding chart page links...") + _beatport_log(" Finding chart page links...") chart_links = [] # Look for the specific links we discovered @@ -450,14 +485,14 @@ class BeatportUnifiedScraper: 'expected': link_info['expected_href'], 'matches_expected': href == link_info['expected_href'] }) - print(f" Found: '{link.get_text(strip=True)}' -> {href}") + _beatport_log(f" Found: '{link.get_text(strip=True)}' -> {href}") # Method 3: Count individual DJ charts - print(" Counting individual DJ charts...") + _beatport_log(" Counting individual DJ charts...") dj_chart_links = soup.find_all('a', href=re.compile(r'/chart/')) individual_dj_charts = [] - for i, chart_link in enumerate(dj_chart_links[:10]): # Show first 10 + for _i, chart_link in enumerate(dj_chart_links[:10]): # Show first 10 href = chart_link.get('href', '') text = chart_link.get_text(strip=True) if text and href: @@ -467,7 +502,7 @@ class BeatportUnifiedScraper: 'full_url': urljoin(self.base_url, href) }) - print(f" Found {len(dj_chart_links)} individual DJ charts") + _beatport_log(f" Found {len(dj_chart_links)} individual DJ charts") return { 'sections': chart_sections, @@ -529,20 +564,20 @@ class BeatportUnifiedScraper: for img in artwork_imgs: src = img.get('src', '') if 'geo-media' in src and ('1050x508' in src or '500x500' in src): - print(f" Found high-quality artwork image: {src}") + _beatport_log(f" Found high-quality artwork image: {src}") return src # Second, try any geo-media images in artwork containers for img in artwork_imgs: src = img.get('src', '') if 'geo-media' in src: - print(f" Found geo-media artwork image: {src}") + _beatport_log(f" Found geo-media artwork image: {src}") return src # Third, use any artwork image as fallback first_artwork_src = artwork_imgs[0].get('src', '') if first_artwork_src: - print(f" Found artwork image (fallback): {first_artwork_src}") + _beatport_log(f" Found artwork image (fallback): {first_artwork_src}") return first_artwork_src # Priority 2: Original method - Look for hero release slideshow images @@ -553,19 +588,19 @@ class BeatportUnifiedScraper: for img in hero_images: src = img.get('src', '') if '1050x508' in src or '500x500' in src: - print(f" Found high-quality hero image: {src}") + _beatport_log(f" Found high-quality hero image: {src}") return src # Fallback to any geo-media image fallback_src = hero_images[0].get('src', '') - print(f" Found hero image (fallback): {fallback_src}") + _beatport_log(f" Found hero image (fallback): {fallback_src}") return fallback_src - print(f" No suitable images found on page") + _beatport_log(" No suitable images found on page") return None except Exception as e: - print(f"Could not get image for {genre_url}: {e}") + _beatport_log(f"Could not get image for {genre_url}: {e}") return None def discover_genres_with_images(self, include_images: bool = False) -> List[Dict]: @@ -573,16 +608,16 @@ class BeatportUnifiedScraper: genres = self.discover_genres_from_homepage() if include_images: - print("Fetching genre images...") + _beatport_log("Fetching genre images...") for i, genre in enumerate(genres[:10]): # Limit to first 10 for demo - print(f"Getting image for {genre['name']} ({i+1}/{min(10, len(genres))})") + _beatport_log(f"Getting image for {genre['name']} ({i+1}/{min(10, len(genres))})") # Check if genre has URL if 'url' in genre and genre['url']: image_url = self.get_genre_image(genre['url']) genre['image_url'] = image_url else: - print(f" No URL available for {genre['name']}, skipping image") + _beatport_log(f" No URL available for {genre['name']}, skipping image") genre['image_url'] = None # Small delay to be respectful @@ -649,7 +684,7 @@ class BeatportUnifiedScraper: } except Exception as e: - print(f"Error extracting release data: {e}") + _beatport_log(f"Error extracting release data: {e}") return None def extract_chart_data_from_card(self, chart_card) -> Optional[Dict]: @@ -695,7 +730,7 @@ class BeatportUnifiedScraper: } except Exception as e: - print(f"Error extracting chart data: {e}") + _beatport_log(f"Error extracting chart data: {e}") return None def extract_tracks_from_page(self, soup: BeautifulSoup, list_name: str, limit: int = 100) -> List[Dict]: @@ -708,9 +743,9 @@ class BeatportUnifiedScraper: # Find all track links on the page track_links = soup.find_all('a', href=re.compile(r'/track/')) - print(f" Found {len(track_links)} track links on {list_name}") + _beatport_log(f" Found {len(track_links)} track links on {list_name}") - for i, link in enumerate(track_links[:limit]): + for _i, link in enumerate(track_links[:limit]): if len(tracks) >= limit: break @@ -725,7 +760,7 @@ class BeatportUnifiedScraper: # Method 1: Look for common artist element patterns parent = link.parent - for level in range(5): # Check up to 5 parent levels + for _level in range(5): # Check up to 5 parent levels if parent: # Try multiple artist class patterns that Beatport commonly uses artist_selectors = [ @@ -800,7 +835,7 @@ class BeatportUnifiedScraper: def scrape_top_100(self, limit: int = 100, enrich: bool = True) -> List[Dict]: """Scrape Beatport Top 100""" - print("\nScraping Beatport Top 100...") + _beatport_log("\nScraping Beatport Top 100...") soup = self.get_page(f"{self.base_url}/top-100") tracks = self.extract_tracks_from_page(soup, "Top 100", limit) @@ -809,12 +844,12 @@ class BeatportUnifiedScraper: if tracks and enrich: tracks = self.enrich_chart_tracks(tracks) - print(f"Extracted {len(tracks)} tracks from Top 100") + _beatport_log(f"Extracted {len(tracks)} tracks from Top 100") return tracks def scrape_new_releases(self, limit: int = 40) -> List[Dict]: """Scrape individual tracks from Beatport New Releases using JSON extraction - ENHANCED""" - print("\nšŸ†• Scraping Beatport New Releases (individual tracks)...") + _beatport_log("\nšŸ†• Scraping Beatport New Releases (individual tracks)...") # Step 1: Get release URLs from homepage cards release_urls = self.extract_new_releases_urls(limit) @@ -824,7 +859,7 @@ class BeatportUnifiedScraper: # Step 2: Extract individual tracks from each release all_tracks = [] for i, release_url in enumerate(release_urls): - print(f"\nProcessing release {i+1}/{len(release_urls)}") + _beatport_log(f"\nProcessing release {i+1}/{len(release_urls)}") tracks = self.extract_tracks_from_release_json(release_url) if tracks: all_tracks.extend(tracks) @@ -833,7 +868,7 @@ class BeatportUnifiedScraper: import time time.sleep(0.5) - print(f"Extracted {len(all_tracks)} individual tracks from {len(release_urls)} releases") + _beatport_log(f"Extracted {len(all_tracks)} individual tracks from {len(release_urls)} releases") return all_tracks def extract_new_releases_urls(self, limit: int) -> List[str]: @@ -844,7 +879,7 @@ class BeatportUnifiedScraper: # Find New Releases section using data-testid release_cards = soup.select('[data-testid="new-releases"]') - print(f" Found {len(release_cards)} release cards in New Releases section") + _beatport_log(f" Found {len(release_cards)} release cards in New Releases section") release_urls = [] for i, card in enumerate(release_cards[:limit]): @@ -860,13 +895,13 @@ class BeatportUnifiedScraper: if href.startswith('/'): href = self.base_url + href release_urls.append(href) - print(f" {i+1}. Found release URL: {href}") + _beatport_log(f" {i+1}. Found release URL: {href}") return release_urls def extract_tracks_from_release_json(self, release_url: str) -> List[Dict]: """Extract individual tracks from a release page using JSON data""" - print(f"Extracting tracks from: {release_url}") + _beatport_log(f"Extracting tracks from: {release_url}") soup = self.get_page(release_url) if not soup: @@ -875,23 +910,23 @@ class BeatportUnifiedScraper: # Extract JSON object from page json_obj = self.extract_json_object_from_release_page(soup) if not json_obj: - print(" No JSON data found") + _beatport_log(" No JSON data found") return [] # Filter tracks for this specific release release_tracks = self.filter_tracks_for_specific_release(json_obj, release_url) if not release_tracks: - print(" No matching tracks found") + _beatport_log(" No matching tracks found") return [] # Convert to our standard format converted_tracks = [] - for i, track_data in enumerate(release_tracks): + for _i, track_data in enumerate(release_tracks): track = self.convert_release_json_to_track_format(track_data, release_url, len(converted_tracks) + 1) if track: converted_tracks.append(track) - print(f" Extracted {len(converted_tracks)} tracks") + _beatport_log(f" Extracted {len(converted_tracks)} tracks") return converted_tracks def extract_json_object_from_release_page(self, soup): @@ -930,7 +965,7 @@ class BeatportUnifiedScraper: converted.append(track) if len(converted) >= 5: - print(f" JSON extraction found {len(converted)} tracks with rich metadata") + _beatport_log(f" JSON extraction found {len(converted)} tracks with rich metadata") return converted return [] @@ -954,12 +989,12 @@ class BeatportUnifiedScraper: if results and isinstance(results, list) and len(results) > 0: first = results[0] if isinstance(results[0], dict) else {} if first.get('title') or first.get('name'): - print(f" Found {len(results)} tracks in queries[{idx}].data.results") + _beatport_log(f" Found {len(results)} tracks in queries[{idx}].data.results") return results # Pattern 2: data itself is a single track object (track pages) if isinstance(data, dict) and (data.get('title') or data.get('name')) and data.get('id'): - print(f" Found single track in queries[{idx}].data") + _beatport_log(f" Found single track in queries[{idx}].data") return [data] # Pattern 3: data.tracks[] @@ -968,11 +1003,11 @@ class BeatportUnifiedScraper: if tracks and isinstance(tracks, list) and len(tracks) > 0: first = tracks[0] if isinstance(tracks[0], dict) else {} if first.get('title') or first.get('name'): - print(f" Found {len(tracks)} tracks in queries[{idx}].data.tracks") + _beatport_log(f" Found {len(tracks)} tracks in queries[{idx}].data.tracks") return tracks except Exception as e: - print(f" Error extracting tracks from JSON: {e}") + _beatport_log(f" Error extracting tracks from JSON: {e}") return [] @@ -1065,7 +1100,7 @@ class BeatportUnifiedScraper: return track except Exception as e: - print(f" Error converting chart JSON track: {e}") + _beatport_log(f" Error converting chart JSON track: {e}") return None def enrich_chart_tracks(self, tracks: List[Dict], progress_callback=None) -> List[Dict]: @@ -1080,7 +1115,7 @@ class BeatportUnifiedScraper: enriched = [] total = len(tracks) - print(f" Enriching {total} chart tracks with per-track metadata...") + _beatport_log(f" Enriching {total} chart tracks with per-track metadata...") for i, track in enumerate(tracks): track_url = track.get('url', '') @@ -1113,14 +1148,14 @@ class BeatportUnifiedScraper: if not matched and json_tracks: # Debug: show what IDs we have vs what we're looking for sample_ids = [str(jt.get('id', '')) for jt in json_tracks[:5]] - print(f" [{i+1}] No ID match for '{track_id_from_url}' in {sample_ids}... trying title match") + _beatport_log(f" [{i+1}] No ID match for '{track_id_from_url}' in {sample_ids}... trying title match") # Fallback: match by title similarity track_title = track.get('title', '').lower().strip() for jt in json_tracks: jt_title = (jt.get('title') or jt.get('name', '')).lower().strip() if track_title and jt_title and (track_title in jt_title or jt_title in track_title): matched = jt - print(f" [{i+1}] Title matched: '{jt_title}'") + _beatport_log(f" [{i+1}] Title matched: '{jt_title}'") break # Fallback: use first track if only one result @@ -1132,14 +1167,14 @@ class BeatportUnifiedScraper: if rich: enriched.append(rich) if (i + 1) <= 3 or (i + 1) % 25 == 0: - print(f" [{i+1}/{total}] {rich.get('artist', '?')} - {rich.get('title', '?')} | {rich.get('release_name', 'no release')}") + _beatport_log(f" [{i+1}/{total}] {rich.get('artist', '?')} - {rich.get('title', '?')} | {rich.get('release_name', 'no release')}") else: enriched.append(track) else: enriched.append(track) except Exception as e: - print(f" [{i+1}/{total}] Error enriching track: {e}") + _beatport_log(f" [{i+1}/{total}] Error enriching track: {e}") enriched.append(track) # Report progress (always runs ā€” success, failure, or exception) @@ -1152,7 +1187,7 @@ class BeatportUnifiedScraper: time.sleep(0.3) enriched_count = sum(1 for t in enriched if t.get('release_name')) - print(f" Enrichment complete: {enriched_count}/{total} tracks have release metadata") + _beatport_log(f" Enrichment complete: {enriched_count}/{total} tracks have release metadata") return enriched def filter_tracks_for_specific_release(self, json_obj: Dict, release_url: str) -> List[Dict]: @@ -1182,7 +1217,7 @@ class BeatportUnifiedScraper: return matching_tracks except Exception as e: - print(f" Error filtering tracks: {e}") + _beatport_log(f" Error filtering tracks: {e}") return [] @@ -1246,7 +1281,7 @@ class BeatportUnifiedScraper: return track except Exception as e: - print(f" Error converting track data: {e}") + _beatport_log(f" Error converting track data: {e}") return None def get_release_metadata(self, release_url: str) -> Dict: @@ -1402,7 +1437,7 @@ class BeatportUnifiedScraper: } except Exception as e: - print(f"Error getting release metadata from {release_url}: {e}") + _beatport_log(f"Error getting release metadata from {release_url}: {e}") import traceback traceback.print_exc() return {'success': False, 'error': str(e)} @@ -1436,7 +1471,7 @@ class BeatportUnifiedScraper: return tracks except Exception as e: - print(f" Error extracting tracks from {release_url}: {e}") + _beatport_log(f" Error extracting tracks from {release_url}: {e}") return [] def scrape_multiple_releases(self, release_urls, source_name: str = "General Release Scraper") -> List[Dict]: @@ -1456,65 +1491,65 @@ class BeatportUnifiedScraper: # Validate input if not release_urls or len(release_urls) == 0: - print("No release URLs provided") + _beatport_log("No release URLs provided") return [] - print(f"\nSCRAPING {len(release_urls)} RELEASE URL{'S' if len(release_urls) > 1 else ''}") - print("=" * 60) + _beatport_log(f"\nSCRAPING {len(release_urls)} RELEASE URL{'S' if len(release_urls) > 1 else ''}") + _beatport_log("=" * 60) all_tracks = [] for i, release_url in enumerate(release_urls, 1): - print(f"\nProcessing release {i}/{len(release_urls)}: {release_url}") + _beatport_log(f"\nProcessing release {i}/{len(release_urls)}: {release_url}") try: tracks = self.extract_individual_tracks_from_release_url(release_url, source_name) if tracks: all_tracks.extend(tracks) - print(f" Found {len(tracks)} tracks") + _beatport_log(f" Found {len(tracks)} tracks") # Show first few tracks for verification for j, track in enumerate(tracks[:3], 1): title = track.get('title', 'Unknown') artist = track.get('artist', 'Unknown') label = track.get('label', 'Unknown') - print(f" Track {j}: '{title}' by '{artist}' [{label}]") + _beatport_log(f" Track {j}: '{title}' by '{artist}' [{label}]") if len(tracks) > 3: - print(f" ... and {len(tracks) - 3} more tracks") + _beatport_log(f" ... and {len(tracks) - 3} more tracks") else: - print(f" No tracks found") + _beatport_log(" No tracks found") except Exception as e: - print(f" Error processing release: {e}") + _beatport_log(f" Error processing release: {e}") continue # Small delay between requests to be respectful if i < len(release_urls): time.sleep(0.5) - print(f"\n" + "=" * 60) - print(f"SCRAPING COMPLETE") - print(f" Total releases processed: {len(release_urls)}") - print(f" Total tracks extracted: {len(all_tracks)}") + _beatport_log("\n" + "=" * 60) + _beatport_log("SCRAPING COMPLETE") + _beatport_log(f" Total releases processed: {len(release_urls)}") + _beatport_log(f" Total tracks extracted: {len(all_tracks)}") return all_tracks def scrape_hype_top_100(self, limit: int = 100, enrich: bool = True) -> List[Dict]: """Scrape Beatport Hype Top 100 - Fixed URL based on parser discovery""" - print("\nScraping Beatport Hype Top 100...") + _beatport_log("\nScraping Beatport Hype Top 100...") # Use the correct URL discovered by parser soup = self.get_page(f"{self.base_url}/hype-100") if soup: tracks = self.extract_tracks_from_page(soup, "Hype Top 100", limit) if tracks and enrich: - print(f" Enriching {len(tracks)} Hype Top 100 tracks with per-track metadata...") + _beatport_log(f" Enriching {len(tracks)} Hype Top 100 tracks with per-track metadata...") tracks = self.enrich_chart_tracks(tracks) - print(f"Extracted {len(tracks)} tracks from Hype Top 100") + _beatport_log(f"Extracted {len(tracks)} tracks from Hype Top 100") return tracks else: - print("Could not access /hype-100, trying homepage Hype Picks section...") + _beatport_log("Could not access /hype-100, trying homepage Hype Picks section...") # Fallback to homepage section soup = self.get_page(self.base_url) if soup: @@ -1534,7 +1569,7 @@ class BeatportUnifiedScraper: else: tracks = [] - print(f"Extracted {len(tracks)} tracks from Hype Top 100 (fallback)") + _beatport_log(f"Extracted {len(tracks)} tracks from Hype Top 100 (fallback)") return tracks def extract_releases_from_page(self, soup: BeautifulSoup, list_name: str, limit: int = 100) -> List[Dict]: @@ -1546,7 +1581,7 @@ class BeatportUnifiedScraper: # Find table rows - each track/release is in a table row table_rows = soup.find_all('div', class_=re.compile(r'Table-style__TableRow')) - print(f" Found {len(table_rows)} table rows on {list_name}") + _beatport_log(f" Found {len(table_rows)} table rows on {list_name}") for i, row in enumerate(table_rows[:limit]): if len(releases) >= limit: @@ -1557,13 +1592,13 @@ class BeatportUnifiedScraper: title_element = row.find('span', class_=re.compile(r'Tables-shared-style__ReleaseName')) if not title_element: if len(releases) < 5: - print(f" Row {i+1}: No release title found") + _beatport_log(f" Row {i+1}: No release title found") continue release_title = title_element.get_text(strip=True) if not release_title: if len(releases) < 5: - print(f" Row {i+1}: Empty release title") + _beatport_log(f" Row {i+1}: Empty release title") continue # Find the release URL from the title link @@ -1601,23 +1636,23 @@ class BeatportUnifiedScraper: # Debug print for first few items if len(releases) <= 5: - print(f" Release {len(releases)}: '{release_title}' by '{artist_text}' (found {len(artists)} artists)") + _beatport_log(f" Release {len(releases)}: '{release_title}' by '{artist_text}' (found {len(artists)} artists)") except Exception as e: - print(f" Error extracting row {i+1}: {e}") + _beatport_log(f" Error extracting row {i+1}: {e}") continue - print(f" Successfully extracted {len(releases)} releases from {len(table_rows)} rows") + _beatport_log(f" Successfully extracted {len(releases)} releases from {len(table_rows)} rows") return releases def scrape_top_100_releases(self, limit: int = 100) -> List[Dict]: """Scrape Beatport Top 100 Releases - Extract individual tracks using URL crawling""" - print("\nScraping Beatport Top 100 Releases...") + _beatport_log("\nScraping Beatport Top 100 Releases...") # Step 1: Extract release URLs from Top 100 page soup = self.get_page(f"{self.base_url}/top-100-releases") if not soup: - print(" Could not access /top-100-releases page") + _beatport_log(" Could not access /top-100-releases page") return [] # Look for rows with release links (Top 100 uses [class*="row"] elements, not tables) @@ -1626,7 +1661,7 @@ class BeatportUnifiedScraper: # Top 100 page uses row-based layout, not table structure table_rows = soup.select('[class*="row"]') - print(f" Found {len(table_rows)} rows on Top 100 page") + _beatport_log(f" Found {len(table_rows)} rows on Top 100 page") release_urls = [] urls_found = 0 @@ -1638,39 +1673,39 @@ class BeatportUnifiedScraper: release_url = urljoin(self.base_url, link_elem.get('href')) release_urls.append(release_url) urls_found += 1 - print(f" {urls_found}. Found Top 100 release URL: {release_url}") + _beatport_log(f" {urls_found}. Found Top 100 release URL: {release_url}") # Stop when we've found enough URLs if urls_found >= limit: break if not release_urls: - print(" No Top 100 release URLs found") + _beatport_log(" No Top 100 release URLs found") return [] # Step 2: Crawl each release URL to extract individual tracks all_individual_tracks = [] for i, release_url in enumerate(release_urls): - print(f" Processing Top 100 release {i+1}/{len(release_urls)}: {release_url}") + _beatport_log(f" Processing Top 100 release {i+1}/{len(release_urls)}: {release_url}") # Extract individual tracks from this release tracks = self.extract_individual_tracks_from_release_url(release_url, "Top 100 Releases") if tracks: - print(f" Found {len(tracks)} individual tracks") + _beatport_log(f" Found {len(tracks)} individual tracks") all_individual_tracks.extend(tracks) else: - print(f" No tracks found") + _beatport_log(f" No tracks found") # Add delay between requests to be respectful if i < len(release_urls) - 1: time.sleep(0.5) - print(f"Extracted {len(all_individual_tracks)} individual tracks from {len(release_urls)} Top 100 releases") + _beatport_log(f"Extracted {len(all_individual_tracks)} individual tracks from {len(release_urls)} Top 100 releases") return all_individual_tracks def scrape_dj_charts(self, limit: int = 20) -> List[Dict]: """Scrape Beatport DJ Charts from homepage section - Improved reliability""" - print("\nScraping Beatport DJ Charts...") + _beatport_log("\nScraping Beatport DJ Charts...") soup = self.get_page(self.base_url) if not soup: @@ -1681,7 +1716,7 @@ class BeatportUnifiedScraper: # Method 1: Find DJ Charts H2 section on homepage dj_charts_heading = soup.find(['h1', 'h2', 'h3'], string=re.compile(r'DJ Charts', re.I)) if dj_charts_heading: - print(" Found DJ Charts section heading") + _beatport_log(" Found DJ Charts section heading") # Get the section content after the heading section_container = dj_charts_heading.find_parent() if section_container: @@ -1689,7 +1724,7 @@ class BeatportUnifiedScraper: if content_area: # Look for individual chart links within this section chart_links = content_area.find_all('a', href=re.compile(r'/chart/')) - print(f" Found {len(chart_links)} individual DJ chart links") + _beatport_log(f" Found {len(chart_links)} individual DJ chart links") for chart_link in chart_links[:limit]: chart_name = chart_link.get_text(strip=True) @@ -1710,9 +1745,9 @@ class BeatportUnifiedScraper: # Method 2: If no section found, look for chart links across entire homepage if not charts: - print(" DJ Charts section not found, scanning entire homepage...") + _beatport_log(" DJ Charts section not found, scanning entire homepage...") all_chart_links = soup.find_all('a', href=re.compile(r'/chart/')) - print(f" Found {len(all_chart_links)} total chart links on homepage") + _beatport_log(f" Found {len(all_chart_links)} total chart links on homepage") for chart_link in all_chart_links[:limit]: chart_name = chart_link.get_text(strip=True) @@ -1730,12 +1765,12 @@ class BeatportUnifiedScraper: } charts.append(chart_info) - print(f"Extracted {len(charts)} DJ charts") + _beatport_log(f"Extracted {len(charts)} DJ charts") return charts def scrape_featured_charts(self, limit: int = 20) -> List[Dict]: """Scrape Beatport Featured Charts from homepage section - FIXED""" - print("\nScraping Beatport Featured Charts...") + _beatport_log("\nScraping Beatport Featured Charts...") soup = self.get_page(self.base_url) if not soup: @@ -1743,7 +1778,7 @@ class BeatportUnifiedScraper: # Find Featured Charts section using data-testid chart_cards = soup.select('[data-testid="featured-charts"]') - print(f" Found {len(chart_cards)} chart cards in Featured Charts section") + _beatport_log(f" Found {len(chart_cards)} chart cards in Featured Charts section") charts = [] for i, card in enumerate(chart_cards[:limit]): @@ -1765,12 +1800,12 @@ class BeatportUnifiedScraper: } charts.append(track_data) - print(f"Extracted {len(charts)} charts from Featured Charts") + _beatport_log(f"Extracted {len(charts)} charts from Featured Charts") return charts def scrape_hype_picks_homepage(self, limit: int = 40) -> List[Dict]: """Scrape individual tracks from Beatport Hype Picks using JSON extraction - ENHANCED""" - print("\nScraping Beatport Hype Picks (individual tracks)...") + _beatport_log("\nScraping Beatport Hype Picks (individual tracks)...") # Step 1: Get release URLs from homepage cards release_urls = self.extract_hype_picks_urls(limit) @@ -1780,7 +1815,7 @@ class BeatportUnifiedScraper: # Step 2: Extract individual tracks from each release all_tracks = [] for i, release_url in enumerate(release_urls): - print(f"\nProcessing release {i+1}/{len(release_urls)}") + _beatport_log(f"\nProcessing release {i+1}/{len(release_urls)}") tracks = self.extract_tracks_from_hype_picks_release_json(release_url) if tracks: all_tracks.extend(tracks) @@ -1789,7 +1824,7 @@ class BeatportUnifiedScraper: import time time.sleep(0.5) - print(f"Extracted {len(all_tracks)} individual tracks from {len(release_urls)} hype picks releases") + _beatport_log(f"Extracted {len(all_tracks)} individual tracks from {len(release_urls)} hype picks releases") return all_tracks def extract_hype_picks_urls(self, limit: int) -> List[str]: @@ -1800,7 +1835,7 @@ class BeatportUnifiedScraper: # Find Hype Picks section using data-testid hype_cards = soup.select('[data-testid="hype-picks"]') - print(f" Found {len(hype_cards)} hype picks cards in section") + _beatport_log(f" Found {len(hype_cards)} hype picks cards in section") release_urls = [] for i, card in enumerate(hype_cards[:limit]): @@ -1816,13 +1851,13 @@ class BeatportUnifiedScraper: if href.startswith('/'): href = self.base_url + href release_urls.append(href) - print(f" {i+1}. Found release URL: {href}") + _beatport_log(f" {i+1}. Found release URL: {href}") return release_urls def extract_tracks_from_hype_picks_release_json(self, release_url: str) -> List[Dict]: """Extract individual tracks from a hype picks release page using JSON data""" - print(f"Extracting tracks from: {release_url}") + _beatport_log(f"Extracting tracks from: {release_url}") soup = self.get_page(release_url) if not soup: @@ -1831,13 +1866,13 @@ class BeatportUnifiedScraper: # Extract JSON object from page (same method as New Releases) json_obj = self.extract_json_object_from_release_page(soup) if not json_obj: - print(" No JSON data found") + _beatport_log(" No JSON data found") return [] # Filter tracks for this specific release (same method as New Releases) release_tracks = self.filter_tracks_for_specific_release(json_obj, release_url) if not release_tracks: - print(" No matching tracks found") + _beatport_log(" No matching tracks found") return [] # Convert to our standard format (with Hype Picks branding) @@ -1847,7 +1882,7 @@ class BeatportUnifiedScraper: if track: converted_tracks.append(track) - print(f" Extracted {len(converted_tracks)} tracks") + _beatport_log(f" Extracted {len(converted_tracks)} tracks") return converted_tracks def convert_hype_picks_json_to_track_format(self, track_data: Dict, release_url: str, position: int): @@ -1912,12 +1947,12 @@ class BeatportUnifiedScraper: return track except Exception as e: - print(f" Error converting track data: {e}") + _beatport_log(f" Error converting track data: {e}") return None def scrape_homepage_top10_lists(self) -> Dict[str, List[Dict]]: """Scrape Top 10 Lists from homepage - Beatport Top 10 and Hype Top 10""" - print("\nScraping Top 10 Lists from homepage...") + _beatport_log("\nScraping Top 10 Lists from homepage...") soup = self.get_page(self.base_url) if not soup: @@ -1925,7 +1960,7 @@ class BeatportUnifiedScraper: # Extract Beatport Top 10 tracks beatport_top10_items = soup.select('[data-testid="top-10-item"]') - print(f" Found {len(beatport_top10_items)} Beatport Top 10 items") + _beatport_log(f" Found {len(beatport_top10_items)} Beatport Top 10 items") beatport_tracks = [] for i, item in enumerate(beatport_top10_items, 1): @@ -1934,11 +1969,11 @@ class BeatportUnifiedScraper: if track_data: beatport_tracks.append(track_data) except Exception as e: - print(f" Error extracting Beatport track {i}: {e}") + _beatport_log(f" Error extracting Beatport track {i}: {e}") # Extract Hype Top 10 tracks hype_top10_items = soup.select('[data-testid="hype-top-10-item"]') - print(f" Found {len(hype_top10_items)} Hype Top 10 items") + _beatport_log(f" Found {len(hype_top10_items)} Hype Top 10 items") hype_tracks = [] for i, item in enumerate(hype_top10_items, 1): @@ -1947,9 +1982,9 @@ class BeatportUnifiedScraper: if track_data: hype_tracks.append(track_data) except Exception as e: - print(f" Error extracting Hype track {i}: {e}") + _beatport_log(f" Error extracting Hype track {i}: {e}") - print(f"Extracted {len(beatport_tracks)} Beatport Top 10 + {len(hype_tracks)} Hype Top 10 tracks") + _beatport_log(f"Extracted {len(beatport_tracks)} Beatport Top 10 + {len(hype_tracks)} Hype Top 10 tracks") return { "beatport_top10": beatport_tracks, @@ -2031,24 +2066,24 @@ class BeatportUnifiedScraper: } except Exception as e: - print(f"Error extracting track data: {e}") + _beatport_log(f"Error extracting track data: {e}") return None def scrape_homepage_top10_releases(self) -> List[Dict]: """Scrape Top 10 Releases from homepage - FIXED VERSION""" - print("\nFIXED: Scraping Top 10 Releases from homepage...") + _beatport_log("\nFIXED: Scraping Top 10 Releases from homepage...") soup = self.get_page(self.base_url) if not soup: - print(" Could not get homepage") + _beatport_log(" Could not get homepage") return [] # Extract Top 10 Releases items - EXACT same as test script top10_releases_items = soup.select('[data-testid="top-10-releases-item"]') - print(f" FOUND {len(top10_releases_items)} Top 10 Releases items") + _beatport_log(f" FOUND {len(top10_releases_items)} Top 10 Releases items") if len(top10_releases_items) == 0: - print(" No items found - trying alternatives") + _beatport_log(" No items found - trying alternatives") return [] releases = [] @@ -2058,13 +2093,13 @@ class BeatportUnifiedScraper: release_data = self.extract_release_from_item_FIXED(item, i) if release_data: releases.append(release_data) - print(f" {i}. {release_data['artist']} - {release_data['title']}") + _beatport_log(f" {i}. {release_data['artist']} - {release_data['title']}") else: - print(f" {i}. No data extracted") + _beatport_log(f" {i}. No data extracted") except Exception as e: - print(f" Error extracting release {i}: {e}") + _beatport_log(f" Error extracting release {i}: {e}") - print(f"FINAL: Extracted {len(releases)} Top 10 Releases") + _beatport_log(f"FINAL: Extracted {len(releases)} Top 10 Releases") return releases def extract_release_from_item_FIXED(self, item, rank): @@ -2177,7 +2212,7 @@ class BeatportUnifiedScraper: } except Exception as e: - print(f"Error extracting release data: {e}") + _beatport_log(f"Error extracting release data: {e}") return None def extract_release_from_top10_item(self, item, rank): @@ -2288,12 +2323,12 @@ class BeatportUnifiedScraper: } except Exception as e: - print(f"Error extracting release data: {e}") + _beatport_log(f"Error extracting release data: {e}") return None def scrape_new_on_beatport_hero(self, limit: int = 10) -> List[Dict]: """Scrape the 'New on Beatport' hero slideshow from homepage using data-testid standard""" - print("\nScraping 'New on Beatport' hero slideshow...") + _beatport_log("\nScraping 'New on Beatport' hero slideshow...") soup = self.get_page(self.base_url) if not soup: @@ -2304,7 +2339,7 @@ class BeatportUnifiedScraper: # Method 1 (PRIMARY): Use data-testid standard like all other rebuild functions hero_items = soup.select('[data-testid="new-on-beatport"]') if hero_items: - print(f" Found {len(hero_items)} items using data-testid='new-on-beatport'") + _beatport_log(f" Found {len(hero_items)} items using data-testid='new-on-beatport'") for i, item in enumerate(hero_items[:limit]): track_data = self._extract_track_from_slide(item, f"Hero Item {i+1}") if track_data and track_data.get('url'): @@ -2314,14 +2349,14 @@ class BeatportUnifiedScraper: if len(tracks) < 5: hero_wrapper = soup.select_one('[class*="Homepage-style__NewOnBeatportWrapper"]') if hero_wrapper: - print(" Found Homepage NewOnBeatportWrapper (fallback)") + _beatport_log(" Found Homepage NewOnBeatportWrapper (fallback)") tracks.extend(self._extract_from_hero_wrapper(hero_wrapper, limit)) # Method 3 (FALLBACK): Look for carousel with aria attributes if len(tracks) < 5: carousel = soup.find('div', {'aria-roledescription': 'carousel', 'aria-label': 'Carousel'}) if carousel: - print(" Found carousel with aria-roledescription and aria-label (fallback)") + _beatport_log(" Found carousel with aria-roledescription and aria-label (fallback)") additional_tracks = self._extract_from_carousel(carousel, limit) # Merge without duplicates existing_urls = {track.get('url') for track in tracks} @@ -2331,9 +2366,9 @@ class BeatportUnifiedScraper: # Method 4 (LAST RESORT): Look for individual slide items more broadly if len(tracks) < 5: - print(" Looking for individual carousel items (last resort)...") + _beatport_log(" Looking for individual carousel items (last resort)...") carousel_items = soup.find_all(['div', 'article'], class_=re.compile(r'carousel.*item|item.*carousel|slide', re.I)) - print(f" Found {len(carousel_items)} potential carousel items") + _beatport_log(f" Found {len(carousel_items)} potential carousel items") for i, item in enumerate(carousel_items[:limit * 2]): # Check more items track_data = self._extract_track_from_slide(item, f"Carousel Item {i+1}") @@ -2343,7 +2378,7 @@ class BeatportUnifiedScraper: if track_data['url'] not in existing_urls: tracks.append(track_data) - print(f" Extracted {len(tracks)} tracks from New on Beatport hero") + _beatport_log(f" Extracted {len(tracks)} tracks from New on Beatport hero") return tracks[:limit] def _extract_from_hero_wrapper(self, wrapper, limit: int) -> List[Dict]: @@ -2529,21 +2564,21 @@ class BeatportUnifiedScraper: if (not title or not artist or title.lower() in ['no title', 'unknown title', 'unknown', ''] or artist.lower() in ['no artist', 'unknown artist', 'unknown', 'various artists', '']): - print(f" {context}: Filtered out invalid track - '{title}' by '{artist}'") + _beatport_log(f" {context}: Filtered out invalid track - '{title}' by '{artist}'") return None # Only return if we found meaningful data if track_data.get('url') or track_data.get('image_url'): track_data['source'] = f"New on Beatport Hero - {context}" track_data['scraped_at'] = time.time() - print(f" {context}: {title} - {artist}") + _beatport_log(f" {context}: {title} - {artist}") return track_data else: - print(f" {context}: No usable data found") + _beatport_log(f" {context}: No usable data found") return None except Exception as e: - print(f" Error extracting from {context}: {e}") + _beatport_log(f" Error extracting from {context}: {e}") return None def _extract_title_artist_from_url(self, url: str) -> Dict[str, str]: @@ -2792,7 +2827,7 @@ class BeatportUnifiedScraper: def scrape_top_10_releases_homepage(self, limit: int = 10) -> List[Dict]: """Scrape Top 10 Releases from homepage - Extract individual tracks using URL crawling""" - print("\nScraping Top 10 Releases from homepage...") + _beatport_log("\nScraping Top 10 Releases from homepage...") soup = self.get_page(self.base_url) if not soup: @@ -2800,7 +2835,7 @@ class BeatportUnifiedScraper: # Step 1: Extract release URLs from Top 10 section release_items = soup.select('[data-testid="top-10-releases-item"]') - print(f" Found {len(release_items)} release items in Top 10 Releases section") + _beatport_log(f" Found {len(release_items)} release items in Top 10 Releases section") release_urls = [] for i, item in enumerate(release_items[:limit]): @@ -2809,30 +2844,30 @@ class BeatportUnifiedScraper: if link_elem and link_elem.get('href'): release_url = urljoin(self.base_url, link_elem.get('href')) release_urls.append(release_url) - print(f" {i+1}. Found Top 10 release URL: {release_url}") + _beatport_log(f" {i+1}. Found Top 10 release URL: {release_url}") if not release_urls: - print(" No Top 10 release URLs found") + _beatport_log(" No Top 10 release URLs found") return [] # Step 2: Crawl each release URL to extract individual tracks all_individual_tracks = [] for i, release_url in enumerate(release_urls): - print(f" Processing Top 10 release {i+1}/{len(release_urls)}: {release_url}") + _beatport_log(f" Processing Top 10 release {i+1}/{len(release_urls)}: {release_url}") # Extract individual tracks from this release tracks = self.extract_individual_tracks_from_release_url(release_url, "Top 10 Releases") if tracks: - print(f" Found {len(tracks)} individual tracks") + _beatport_log(f" Found {len(tracks)} individual tracks") all_individual_tracks.extend(tracks) else: - print(f" No tracks found") + _beatport_log(f" No tracks found") # Add delay between requests to be respectful if i < len(release_urls) - 1: time.sleep(0.5) - print(f"Extracted {len(all_individual_tracks)} individual tracks from {len(release_urls)} Top 10 releases") + _beatport_log(f"Extracted {len(all_individual_tracks)} individual tracks from {len(release_urls)} Top 10 releases") return all_individual_tracks def scrape_genre_charts(self, genre: Dict, limit: int = 100, enrich: bool = True) -> List[Dict]: @@ -2852,20 +2887,20 @@ class BeatportUnifiedScraper: ] for chart_url in chart_urls_to_try: - print(f" Trying chart URL: {chart_url}") + _beatport_log(f" Trying chart URL: {chart_url}") soup = self.get_page(chart_url) if soup: tracks = self.extract_tracks_from_page(soup, f"{genre['name']} Top 100", limit) if tracks and len(tracks) >= min(limit, 50): - print(f" Successfully extracted {len(tracks)} tracks from {chart_url}") + _beatport_log(f" Successfully extracted {len(tracks)} tracks from {chart_url}") break elif tracks: - print(f" Only found {len(tracks)} tracks at {chart_url}, trying next URL...") + _beatport_log(f" Only found {len(tracks)} tracks at {chart_url}, trying next URL...") else: - print(f" No tracks found at {chart_url}") + _beatport_log(f" No tracks found at {chart_url}") if tracks and enrich: - print(f" Enriching {len(tracks)} {genre['name']} chart tracks with per-track metadata...") + _beatport_log(f" Enriching {len(tracks)} {genre['name']} chart tracks with per-track metadata...") tracks = self.enrich_chart_tracks(tracks) return tracks @@ -2892,7 +2927,7 @@ class BeatportUnifiedScraper: ] for release_url in release_urls_to_try: - print(f" Trying release URL: {release_url}") + _beatport_log(f" Trying release URL: {release_url}") soup = self.get_page(release_url) if soup: # Try to find releases section on the page @@ -2900,19 +2935,19 @@ class BeatportUnifiedScraper: # If no releases found with release extraction, try track extraction if not releases: - print(f" No releases found with release method, trying track method for {genre['name']}") + _beatport_log(f" No releases found with release method, trying track method for {genre['name']}") releases = self.extract_tracks_from_page(soup, f"{genre['name']} Top Releases", limit) # Mark these as releases for release in releases: release['type'] = 'release' if releases and len(releases) >= min(limit, 30): # If we got a decent number of releases - print(f" Successfully extracted {len(releases)} releases from {release_url}") + _beatport_log(f" Successfully extracted {len(releases)} releases from {release_url}") break elif releases: - print(f" Only found {len(releases)} releases at {release_url}, trying next URL...") + _beatport_log(f" Only found {len(releases)} releases at {release_url}, trying next URL...") else: - print(f" No releases found at {release_url}") + _beatport_log(f" No releases found at {release_url}") return releases @@ -2933,22 +2968,22 @@ class BeatportUnifiedScraper: ] for hype_url in hype_urls_to_try: - print(f" Trying hype URL: {hype_url}") + _beatport_log(f" Trying hype URL: {hype_url}") soup = self.get_page(hype_url) if soup: # Use the new dedicated hype extraction method tracks = self.extract_hype_tracks_from_beatport_page(soup, f"{genre['name']} Hype Charts", limit) if tracks and len(tracks) >= min(limit, 10): # If we got a decent number of tracks - print(f" Successfully extracted {len(tracks)} hype tracks from {hype_url}") + _beatport_log(f" Successfully extracted {len(tracks)} hype tracks from {hype_url}") break elif tracks: - print(f" Only found {len(tracks)} hype tracks at {hype_url}, trying next URL...") + _beatport_log(f" Only found {len(tracks)} hype tracks at {hype_url}, trying next URL...") else: - print(f" No hype tracks found at {hype_url}") + _beatport_log(f" No hype tracks found at {hype_url}") # If no dedicated hype page found, try main genre page for hype content if not tracks: - print(f" No dedicated hype page found, looking for hype content on main page...") + _beatport_log(f" No dedicated hype page found, looking for hype content on main page...") genre_url = f"{self.base_url}/genre/{genre['slug']}/{genre['id']}" soup = self.get_page(genre_url) if soup: @@ -2958,7 +2993,7 @@ class BeatportUnifiedScraper: def scrape_genre_hype_picks(self, genre: Dict, limit: int = 100) -> List[Dict]: """Scrape individual tracks from Genre Hype Picks using JSON extraction - ENHANCED (same pattern as Latest Releases)""" - print(f"\nScraping {genre['name']} Hype Picks (individual tracks)...") + _beatport_log(f"\nScraping {genre['name']} Hype Picks (individual tracks)...") # Step 1: Get release URLs from genre Hype Picks carousel (same logic as Latest Releases) release_urls = self.extract_genre_hype_picks_urls(genre, limit) @@ -2968,7 +3003,7 @@ class BeatportUnifiedScraper: # Step 2: Extract individual tracks from each release (same method as Latest Releases) all_tracks = [] for i, release_url in enumerate(release_urls): - print(f"\nProcessing {genre['name']} hype pick {i+1}/{len(release_urls)}") + _beatport_log(f"\nProcessing {genre['name']} hype pick {i+1}/{len(release_urls)}") tracks = self.extract_tracks_from_release_json(release_url) if tracks: # Update list_name to match genre context @@ -2980,7 +3015,7 @@ class BeatportUnifiedScraper: import time time.sleep(0.5) - print(f"Extracted {len(all_tracks)} individual tracks from {len(release_urls)} {genre['name']} hype picks") + _beatport_log(f"Extracted {len(all_tracks)} individual tracks from {len(release_urls)} {genre['name']} hype picks") return all_tracks def extract_genre_hype_picks_urls(self, genre: Dict, limit: int) -> List[str]: @@ -2998,16 +3033,16 @@ class BeatportUnifiedScraper: h2 = container.select_one('h2') if h2 and 'hype' in h2.get_text().lower() and 'pick' in h2.get_text().lower(): hype_container = container - print(f" Found Hype Picks section: '{h2.get_text().strip()}'") + _beatport_log(f" Found Hype Picks section: '{h2.get_text().strip()}'") break if not hype_container: - print(f" Could not find Hype Picks section for {genre['name']}") + _beatport_log(f" Could not find Hype Picks section for {genre['name']}") return [] # Extract release URLs from ALL releases in Hype Picks section (same as Latest Releases) release_links = hype_container.select('a[href*="/release/"]') - print(f" Found {len(release_links)} release links in Hype Picks section") + _beatport_log(f" Found {len(release_links)} release links in Hype Picks section") release_urls = [] seen_urls = set() @@ -3024,7 +3059,7 @@ class BeatportUnifiedScraper: if href not in seen_urls: release_urls.append(href) seen_urls.add(href) - print(f" {len(release_urls)}. Found hype pick URL: {href}") + _beatport_log(f" {len(release_urls)}. Found hype pick URL: {href}") # Stop when we reach the desired number of unique releases if len(release_urls) >= limit: @@ -3041,7 +3076,7 @@ class BeatportUnifiedScraper: string=re.compile(r'hype', re.I)) for heading in hype_headings: - print(f" Found hype heading: {heading.get_text(strip=True)}") + _beatport_log(f" Found hype heading: {heading.get_text(strip=True)}") # Get the section after this heading section_container = heading.find_parent() @@ -3146,7 +3181,7 @@ class BeatportUnifiedScraper: } tracks.append(track_data) - print(f" Release Track: {artist_text} - {track_title}") + _beatport_log(f" Release Track: {artist_text} - {track_title}") except Exception: continue @@ -3171,7 +3206,7 @@ class BeatportUnifiedScraper: string=re.compile(rf'{section_name}', re.I)) if section_heading: - print(f" Found hype picks section: {section_heading.get_text(strip=True)}") + _beatport_log(f" Found hype picks section: {section_heading.get_text(strip=True)}") section_container = section_heading.find_parent() if section_container: content_area = section_container.find_next_sibling() @@ -3193,7 +3228,7 @@ class BeatportUnifiedScraper: if not soup: return tracks - print(f" Looking for HYPE labeled tracks on page...") + _beatport_log(f" Looking for HYPE labeled tracks on page...") # Look for elements containing "HYPE" text hype_elements = soup.find_all(text=re.compile(r'HYPE', re.I)) @@ -3261,7 +3296,7 @@ class BeatportUnifiedScraper: # Avoid duplicates if not any(existing['url'] == track_data['url'] for existing in tracks): tracks.append(track_data) - print(f" Found HYPE track: {track_data['artist']} - {track_data['title']}") + _beatport_log(f" Found HYPE track: {track_data['artist']} - {track_data['title']}") except Exception as e: continue @@ -3269,7 +3304,7 @@ class BeatportUnifiedScraper: except Exception as e: continue - print(f" Extracted {len(tracks)} HYPE labeled tracks") + _beatport_log(f" Extracted {len(tracks)} HYPE labeled tracks") return tracks def extract_hype_tracks_from_beatport_page(self, soup: BeautifulSoup, list_name: str, limit: int = 100) -> List[Dict]: @@ -3279,7 +3314,7 @@ class BeatportUnifiedScraper: if not soup: return tracks - print(f" Extracting hype tracks from Beatport page...") + _beatport_log(f" Extracting hype tracks from Beatport page...") # Method 1: Extract from Hype Picks carousel (release cards with HYPE badges) hype_picks_tracks = self.extract_hype_picks_from_carousel(soup, list_name, limit) @@ -3295,7 +3330,7 @@ class BeatportUnifiedScraper: hype_table_tracks = self.extract_hype_from_track_table(soup, list_name, limit - len(tracks)) tracks.extend(hype_table_tracks) - print(f" Extracted {len(tracks)} hype tracks using actual Beatport structure") + _beatport_log(f" Extracted {len(tracks)} hype tracks using actual Beatport structure") return tracks[:limit] def extract_hype_picks_from_carousel(self, soup: BeautifulSoup, list_name: str, limit: int) -> List[Dict]: @@ -3342,7 +3377,7 @@ class BeatportUnifiedScraper: } tracks.append(track_data) - print(f" Hype Pick: {artist_text} - {release_title}") + _beatport_log(f" Hype Pick: {artist_text} - {release_title}") except Exception as e: continue @@ -3395,7 +3430,7 @@ class BeatportUnifiedScraper: } tracks.append(track_data) - print(f" Hype Track {position}: {artist_text} - {track_title}") + _beatport_log(f" Hype Track {position}: {artist_text} - {track_title}") except Exception as e: continue @@ -3452,7 +3487,7 @@ class BeatportUnifiedScraper: } tracks.append(track_data) - print(f" Hype Track {position}: {artist_text} - {track_title}") + _beatport_log(f" Hype Track {position}: {artist_text} - {track_title}") except Exception as e: continue @@ -3461,7 +3496,7 @@ class BeatportUnifiedScraper: def scrape_genre_staff_picks(self, genre: Dict, limit: int = 100) -> List[Dict]: """Scrape individual tracks from Genre Staff Picks using JSON extraction - ENHANCED (same pattern as Latest Releases)""" - print(f"\nScraping {genre['name']} Staff Picks (individual tracks)...") + _beatport_log(f"\nScraping {genre['name']} Staff Picks (individual tracks)...") # Step 1: Get release URLs from genre Staff Picks carousel (same logic as Latest Releases) release_urls = self.extract_genre_staff_picks_urls(genre, limit) @@ -3471,7 +3506,7 @@ class BeatportUnifiedScraper: # Step 2: Extract individual tracks from each release (same method as Latest Releases) all_tracks = [] for i, release_url in enumerate(release_urls): - print(f"\nProcessing {genre['name']} staff pick {i+1}/{len(release_urls)}") + _beatport_log(f"\nProcessing {genre['name']} staff pick {i+1}/{len(release_urls)}") tracks = self.extract_tracks_from_release_json(release_url) if tracks: # Update list_name to match genre context @@ -3483,7 +3518,7 @@ class BeatportUnifiedScraper: import time time.sleep(0.5) - print(f"Extracted {len(all_tracks)} individual tracks from {len(release_urls)} {genre['name']} staff picks") + _beatport_log(f"Extracted {len(all_tracks)} individual tracks from {len(release_urls)} {genre['name']} staff picks") return all_tracks def extract_genre_staff_picks_urls(self, genre: Dict, limit: int) -> List[str]: @@ -3501,16 +3536,16 @@ class BeatportUnifiedScraper: h2 = container.select_one('h2') if h2 and 'staff' in h2.get_text().lower() and 'pick' in h2.get_text().lower(): staff_container = container - print(f" Found Staff Picks section: '{h2.get_text().strip()}'") + _beatport_log(f" Found Staff Picks section: '{h2.get_text().strip()}'") break if not staff_container: - print(f" Could not find Staff Picks section for {genre['name']}") + _beatport_log(f" Could not find Staff Picks section for {genre['name']}") return [] # Extract release URLs from ALL releases in Staff Picks section (same as Latest Releases) release_links = staff_container.select('a[href*="/release/"]') - print(f" Found {len(release_links)} release links in Staff Picks section") + _beatport_log(f" Found {len(release_links)} release links in Staff Picks section") release_urls = [] seen_urls = set() @@ -3527,7 +3562,7 @@ class BeatportUnifiedScraper: if href not in seen_urls: release_urls.append(href) seen_urls.add(href) - print(f" {len(release_urls)}. Found staff pick URL: {href}") + _beatport_log(f" {len(release_urls)}. Found staff pick URL: {href}") # Stop when we reach the desired number of unique releases if len(release_urls) >= limit: @@ -3537,7 +3572,7 @@ class BeatportUnifiedScraper: def scrape_genre_latest_releases(self, genre: Dict, limit: int = 100) -> List[Dict]: """Scrape individual tracks from Genre Latest Releases using JSON extraction - ENHANCED (same pattern as homepage)""" - print(f"\nšŸ†• Scraping {genre['name']} Latest Releases (individual tracks)...") + _beatport_log(f"\nšŸ†• Scraping {genre['name']} Latest Releases (individual tracks)...") # Step 1: Get release URLs from genre Latest Releases carousel (same logic as homepage) release_urls = self.extract_genre_latest_releases_urls(genre, limit) @@ -3547,7 +3582,7 @@ class BeatportUnifiedScraper: # Step 2: Extract individual tracks from each release (same method as homepage) all_tracks = [] for i, release_url in enumerate(release_urls): - print(f"\nProcessing {genre['name']} latest release {i+1}/{len(release_urls)}") + _beatport_log(f"\nProcessing {genre['name']} latest release {i+1}/{len(release_urls)}") tracks = self.extract_tracks_from_release_json(release_url) if tracks: # Update list_name to match genre context @@ -3559,7 +3594,7 @@ class BeatportUnifiedScraper: import time time.sleep(0.5) - print(f"Extracted {len(all_tracks)} individual tracks from {len(release_urls)} latest {genre['name']} releases") + _beatport_log(f"Extracted {len(all_tracks)} individual tracks from {len(release_urls)} latest {genre['name']} releases") return all_tracks def extract_genre_latest_releases_urls(self, genre: Dict, limit: int) -> List[str]: @@ -3577,16 +3612,16 @@ class BeatportUnifiedScraper: h2 = container.select_one('h2') if h2 and 'latest' in h2.get_text().lower() and 'release' in h2.get_text().lower(): latest_container = container - print(f" Found Latest Releases section: '{h2.get_text().strip()}'") + _beatport_log(f" Found Latest Releases section: '{h2.get_text().strip()}'") break if not latest_container: - print(f" Could not find Latest Releases section for {genre['name']}") + _beatport_log(f" Could not find Latest Releases section for {genre['name']}") return [] # Extract release URLs from ALL releases in Latest Releases section (same as homepage gets all cards) release_links = latest_container.select('a[href*="/release/"]') - print(f" Found {len(release_links)} release links in Latest Releases section") + _beatport_log(f" Found {len(release_links)} release links in Latest Releases section") release_urls = [] seen_urls = set() @@ -3603,7 +3638,7 @@ class BeatportUnifiedScraper: if href not in seen_urls: release_urls.append(href) seen_urls.add(href) - print(f" {len(release_urls)}. Found latest release URL: {href}") + _beatport_log(f" {len(release_urls)}. Found latest release URL: {href}") # Stop when we reach the desired number of unique releases if len(release_urls) >= limit: @@ -3622,7 +3657,7 @@ class BeatportUnifiedScraper: charts = [] chart_links = soup.find_all('a', href=re.compile(r'/chart/')) - print(f" Found {len(chart_links)} chart links on genre page") + _beatport_log(f" Found {len(chart_links)} chart links on genre page") for chart_link in chart_links[:limit]: chart_name = chart_link.get_text(strip=True) @@ -3642,9 +3677,9 @@ class BeatportUnifiedScraper: } charts.append(chart_info) - print(f" Chart {len(charts)}: {chart_name}") + _beatport_log(f" Chart {len(charts)}: {chart_name}") - print(f" Found {len(charts)} charts in New Charts Collection") + _beatport_log(f" Found {len(charts)} charts in New Charts Collection") return charts[:limit] def extract_tracks_from_chart(self, chart_url: str, chart_name: str, limit: int) -> List[Dict]: @@ -3656,14 +3691,14 @@ class BeatportUnifiedScraper: if not soup: return tracks - print(f" Extracting tracks from chart page: {chart_url}") - print(f" Chart name: {chart_name}") + _beatport_log(f" Extracting tracks from chart page: {chart_url}") + _beatport_log(f" Chart name: {chart_name}") # Step 1: Get basic track list from HTML tracks = self.extract_tracks_from_chart_table(soup, chart_name, limit) if len(tracks) < 10: - print(f" Chart table extraction found {len(tracks)} tracks, trying general extraction...") + _beatport_log(f" Chart table extraction found {len(tracks)} tracks, trying general extraction...") general_tracks = self.extract_tracks_from_page(soup, f"New Chart: {chart_name}", limit) if len(general_tracks) > len(tracks): tracks = general_tracks @@ -3673,7 +3708,7 @@ class BeatportUnifiedScraper: if len(table_tracks) > len(tracks): tracks = table_tracks - print(f" Found {len(tracks)} tracks, enriching with per-track metadata...") + _beatport_log(f" Found {len(tracks)} tracks, enriching with per-track metadata...") # Step 2: Enrich each track by visiting its individual page if tracks: @@ -3682,47 +3717,47 @@ class BeatportUnifiedScraper: return tracks except Exception as e: - print(f" Error extracting tracks from chart {chart_name}: {e}") + _beatport_log(f" Error extracting tracks from chart {chart_name}: {e}") return [] def extract_tracks_from_chart_table(self, soup, chart_name: str, limit: int) -> List[Dict]: """Extract tracks from Beatport chart table structure (tracks-table class)""" tracks = [] - print(f" DEBUG: Looking for tracks-table container...") + _beatport_log(f" DEBUG: Looking for tracks-table container...") # Look for the tracks table container tracks_table = soup.find(class_=re.compile(r'tracks-table')) if not tracks_table: - print(f" No tracks-table container found") + _beatport_log(f" No tracks-table container found") # Debug: Let's see what table classes ARE available all_tables = soup.find_all(['table', 'div'], class_=re.compile(r'table|Table', re.I)) - print(f" DEBUG: Found {len(all_tables)} table-like elements") + _beatport_log(f" DEBUG: Found {len(all_tables)} table-like elements") for i, table in enumerate(all_tables[:5]): classes = table.get('class', []) - print(f" Table {i+1}: {' '.join(classes)}") + _beatport_log(f" Table {i+1}: {' '.join(classes)}") return tracks - print(f" Found tracks-table container with classes: {tracks_table.get('class', [])}") + _beatport_log(f" Found tracks-table container with classes: {tracks_table.get('class', [])}") # Find all track rows using data-testid or table row classes track_rows_testid = tracks_table.find_all(['div', 'tr'], attrs={'data-testid': 'tracks-table-row'}) track_rows_class = tracks_table.find_all(class_=re.compile(r'Table.*Row.*tracks-table')) track_rows_generic = tracks_table.find_all(class_=re.compile(r'Table.*Row')) - print(f" DEBUG: Track rows found:") - print(f" - By data-testid='tracks-table-row': {len(track_rows_testid)}") - print(f" - By class pattern 'Table.*Row.*tracks-table': {len(track_rows_class)}") - print(f" - By generic 'Table.*Row': {len(track_rows_generic)}") + _beatport_log(f" DEBUG: Track rows found:") + _beatport_log(f" - By data-testid='tracks-table-row': {len(track_rows_testid)}") + _beatport_log(f" - By class pattern 'Table.*Row.*tracks-table': {len(track_rows_class)}") + _beatport_log(f" - By generic 'Table.*Row': {len(track_rows_generic)}") # Use the best available option track_rows = track_rows_testid or track_rows_class or track_rows_generic if not track_rows: - print(f" No track rows found in any format") + _beatport_log(f" No track rows found in any format") return tracks - print(f" Using {len(track_rows)} track rows for extraction") + _beatport_log(f" Using {len(track_rows)} track rows for extraction") for i, row in enumerate(track_rows[:limit]): try: @@ -3760,11 +3795,11 @@ class BeatportUnifiedScraper: # DEBUG: Print track details for first few if len(tracks) < 3: - print(f" DEBUG Track {len(tracks)+1}:") - print(f" Title: '{track_title}'") - print(f" Artist: '{artist_text}'") - print(f" URL: {track_url}") - print(f" Track link href: {track_link.get('href', 'NO HREF')}") + _beatport_log(f" DEBUG Track {len(tracks)+1}:") + _beatport_log(f" Title: '{track_title}'") + _beatport_log(f" Artist: '{artist_text}'") + _beatport_log(f" URL: {track_url}") + _beatport_log(f" Track link href: {track_link.get('href', 'NO HREF')}") # Extract track number if available track_no_elem = row.find(class_=re.compile(r'TrackNo')) @@ -3783,13 +3818,13 @@ class BeatportUnifiedScraper: # Debug output for first few tracks if len(tracks) <= 5: - print(f" Track {len(tracks)}: {artist_text} - {track_title}") + _beatport_log(f" Track {len(tracks)}: {artist_text} - {track_title}") except Exception as e: - print(f" Error parsing track row {i+1}: {e}") + _beatport_log(f" Error parsing track row {i+1}: {e}") continue - print(f" Chart table extraction completed: {len(tracks)} tracks found") + _beatport_log(f" Chart table extraction completed: {len(tracks)} tracks found") return tracks def extract_tracks_from_table_format(self, soup, chart_name: str, limit: int) -> List[Dict]: @@ -3799,7 +3834,7 @@ class BeatportUnifiedScraper: # Look for table rows containing track data table_rows = soup.find_all('tr') + soup.find_all('div', class_=re.compile(r'Table.*Row|track.*row', re.I)) - print(f" Found {len(table_rows)} potential table rows") + _beatport_log(f" Found {len(table_rows)} potential table rows") for i, row in enumerate(table_rows[:limit]): try: @@ -3837,7 +3872,7 @@ class BeatportUnifiedScraper: tracks.append(track_data) if len(tracks) <= 3: # Debug first few - print(f" Track {len(tracks)}: {artist_text} - {track_title}") + _beatport_log(f" Track {len(tracks)}: {artist_text} - {track_title}") except Exception as e: continue @@ -3848,7 +3883,7 @@ class BeatportUnifiedScraper: """Analyze a genre page to discover all available sections""" genre_url = f"{self.base_url}/genre/{genre['slug']}/{genre['id']}" - print(f"Discovering sections for {genre['name']} genre page...") + _beatport_log(f"Discovering sections for {genre['name']} genre page...") soup = self.get_page(genre_url) if not soup: @@ -3886,17 +3921,17 @@ class BeatportUnifiedScraper: chart_links = soup.find_all('a', href=re.compile(r'/chart/')) sections['chart_count'] = len(chart_links) - print(f"Discovered sections for {genre['name']}:") + _beatport_log(f"Discovered sections for {genre['name']}:") for section_type, items in sections.items(): if items and section_type != 'chart_count': - print(f" ā€¢ {section_type}: {len(items)} sections") - print(f" ā€¢ Individual charts found: {sections['chart_count']}") + _beatport_log(f" ā€¢ {section_type}: {len(items)} sections") + _beatport_log(f" ā€¢ Individual charts found: {sections['chart_count']}") return sections def scrape_genre_hero_slider(self, genre_slug: str, genre_id: str) -> List[Dict]: """Scrape hero slider data from a genre page""" - print(f"\nScraping hero slider for {genre_slug}...") + _beatport_log(f"\nScraping hero slider for {genre_slug}...") genre_url = f"{self.base_url}/genre/{genre_slug}/{genre_id}" soup = self.get_page(genre_url) @@ -3906,18 +3941,18 @@ class BeatportUnifiedScraper: # Find the main section container main_section = soup.find('div', class_=re.compile(r'Genre-style__MainSection')) if not main_section: - print(f" Main section not found for {genre_slug}") + _beatport_log(f" Main section not found for {genre_slug}") return [] # Find the hero slider hero_slider = main_section.find('div', class_='hero-slider') if not hero_slider: - print(f" Hero slider not found for {genre_slug}") + _beatport_log(f" Hero slider not found for {genre_slug}") return [] # Extract all hero releases hero_releases = hero_slider.find_all(class_='hero-release') - print(f" Found {len(hero_releases)} hero releases") + _beatport_log(f" Found {len(hero_releases)} hero releases") releases_data = [] for i, release in enumerate(hero_releases): @@ -3925,18 +3960,18 @@ class BeatportUnifiedScraper: release_data = self.extract_hero_release_data(release) if release_data and release_data.get('url'): releases_data.append(release_data) - print(f" Extracted: {release_data.get('title', 'Unknown')} by {release_data.get('artists_string', 'Unknown')}") + _beatport_log(f" Extracted: {release_data.get('title', 'Unknown')} by {release_data.get('artists_string', 'Unknown')}") else: - print(f" Skipped release {i+1} - incomplete data") + _beatport_log(f" Skipped release {i+1} - incomplete data") except Exception as e: - print(f" Error extracting release {i+1}: {e}") + _beatport_log(f" Error extracting release {i+1}: {e}") - print(f" Successfully extracted {len(releases_data)} hero releases") + _beatport_log(f" Successfully extracted {len(releases_data)} hero releases") return releases_data def scrape_genre_top10_tracks(self, genre_slug, genre_id): """Scrape Top 10 tracks lists from genre page (Beatport Top 10 + Hype Top 10 if available)""" - print(f"Scraping Top 10 tracks for {genre_slug} (ID: {genre_id})") + _beatport_log(f"Scraping Top 10 tracks for {genre_slug} (ID: {genre_id})") genre_url = f"https://www.beatport.com/genre/{genre_slug}/{genre_id}" @@ -3948,7 +3983,7 @@ class BeatportUnifiedScraper: track_items = soup.find_all(attrs={'data-testid': 'tracks-list-item'}) if not track_items: - print(f"No tracks-list-item elements found on {genre_url}") + _beatport_log(f"No tracks-list-item elements found on {genre_url}") return { 'beatport_top10': [], 'hype_top10': [], @@ -3956,7 +3991,7 @@ class BeatportUnifiedScraper: 'has_hype_section': False } - print(f"Found {len(track_items)} total track items") + _beatport_log(f"Found {len(track_items)} total track items") # Extract track data from all items all_tracks = [] @@ -3983,7 +4018,7 @@ class BeatportUnifiedScraper: has_hype_section = len(all_tracks) > 10 - print(f"Extracted {len(beatport_top10)} Beatport Top 10 + {len(hype_top10)} Hype Top 10 tracks") + _beatport_log(f"Extracted {len(beatport_top10)} Beatport Top 10 + {len(hype_top10)} Hype Top 10 tracks") return { 'beatport_top10': beatport_top10, @@ -4059,12 +4094,12 @@ class BeatportUnifiedScraper: } except Exception as e: - print(f"Error extracting track data: {e}") + _beatport_log(f"Error extracting track data: {e}") return None def scrape_genre_top10_releases(self, genre_slug, genre_id): """Scrape Top 10 releases from genre page using .partial-artwork elements""" - print(f"Scraping Top 10 releases for {genre_slug} (ID: {genre_id})") + _beatport_log(f"Scraping Top 10 releases for {genre_slug} (ID: {genre_id})") genre_url = f"https://www.beatport.com/genre/{genre_slug}/{genre_id}" @@ -4076,10 +4111,10 @@ class BeatportUnifiedScraper: partial_artwork_elements = soup.find_all(class_='partial-artwork') if not partial_artwork_elements: - print(f"No .partial-artwork elements found on {genre_url}") + _beatport_log(f"No .partial-artwork elements found on {genre_url}") return [] - print(f"Found {len(partial_artwork_elements)} .partial-artwork elements") + _beatport_log(f"Found {len(partial_artwork_elements)} .partial-artwork elements") # Extract release data from each element releases = [] @@ -4088,7 +4123,7 @@ class BeatportUnifiedScraper: if release_data: releases.append(release_data) - print(f"Extracted {len(releases)} Top 10 releases") + _beatport_log(f"Extracted {len(releases)} Top 10 releases") return releases def extract_release_data_from_partial_artwork(self, artwork_element, rank): @@ -4144,7 +4179,7 @@ class BeatportUnifiedScraper: artist = self.clean_beatport_text(artist) if artist != "Unknown Artist" else artist label = self.clean_beatport_text(label) if label != "Unknown Label" else label - print(f" Release #{rank}: '{title}' by '{artist}' [{label}]") + _beatport_log(f" Release #{rank}: '{title}' by '{artist}' [{label}]") return { 'title': title, @@ -4158,7 +4193,7 @@ class BeatportUnifiedScraper: } except Exception as e: - print(f"Error extracting release data from .partial-artwork: {e}") + _beatport_log(f"Error extracting release data from .partial-artwork: {e}") return None def extract_hero_release_data(self, release_element) -> Dict: @@ -4234,7 +4269,7 @@ class BeatportUnifiedScraper: return data except Exception as e: - print(f"Error extracting hero release data: {e}") + _beatport_log(f"Error extracting hero release data: {e}") return {} def scrape_all_genres(self, tracks_per_genre: int = 100, max_workers: int = 5, include_images: bool = False) -> Dict[str, List[Dict]]: @@ -4243,7 +4278,7 @@ class BeatportUnifiedScraper: if not self.all_genres: self.all_genres = self.discover_genres_with_images(include_images=include_images) - print(f"\nScraping {len(self.all_genres)} genres...") + _beatport_log(f"\nScraping {len(self.all_genres)} genres...") all_results = {} completed = 0 @@ -4251,14 +4286,14 @@ class BeatportUnifiedScraper: def scrape_single_genre(genre): nonlocal completed - print(f"Scraping {genre['name']}...") + _beatport_log(f"Scraping {genre['name']}...") tracks = self.scrape_genre_charts(genre, tracks_per_genre) with self.results_lock: if tracks: # Only store genres that have tracks all_results[genre['name']] = tracks completed += 1 - print(f"{genre['name']}: {len(tracks)} tracks ({completed}/{len(self.all_genres)} complete)") + _beatport_log(f"{genre['name']}: {len(tracks)} tracks ({completed}/{len(self.all_genres)} complete)") return genre['name'], tracks @@ -4273,7 +4308,7 @@ class BeatportUnifiedScraper: try: future.result() except Exception as e: - print(f"Error processing {genre['name']}: {e}") + _beatport_log(f"Error processing {genre['name']}: {e}") return all_results @@ -4304,119 +4339,119 @@ class BeatportUnifiedScraper: def test_dynamic_genre_discovery(): """Test the dynamic genre discovery functionality""" - print("Dynamic Genre Discovery Test") - print("=" * 80) + _beatport_log("Dynamic Genre Discovery Test") + _beatport_log("=" * 80) scraper = BeatportUnifiedScraper() # Test genre discovery - print("\nTEST 1: Genre Discovery") + _beatport_log("\nTEST 1: Genre Discovery") genres = scraper.discover_genres_from_homepage() - print(f"\nDiscovered {len(genres)} genres:") + _beatport_log(f"\nDiscovered {len(genres)} genres:") for i, genre in enumerate(genres[:10]): # Show first 10 - print(f" {i+1:2}. {genre['name']} -> {genre['slug']} (ID: {genre['id']})") + _beatport_log(f" {i+1:2}. {genre['name']} -> {genre['slug']} (ID: {genre['id']})") if 'url' in genre: - print(f" URL: {genre['url']}") + _beatport_log(f" URL: {genre['url']}") if len(genres) > 10: - print(f" ... and {len(genres) - 10} more genres") + _beatport_log(f" ... and {len(genres) - 10} more genres") # Test with images (limit to 3 for demo) - print("\nTEST 2: Genre Discovery with Images (Sample)") + _beatport_log("\nTEST 2: Genre Discovery with Images (Sample)") genres_with_images = scraper.discover_genres_with_images(include_images=True) - print(f"\nSample genres with images:") + _beatport_log(f"\nSample genres with images:") for genre in genres_with_images[:3]: - print(f" ā€¢ {genre['name']}: {genre.get('image_url', 'No image')}") + _beatport_log(f" ā€¢ {genre['name']}: {genre.get('image_url', 'No image')}") # Test a few genre scrapes - print("\nTEST 3: Sample Genre Chart Scraping") + _beatport_log("\nTEST 3: Sample Genre Chart Scraping") sample_genres = genres[:3] for genre in sample_genres: - print(f"\nTesting {genre['name']}...") + _beatport_log(f"\nTesting {genre['name']}...") tracks = scraper.scrape_genre_charts(genre, limit=3) if tracks: - print(f" Found {len(tracks)} tracks:") + _beatport_log(f" Found {len(tracks)} tracks:") for track in tracks: - print(f" ā€¢ {track['artist']} - {track['title']}") + _beatport_log(f" ā€¢ {track['artist']} - {track['title']}") else: - print(f" No tracks found") + _beatport_log(f" No tracks found") return genres def test_improved_chart_sections(): """Test the improved chart section discovery and scraping""" - print("Testing Improved Chart Section Discovery & Scraping") - print("=" * 80) + _beatport_log("Testing Improved Chart Section Discovery & Scraping") + _beatport_log("=" * 80) scraper = BeatportUnifiedScraper() # Test 1: Chart Section Discovery - print("\nTEST 1: Chart Section Discovery") + _beatport_log("\nTEST 1: Chart Section Discovery") chart_discovery = scraper.discover_chart_sections() - print(f"\nDiscovery Results:") + _beatport_log(f"\nDiscovery Results:") summary = chart_discovery.get('summary', {}) - print(f" ā€¢ Top Charts sections: {summary.get('top_charts_sections', 0)}") - print(f" ā€¢ Staff Picks sections: {summary.get('staff_picks_sections', 0)}") - print(f" ā€¢ Other sections: {summary.get('other_sections', 0)}") - print(f" ā€¢ Main chart links: {summary.get('main_chart_links', 0)}") - print(f" ā€¢ Individual DJ charts: {summary.get('individual_dj_charts', 0)}") + _beatport_log(f" ā€¢ Top Charts sections: {summary.get('top_charts_sections', 0)}") + _beatport_log(f" ā€¢ Staff Picks sections: {summary.get('staff_picks_sections', 0)}") + _beatport_log(f" ā€¢ Other sections: {summary.get('other_sections', 0)}") + _beatport_log(f" ā€¢ Main chart links: {summary.get('main_chart_links', 0)}") + _beatport_log(f" ā€¢ Individual DJ charts: {summary.get('individual_dj_charts', 0)}") # Test 2: New/Improved Scraping Methods - print("\nTEST 2: Improved Chart Scraping Methods") + _beatport_log("\nTEST 2: Improved Chart Scraping Methods") # Test Hype Top 100 (fixed URL) - print("\n2a. Testing Hype Top 100 (fixed URL)...") + _beatport_log("\n2a. Testing Hype Top 100 (fixed URL)...") hype_tracks = scraper.scrape_hype_top_100(limit=5) if hype_tracks: - print(f" Found {len(hype_tracks)} tracks:") + _beatport_log(f" Found {len(hype_tracks)} tracks:") for track in hype_tracks[:3]: - print(f" ā€¢ {track['artist']} - {track['title']}") + _beatport_log(f" ā€¢ {track['artist']} - {track['title']}") else: - print(" No tracks found") + _beatport_log(" No tracks found") # Test Top 100 Releases (new method) - print("\n2b. Testing Top 100 Releases (new method)...") + _beatport_log("\n2b. Testing Top 100 Releases (new method)...") releases_tracks = scraper.scrape_top_100_releases(limit=5) if releases_tracks: - print(f" Found {len(releases_tracks)} tracks:") + _beatport_log(f" Found {len(releases_tracks)} tracks:") for track in releases_tracks[:3]: - print(f" ā€¢ {track['artist']} - {track['title']}") + _beatport_log(f" ā€¢ {track['artist']} - {track['title']}") else: - print(" No tracks found") + _beatport_log(" No tracks found") # Test Improved New Releases - print("\n2c. Testing Improved New Releases...") + _beatport_log("\n2c. Testing Improved New Releases...") new_releases = scraper.scrape_new_releases(limit=5) if new_releases: - print(f" Found {len(new_releases)} tracks:") + _beatport_log(f" Found {len(new_releases)} tracks:") for track in new_releases[:3]: - print(f" ā€¢ {track['artist']} - {track['title']}") + _beatport_log(f" ā€¢ {track['artist']} - {track['title']}") else: - print(" No tracks found") + _beatport_log(" No tracks found") # Test Improved DJ Charts - print("\n2d. Testing Improved DJ Charts...") + _beatport_log("\n2d. Testing Improved DJ Charts...") dj_charts = scraper.scrape_dj_charts(limit=5) if dj_charts: - print(f" Found {len(dj_charts)} charts:") + _beatport_log(f" Found {len(dj_charts)} charts:") for chart in dj_charts[:3]: - print(f" ā€¢ {chart['title']} by {chart['artist']}") + _beatport_log(f" ā€¢ {chart['title']} by {chart['artist']}") else: - print(" No charts found") + _beatport_log(" No charts found") # Test Improved Featured Charts - print("\n2e. Testing Improved Featured Charts...") + _beatport_log("\n2e. Testing Improved Featured Charts...") featured_charts = scraper.scrape_featured_charts(limit=5) if featured_charts: - print(f" Found {len(featured_charts)} items:") + _beatport_log(f" Found {len(featured_charts)} items:") for item in featured_charts[:3]: - print(f" ā€¢ {item['title']} by {item['artist']}") + _beatport_log(f" ā€¢ {item['title']} by {item['artist']}") else: - print(" No items found") + _beatport_log(" No items found") return { 'chart_discovery': chart_discovery, @@ -4429,66 +4464,66 @@ def test_improved_chart_sections(): def main(): """Test the unified Beatport scraper""" - print("Beatport Unified Scraper - Improved Chart Discovery") - print("=" * 80) + _beatport_log("Beatport Unified Scraper - Improved Chart Discovery") + _beatport_log("=" * 80) scraper = BeatportUnifiedScraper() # Test New on Beatport Hero first - print("\nNEW ON BEATPORT HERO TEST") + _beatport_log("\nNEW ON BEATPORT HERO TEST") hero_tracks = scraper.scrape_new_on_beatport_hero(limit=10) if hero_tracks: - print(f"Successfully extracted {len(hero_tracks)} tracks from hero slideshow") + _beatport_log(f"Successfully extracted {len(hero_tracks)} tracks from hero slideshow") for i, track in enumerate(hero_tracks[:3]): # Show first 3 - print(f" {i+1}. {track.get('title', 'No title')} - {track.get('artist', 'No artist')}") - print(f" URL: {track.get('url', 'No URL')}") - print(f" Classes: {track.get('element_classes', 'No classes')}") + _beatport_log(f" {i+1}. {track.get('title', 'No title')} - {track.get('artist', 'No artist')}") + _beatport_log(f" URL: {track.get('url', 'No URL')}") + _beatport_log(f" Classes: {track.get('element_classes', 'No classes')}") else: - print("No tracks found in hero slideshow") + _beatport_log("No tracks found in hero slideshow") # Test improved chart sections - print("\nšŸ†• IMPROVED CHART SECTIONS TEST") + _beatport_log("\nšŸ†• IMPROVED CHART SECTIONS TEST") improved_results = test_improved_chart_sections() # Test dynamic genre discovery (existing) - print("\n\nšŸ†• DYNAMIC GENRE DISCOVERY TEST") + _beatport_log("\n\nšŸ†• DYNAMIC GENRE DISCOVERY TEST") discovered_genres = test_dynamic_genre_discovery() # Update scraper with discovered genres scraper.all_genres = discovered_genres # Test 1: Top 100 - print("\nTEST 1: Top 100 Chart") + _beatport_log("\nTEST 1: Top 100 Chart") top_100 = scraper.scrape_top_100(limit=10) # Test with 10 for now if top_100: - print(f"\nTop 100 Sample (showing first 5):") + _beatport_log(f"\nTop 100 Sample (showing first 5):") for track in top_100[:5]: - print(f" {track['position']}. {track['artist']} - {track['title']}") + _beatport_log(f" {track['position']}. {track['artist']} - {track['title']}") quality = scraper.test_data_quality(top_100) - print(f"\nData Quality: {quality['quality_score']:.1f}% ({quality['valid_tracks']}/{quality['total_tracks']} tracks)") + _beatport_log(f"\nData Quality: {quality['quality_score']:.1f}% ({quality['valid_tracks']}/{quality['total_tracks']} tracks)") else: - print("Failed to extract Top 100") + _beatport_log("Failed to extract Top 100") # Test 2: Sample of discovered genres - print("\nTEST 2: Dynamic Genre Charts Sample") + _beatport_log("\nTEST 2: Dynamic Genre Charts Sample") test_genres = scraper.all_genres[:5] # Test first 5 discovered genres - print(f"Testing {len(test_genres)} dynamically discovered genres...") + _beatport_log(f"Testing {len(test_genres)} dynamically discovered genres...") genre_results = {} for genre in test_genres: tracks = scraper.scrape_genre_charts(genre, limit=5) # 5 tracks per genre for testing if tracks: genre_results[genre['name']] = tracks - print(f"\n{genre['name']} Top 5:") + _beatport_log(f"\n{genre['name']} Top 5:") for track in tracks[:3]: - print(f" ā€¢ {track['artist']} - {track['title']}") + _beatport_log(f" ā€¢ {track['artist']} - {track['title']}") # Test 3: Full genre scraping (smaller sample) - print("\nTEST 3: Full Multi-Genre Scraping") - print("Testing parallel scraping of 10 genres...") + _beatport_log("\nTEST 3: Full Multi-Genre Scraping") + _beatport_log("Testing parallel scraping of 10 genres...") sample_genres = scraper.all_genres[:10] scraper.all_genres = sample_genres # Temporarily limit for testing @@ -4496,29 +4531,29 @@ def main(): all_genre_results = scraper.scrape_all_genres(tracks_per_genre=5, max_workers=3) # Results summary - print("\n" + "=" * 80) - print("FINAL RESULTS SUMMARY") - print("=" * 80) + _beatport_log("\n" + "=" * 80) + _beatport_log("FINAL RESULTS SUMMARY") + _beatport_log("=" * 80) total_tracks = len(top_100) if top_100 else 0 total_genres = len(all_genre_results) total_genre_tracks = sum(len(tracks) for tracks in all_genre_results.values()) - print(f"ā€¢ Top 100 tracks extracted: {total_tracks}") - print(f"ā€¢ Genres successfully scraped: {total_genres}") - print(f"ā€¢ Total genre tracks: {total_genre_tracks}") - print(f"ā€¢ Grand total tracks: {total_tracks + total_genre_tracks}") + _beatport_log(f"ā€¢ Top 100 tracks extracted: {total_tracks}") + _beatport_log(f"ā€¢ Genres successfully scraped: {total_genres}") + _beatport_log(f"ā€¢ Total genre tracks: {total_genre_tracks}") + _beatport_log(f"ā€¢ Grand total tracks: {total_tracks + total_genre_tracks}") # Data quality assessment all_tracks = (top_100 or []) + [track for tracks in all_genre_results.values() for track in tracks] if all_tracks: overall_quality = scraper.test_data_quality(all_tracks) - print(f"\nOVERALL DATA QUALITY") - print(f"ā€¢ Quality Score: {overall_quality['quality_score']:.1f}%") - print(f"ā€¢ Valid Tracks: {overall_quality['valid_tracks']}/{overall_quality['total_tracks']}") + _beatport_log(f"\nOVERALL DATA QUALITY") + _beatport_log(f"ā€¢ Quality Score: {overall_quality['quality_score']:.1f}%") + _beatport_log(f"ā€¢ Valid Tracks: {overall_quality['valid_tracks']}/{overall_quality['total_tracks']}") if overall_quality['issues']: - print(f"ā€¢ Issues Found: {len(overall_quality['issues'])}") + _beatport_log(f"ā€¢ Issues Found: {len(overall_quality['issues'])}") # Save results results = { @@ -4536,28 +4571,28 @@ def main(): try: with open('beatport_unified_results.json', 'w', encoding='utf-8') as f: json.dump(results, f, indent=2, ensure_ascii=False) - print(f"\nResults saved to beatport_unified_results.json") + _beatport_log(f"\nResults saved to beatport_unified_results.json") except Exception as e: - print(f"Failed to save results: {e}") + _beatport_log(f"Failed to save results: {e}") # Virtual playlist possibilities if overall_quality['quality_score'] > 70: - print(f"\nSUCCESS! Ready for virtual playlist creation") - print(f"You can now create playlists for:") - print(f" ā€¢ Beatport Top 100") + _beatport_log(f"\nSUCCESS! Ready for virtual playlist creation") + _beatport_log(f"You can now create playlists for:") + _beatport_log(f" ā€¢ Beatport Top 100") for genre_name in list(all_genre_results.keys())[:5]: - print(f" ā€¢ {genre_name} Top 100") + _beatport_log(f" ā€¢ {genre_name} Top 100") if len(all_genre_results) > 5: - print(f" ā€¢ ...and {len(all_genre_results) - 5} more genres!") + _beatport_log(f" ā€¢ ...and {len(all_genre_results) - 5} more genres!") - print(f"\nIntegration Notes:") - print(f" ā€¢ Artist and title data is clean and ready") - print(f" ā€¢ {total_genres} genres confirmed working") - print(f" ā€¢ Data quality: {overall_quality['quality_score']:.1f}%") + _beatport_log(f"\nIntegration Notes:") + _beatport_log(f" ā€¢ Artist and title data is clean and ready") + _beatport_log(f" ā€¢ {total_genres} genres confirmed working") + _beatport_log(f" ā€¢ Data quality: {overall_quality['quality_score']:.1f}%") else: - print(f"\nData quality needs improvement ({overall_quality['quality_score']:.1f}%)") - print(f"Consider refining extraction methods") + _beatport_log(f"\nData quality needs improvement ({overall_quality['quality_score']:.1f}%)") + _beatport_log(f"Consider refining extraction methods") if __name__ == "__main__": - main() \ No newline at end of file + main() diff --git a/config/settings.py b/config/settings.py index e304f1aa..19b24e6c 100644 --- a/config/settings.py +++ b/config/settings.py @@ -5,8 +5,14 @@ import sqlite3 from typing import Dict, Any, Optional from cryptography.fernet import Fernet, InvalidToken from pathlib import Path +from utils.logging_config import get_logger + + +logger = get_logger("config") class ConfigManager: + _VALID_LOG_LEVELS = frozenset({"DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"}) + def __init__(self, config_path: str = "config/config.json"): # Determine strict absolute path to settings.py directory to help resolve config.json # This handles cases where CWD is different (e.g. running from /Users vs /Users/project) @@ -33,7 +39,7 @@ class ConfigManager: # Default to project path even if it doesn't exist yet (for creation/fallback) self.config_path = project_path - print(f"ConfigManager initialized with path: {self.config_path}") + logger.info(f"ConfigManager initialized with path: {self.config_path}") self.config_data: Dict[str, Any] = {} self._fernet: Optional[Fernet] = None @@ -45,7 +51,7 @@ class ConfigManager: else: self.database_path = self.base_dir / "database" / "music_library.db" - print(f"Database path set to: {self.database_path}") + logger.info(f"Database path set to: {self.database_path}") self.load_config(str(self.config_path)) @@ -107,7 +113,7 @@ class ConfigManager: try: import shutil shutil.move(str(old_key_file), str(key_file)) - print(f"[MIGRATE] Moved encryption key to {key_file}") + logger.info(f"Moved encryption key to {key_file}") except Exception: key_file = old_key_file # Fall back to old location if key_file.exists(): @@ -155,8 +161,10 @@ class ConfigManager: return decrypted except InvalidToken: # Key mismatch ā€” encrypted with a different key (key file deleted/replaced) - print(f"[ERROR] Failed to decrypt a config value ā€” encryption key may have changed. " - f"Re-enter credentials in Settings or restore the original .encryption_key file.") + logger.error( + "Failed to decrypt a config value ā€” encryption key may have changed. " + "Re-enter credentials in Settings or restore the original .encryption_key file." + ) return value except Exception: return value @@ -243,11 +251,11 @@ class ConfigManager: needs_migration = True break if needs_migration: - print("[MIGRATE] Encrypting sensitive config values at rest...") + logger.info("Encrypting sensitive config values at rest...") self._save_to_database(self.config_data) - print("[OK] Sensitive config values encrypted successfully") + logger.info("Sensitive config values encrypted successfully") except Exception as e: - print(f"[WARN] Could not migrate encryption: {e}") + logger.warning(f"Could not migrate encryption: {e}") def _ensure_database_exists(self): """Ensure database file and metadata table exist""" @@ -271,7 +279,7 @@ class ConfigManager: conn.commit() conn.close() except Exception as e: - print(f"Warning: Could not ensure database exists: {e}") + logger.warning(f"Could not ensure database exists: {e}") def _load_from_database(self) -> Optional[Dict[str, Any]]: """Load configuration from database, decrypting sensitive values.""" @@ -289,18 +297,70 @@ class ConfigManager: config_data = json.loads(row[0]) # Decrypt sensitive values (gracefully handles plaintext migration) config_data = self._decrypt_sensitive(config_data) - print("[OK] Configuration loaded from database") + logger.info("Configuration loaded from database") return config_data else: return None except Exception as e: - print(f"Warning: Could not load config from database: {e}") + logger.warning(f"Could not load config from database: {e}") return None finally: if conn: conn.close() + def _load_stored_log_level(self) -> Optional[str]: + """Load the persisted UI log level preference, if one exists.""" + conn = None + try: + self._ensure_database_exists() + conn = sqlite3.connect(str(self.database_path), timeout=30.0) + conn.execute("PRAGMA journal_mode=WAL") + cursor = conn.cursor() + cursor.execute("SELECT value FROM metadata WHERE key = 'log_level'") + row = cursor.fetchone() + if not row or not row[0]: + return None + + level = str(row[0]).upper() + if level not in self._VALID_LOG_LEVELS: + logger.warning(f"Ignoring invalid stored log level: {row[0]}") + return None + return level + except Exception as e: + logger.warning(f"Could not load stored log level from database: {e}") + return None + finally: + if conn: + conn.close() + + def _load_env_log_level(self) -> Optional[str]: + """Load the log level override from the environment, if one exists.""" + raw_level = os.environ.get("SOULSYNC_LOG_LEVEL") + if not raw_level: + return None + + level = raw_level.upper() + if level not in self._VALID_LOG_LEVELS: + logger.warning(f"Ignoring invalid SOULSYNC_LOG_LEVEL value: {raw_level}") + return None + + return level + + def _apply_log_level_overrides(self, config_data: Dict[str, Any]) -> Dict[str, Any]: + """Overlay env and persisted log level preferences onto the loaded config.""" + env_level = self._load_env_log_level() + if env_level: + config_data.setdefault("logging", {})["level"] = env_level + logger.info(f"Using log level from SOULSYNC_LOG_LEVEL: {env_level}") + return config_data + + stored_level = self._load_stored_log_level() + if stored_level: + config_data.setdefault("logging", {})["level"] = stored_level + logger.info(f"Using stored logging level from database: {stored_level}") + return config_data + def _save_to_database(self, config_data: Dict[str, Any]) -> bool: """Save configuration to database, encrypting sensitive values.""" conn = None @@ -325,7 +385,7 @@ class ConfigManager: return True except Exception as e: - print(f"Error: Could not save config to database: {e}") + logger.error(f"Could not save config to database: {e}") return False finally: if conn: @@ -337,12 +397,12 @@ class ConfigManager: if self.config_path.exists(): with open(self.config_path, 'r') as f: config_data = json.load(f) - print(f"[OK] Configuration loaded from {self.config_path}") + logger.info(f"Configuration loaded from {self.config_path}") return config_data else: return None except Exception as e: - print(f"Warning: Could not load config from file: {e}") + logger.warning(f"Could not load config from file: {e}") return None def _get_default_config(self) -> Dict[str, Any]: @@ -506,45 +566,45 @@ class ConfigManager: 2. config.json (migration from file-based config) 3. Defaults (fresh install) """ - print(f"Loading configuration...") + logger.info("Loading configuration...") # Try loading from database first config_data = self._load_from_database() if config_data: # Configuration exists in database - self.config_data = config_data + self.config_data = self._apply_log_level_overrides(config_data) # Ensure sensitive values are encrypted at rest (one-time migration) self._migrate_encrypt_if_needed() return # Database is empty - try migration from config.json - print(f"Configuration not found in database. Attempting migration from: {self.config_path}") + logger.info(f"Configuration not found in database. Attempting migration from: {self.config_path}") config_data = self._load_from_config_file() if config_data: # Migrate from config.json to database - print("[MIGRATE] Migrating configuration from config.json to database...") + logger.info("Migrating configuration from config.json to database...") if self._save_to_database(config_data): - print("[OK] Configuration migrated successfully to database.") - self.config_data = config_data + logger.info("Configuration migrated successfully to database.") + self.config_data = self._apply_log_level_overrides(config_data) return else: - print("[WARN] Migration failed - using file-based config temporarily.") - self.config_data = config_data + logger.warning("Migration failed - using file-based config temporarily.") + self.config_data = self._apply_log_level_overrides(config_data) return # No config.json either - use defaults - print("[INFO] ā„¹ļø No existing configuration found (DB or File) - using defaults") + logger.info("No existing configuration found (DB or File) - using defaults") config_data = self._get_default_config() # Try to save defaults to database if self._save_to_database(config_data): - print("[OK] Default configuration saved to database") + logger.info("Default configuration saved to database") else: - print("[WARN] Could not save defaults to database - using in-memory config") + logger.warning("Could not save defaults to database - using in-memory config") - self.config_data = config_data + self.config_data = self._apply_log_level_overrides(config_data) def _save_config(self): """Save configuration to database with retry on lock.""" @@ -558,14 +618,14 @@ class ConfigManager: if not success: # Fallback: Try to save to config.json if database fails - print("[WARN] Database save failed - attempting file fallback") + logger.warning("Database save failed - attempting file fallback") try: self.config_path.parent.mkdir(parents=True, exist_ok=True) with open(self.config_path, 'w') as f: json.dump(self.config_data, f, indent=2) - print("[OK] Configuration saved to config.json as fallback") + logger.info("Configuration saved to config.json as fallback") except Exception as e: - print(f"[ERROR] Failed to save configuration: {e}") + logger.error(f"Failed to save configuration: {e}") def get(self, key: str, default: Any = None) -> Any: keys = key.split('.') diff --git a/core/acoustid_client.py b/core/acoustid_client.py index 80c64709..a0edb64b 100644 --- a/core/acoustid_client.py +++ b/core/acoustid_client.py @@ -20,6 +20,7 @@ from typing import Dict, List, Optional, Any, Tuple from pathlib import Path import os import shutil +import logging import logging.handlers from utils.logging_config import get_logger @@ -29,22 +30,23 @@ from config.settings import config_manager FPCALC_BIN_DIR = Path(__file__).parent.parent / "bin" CHROMAPRINT_VERSION = "1.5.1" -# Set up dedicated AcoustID logger with its own file -logger = get_logger("acoustid_client") - -# Add dedicated file handler for AcoustID logs -_acoustid_log_path = Path(__file__).parent.parent / "logs" / "acoustid.log" +_acoustid_logger = logging.getLogger("soulsync.acoustid") +_acoustid_logger.setLevel(logging.DEBUG) +_acoustid_log_path = Path(config_manager.get('logging.path', 'logs/app.log')).parent / "acoustid.log" _acoustid_log_path.parent.mkdir(parents=True, exist_ok=True) -_acoustid_file_handler = logging.handlers.RotatingFileHandler( - _acoustid_log_path, encoding='utf-8', maxBytes=5*1024*1024, backupCount=2 -) -_acoustid_file_handler.setLevel(logging.DEBUG) -_acoustid_file_handler.setFormatter(logging.Formatter( - fmt='%(asctime)s - %(name)s - %(levelname)s - %(funcName)s:%(lineno)d - %(message)s', - datefmt='%Y-%m-%d %H:%M:%S' -)) -logger.addHandler(_acoustid_file_handler) -logging.getLogger("newmusic.acoustid_verification").addHandler(_acoustid_file_handler) +if not _acoustid_logger.handlers: + _acoustid_file_handler = logging.handlers.RotatingFileHandler( + _acoustid_log_path, encoding='utf-8', maxBytes=5*1024*1024, backupCount=2 + ) + _acoustid_file_handler.setLevel(logging.DEBUG) + _acoustid_file_handler.setFormatter(logging.Formatter( + fmt='%(asctime)s - %(name)s - %(levelname)s - %(message)s', + datefmt='%Y-%m-%d %H:%M:%S' + )) + _acoustid_logger.addHandler(_acoustid_file_handler) + _acoustid_logger.propagate = False + +logger = get_logger("acoustid.client") # Check if pyacoustid is available try: @@ -194,7 +196,7 @@ class AcoustIDClient: result = client.fingerprint_and_lookup("/path/to/audio.mp3") if result: for mbid in result['recording_mbids']: - print(f"Match: {mbid}") + logger.info(f"Match: {mbid}") """ def __init__(self): diff --git a/core/acoustid_verification.py b/core/acoustid_verification.py index 5bfb6f92..ee4100b5 100644 --- a/core/acoustid_verification.py +++ b/core/acoustid_verification.py @@ -17,7 +17,7 @@ from utils.logging_config import get_logger from core.acoustid_client import AcoustIDClient from core.musicbrainz_client import MusicBrainzClient -logger = get_logger("acoustid_verification") +logger = get_logger("acoustid.verification") # Thresholds MIN_ACOUSTID_SCORE = 0.80 # Minimum AcoustID fingerprint score to trust diff --git a/core/api_call_tracker.py b/core/api_call_tracker.py index 104e1a29..357ba4e4 100644 --- a/core/api_call_tracker.py +++ b/core/api_call_tracker.py @@ -12,6 +12,11 @@ import threading import time from collections import deque, defaultdict +from utils.logging_config import get_logger + + +logger = get_logger("api_call_tracker") + # Known rate limits per service (calls/minute) RATE_LIMITS = { @@ -281,13 +286,16 @@ class ApiCallTracker: with open(_PERSIST_PATH, 'w') as f: json.dump({'ts': now, 'history': data, 'events': events}, f) except Exception as e: - print(f"[ApiCallTracker] Failed to save history: {e}") + logger.error(f"[ApiCallTracker] Failed to save history: {e}") def _load(self): """Restore 24h minute history from disk. Called on init.""" try: if not os.path.exists(_PERSIST_PATH): return + if os.path.getsize(_PERSIST_PATH) == 0: + logger.info(f"[ApiCallTracker] History file is empty, starting fresh: {_PERSIST_PATH}") + return with open(_PERSIST_PATH, 'r') as f: raw = json.load(f) saved_ts = raw.get('ts', 0) @@ -305,9 +313,11 @@ class ApiCallTracker: for e in events: if e.get('ts', 0) >= cutoff: self._events.append(e) - print(f"[ApiCallTracker] Restored history for {len(history)} services, {len(events)} events") + logger.info(f"[ApiCallTracker] Restored history for {len(history)} services, {len(events)} events") + except json.JSONDecodeError as e: + logger.warning(f"[ApiCallTracker] History file is not valid JSON, starting fresh: {_PERSIST_PATH} ({e})") except Exception as e: - print(f"[ApiCallTracker] Failed to load history: {e}") + logger.error(f"[ApiCallTracker] Failed to load history: {e}") # Singleton instance diff --git a/core/auto_import_worker.py b/core/auto_import_worker.py index d05af689..a564d862 100644 --- a/core/auto_import_worker.py +++ b/core/auto_import_worker.py @@ -968,6 +968,34 @@ class AutoImportWorker: artist_name = identification.get('artist_name', 'Unknown') album_name = identification.get('album_name', 'Unknown') image_url = identification.get('image_url', '') + + # Parent folder artist override: if the staging folder structure is + # Artist/Albums/AlbumName or Artist/AlbumName, use the parent folder + # as the artist name when the tag-extracted artist looks wrong. + # This handles mixtapes/compilations where embedded tags have DJ names. + try: + staging_root = self._resolve_staging_path() or self.staging_path + rel_path = os.path.relpath(candidate.path, staging_root) + parts = [p for p in rel_path.replace('\\', '/').split('/') if p] + + # parts[0] = artist folder, parts[1] = album or category subfolder, etc. + # Only attempt override if there's at least 2 levels (artist/album) + folder_artist = None + if len(parts) >= 2: + _category_names = {'albums', 'singles', 'eps', 'compilations', 'mixtapes', + 'discography', 'music', 'downloads'} + if len(parts) >= 3 and parts[1].lower() in _category_names: + # Artist/Albums/AlbumFolder ā†’ parts[0] is artist + folder_artist = parts[0] + elif parts[0].lower() not in _category_names: + # Artist/AlbumFolder ā†’ parts[0] is artist + folder_artist = parts[0] + + if folder_artist and folder_artist.lower() != artist_name.lower(): + logger.info(f"[Auto-Import] Parent folder artist '{folder_artist}' differs from tag artist '{artist_name}' ā€” using folder artist") + artist_name = folder_artist + except Exception: + pass release_date = identification.get('release_date', '') or album_data.get('release_date', '') # Compute total discs diff --git a/core/database_update_worker.py b/core/database_update_worker.py index 77c23436..e0645e2d 100644 --- a/core/database_update_worker.py +++ b/core/database_update_worker.py @@ -930,10 +930,16 @@ class DatabaseUpdateWorker: if (db_track.title != current_title or db_track.artist_name != current_artist or db_track.album_title != current_album): - logger.debug(f"Metadata change detected for track ID {track_id}:") - logger.debug(f" Title: '{db_track.title}' ā†’ '{current_title}'") - logger.debug(f" Artist: '{db_track.artist_name}' ā†’ '{current_artist}'") - logger.debug(f" Album: '{db_track.album_title}' ā†’ '{current_album}'") + logger.debug( + "Metadata change detected for track %s: title=%rā†’%r artist=%rā†’%r album=%rā†’%r", + track_id, + db_track.title, + current_title, + db_track.artist_name, + current_artist, + db_track.album_title, + current_album, + ) changes_detected += 1 except Exception as e: diff --git a/core/download_orchestrator.py b/core/download_orchestrator.py index f91a9c55..5f120309 100644 --- a/core/download_orchestrator.py +++ b/core/download_orchestrator.py @@ -61,10 +61,12 @@ class DownloadOrchestrator: logger.info(f"Download Orchestrator initialized - Mode: {self.mode}") if self.mode == 'hybrid': - if self.hybrid_order: - logger.info(f" Source priority: {' ā†’ '.join(self.hybrid_order)}") - else: - logger.info(f" Primary: {self.hybrid_primary}, Fallback: {self.hybrid_secondary}") + logger.info( + "Hybrid source order: order=%s primary=%s secondary=%s", + " ā†’ ".join(self.hybrid_order) if self.hybrid_order else "default", + self.hybrid_primary, + self.hybrid_secondary, + ) def _safe_init(self, name, cls): """Initialize a download client, returning None on failure instead of crashing.""" @@ -154,8 +156,10 @@ class DownloadOrchestrator: except Exception: results[source] = False - status_parts = [f"{s}: {'' if ok else ''}" for s, ok in results.items()] - logger.info(f" {' | '.join(status_parts)}") + logger.info( + "Hybrid connection check: %s", + " | ".join(f"{source}={'ok' if ok else 'fail'}" for source, ok in results.items()), + ) return any(results.values()) diff --git a/core/jellyfin_client.py b/core/jellyfin_client.py index dac2212a..dcd4f14d 100644 --- a/core/jellyfin_client.py +++ b/core/jellyfin_client.py @@ -1633,14 +1633,14 @@ class JellyfinClient: def is_library_scanning(self, library_name: str = "Music") -> bool: """Check if Jellyfin library is currently scanning""" if not self.ensure_connection(): - logger.debug("DEBUG: Not connected to Jellyfin, cannot check scan status") + logger.debug("Not connected to Jellyfin, cannot check scan status") return False try: # Check scheduled tasks for library scan activities response = self._make_request('/ScheduledTasks') if not response: - logger.debug("DEBUG: Could not get scheduled tasks") + logger.debug("Could not get scheduled tasks") return False for task in response: @@ -1650,10 +1650,14 @@ class JellyfinClient: # Look for library scan related tasks that are running if ('scan' in task_name or 'refresh' in task_name or 'library' in task_name): if task_state in ['Running', 'Cancelling']: - logger.debug(f"DEBUG: Found running scan task: {task.get('Name')} (State: {task_state})") + logger.debug( + "Found running scan task: name=%s state=%s", + task.get('Name'), + task_state, + ) return True - logger.debug("DEBUG: No active scan tasks detected") + logger.debug("No active scan tasks detected") return False except Exception as e: @@ -1819,4 +1823,4 @@ class JellyfinClient: return True except Exception as e: logger.error(f"Error setting metadata-only mode: {e}") - return False \ No newline at end of file + return False diff --git a/core/matching_engine.py b/core/matching_engine.py index d38a5916..da1fb9bc 100644 --- a/core/matching_engine.py +++ b/core/matching_engine.py @@ -421,7 +421,7 @@ class MusicMatchingEngine: if is_likely_album and 4 <= len(potential_album_part) <= 30: cleaned_title = re.sub(dash_pattern, '', track_title).strip() - print(f"Heuristic album detection: '{original_title}' ā†’ '{cleaned_title}' (removed: '{potential_album_part}')") + logger.debug(f"Heuristic album detection: '{original_title}' ā†’ '{cleaned_title}' (removed: '{potential_album_part}')") return cleaned_title, True return track_title, False @@ -1004,13 +1004,13 @@ class MusicMatchingEngine: # Debug logging for troubleshooting if scored_results and not confident_results: - print(f"DEBUG: Found {len(scored_results)} scored results but none met confidence threshold 0.58") + logger.debug(f"Found {len(scored_results)} scored results but none met confidence threshold 0.58") for i, result in enumerate(sorted_results[:3]): # Show top 3 - print(f" {i+1}. {result.confidence:.3f} - {getattr(result, 'version_type', 'unknown')} - {result.filename[:60]}...") + logger.debug(f" {i+1}. {result.confidence:.3f} - {getattr(result, 'version_type', 'unknown')} - {result.filename[:60]}...") elif confident_results: - print(f"DEBUG: {len(confident_results)} results passed confidence threshold 0.58") + logger.debug(f"{len(confident_results)} results passed confidence threshold 0.58") for i, result in enumerate(confident_results[:3]): # Show top 3 - print(f" {i+1}. {result.confidence:.3f} - {getattr(result, 'version_type', 'unknown')} - {result.filename[:60]}...") + logger.debug(f" {i+1}. {result.confidence:.3f} - {getattr(result, 'version_type', 'unknown')} - {result.filename[:60]}...") return confident_results diff --git a/core/metadata_service.py b/core/metadata_service.py index bebe1f92..04013a49 100644 --- a/core/metadata_service.py +++ b/core/metadata_service.py @@ -10,6 +10,7 @@ auth checks, or source-fallback behavior. import threading from dataclasses import dataclass from typing import List, Optional, Dict, Any, Literal +import requests from core.spotify_client import SpotifyClient from core.itunes_client import iTunesClient from utils.logging_config import get_logger @@ -1032,8 +1033,15 @@ def check_album_completion( artist_name: str, source_override: Optional[str] = None, source_chain: Optional[List[str]] = None, + candidate_albums: Optional[List[Any]] = None, ) -> Dict[str, Any]: - """Check completion status for a single album.""" + """Check completion status for a single album. + + When `candidate_albums` is provided, the DB matcher skips per-album SQL + searches and scores every pre-fetched candidate in-memory. Intended for + callers iterating a discography that have already loaded the artist's + full library once via `db.get_candidate_albums_for_artist(...)`. + """ try: source_chain = source_chain or _get_completion_source_chain(source_override) album_name = album_data.get('name', '') @@ -1045,7 +1053,7 @@ def check_album_completion( if total_tracks == 0 and album_id: logger.debug("No track count found for '%s' (%s)", album_name, album_id) - print(f"Checking album: '{album_name}' ({total_tracks} tracks)") + logger.debug(f"Checking album: '{album_name}' ({total_tracks} tracks)") formats = [] # Check if album exists in database with completeness info @@ -1057,10 +1065,11 @@ def check_album_completion( artist=artist_name, expected_track_count=total_tracks if total_tracks > 0 else None, confidence_threshold=0.7, - server_source=active_server + server_source=active_server, + candidate_albums=candidate_albums ) except Exception as db_error: - print(f"Database error for album '{album_name}': {db_error}") + logger.error(f"Database error for album '{album_name}': {db_error}") return { "id": album_id, "name": album_name, @@ -1088,7 +1097,14 @@ def check_album_completion( else: status = "missing" - print(f" Result: {owned_tracks}/{expected_tracks or total_tracks} tracks ({completion_percentage:.1f}%) - {status}") + logger.debug( + "Album completion result: owned=%s expected=%s total=%s completion=%.1f status=%s", + owned_tracks, + expected_tracks or total_tracks, + total_tracks, + completion_percentage, + status, + ) return { "id": album_id, @@ -1103,7 +1119,7 @@ def check_album_completion( } except Exception as e: - print(f"Error checking album completion for '{album_data.get('name', 'Unknown')}': {e}") + logger.error(f"Error checking album completion for '{album_data.get('name', 'Unknown')}': {e}") return { "id": album_data.get('id', ''), "name": album_data.get('name', 'Unknown'), @@ -1123,8 +1139,16 @@ def check_single_completion( artist_name: str, source_override: Optional[str] = None, source_chain: Optional[List[str]] = None, + candidate_albums: Optional[List[Any]] = None, + candidate_tracks: Optional[List[Any]] = None, ) -> Dict[str, Any]: - """Check completion status for a single/EP.""" + """Check completion status for a single/EP. + + `candidate_albums` applies to the EP branch (treated as an album lookup). + `candidate_tracks` applies to the true-single branch (track-level lookup). + Both are optional; None on either preserves the legacy per-item SQL path + for that branch. + """ try: source_chain = source_chain or _get_completion_source_chain(source_override) single_name = single_data.get('name', '') @@ -1137,7 +1161,12 @@ def check_single_completion( if total_tracks == 0: total_tracks = _resolve_completion_track_total(single_data, source_chain) or 1 - print(f"Checking {album_type}: '{single_name}' ({total_tracks} tracks)") + logger.debug( + "Checking %s: name=%r tracks=%s", + album_type, + single_name, + total_tracks, + ) if album_type == 'ep' or total_tracks > 1: try: @@ -1148,10 +1177,11 @@ def check_single_completion( artist=artist_name, expected_track_count=total_tracks, confidence_threshold=0.7, - server_source=active_server + server_source=active_server, + candidate_albums=candidate_albums ) except Exception as db_error: - print(f"Database error for EP '{single_name}': {db_error}") + logger.error(f"Database error for EP '{single_name}': {db_error}") owned_tracks, expected_tracks, confidence = 0, total_tracks, 0.0 db_album = None @@ -1167,7 +1197,14 @@ def check_single_completion( else: status = "missing" - print(f" EP Result: {owned_tracks}/{expected_tracks or total_tracks} tracks ({completion_percentage:.1f}%) - {status}") + logger.debug( + "EP completion result: owned=%s expected=%s total=%s completion=%.1f status=%s", + owned_tracks, + expected_tracks or total_tracks, + total_tracks, + completion_percentage, + status, + ) return { "id": single_id, @@ -1189,10 +1226,11 @@ def check_single_completion( title=single_name, artist=artist_name, confidence_threshold=0.7, - server_source=active_server + server_source=active_server, + candidate_tracks=candidate_tracks ) except Exception as db_error: - print(f"Database error for single '{single_name}': {db_error}") + logger.error(f"Database error for single '{single_name}': {db_error}") db_track, confidence = None, 0.0 owned_tracks = 1 if db_track else 0 @@ -1208,7 +1246,12 @@ def check_single_completion( elif ext: formats = [ext] - print(f" Single Result: {owned_tracks}/1 tracks ({completion_percentage:.1f}%) - {status}") + logger.debug( + "Single completion result: owned=%s expected=1 completion=%.1f status=%s", + owned_tracks, + completion_percentage, + status, + ) return { "id": single_id, @@ -1224,7 +1267,7 @@ def check_single_completion( } except Exception as e: - print(f"Error checking single/EP completion for '{single_data.get('name', 'Unknown')}': {e}") + logger.error(f"Error checking single/EP completion for '{single_data.get('name', 'Unknown')}': {e}") return { "id": single_data.get('id', ''), "name": single_data.get('name', 'Unknown'), @@ -1258,12 +1301,35 @@ def iter_artist_discography_completion_events( total_items = len(albums) + len(singles) processed_count = 0 + # Pre-fetch the artist's library albums AND tracks ONCE so per-item matching + # runs in-memory. Same batching trick as the library completion-stream endpoint. + import time as _time_metadata + candidate_albums = None + candidate_tracks = None + try: + from config.settings import config_manager as _cm_metadata + _active_server = _cm_metadata.get_active_media_server() + _t0 = _time_metadata.perf_counter() + candidate_albums = db.get_candidate_albums_for_artist(resolved_artist_name, server_source=_active_server) + _t1 = _time_metadata.perf_counter() + print(f"[artist-completion-stream] Pre-fetched {len(candidate_albums) if candidate_albums is not None else 0} library albums for '{resolved_artist_name}' in {(_t1 - _t0) * 1000:.0f}ms") + if candidate_albums: + _t2 = _time_metadata.perf_counter() + candidate_tracks = db.get_candidate_tracks_for_albums([a.id for a in candidate_albums]) + _t3 = _time_metadata.perf_counter() + print(f"[artist-completion-stream] Pre-fetched {len(candidate_tracks) if candidate_tracks is not None else 0} library tracks in {(_t3 - _t2) * 1000:.0f}ms") + except Exception as _pre_err: + print(f"[artist-completion-stream] Failed to pre-fetch candidates for '{resolved_artist_name}': {_pre_err}") + candidate_albums = None + candidate_tracks = None + yield { 'type': 'start', 'total_items': total_items, 'artist_name': resolved_artist_name, } + _loop_start = _time_metadata.perf_counter() for album in albums: try: completion_data = check_album_completion( @@ -1272,6 +1338,7 @@ def iter_artist_discography_completion_events( resolved_artist_name, source_override=source_override, source_chain=source_chain, + candidate_albums=candidate_albums, ) completion_data['type'] = 'album_completion' completion_data['container_type'] = 'albums' @@ -1295,6 +1362,8 @@ def iter_artist_discography_completion_events( resolved_artist_name, source_override=source_override, source_chain=source_chain, + candidate_albums=candidate_albums, + candidate_tracks=candidate_tracks, ) completion_data['type'] = 'single_completion' completion_data['container_type'] = 'singles' @@ -1310,6 +1379,9 @@ def iter_artist_discography_completion_events( 'error': str(e), } + _loop_elapsed = _time_metadata.perf_counter() - _loop_start + print(f"[artist-completion-stream] Processed {total_items} items for '{resolved_artist_name}' in {_loop_elapsed * 1000:.0f}ms") + yield { 'type': 'complete', 'processed_count': processed_count, @@ -1344,6 +1416,397 @@ def check_artist_discography_completion( } +def _fetch_musicmap_similar_artist_names(artist_name: str) -> List[str]: + """Fetch similar artist names from MusicMap.""" + if not (artist_name or '').strip(): + raise ValueError('Artist name is required') + + from bs4 import BeautifulSoup + from urllib.parse import quote_plus + + url_artist = quote_plus(artist_name.strip()) + musicmap_url = f'https://www.music-map.com/{url_artist}' + + headers = { + 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36', + 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8', + 'Accept-Language': 'en-US,en;q=0.5', + } + + logger.debug("Fetching MusicMap: %s", musicmap_url) + response = requests.get(musicmap_url, headers=headers, timeout=10) + response.raise_for_status() + + soup = BeautifulSoup(response.text, 'html.parser') + gnod_map = soup.find(id='gnodMap') + if not gnod_map: + raise ValueError('Could not find artist map on MusicMap') + + searched_artist_lower = _normalize_artist_name(artist_name) + similar_artist_names: List[str] = [] + seen_names = set() + + for anchor in gnod_map.find_all('a'): + artist_text = anchor.get_text(strip=True) + normalized_name = _normalize_artist_name(artist_text) + if not normalized_name or normalized_name == searched_artist_lower or normalized_name in seen_names: + continue + seen_names.add(normalized_name) + similar_artist_names.append(artist_text) + + logger.debug("Found %s similar artists from MusicMap", len(similar_artist_names)) + return similar_artist_names + + +def _extract_artist_image_url(artist_data: Any) -> Optional[str]: + if not artist_data: + return None + + images = _extract_lookup_value(artist_data, 'images', default=[]) or [] + if not isinstance(images, list): + try: + images = list(images) + except TypeError: + images = [] + + if images: + first_image = images[0] + image_url = _extract_lookup_value(first_image, 'url') + if image_url: + return image_url + + return _extract_lookup_value( + artist_data, + 'image_url', + 'thumb_url', + 'cover_image', + 'picture_xl', + 'picture_big', + 'picture_medium', + ) + + +def _build_similar_artist_payload(artist_data: Any, source: str) -> Optional[Dict[str, Any]]: + artist_id = _extract_lookup_value(artist_data, 'id', 'artist_id', 'spotify_id', 'itunes_id', 'deezer_id') + if not artist_id: + return None + + if isinstance(artist_data, dict): + name = artist_data.get('name') or artist_data.get('artist_name') or artist_data.get('title') + genres = artist_data.get('genres') or [] + popularity = artist_data.get('popularity') or artist_data.get('rank') or 0 + else: + name = ( + getattr(artist_data, 'name', None) + or getattr(artist_data, 'artist_name', None) + or getattr(artist_data, 'title', None) + ) + genres = getattr(artist_data, 'genres', None) or [] + popularity = getattr(artist_data, 'popularity', None) or getattr(artist_data, 'rank', None) or 0 + + if isinstance(genres, str): + genres = [genres] + elif not isinstance(genres, list): + try: + genres = list(genres) + except TypeError: + genres = [] + + try: + popularity = int(popularity or 0) + except Exception: + popularity = 0 + + return { + 'id': str(artist_id), + 'name': str(name or artist_id), + 'image_url': _extract_artist_image_url(artist_data), + 'genres': genres, + 'popularity': popularity, + 'source': source, + } + + +def _resolve_musicmap_artist_source_ids(artist_name: str, source_chain: List[str]) -> Dict[str, Optional[str]]: + searched_source_ids: Dict[str, Optional[str]] = {} + + for source in source_chain: + client = get_client_for_source(source) + if not client: + searched_source_ids[source] = None + continue + + search_results = _search_artists_for_source(source, client, artist_name, limit=1) + searched_source_ids[source] = _extract_lookup_value(search_results[0], 'id', 'artist_id') if search_results else None + + return searched_source_ids + + +def _match_musicmap_similar_artist( + candidate_name: str, + source_chain: List[str], + searched_artist_name: str, + searched_source_ids: Dict[str, Optional[str]], +) -> tuple[Optional[str], Optional[Dict[str, Any]]]: + target_name = _normalize_artist_name(candidate_name) + searched_name = _normalize_artist_name(searched_artist_name) + + for source in source_chain: + client = get_client_for_source(source) + if not client: + continue + + search_results = _search_artists_for_source(source, client, candidate_name, limit=1) + if not search_results: + continue + + matched_artist = _pick_best_artist_match(search_results, candidate_name) + if not matched_artist: + continue + + matched_name = _normalize_artist_name( + _extract_lookup_value(matched_artist, 'name', 'artist_name', 'title') + ) + if matched_name and matched_name == searched_name: + continue + + matched_id = _extract_lookup_value(matched_artist, 'id', 'artist_id') + if not matched_id: + continue + + if str(matched_id) == str(searched_source_ids.get(source) or ''): + continue + + payload = _build_similar_artist_payload(matched_artist, source) + if not payload: + continue + + if source == 'itunes' and not payload.get('image_url') and hasattr(client, 'get_artist'): + try: + full_artist = client.get_artist(str(matched_id)) + image_url = _extract_artist_image_url(full_artist) + if image_url: + payload['image_url'] = image_url + elif hasattr(client, '_get_artist_image_from_albums'): + album_image_url = client._get_artist_image_from_albums(str(matched_id)) + if album_image_url: + payload['image_url'] = album_image_url + except Exception as exc: + logger.debug("Could not enrich iTunes image for %s: %s", matched_id, exc) + + if target_name and _normalize_artist_name(payload['name']) == searched_name: + continue + + return source, payload + + return None, None + + +def iter_musicmap_similar_artist_events( + artist_name: str, + limit: int = 20, + source_override: Optional[str] = None, +): + """Yield MusicMap similar-artist events using source priority.""" + try: + source_chain = _get_source_chain_for_lookup( + MetadataLookupOptions(source_override=source_override, allow_fallback=True) + ) + available_sources = [source for source in source_chain if get_client_for_source(source)] + if not available_sources: + yield { + 'type': 'error', + 'error': 'No metadata providers available for similar artist matching', + 'status_code': 503, + } + return + + similar_artist_names = _fetch_musicmap_similar_artist_names(artist_name) + searched_source_ids = _resolve_musicmap_artist_source_ids(artist_name, source_chain) + + yield { + 'type': 'start', + 'artist_name': artist_name, + 'total_found': len(similar_artist_names), + 'source_priority': source_chain, + } + + matched_count = 0 + seen_names = set() + seen_ids = set() + + for candidate_name in similar_artist_names[:limit]: + normalized_candidate = _normalize_artist_name(candidate_name) + if not normalized_candidate or normalized_candidate in seen_names: + continue + + source, payload = _match_musicmap_similar_artist( + candidate_name, + source_chain, + artist_name, + searched_source_ids, + ) + if not payload: + continue + + payload_id = str(payload.get('id') or '') + if payload_id in seen_ids: + continue + + seen_names.add(normalized_candidate) + seen_ids.add(payload_id) + matched_count += 1 + + yield { + 'type': 'artist', + 'artist': payload, + 'source': source, + } + + yield { + 'type': 'complete', + 'complete': True, + 'total': matched_count, + 'total_found': len(similar_artist_names), + 'artist_name': artist_name, + 'source_priority': source_chain, + } + + except requests.exceptions.RequestException as exc: + logger.debug("Error fetching MusicMap for %s: %s", artist_name, exc) + yield { + 'type': 'error', + 'error': f'Failed to fetch from MusicMap: {exc}', + 'status_code': 502, + } + except ValueError as exc: + status_code = 404 if 'Could not find artist map on MusicMap' in str(exc) else 400 + yield { + 'type': 'error', + 'error': str(exc), + 'status_code': status_code, + } + except Exception as exc: + logger.error("Error streaming similar artists for %s: %s", artist_name, exc) + yield { + 'type': 'error', + 'error': str(exc), + 'status_code': 500, + } + + +def get_musicmap_similar_artists( + artist_name: str, + limit: int = 20, + source_override: Optional[str] = None, +) -> Dict[str, Any]: + """Return matched MusicMap similar artists as a single payload.""" + artists: List[Dict[str, Any]] = [] + total_found = 0 + error_message = None + status_code = 500 + source_priority: List[str] = [] + + for event in iter_musicmap_similar_artist_events( + artist_name, + limit=limit, + source_override=source_override, + ): + if event.get('type') == 'start': + total_found = event.get('total_found', 0) + source_priority = event.get('source_priority', []) + elif event.get('type') == 'artist' and event.get('artist'): + artists.append(event['artist']) + elif event.get('type') == 'complete': + total_found = event.get('total_found', total_found) + source_priority = event.get('source_priority', source_priority) + elif event.get('type') == 'error': + error_message = event.get('error', 'Unknown error') + status_code = int(event.get('status_code') or status_code or 500) + break + + if error_message: + return { + 'success': False, + 'error': error_message, + 'status_code': status_code, + 'artist': artist_name, + 'similar_artists': [], + 'total_found': total_found, + 'total_matched': 0, + 'source_priority': source_priority, + } + + return { + 'success': True, + 'artist': artist_name, + 'similar_artists': artists, + 'total_found': total_found, + 'total_matched': len(artists), + 'source_priority': source_priority, + } + + +def _get_artist_image_from_source(source: str, artist_id: str) -> Optional[str]: + client = get_client_for_source(source) + if not client: + return None + + try: + if source == 'spotify': + artist_data = client.get_artist(artist_id, allow_fallback=False) + else: + artist_data = client.get_artist(artist_id) + except Exception as exc: + logger.debug("Could not fetch artist image for %s on %s: %s", artist_id, source, exc) + artist_data = None + + image_url = _extract_artist_image_url(artist_data) + if image_url: + return image_url + + if hasattr(client, '_get_artist_image_from_albums'): + try: + return client._get_artist_image_from_albums(artist_id) + except Exception as exc: + logger.debug("Could not fetch artist album art for %s on %s: %s", artist_id, source, exc) + + return None + + +def get_artist_image_url( + artist_id: str, + source_override: Optional[str] = None, + plugin: Optional[str] = None, +) -> Optional[str]: + """Resolve an artist image URL using the configured source priority.""" + if not artist_id: + return None + + if artist_id.startswith('soul_'): + return None + + source_override = (source_override or '').strip().lower() + plugin = (plugin or '').strip().lower() + + if source_override == 'hydrabase': + if plugin in ('deezer', 'itunes'): + return _get_artist_image_from_source(plugin, artist_id) + if artist_id.isdigit(): + return _get_artist_image_from_source('itunes', artist_id) + return None + + if source_override: + return _get_artist_image_from_source(source_override, artist_id) + + for source in get_source_priority(get_primary_source()): + image_url = _get_artist_image_from_source(source, artist_id) + if image_url: + return image_url + + return None + + def get_deezer_client(): """Get cached Deezer client. diff --git a/core/plex_client.py b/core/plex_client.py index 39e0e9f4..dc97968b 100644 --- a/core/plex_client.py +++ b/core/plex_client.py @@ -937,7 +937,7 @@ class PlexClient: def is_library_scanning(self, library_name: str = "Music") -> bool: """Check if Plex library is currently scanning""" if not self.ensure_connection(): - logger.debug(f"DEBUG: Not connected to Plex, cannot check scan status") + logger.debug("Not connected to Plex, cannot check scan status") return False try: @@ -946,31 +946,31 @@ class PlexClient: # Check if library has a scanning attribute or is refreshing # The Plex API exposes this through the library's refreshing property refreshing = hasattr(library, 'refreshing') and library.refreshing - logger.debug(f"DEBUG: Library.refreshing = {refreshing}") + logger.debug("Library.refreshing = %s", refreshing) if refreshing: - logger.debug(f"DEBUG: Library is refreshing") + logger.debug("Library is refreshing") return True # Alternative method: Check server activities for scanning try: activities = self.server.activities() - logger.debug(f"DEBUG: Found {len(activities)} server activities") + logger.debug("Found %s server activities", len(activities)) for activity in activities: # Look for library scan activities activity_type = getattr(activity, 'type', 'unknown') activity_title = getattr(activity, 'title', 'unknown') - logger.debug(f"DEBUG: Activity - type: {activity_type}, title: {activity_title}") + logger.debug("Activity - type=%s title=%s", activity_type, activity_title) if (activity_type in ['library.scan', 'library.refresh'] and library_name.lower() in activity_title.lower()): - logger.debug(f"DEBUG: Found matching scan activity: {activity_title}") + logger.debug("Found matching scan activity: %s", activity_title) return True except Exception as activities_error: logger.debug(f"Could not check server activities: {activities_error}") - logger.debug(f"DEBUG: No scan activity detected") + logger.debug("No scan activity detected") return False except Exception as e: diff --git a/core/repair_jobs/__init__.py b/core/repair_jobs/__init__.py index 159dc7bc..c6f780e8 100644 --- a/core/repair_jobs/__init__.py +++ b/core/repair_jobs/__init__.py @@ -43,6 +43,7 @@ _JOB_MODULES = [ 'core.repair_jobs.album_tag_consistency', 'core.repair_jobs.live_commentary_cleaner', 'core.repair_jobs.unknown_artist_fixer', + 'core.repair_jobs.discography_backfill', ] diff --git a/core/repair_jobs/discography_backfill.py b/core/repair_jobs/discography_backfill.py new file mode 100644 index 00000000..6b307293 --- /dev/null +++ b/core/repair_jobs/discography_backfill.py @@ -0,0 +1,387 @@ +"""Discography Backfill Job ā€” finds missing albums/tracks for library artists.""" + +from core.metadata_service import ( + get_album_tracks_for_source, + get_artist_discography, + get_primary_source, + MetadataLookupOptions, +) +from core.repair_jobs import register_job +from core.repair_jobs.base import JobContext, JobResult, RepairJob +from core.watchlist_scanner import ( + is_acoustic_version, + is_compilation_album, + is_instrumental_version, + is_live_version, + is_remix_version, +) +from utils.logging_config import get_logger + +logger = get_logger("repair_job.discography_backfill") + + +@register_job +class DiscographyBackfillJob(RepairJob): + job_id = 'discography_backfill' + display_name = 'Discography Backfill' + description = 'Finds missing albums and tracks for artists in your library' + help_text = ( + 'Scans each artist in your library, fetches their full discography from ' + 'the configured metadata source, and adds any tracks you don\'t already ' + 'own to the wishlist for automatic download.\n\n' + 'Respects content filters: live versions, remixes, acoustic versions, ' + 'instrumentals, and compilations are excluded by default.\n\n' + 'Settings:\n' + '- Include Albums/EPs/Singles: Which release types to check\n' + '- Include Live/Remixes/Acoustic/Compilations/Instrumentals: Content type filters\n' + '- Max Artists Per Run: Limit how many artists to process per scan (default: 50)' + ) + icon = 'repair-icon-backfill' + default_enabled = False + default_interval_hours = 168 # Weekly + default_settings = { + 'include_albums': True, + 'include_eps': True, + 'include_singles': False, + 'include_live': False, + 'include_remixes': False, + 'include_acoustic': False, + 'include_compilations': False, + 'include_instrumentals': False, + 'max_artists_per_run': 50, + } + auto_fix = False + + def scan(self, context: JobContext) -> JobResult: + result = JobResult() + settings = self._get_settings(context) + + max_artists = settings.get('max_artists_per_run', 50) + + # Fetch all library artists with their metadata source IDs + artists = self._get_library_artists(context) + if not artists: + logger.info("No artists in library to scan") + return result + + total = min(len(artists), max_artists) + if context.update_progress: + context.update_progress(0, total) + if context.report_progress: + context.report_progress( + phase=f'Scanning discography for {total} artists...', + total=total, + ) + + logger.info("Discography backfill: scanning %d artists (of %d total)", total, len(artists)) + primary_source = get_primary_source() + + for i, artist in enumerate(artists[:max_artists]): + if context.check_stop(): + return result + if i % 5 == 0 and context.wait_if_paused(): + return result + + artist_id = artist['id'] + artist_name = artist['name'] + + if context.report_progress: + context.report_progress( + scanned=i + 1, total=total, + phase=f'Scanning {i + 1} / {total}', + log_line=f'Fetching discography: {artist_name}', + log_type='info', + ) + + try: + missing_count = self._scan_artist(context, artist, settings, primary_source, result) + if missing_count > 0: + logger.info("Found %d missing tracks for %s", missing_count, artist_name) + except Exception as e: + logger.warning("Error scanning discography for %s: %s", artist_name, e) + result.errors += 1 + + if context.update_progress and (i + 1) % 3 == 0: + context.update_progress(i + 1, total) + + # Rate limit between artists + if context.sleep_or_stop(1.0): + return result + + if context.update_progress: + context.update_progress(total, total) + + logger.info( + "Discography backfill complete: %d artists scanned, %d missing tracks found, %d errors", + result.scanned, result.findings_created, result.errors, + ) + return result + + def _scan_artist(self, context, artist, settings, primary_source, result): + """Scan one artist's discography and create findings for missing tracks.""" + artist_name = artist['name'] + result.scanned += 1 + + # Build source ID map for more accurate lookups + source_ids = {} + if artist.get('spotify_artist_id'): + source_ids['spotify'] = artist['spotify_artist_id'] + if artist.get('itunes_artist_id'): + source_ids['itunes'] = artist['itunes_artist_id'] + if artist.get('deezer_artist_id'): + source_ids['deezer'] = artist['deezer_artist_id'] + + # Fetch full discography + discography = get_artist_discography( + artist_id=str(artist['id']), + artist_name=artist_name, + options=MetadataLookupOptions( + allow_fallback=True, + skip_cache=False, + artist_source_ids=source_ids if source_ids else None, + ), + ) + + if not discography: + result.skipped += 1 + return 0 + + source = discography.get('source', primary_source) + albums = discography.get('albums', []) + singles = discography.get('singles', []) + missing_count = 0 + active_server = None + if context.config_manager: + active_server = context.config_manager.get_active_media_server() + + # Process albums and singles + for release in albums + singles: + if context.check_stop(): + return missing_count + + release_name = release.get('name', '') + release_id = release.get('id', '') + total_tracks = release.get('total_tracks', 0) or 0 + album_type = release.get('album_type', 'album') + release_image = release.get('image_url', '') + + # Filter by release type + if not self._should_include_release(total_tracks, album_type, settings): + continue + + # Filter compilation albums + if not settings.get('include_compilations', False): + if is_compilation_album(release_name): + continue + + # Fetch tracks for this release + try: + tracks_data = get_album_tracks_for_source(source, str(release_id)) + except Exception: + tracks_data = None + + if not tracks_data: + continue + + # Extract track items + items = [] + if isinstance(tracks_data, dict): + items = tracks_data.get('items', []) + elif isinstance(tracks_data, list): + items = tracks_data + + if not items: + continue + + for track_item in items: + if context.check_stop(): + return missing_count + + track_name = track_item.get('name', '') + if not track_name: + continue + + # Extract artist name from track + track_artists = track_item.get('artists', []) + if track_artists: + first_artist = track_artists[0] + if isinstance(first_artist, dict): + track_artist = first_artist.get('name', artist_name) + else: + track_artist = str(first_artist) + else: + track_artist = artist_name + + # Content type filters + if not settings.get('include_live', False): + if is_live_version(track_name, release_name): + continue + if not settings.get('include_remixes', False): + if is_remix_version(track_name, release_name): + continue + if not settings.get('include_acoustic', False): + if is_acoustic_version(track_name, release_name): + continue + if not settings.get('include_instrumentals', False): + if is_instrumental_version(track_name, release_name): + continue + + # Check if track already exists in library + db_track, confidence = context.db.check_track_exists( + track_name, track_artist, + confidence_threshold=0.7, + server_source=active_server, + album=release_name, + ) + if db_track and confidence >= 0.7: + continue # Already owned + + # Check if already in wishlist + try: + track_id = track_item.get('id', '') + if track_id and self._is_in_wishlist(context.db, track_id): + continue + except Exception: + pass + + # Build track data for wishlist + track_data = { + 'id': track_item.get('id', f'backfill_{hash(f"{track_artist}_{track_name}") % 100000}'), + 'name': track_name, + 'artists': [{'name': track_artist}], + 'album': { + 'name': release_name, + 'id': str(release_id), + 'images': [{'url': release_image}] if release_image else [], + 'album_type': album_type, + 'release_date': release.get('release_date', ''), + }, + 'duration_ms': track_item.get('duration_ms', 0), + 'track_number': track_item.get('track_number', 0), + 'disc_number': track_item.get('disc_number', 1), + } + + # Create finding + if context.create_finding: + try: + context.create_finding( + job_id=self.job_id, + finding_type='missing_discography_track', + severity='info', + entity_type='track', + entity_id=str(track_data['id']), + file_path=None, + title=f'Missing: {track_name}', + description=( + f'"{track_name}" by {track_artist} from ' + f'"{release_name}" is not in your library.' + ), + details={ + 'track_data': track_data, + 'artist_name': artist_name, + 'album_name': release_name, + 'album_image_url': release_image, + 'source': source, + }, + ) + result.findings_created += 1 + missing_count += 1 + except Exception as e: + logger.debug("Error creating finding for %s: %s", track_name, e) + result.errors += 1 + + return missing_count + + @staticmethod + def _should_include_release(total_tracks, album_type, settings): + """Check if a release should be included based on type settings.""" + # Use album_type from metadata source when available + normalized = (album_type or '').lower() + if normalized == 'compilation': + return settings.get('include_compilations', False) + if normalized in ('single',): + return settings.get('include_singles', False) + if normalized in ('ep',): + return settings.get('include_eps', True) + # Fall back to track count heuristic + if total_tracks >= 7: + return settings.get('include_albums', True) + elif total_tracks >= 4: + return settings.get('include_eps', True) + elif total_tracks >= 1: + return settings.get('include_singles', False) + return settings.get('include_albums', True) + + @staticmethod + def _is_in_wishlist(db, track_id): + """Check if a track ID is already in the wishlist.""" + conn = db._get_connection() + try: + cursor = conn.cursor() + cursor.execute( + "SELECT COUNT(*) FROM wishlist_tracks WHERE spotify_track_id = ?", + (str(track_id),), + ) + return cursor.fetchone()[0] > 0 + finally: + conn.close() + + def _get_library_artists(self, context): + """Get all artists from the library database with source IDs.""" + conn = None + try: + conn = context.db._get_connection() + cursor = conn.cursor() + + # Check which columns exist + cursor.execute("PRAGMA table_info(artists)") + columns = {col[1] for col in cursor.fetchall()} + + select = ["id", "name"] + if 'spotify_artist_id' in columns: + select.append("spotify_artist_id") + if 'itunes_artist_id' in columns: + select.append("itunes_artist_id") + if 'deezer_artist_id' in columns: + select.append("deezer_artist_id") + + cursor.execute(f""" + SELECT {', '.join(select)} + FROM artists + WHERE name IS NOT NULL AND name != '' AND name != 'Unknown Artist' + ORDER BY name + """) + return [dict(row) for row in cursor.fetchall()] + except Exception as e: + logger.error("Error fetching library artists: %s", e, exc_info=True) + return [] + finally: + if conn: + conn.close() + + def _get_settings(self, context: JobContext) -> dict: + if not context.config_manager: + return self.default_settings.copy() + cfg = context.config_manager.get(f'repair.jobs.{self.job_id}.settings', {}) + merged = self.default_settings.copy() + merged.update(cfg) + return merged + + def estimate_scope(self, context: JobContext) -> int: + conn = None + try: + conn = context.db._get_connection() + cursor = conn.cursor() + cursor.execute(""" + SELECT COUNT(*) FROM artists + WHERE name IS NOT NULL AND name != '' AND name != 'Unknown Artist' + """) + row = cursor.fetchone() + settings = self._get_settings(context) + max_artists = settings.get('max_artists_per_run', 50) + return min(row[0] if row else 0, max_artists) + except Exception: + return 0 + finally: + if conn: + conn.close() diff --git a/core/repair_worker.py b/core/repair_worker.py index 207f9df0..0810677f 100644 --- a/core/repair_worker.py +++ b/core/repair_worker.py @@ -845,12 +845,33 @@ class RepairWorker: 'unwanted_content': self._fix_unwanted_content, 'unknown_artist': self._fix_unknown_artist, 'acoustid_mismatch': self._fix_acoustid_mismatch, + 'missing_discography_track': self._fix_discography_backfill, } handler = handlers.get(finding_type) if not handler: return {'success': False, 'error': f'No fix available for finding type: {finding_type}'} return handler(entity_type, entity_id, file_path, details) + def _fix_discography_backfill(self, entity_type, entity_id, file_path, details): + """Add missing discography track to wishlist.""" + track_data = details.get('track_data') + if not track_data: + return {'success': False, 'error': 'No track data in finding'} + try: + success = self.db.add_to_wishlist( + spotify_track_data=track_data, + failure_reason='Discography backfill ā€” missing from library', + source_type='repair', + source_info={'job': 'discography_backfill', 'artist': details.get('artist_name', '')} + ) + track_name = track_data.get('name', '?') + if success: + return {'success': True, 'action': 'added_to_wishlist', + 'message': f"Added '{track_name}' to wishlist"} + return {'success': False, 'error': f"Could not add '{track_name}' to wishlist (may already exist)"} + except Exception as e: + return {'success': False, 'error': str(e)} + def _fix_dead_file(self, entity_type, entity_id, file_path, details): """Fix a dead file reference. Action depends on details['_fix_action']: 'redownload' (default) ā€” add to wishlist + remove DB entry diff --git a/core/soulid_worker.py b/core/soulid_worker.py index cc800460..5dc011bb 100644 --- a/core/soulid_worker.py +++ b/core/soulid_worker.py @@ -455,11 +455,23 @@ class SoulIDWorker: matching.normalize_string(db_name) ) if score >= self.album_match_threshold: - logger.debug(f" {source_name}: matched '{artist.name}' via album '{api_name}' ā†” '{db_name}' (score={score:.2f})") + logger.debug( + "%s matched artist=%r via album api=%r db=%r score=%.2f", + source_name, + artist.name, + api_name, + db_name, + score, + ) return discog except Exception as e: - logger.debug(f" {source_name}: discography fetch failed for '{artist.name}': {e}") + logger.debug( + "%s discography fetch failed for artist=%r: %s", + source_name, + artist.name, + e, + ) continue return None diff --git a/core/tag_writer.py b/core/tag_writer.py index 9ea89a34..cbdfdf11 100644 --- a/core/tag_writer.py +++ b/core/tag_writer.py @@ -16,7 +16,7 @@ from mutagen.mp4 import MP4, MP4Cover, MP4FreeForm from mutagen.oggvorbis import OggVorbis from mutagen.apev2 import APEv2, APENoHeaderError -logger = logging.getLogger("newmusic.tag_writer") +logger = logging.getLogger("tag_writer") # Supported extensions SUPPORTED_EXTENSIONS = {'.mp3', '.flac', '.ogg', '.oga', '.opus', '.m4a', '.mp4'} diff --git a/core/wishlist_service.py b/core/wishlist_service.py index b48e8ba5..0885bf09 100644 --- a/core/wishlist_service.py +++ b/core/wishlist_service.py @@ -311,15 +311,17 @@ class WishlistService: def _spotify_track_object_to_dict(self, spotify_track) -> Dict[str, Any]: """Convert a Spotify track object or TrackResult object to a dictionary""" try: - # Add debug logging to see what we're dealing with - logger.info(f"DEBUG: Converting track object to dict. Type: {type(spotify_track)}") - logger.info(f"DEBUG: Has 'title' attribute: {hasattr(spotify_track, 'title')}") - logger.info(f"DEBUG: Has 'artist' attribute: {hasattr(spotify_track, 'artist')}") - logger.info(f"DEBUG: Has 'id' attribute: {hasattr(spotify_track, 'id')}") + logger.debug( + "Converting track object to dict: type=%s has_title=%s has_artist=%s has_id=%s", + type(spotify_track), + hasattr(spotify_track, 'title'), + hasattr(spotify_track, 'artist'), + hasattr(spotify_track, 'id'), + ) # Check if this is a TrackResult object (has title/artist but no id) if hasattr(spotify_track, 'title') and hasattr(spotify_track, 'artist') and not hasattr(spotify_track, 'id'): - logger.info("DEBUG: Detected TrackResult object, converting...") + logger.debug("Detected TrackResult object, converting") # Handle TrackResult objects - these don't have Spotify IDs album_name = getattr(spotify_track, 'album', '') or getattr(spotify_track, 'title', 'Unknown Album') result = { @@ -333,19 +335,23 @@ class WishlistService: 'popularity': 0, 'source': 'trackresult' } - logger.info(f"DEBUG: TrackResult converted successfully: {result['name']} by {result['artists'][0]['name']}") + logger.debug( + "TrackResult converted successfully: name=%s artist=%s", + result['name'], + result['artists'][0]['name'], + ) return result # Handle regular Spotify Track objects - logger.info("DEBUG: Processing as Spotify Track object") + logger.debug("Processing as Spotify Track object") # Handle artists list carefully to avoid TrackResult serialization issues artists_list = [] raw_artists = getattr(spotify_track, 'artists', []) - logger.info(f"DEBUG: Raw artists: {raw_artists}, type: {type(raw_artists)}") + logger.debug("Raw artists: %r (type=%s)", raw_artists, type(raw_artists)) for artist in raw_artists: - logger.info(f"DEBUG: Processing artist: {artist}, type: {type(artist)}") + logger.debug("Processing artist: %r (type=%s)", artist, type(artist)) if hasattr(artist, 'name'): artists_list.append({'name': artist.name}) elif isinstance(artist, str): @@ -375,16 +381,20 @@ class WishlistService: 'disc_number': getattr(spotify_track, 'disc_number', 1) } - logger.info(f"DEBUG: Spotify Track converted: {result['name']} by {[a['name'] for a in result['artists']]}") + logger.debug( + "Spotify Track converted: name=%s artists=%s", + result['name'], + [a['name'] for a in result['artists']], + ) # Test JSON serialization before returning to catch any remaining issues try: import json json.dumps(result) - logger.info("DEBUG: Conversion result is JSON serializable") + logger.debug("Conversion result is JSON serializable") except Exception as json_error: - logger.error(f"DEBUG: Conversion result is NOT JSON serializable: {json_error}") - logger.error(f"DEBUG: Result content: {result}") + logger.error("Conversion result is NOT JSON serializable: %s", json_error) + logger.error("Conversion result content: %r", result) # Return a safe fallback return { 'id': f"fallback_{hash(str(spotify_track))}", @@ -413,4 +423,4 @@ def get_wishlist_service() -> WishlistService: global _wishlist_service if _wishlist_service is None: _wishlist_service = WishlistService() - return _wishlist_service \ No newline at end of file + return _wishlist_service diff --git a/database/music_database.py b/database/music_database.py index 8bc5684e..f806ef27 100644 --- a/database/music_database.py +++ b/database/music_database.py @@ -26,8 +26,6 @@ try: except ImportError: logger.warning("Could not import MusicMatchingEngine, falling back to basic similarity") _matching_engine = None -# Temporarily enable debug logging for edition matching -logger.setLevel(logging.DEBUG) @dataclass class DatabaseArtist: @@ -5371,48 +5369,63 @@ class MusicDatabase: return list(set(variations)) - def check_track_exists(self, title: str, artist: str, confidence_threshold: float = 0.8, server_source: str = None, album: str = None) -> Tuple[Optional[DatabaseTrack], float]: + def check_track_exists(self, title: str, artist: str, confidence_threshold: float = 0.8, server_source: str = None, album: str = None, candidate_tracks: Optional[List[DatabaseTrack]] = None) -> Tuple[Optional[DatabaseTrack], float]: """ Check if a track exists in the database with enhanced fuzzy matching and confidence scoring. Args: album: Optional album name ā€” enables album-aware matching for multi-artist albums + candidate_tracks: Optional pre-fetched list of tracks to match against in-memory, + skipping the per-variation SQL loop. Intended for callers iterating + a discography that already fetched the artist's tracks once via + get_candidate_tracks_for_albums. None preserves original behavior. Returns (track, confidence) tuple where confidence is 0.0-1.0 """ try: - # Generate title variations for better matching (similar to album approach) - title_variations = self._generate_track_title_variations(title) - - logger.debug(f"Enhanced track matching for '{title}' by '{artist}': trying {len(title_variations)} variations") - for i, var in enumerate(title_variations): - logger.debug(f" {i+1}. '{var}'") - best_match = None best_confidence = 0.0 - - # Try each title variation - for title_variation in title_variations: - # Search for potential matches with this variation - potential_matches = [] - artist_variations = self._get_artist_variations(artist) - for artist_variation in artist_variations: - potential_matches.extend(self.search_tracks(title=title_variation, artist=artist_variation, limit=20, server_source=server_source)) - - if not potential_matches: - continue - - logger.debug(f"Found {len(potential_matches)} tracks for variation '{title_variation}'") - - # Score each potential match - for track in potential_matches: + + if candidate_tracks is not None: + # BATCHED PATH ā€” score every pre-fetched track in-memory. + # _calculate_track_confidence already handles title normalization, + # so no need for the per-variation SQL widening. + logger.debug(f"Enhanced track matching for '{title}' by '{artist}': batched against {len(candidate_tracks)} candidates") + for track in candidate_tracks: confidence = self._calculate_track_confidence(title, artist, track) - logger.debug(f" '{track.title}' confidence: {confidence:.3f}") - if confidence > best_confidence: best_confidence = confidence best_match = track - + else: + # LEGACY PATH ā€” generate title variations and fire SQL per variation. + title_variations = self._generate_track_title_variations(title) + + logger.debug(f"Enhanced track matching for '{title}' by '{artist}': trying {len(title_variations)} variations") + for i, var in enumerate(title_variations): + logger.debug(f" {i+1}. '{var}'") + + # Try each title variation + for title_variation in title_variations: + # Search for potential matches with this variation + potential_matches = [] + artist_variations = self._get_artist_variations(artist) + for artist_variation in artist_variations: + potential_matches.extend(self.search_tracks(title=title_variation, artist=artist_variation, limit=20, server_source=server_source)) + + if not potential_matches: + continue + + logger.debug(f"Found {len(potential_matches)} tracks for variation '{title_variation}'") + + # Score each potential match + for track in potential_matches: + confidence = self._calculate_track_confidence(title, artist, track) + logger.debug(f" '{track.title}' confidence: {confidence:.3f}") + + if confidence > best_confidence: + best_confidence = confidence + best_match = track + # Return match only if it meets threshold if best_match and best_confidence >= confidence_threshold: logger.debug(f"Enhanced track match found: '{title}' -> '{best_match.title}' (confidence: {best_confidence:.3f})") @@ -5686,15 +5699,84 @@ class MusicDatabase: logger.error(f"Error getting album formats: {e}") return [] - def check_album_exists_with_completeness(self, title: str, artist: str, expected_track_count: Optional[int] = None, confidence_threshold: float = 0.8, server_source: Optional[str] = None) -> Tuple[Optional[DatabaseAlbum], float, int, int, bool, List[str]]: + def get_candidate_albums_for_artist(self, artist: str, server_source: Optional[str] = None, limit: int = 200) -> List[DatabaseAlbum]: + """ + Fetch every library album for an artist, merged across artist-name variations + and deduplicated by album ID. Intended to be called once per artist page load + so subsequent per-album matching can run in-memory against this list without + re-hitting SQL for each discography item. + """ + candidates: List[DatabaseAlbum] = [] + try: + seen_ids = set() + for artist_var in self._get_artist_variations(artist): + found = self.search_albums(title="", artist=artist_var, limit=limit, server_source=server_source) + for album in found: + if album.id not in seen_ids: + candidates.append(album) + seen_ids.add(album.id) + return candidates + except Exception as e: + logger.error(f"Error fetching candidate albums for artist '{artist}': {e}") + return candidates + + def get_candidate_tracks_for_albums(self, album_ids: List) -> List[DatabaseTrack]: + """ + Fetch every track belonging to the given set of album IDs in a single query. + Used for batched track-level completion checks (true singles on discography). + Returns DatabaseTrack objects with artist_name/album_title/server_source attrs + attached, matching the shape produced by search_tracks. + """ + if not album_ids: + return [] + try: + conn = self._get_connection() + cursor = conn.cursor() + placeholders = ','.join('?' for _ in album_ids) + cursor.execute(f""" + SELECT t.*, a.name as artist_name, al.title as album_title, al.thumb_url as album_thumb_url + FROM tracks t + JOIN artists a ON a.id = t.artist_id + JOIN albums al ON al.id = t.album_id + WHERE t.album_id IN ({placeholders}) + """, list(album_ids)) + rows = cursor.fetchall() + tracks: List[DatabaseTrack] = [] + for row in rows: + track = DatabaseTrack( + id=row['id'], + album_id=row['album_id'], + artist_id=row['artist_id'], + title=row['title'], + track_number=row['track_number'], + duration=row['duration'], + file_path=row['file_path'], + bitrate=row['bitrate'], + ) + # Attach joined fields the same way search_tracks does + track.artist_name = row['artist_name'] + track.album_title = row['album_title'] + track.album_thumb_url = row['album_thumb_url'] if 'album_thumb_url' in row.keys() else '' + track.server_source = row['server_source'] if 'server_source' in row.keys() else '' + tracks.append(track) + return tracks + except Exception as e: + logger.error(f"Error fetching candidate tracks for {len(album_ids)} album IDs: {e}") + return [] + + def check_album_exists_with_completeness(self, title: str, artist: str, expected_track_count: Optional[int] = None, confidence_threshold: float = 0.8, server_source: Optional[str] = None, candidate_albums: Optional[List[DatabaseAlbum]] = None) -> Tuple[Optional[DatabaseAlbum], float, int, int, bool, List[str]]: """ Check if an album exists in the database with completeness information. Enhanced to handle edition matching (standard <-> deluxe variants). Returns (album, confidence, owned_tracks, expected_tracks, is_complete, formats) + + When `candidate_albums` is provided (via get_candidate_albums_for_artist), + the matcher runs in-memory against that list instead of firing per-album + SQL searches. `None` preserves the original search-every-time behavior. """ try: # Try enhanced edition-aware matching first with expected track count for Smart Edition Matching - album, confidence = self.check_album_exists_with_editions(title, artist, confidence_threshold, expected_track_count, server_source) + album, confidence = self.check_album_exists_with_editions(title, artist, confidence_threshold, expected_track_count, server_source, candidate_albums=candidate_albums) if not album: return None, 0.0, 0, 0, False, [] @@ -5708,88 +5790,108 @@ class MusicDatabase: logger.error(f"Error checking album existence with completeness for '{title}' by '{artist}': {e}") return None, 0.0, 0, 0, False, [] - def check_album_exists_with_editions(self, title: str, artist: str, confidence_threshold: float = 0.8, expected_track_count: Optional[int] = None, server_source: Optional[str] = None) -> Tuple[Optional[DatabaseAlbum], float]: + def check_album_exists_with_editions(self, title: str, artist: str, confidence_threshold: float = 0.8, expected_track_count: Optional[int] = None, server_source: Optional[str] = None, candidate_albums: Optional[List[DatabaseAlbum]] = None) -> Tuple[Optional[DatabaseAlbum], float]: """ Enhanced album existence check that handles edition variants. Matches standard albums with deluxe/platinum/special editions and vice versa. + + When `candidate_albums` is provided, the artist-level SQL searches are + skipped and matching runs in-memory against that list ā€” used by callers + that already fetched the artist's full library via + get_candidate_albums_for_artist, so a discography of N items doesn't + trigger N*K SQL queries. The title-only cross-artist fallback for + collaborative albums is preserved in both paths. """ try: - # Generate album title variations for edition matching - title_variations = self._generate_album_title_variations(title) - - logger.debug(f"Edition matching for '{title}' by '{artist}': trying {len(title_variations)} variations") - for i, var in enumerate(title_variations): - logger.debug(f" {i+1}. '{var}'") - best_match = None best_confidence = 0.0 - - for variation in title_variations: - # Search for this variation - albums = [] - artist_variations = self._get_artist_variations(artist) - for artist_variation in artist_variations: - found = self.search_albums(title=variation, artist=artist_variation, limit=10, server_source=server_source) - # Deduplicate by ID - existing_ids = {a.id for a in albums} - for album in found: - if album.id not in existing_ids: - albums.append(album) - existing_ids.add(album.id) - - if albums: - logger.debug(f"Found {len(albums)} albums for variation '{variation}'") - - if not albums: - continue - - # Score each potential match with Smart Edition Matching - for album in albums: + + if candidate_albums is not None: + # BATCHED PATH ā€” score every pre-fetched candidate in-memory. + # _calculate_album_confidence handles title normalization and + # expected-track-count edition matching, so we don't need the + # per-variation SQL widening that the legacy path does. + logger.debug(f"Edition matching for '{title}' by '{artist}': batched against {len(candidate_albums)} candidates") + for album in candidate_albums: confidence = self._calculate_album_confidence(title, artist, album, expected_track_count) - logger.debug(f" '{album.title}' confidence: {confidence:.3f}") - if confidence > best_confidence: best_confidence = confidence best_match = album - - # Return match only if it meets threshold - if best_match and best_confidence >= confidence_threshold: - logger.debug(f"Edition match found: '{title}' -> '{best_match.title}' (confidence: {best_confidence:.3f})") - return best_match, best_confidence - - # Fallback: Check ALL albums by this artist (resolves SQL accent sensitivity issues #101) - # If we haven't found a match yet, fetch broader list from artist and double check - if best_confidence < confidence_threshold: - logger.debug(f"specific title search failed, trying broad artist search fallback for '{artist}'") - try: - # Get ALL albums by this artist (limit 100 to be safe) - # This bypasses SQL 'LIKE' limitations for diacritics (e.g. 'ă' vs 'a') - # And relies on Python-side normalization in _calculate_album_confidence - artist_albums = [] + else: + # LEGACY PATH ā€” generate title variations and fire SQL per variation. + title_variations = self._generate_album_title_variations(title) + + logger.debug(f"Edition matching for '{title}' by '{artist}': trying {len(title_variations)} variations") + for i, var in enumerate(title_variations): + logger.debug(f" {i+1}. '{var}'") + + for variation in title_variations: + # Search for this variation + albums = [] artist_variations = self._get_artist_variations(artist) - for artist_var in artist_variations: - found_albums = self.search_albums(title="", artist=artist_var, limit=100, server_source=server_source) - # Deduplicate - existing_ids = {a.id for a in artist_albums} - for album in found_albums: + for artist_variation in artist_variations: + found = self.search_albums(title=variation, artist=artist_variation, limit=10, server_source=server_source) + # Deduplicate by ID + existing_ids = {a.id for a in albums} + for album in found: if album.id not in existing_ids: - artist_albums.append(album) + albums.append(album) existing_ids.add(album.id) - - if artist_albums: - logger.debug(f" Found {len(artist_albums)} total albums for artist fallback") - - for album in artist_albums: + + if albums: + logger.debug(f"Found {len(albums)} albums for variation '{variation}'") + + if not albums: + continue + + # Score each potential match with Smart Edition Matching + for album in albums: confidence = self._calculate_album_confidence(title, artist, album, expected_track_count) + logger.debug(f" '{album.title}' confidence: {confidence:.3f}") + if confidence > best_confidence: best_confidence = confidence best_match = album - logger.debug(f" Fallback match: '{album.title}' confidence: {confidence:.3f}") - except Exception as fallback_error: - logger.warning(f"Fallback artist search failed: {fallback_error}") + + # Return match only if it meets threshold + if best_match and best_confidence >= confidence_threshold: + logger.debug(f"Edition match found: '{title}' -> '{best_match.title}' (confidence: {best_confidence:.3f})") + return best_match, best_confidence + + # Fallback: Check ALL albums by this artist (resolves SQL accent sensitivity issues #101) + # Only runs in the legacy path ā€” batched callers have already + # fetched this broader list via get_candidate_albums_for_artist. + if best_confidence < confidence_threshold: + logger.debug(f"specific title search failed, trying broad artist search fallback for '{artist}'") + try: + # Get ALL albums by this artist (limit 100 to be safe) + # This bypasses SQL 'LIKE' limitations for diacritics (e.g. 'ă' vs 'a') + # And relies on Python-side normalization in _calculate_album_confidence + artist_albums = [] + artist_variations = self._get_artist_variations(artist) + for artist_var in artist_variations: + found_albums = self.search_albums(title="", artist=artist_var, limit=100, server_source=server_source) + # Deduplicate + existing_ids = {a.id for a in artist_albums} + for album in found_albums: + if album.id not in existing_ids: + artist_albums.append(album) + existing_ids.add(album.id) + + if artist_albums: + logger.debug(f" Found {len(artist_albums)} total albums for artist fallback") + + for album in artist_albums: + confidence = self._calculate_album_confidence(title, artist, album, expected_track_count) + if confidence > best_confidence: + best_confidence = confidence + best_match = album + logger.debug(f" Fallback match: '{album.title}' confidence: {confidence:.3f}") + except Exception as fallback_error: + logger.warning(f"Fallback artist search failed: {fallback_error}") if best_match and best_confidence >= confidence_threshold: - logger.debug(f"Fallback match succeeded: '{title}' -> '{best_match.title}' (confidence: {best_confidence:.3f})") + logger.debug(f"Match succeeded: '{title}' -> '{best_match.title}' (confidence: {best_confidence:.3f})") return best_match, best_confidence # Multi-artist fallback: search by title only (any artist) diff --git a/gunicorn.conf.py b/gunicorn.conf.py index 0500e468..f33ead35 100644 --- a/gunicorn.conf.py +++ b/gunicorn.conf.py @@ -11,7 +11,9 @@ timeout = 120 # Keep shutdowns under Docker's stop window so container restarts stay graceful. graceful_timeout = 8 -# Logging goes to stdout/stderr so Docker can collect it. +# Logging goes to stdout/stderr and is filtered by the custom logger class. accesslog = "-" errorlog = "-" +access_log_format = '%(h)s - - "%(r)s" %(s)s %(b)s "%(f)s" "%(a)s"' loglevel = "info" +logger_class = "utils.gunicorn_logger.FilteredGunicornLogger" diff --git a/gunicorn.dev.conf.py b/gunicorn.dev.conf.py index e62ce120..5bf2132e 100644 --- a/gunicorn.dev.conf.py +++ b/gunicorn.dev.conf.py @@ -13,7 +13,10 @@ timeout = 120 # Don't let local reloads wait too long for shutdown. graceful_timeout = 1 -# Logging goes to stdout/stderr so the shell launcher can collect it. +# Logging goes to stdout/stderr and is filtered by the custom logger class. accesslog = "-" errorlog = "-" +# Mimic process log format +access_log_format = '%(h)s - - "%(r)s" %(s)s %(b)s "%(f)s" "%(a)s"' loglevel = "info" +logger_class = "utils.gunicorn_logger.FilteredGunicornLogger" diff --git a/pyproject.toml b/pyproject.toml new file mode 100644 index 00000000..79ca43ed --- /dev/null +++ b/pyproject.toml @@ -0,0 +1,18 @@ +[tool.ruff] +target-version = "py311" +line-length = 160 + +[tool.ruff.lint] +# Start lenient ā€” catch real bugs, not style nits +# E: pycodestyle errors, F: pyflakes, UP: pyupgrade, B: bugbear +select = ["F", "E9", "W6", "B"] +# Ignore rules that will flag too much in an existing codebase +ignore = [ + "F401", # unused imports (too noisy initially) + "F841", # unused variables + "E501", # line length (handled by line-length setting) +] + +[tool.ruff.lint.per-file-ignores] +# Tests can use assert, magic values, etc. +"tests/**" = ["B", "F"] diff --git a/requirements-dev.txt b/requirements-dev.txt index a0c7797e..587022df 100644 --- a/requirements-dev.txt +++ b/requirements-dev.txt @@ -2,6 +2,7 @@ # Runtime web dependencies + test runner -r requirements.txt +ruff # Test runner pytest>=9.0.0 diff --git a/scripts/system_info.py b/scripts/system_info.py index d3229caf..c594e9e6 100644 --- a/scripts/system_info.py +++ b/scripts/system_info.py @@ -1,12 +1,18 @@ #!/usr/bin/env python3 """Reports basic system info ā€” useful for debugging Docker setups.""" +import logging import os import platform import shutil -print(f"Platform: {platform.system()} {platform.release()}") -print(f"Python: {platform.python_version()}") -print(f"Working Dir: {os.getcwd()}") +if not logging.getLogger().handlers: + logging.basicConfig(level=logging.INFO, format="%(message)s") + +logger = logging.getLogger("system_info") + +logger.info(f"Platform: {platform.system()} {platform.release()}") +logger.info(f"Python: {platform.python_version()}") +logger.info(f"Working Dir: {os.getcwd()}") # Disk usage for common SoulSync paths for path in ['/app/downloads', '/app/Transfer', '/app/data', './downloads', './Transfer']: @@ -14,4 +20,4 @@ for path in ['/app/downloads', '/app/Transfer', '/app/data', './downloads', './T usage = shutil.disk_usage(path) free_gb = usage.free / (1024**3) total_gb = usage.total / (1024**3) - print(f"Disk {path}: {free_gb:.1f} GB free / {total_gb:.1f} GB total") + logger.info(f"Disk {path}: {free_gb:.1f} GB free / {total_gb:.1f} GB total") diff --git a/tests/test_metadata_service_artist_image.py b/tests/test_metadata_service_artist_image.py new file mode 100644 index 00000000..2ad20ed6 --- /dev/null +++ b/tests/test_metadata_service_artist_image.py @@ -0,0 +1,155 @@ +import sys +import types + + +if "spotipy" not in sys.modules: + spotipy = types.ModuleType("spotipy") + + class _DummySpotify: + def __init__(self, *args, **kwargs): + pass + + oauth2 = types.ModuleType("spotipy.oauth2") + + class _DummyOAuth: + def __init__(self, *args, **kwargs): + pass + + spotipy.Spotify = _DummySpotify + oauth2.SpotifyOAuth = _DummyOAuth + oauth2.SpotifyClientCredentials = _DummyOAuth + spotipy.oauth2 = oauth2 + sys.modules["spotipy"] = spotipy + sys.modules["spotipy.oauth2"] = oauth2 + +if "config.settings" not in sys.modules: + config_pkg = types.ModuleType("config") + settings_mod = types.ModuleType("config.settings") + + class _DummyConfigManager: + def get(self, key, default=None): + return default + + def get_active_media_server(self): + return "primary" + + settings_mod.config_manager = _DummyConfigManager() + config_pkg.settings = settings_mod + sys.modules["config"] = config_pkg + sys.modules["config.settings"] = settings_mod + +from core import metadata_service + + +class _FakeSpotifyClient: + def __init__(self, image_url="https://spotify.example/artist.jpg"): + self.image_url = image_url + self.calls = [] + + def is_spotify_authenticated(self): + return True + + def get_artist(self, artist_id, allow_fallback=True): + self.calls.append((artist_id, allow_fallback)) + return { + "id": artist_id, + "name": "Spotify Artist", + "images": [{"url": self.image_url}], + "genres": ["rock"], + "popularity": 80, + } + + +class _FakeDeezerClient: + def __init__(self, image_url="https://deezer.example/artist.jpg"): + self.image_url = image_url + self.calls = [] + + def get_artist(self, artist_id): + self.calls.append(artist_id) + return types.SimpleNamespace( + id=artist_id, + name="Deezer Artist", + image_url=self.image_url, + genres=["indie"], + popularity=0, + ) + + +class _FakeItunesClient: + def __init__(self, album_art_url="https://itunes.example/artist.jpg"): + self.album_art_url = album_art_url + self.calls = [] + self.album_art_calls = [] + + def get_artist(self, artist_id): + self.calls.append(artist_id) + return { + "id": artist_id, + "name": "iTunes Artist", + "images": [], + "genres": ["alt"], + "popularity": 0, + } + + def _get_artist_image_from_albums(self, artist_id): + self.album_art_calls.append(artist_id) + return self.album_art_url + + +def test_get_artist_image_url_uses_primary_source_priority(monkeypatch): + deezer = _FakeDeezerClient() + spotify = _FakeSpotifyClient() + + monkeypatch.setattr(metadata_service, "get_primary_source", lambda: "deezer") + monkeypatch.setattr(metadata_service, "get_source_priority", lambda primary: [primary, "spotify"]) + monkeypatch.setattr( + metadata_service, + "get_client_for_source", + lambda source: {"deezer": deezer, "spotify": spotify}.get(source), + ) + + image_url = metadata_service.get_artist_image_url("artist-1") + + assert image_url == "https://deezer.example/artist.jpg" + assert deezer.calls == ["artist-1"] + assert spotify.calls == [] + + +def test_get_artist_image_url_uses_itunes_album_art_for_explicit_override(monkeypatch): + itunes = _FakeItunesClient() + spotify = _FakeSpotifyClient() + + monkeypatch.setattr(metadata_service, "get_primary_source", lambda: "spotify") + monkeypatch.setattr(metadata_service, "get_source_priority", lambda primary: [primary, "itunes"]) + monkeypatch.setattr( + metadata_service, + "get_client_for_source", + lambda source: {"itunes": itunes, "spotify": spotify}.get(source), + ) + + image_url = metadata_service.get_artist_image_url("12345", source_override="itunes") + + assert image_url == "https://itunes.example/artist.jpg" + assert itunes.calls == ["12345"] + assert itunes.album_art_calls == ["12345"] + assert spotify.calls == [] + + +def test_get_artist_image_url_handles_hydrabase_plugin(monkeypatch): + deezer = _FakeDeezerClient("https://deezer.example/hydra.jpg") + spotify = _FakeSpotifyClient() + + monkeypatch.setattr(metadata_service, "get_primary_source", lambda: "spotify") + monkeypatch.setattr(metadata_service, "get_source_priority", lambda primary: [primary, "deezer"]) + monkeypatch.setattr( + metadata_service, + "get_client_for_source", + lambda source: {"deezer": deezer, "spotify": spotify}.get(source), + ) + + image_url = metadata_service.get_artist_image_url("artist-1", source_override="hydrabase", plugin="deezer") + + assert image_url == "https://deezer.example/hydra.jpg" + assert deezer.calls == ["artist-1"] + assert spotify.calls == [] diff --git a/tests/test_metadata_service_musicmap.py b/tests/test_metadata_service_musicmap.py new file mode 100644 index 00000000..c5ccbbda --- /dev/null +++ b/tests/test_metadata_service_musicmap.py @@ -0,0 +1,235 @@ +import sys +import types + + +if "spotipy" not in sys.modules: + spotipy = types.ModuleType("spotipy") + + class _DummySpotify: + def __init__(self, *args, **kwargs): + pass + + oauth2 = types.ModuleType("spotipy.oauth2") + + class _DummyOAuth: + def __init__(self, *args, **kwargs): + pass + + spotipy.Spotify = _DummySpotify + oauth2.SpotifyOAuth = _DummyOAuth + oauth2.SpotifyClientCredentials = _DummyOAuth + spotipy.oauth2 = oauth2 + sys.modules["spotipy"] = spotipy + sys.modules["spotipy.oauth2"] = oauth2 + +if "config.settings" not in sys.modules: + config_pkg = types.ModuleType("config") + settings_mod = types.ModuleType("config.settings") + + class _DummyConfigManager: + def get(self, key, default=None): + return default + + def get_active_media_server(self): + return "primary" + + settings_mod.config_manager = _DummyConfigManager() + config_pkg.settings = settings_mod + sys.modules["config"] = config_pkg + sys.modules["config.settings"] = settings_mod + +import types as pytypes + +from core import metadata_service + + +class _FakeMusicMapResponse: + def __init__(self, text): + self.text = text + + def raise_for_status(self): + return None + + +class _FakeSourceClient: + def __init__(self, results_by_query): + self.results_by_query = results_by_query + self.search_calls = [] + + def search_artists(self, query, **kwargs): + self.search_calls.append((query, dict(kwargs))) + return list(self.results_by_query.get(query, [])) + + +def test_iter_musicmap_similar_artist_events_uses_source_priority(monkeypatch): + html = """ + + +
    + Artist One + Similar Artist +
    + + + """ + + deezer = _FakeSourceClient({ + "Artist One": [pytypes.SimpleNamespace(id="dz-seed", name="Artist One")], + "Similar Artist": [], + }) + itunes = _FakeSourceClient({ + "Artist One": [pytypes.SimpleNamespace(id="it-seed", name="Artist One")], + "Similar Artist": [ + pytypes.SimpleNamespace( + id="it-match", + name="iTunes Canonical", + image_url="https://itunes.example/it-match.jpg", + genres=["indie", "alt"], + popularity=77, + ) + ], + }) + spotify = _FakeSourceClient({}) + + monkeypatch.setattr(metadata_service.requests, "get", lambda *args, **kwargs: _FakeMusicMapResponse(html)) + monkeypatch.setattr(metadata_service, "get_primary_source", lambda: "deezer") + monkeypatch.setattr(metadata_service, "get_source_priority", lambda primary: [primary, "itunes", "spotify"]) + monkeypatch.setattr( + metadata_service, + "get_client_for_source", + lambda source: {"deezer": deezer, "itunes": itunes, "spotify": spotify}.get(source), + ) + + events = list(metadata_service.iter_musicmap_similar_artist_events("Artist One", limit=5)) + + assert events[0]["type"] == "start" + assert events[0]["source_priority"] == ["deezer", "itunes", "spotify"] + assert events[1]["type"] == "artist" + assert events[1]["artist"]["id"] == "it-match" + assert events[1]["artist"]["name"] == "iTunes Canonical" + assert events[1]["artist"]["image_url"] == "https://itunes.example/it-match.jpg" + assert events[1]["artist"]["genres"] == ["indie", "alt"] + assert events[1]["artist"]["popularity"] == 77 + assert events[1]["artist"]["source"] == "itunes" + assert events[-1]["type"] == "complete" + assert events[-1]["complete"] is True + assert events[-1]["total"] == 1 + assert events[-1]["total_found"] == 1 + + assert [call[0] for call in deezer.search_calls] == ["Artist One", "Similar Artist"] + assert [call[0] for call in itunes.search_calls] == ["Artist One", "Similar Artist"] + assert spotify.search_calls == [("Artist One", {"limit": 1, "allow_fallback": False})] + + +def test_iter_musicmap_similar_artist_events_enriches_itunes_images(monkeypatch): + html = """ + + +
    + Similar Artist +
    + + + """ + + class _ItunesClient(_FakeSourceClient): + def __init__(self): + super().__init__({ + "Artist One": [pytypes.SimpleNamespace(id="it-seed", name="Artist One")], + "Similar Artist": [pytypes.SimpleNamespace(id="it-match", name="iTunes Canonical")], + }) + self.get_artist_calls = [] + + def get_artist(self, artist_id): + self.get_artist_calls.append(artist_id) + return { + "id": artist_id, + "name": "iTunes Canonical", + "images": [{"url": "https://itunes.example/full-art.jpg"}], + "genres": ["indie"], + "popularity": 0, + } + + itunes = _ItunesClient() + monkeypatch.setattr(metadata_service.requests, "get", lambda *args, **kwargs: _FakeMusicMapResponse(html)) + monkeypatch.setattr(metadata_service, "get_primary_source", lambda: "itunes") + monkeypatch.setattr(metadata_service, "get_source_priority", lambda primary: [primary]) + monkeypatch.setattr(metadata_service, "get_client_for_source", lambda source: itunes if source == "itunes" else None) + + events = list(metadata_service.iter_musicmap_similar_artist_events("Artist One", limit=5)) + + artist_events = [event for event in events if event.get("type") == "artist"] + assert len(artist_events) == 1 + assert artist_events[0]["artist"]["image_url"] == "https://itunes.example/full-art.jpg" + assert itunes.get_artist_calls == ["it-match"] + + +def test_iter_musicmap_similar_artist_events_falls_back_to_itunes_album_art(monkeypatch): + html = """ + + +
    + Similar Artist +
    + + + """ + + class _ItunesClient(_FakeSourceClient): + def __init__(self): + super().__init__({ + "Artist One": [pytypes.SimpleNamespace(id="it-seed", name="Artist One")], + "Similar Artist": [pytypes.SimpleNamespace(id="it-match", name="iTunes Canonical")], + }) + self.get_artist_calls = [] + self.album_art_calls = [] + + def get_artist(self, artist_id): + self.get_artist_calls.append(artist_id) + return { + "id": artist_id, + "name": "iTunes Canonical", + "images": [], + "genres": ["indie"], + "popularity": 0, + } + + def _get_artist_image_from_albums(self, artist_id): + self.album_art_calls.append(artist_id) + return "https://itunes.example/album-art.jpg" + + itunes = _ItunesClient() + monkeypatch.setattr(metadata_service.requests, "get", lambda *args, **kwargs: _FakeMusicMapResponse(html)) + monkeypatch.setattr(metadata_service, "get_primary_source", lambda: "itunes") + monkeypatch.setattr(metadata_service, "get_source_priority", lambda primary: [primary]) + monkeypatch.setattr(metadata_service, "get_client_for_source", lambda source: itunes if source == "itunes" else None) + + events = list(metadata_service.iter_musicmap_similar_artist_events("Artist One", limit=5)) + + artist_events = [event for event in events if event.get("type") == "artist"] + assert len(artist_events) == 1 + assert artist_events[0]["artist"]["image_url"] == "https://itunes.example/album-art.jpg" + assert itunes.get_artist_calls == ["it-match"] + assert itunes.album_art_calls == ["it-match"] + + +def test_get_musicmap_similar_artists_returns_not_found_when_musicmap_missing(monkeypatch): + html = """ + + +
    Nothing here
    + + + """ + + monkeypatch.setattr(metadata_service.requests, "get", lambda *args, **kwargs: _FakeMusicMapResponse(html)) + monkeypatch.setattr(metadata_service, "get_primary_source", lambda: "deezer") + monkeypatch.setattr(metadata_service, "get_source_priority", lambda primary: [primary, "itunes"]) + monkeypatch.setattr(metadata_service, "get_client_for_source", lambda source: object()) + + result = metadata_service.get_musicmap_similar_artists("Artist One", limit=5) + + assert result["success"] is False + assert result["status_code"] == 404 + assert "Could not find artist map" in result["error"] + assert result["similar_artists"] == [] diff --git a/tests/test_unknown_artist_fixer.py b/tests/test_unknown_artist_fixer.py index 1ee99bc0..4ff15f59 100644 --- a/tests/test_unknown_artist_fixer.py +++ b/tests/test_unknown_artist_fixer.py @@ -110,7 +110,7 @@ def test_unknown_artist_fixer_uses_primary_source_track_id_first(monkeypatch): "title": "Unknown Title", "album_title": "Unknown Album", "spotify_track_id": "sp-1", - "deezer_track_id": "dz-1", + "deezer_id": "dz-1", "itunes_track_id": "", } @@ -176,7 +176,7 @@ def test_unknown_artist_fixer_searches_primary_source_first(monkeypatch): "title": "Matching Title", "album_title": "Matching Album", "spotify_track_id": "", - "deezer_track_id": "", + "deezer_id": "", "itunes_track_id": "", } @@ -229,7 +229,7 @@ def test_unknown_artist_fixer_supports_hydrabase_title_search(monkeypatch): "title": "Hydra Match", "album_title": "Hydra Album", "spotify_track_id": "", - "deezer_track_id": "", + "deezer_id": "", "itunes_track_id": "", } diff --git a/tools/diagnose_itunes_discover.py b/tools/diagnose_itunes_discover.py index f3b0a15b..ff047c26 100644 --- a/tools/diagnose_itunes_discover.py +++ b/tools/diagnose_itunes_discover.py @@ -7,14 +7,12 @@ Run this script to identify issues with iTunes data population: - Discovery pool tracks by source - Recent albums by source - Curated playlists status - -Usage: - python tools/diagnose_itunes_discover.py """ -import sys -import os import json +import logging +import os +import sys # Add parent directory to path for imports sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) @@ -22,36 +20,42 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from database.music_database import MusicDatabase +if not logging.getLogger().handlers: + logging.basicConfig(level=logging.INFO, format="%(message)s") + +logger = logging.getLogger("diagnose_itunes_discover") + + +def _section(title: str) -> None: + logger.info("") + logger.info(title) + logger.info("-" * 40) + + def diagnose_itunes_discover(): """Run diagnostic checks for iTunes discover data.""" - print("=" * 60) - print("iTunes Discover Page Diagnostic Report") - print("=" * 60) + logger.info("=" * 60) + logger.info("iTunes Discover Page Diagnostic Report") + logger.info("=" * 60) db = MusicDatabase() # 1. Check Similar Artists - print("\n[1] SIMILAR ARTISTS") - print("-" * 40) - + _section("[1] SIMILAR ARTISTS") try: with db._get_connection() as conn: cursor = conn.cursor() - # Total similar artists cursor.execute("SELECT COUNT(*) as total FROM similar_artists") total = cursor.fetchone()['total'] - # With iTunes IDs cursor.execute("SELECT COUNT(*) as count FROM similar_artists WHERE similar_artist_itunes_id IS NOT NULL") with_itunes = cursor.fetchone()['count'] - # With Spotify IDs cursor.execute("SELECT COUNT(*) as count FROM similar_artists WHERE similar_artist_spotify_id IS NOT NULL") with_spotify = cursor.fetchone()['count'] - # With both cursor.execute(""" SELECT COUNT(*) as count FROM similar_artists WHERE similar_artist_itunes_id IS NOT NULL @@ -59,34 +63,29 @@ def diagnose_itunes_discover(): """) with_both = cursor.fetchone()['count'] - print(f" Total similar artists: {total}") - print(f" With iTunes ID: {with_itunes} ({100*with_itunes/total:.1f}%)" if total > 0 else " With iTunes ID: 0") - print(f" With Spotify ID: {with_spotify} ({100*with_spotify/total:.1f}%)" if total > 0 else " With Spotify ID: 0") - print(f" With BOTH IDs: {with_both} ({100*with_both/total:.1f}%)" if total > 0 else " With BOTH IDs: 0") + logger.info(f" Total similar artists: {total}") + logger.info(f" With iTunes ID: {with_itunes} ({100 * with_itunes / total:.1f}%)" if total > 0 else " With iTunes ID: 0") + logger.info(f" With Spotify ID: {with_spotify} ({100 * with_spotify / total:.1f}%)" if total > 0 else " With Spotify ID: 0") + logger.info(f" With BOTH IDs: {with_both} ({100 * with_both / total:.1f}%)" if total > 0 else " With BOTH IDs: 0") if with_itunes == 0 and total > 0: - print(" [CRITICAL] No similar artists have iTunes IDs - Hero section will be empty!") + logger.critical("No similar artists have iTunes IDs - Hero section will be empty!") elif with_itunes < total * 0.5: - print(" [WARNING] Less than 50% of similar artists have iTunes IDs") + logger.warning("Less than 50% of similar artists have iTunes IDs") else: - print(" [OK] iTunes coverage is adequate") - + logger.info("iTunes coverage is adequate") except Exception as e: - print(f" [ERROR] Could not check similar artists: {e}") + logger.error(f"Could not check similar artists: {e}") # 2. Check Discovery Pool - print("\n[2] DISCOVERY POOL") - print("-" * 40) - + _section("[2] DISCOVERY POOL") try: with db._get_connection() as conn: cursor = conn.cursor() - # Total tracks cursor.execute("SELECT COUNT(*) as total FROM discovery_pool") total = cursor.fetchone()['total'] - # By source cursor.execute(""" SELECT source, COUNT(*) as count FROM discovery_pool @@ -94,33 +93,28 @@ def diagnose_itunes_discover(): """) source_counts = {row['source']: row['count'] for row in cursor.fetchall()} - print(f" Total tracks: {total}") - print(f" Spotify tracks: {source_counts.get('spotify', 0)}") - print(f" iTunes tracks: {source_counts.get('itunes', 0)}") + logger.info(f" Total tracks: {total}") + logger.info(f" Spotify tracks: {source_counts.get('spotify', 0)}") + logger.info(f" iTunes tracks: {source_counts.get('itunes', 0)}") if source_counts.get('itunes', 0) == 0 and total > 0: - print(" [CRITICAL] No iTunes tracks in discovery pool - Fresh Tape/Archives will be empty!") + logger.critical("No iTunes tracks in discovery pool - Fresh Tape/Archives will be empty!") elif source_counts.get('itunes', 0) < total * 0.3: - print(" [WARNING] Low iTunes track count in discovery pool") + logger.warning("Low iTunes track count in discovery pool") else: - print(" [OK] iTunes tracks present") - + logger.info("iTunes tracks present") except Exception as e: - print(f" [ERROR] Could not check discovery pool: {e}") + logger.error(f"Could not check discovery pool: {e}") # 3. Check Recent Albums - print("\n[3] RECENT ALBUMS CACHE") - print("-" * 40) - + _section("[3] RECENT ALBUMS CACHE") try: with db._get_connection() as conn: cursor = conn.cursor() - # Total albums cursor.execute("SELECT COUNT(*) as total FROM discovery_recent_albums") total = cursor.fetchone()['total'] - # By source cursor.execute(""" SELECT source, COUNT(*) as count FROM discovery_recent_albums @@ -128,24 +122,21 @@ def diagnose_itunes_discover(): """) source_counts = {row['source']: row['count'] for row in cursor.fetchall()} - print(f" Total recent albums: {total}") - print(f" Spotify albums: {source_counts.get('spotify', 0)}") - print(f" iTunes albums: {source_counts.get('itunes', 0)}") + logger.info(f" Total recent albums: {total}") + logger.info(f" Spotify albums: {source_counts.get('spotify', 0)}") + logger.info(f" iTunes albums: {source_counts.get('itunes', 0)}") if source_counts.get('itunes', 0) == 0 and total > 0: - print(" [CRITICAL] No iTunes albums cached - Recent Releases section will be empty!") + logger.critical("No iTunes albums cached - Recent Releases section will be empty!") elif source_counts.get('itunes', 0) < 5: - print(" [WARNING] Very few iTunes albums cached") + logger.warning("Very few iTunes albums cached") else: - print(" [OK] iTunes albums cached") - + logger.info("iTunes albums cached") except Exception as e: - print(f" [ERROR] Could not check recent albums: {e}") + logger.error(f"Could not check recent albums: {e}") # 4. Check Curated Playlists - print("\n[4] CURATED PLAYLISTS") - print("-" * 40) - + _section("[4] CURATED PLAYLISTS") try: with db._get_connection() as conn: cursor = conn.cursor() @@ -156,7 +147,7 @@ def diagnose_itunes_discover(): 'release_radar_itunes', 'discovery_weekly', 'discovery_weekly_spotify', - 'discovery_weekly_itunes' + 'discovery_weekly_itunes', ] for playlist_type in playlists_to_check: @@ -174,9 +165,8 @@ def diagnose_itunes_discover(): else: status = "[NOT FOUND]" - print(f" {playlist_type}: {status}") + logger.info(f" {playlist_type}: {status}") - # Check iTunes-specific playlists cursor.execute(""" SELECT track_ids_json FROM discovery_curated_playlists WHERE playlist_type = 'release_radar_itunes' @@ -190,49 +180,43 @@ def diagnose_itunes_discover(): itunes_dw = cursor.fetchone() if not itunes_rr or len(json.loads(itunes_rr['track_ids_json'])) == 0: - print("\n [CRITICAL] release_radar_itunes is empty or missing!") + logger.critical("release_radar_itunes is empty or missing!") if not itunes_dw or len(json.loads(itunes_dw['track_ids_json'])) == 0: - print(" [CRITICAL] discovery_weekly_itunes is empty or missing!") - + logger.critical("discovery_weekly_itunes is empty or missing!") except Exception as e: - print(f" [ERROR] Could not check curated playlists: {e}") + logger.error(f"Could not check curated playlists: {e}") # 5. Check Watchlist Artists - print("\n[5] WATCHLIST ARTISTS") - print("-" * 40) - + _section("[5] WATCHLIST ARTISTS") try: with db._get_connection() as conn: cursor = conn.cursor() - # Total artists cursor.execute("SELECT COUNT(*) as total FROM watchlist_artists") total = cursor.fetchone()['total'] - # With iTunes IDs cursor.execute("SELECT COUNT(*) as count FROM watchlist_artists WHERE itunes_artist_id IS NOT NULL") with_itunes = cursor.fetchone()['count'] - # With Spotify IDs cursor.execute("SELECT COUNT(*) as count FROM watchlist_artists WHERE spotify_artist_id IS NOT NULL") with_spotify = cursor.fetchone()['count'] - print(f" Total watchlist artists: {total}") - print(f" With iTunes ID: {with_itunes} ({100*with_itunes/total:.1f}%)" if total > 0 else " With iTunes ID: 0") - print(f" With Spotify ID: {with_spotify} ({100*with_spotify/total:.1f}%)" if total > 0 else " With Spotify ID: 0") + logger.info(f" Total watchlist artists: {total}") + logger.info(f" With iTunes ID: {with_itunes} ({100 * with_itunes / total:.1f}%)" if total > 0 else " With iTunes ID: 0") + logger.info(f" With Spotify ID: {with_spotify} ({100 * with_spotify / total:.1f}%)" if total > 0 else " With Spotify ID: 0") if with_itunes == 0 and total > 0: - print(" [WARNING] No watchlist artists have iTunes IDs - source artist data limited") - + logger.warning("No watchlist artists have iTunes IDs - source artist data limited") except Exception as e: - print(f" [ERROR] Could not check watchlist artists: {e}") + logger.error(f"Could not check watchlist artists: {e}") - # Summary - print("\n" + "=" * 60) - print("SUMMARY & RECOMMENDED ACTIONS") - print("=" * 60) - print(""" -If you see [CRITICAL] or [WARNING] messages above, follow these steps: + logger.info("") + logger.info("=" * 60) + logger.info("SUMMARY & RECOMMENDED ACTIONS") + logger.info("=" * 60) + logger.info( + """ +If you see critical or warning messages above, follow these steps: QUICK FIX - Force Refresh Discover Data: ----------------------------------------- @@ -263,7 +247,8 @@ ROOT CAUSE NOTES: The discover page will now fall back to watchlist artists if similar artists are not available, so basic functionality should still work. -""") +""".strip() + ) if __name__ == '__main__': diff --git a/utils/gunicorn_logger.py b/utils/gunicorn_logger.py new file mode 100644 index 00000000..0dade80b --- /dev/null +++ b/utils/gunicorn_logger.py @@ -0,0 +1,83 @@ +"""Gunicorn logger tweaks for SoulSync.""" + +from __future__ import annotations + +import logging + +from gunicorn.glogging import Logger as GunicornLogger +from utils.logging_config import ColoredFormatter + + +class FilteredGunicornLogger(GunicornLogger): + """Gunicorn logger that skips noisy static and Socket.IO access logs.""" + + _STATIC_PREFIXES = ( + "/static/", + "/assets/", + "/socket.io", + "/favicon.ico", + "/robots.txt", + ) + + _STATIC_SUFFIXES = ( + ".css", + ".js", + ".map", + ".png", + ".jpg", + ".jpeg", + ".gif", + ".svg", + ".ico", + ".woff", + ".woff2", + ".ttf", + ".eot", + ) + + _HEALTHCHECK_USER_AGENTS = ( + "curl/", + ) + + def _should_skip_access_log(self, environ) -> bool: + path = environ.get("PATH_INFO") or "" + if not path: + return False + + normalized = path if path.startswith("/") else f"/{path}" + lower_path = normalized.lower() + + if any( + lower_path == prefix.rstrip("/") or lower_path.startswith(prefix) + for prefix in self._STATIC_PREFIXES + ): + return True + + if lower_path == "/": + user_agent = (environ.get("HTTP_USER_AGENT") or "").lower() + if any(token in user_agent for token in self._HEALTHCHECK_USER_AGENTS): + return True + + return any(lower_path.endswith(suffix) for suffix in self._STATIC_SUFFIXES) + + def access(self, resp, req, environ, request_time): + if self._should_skip_access_log(environ): + return + super().access(resp, req, environ, request_time) + + def setup(self, cfg): + super().setup(cfg) + + app_like_formatter = ColoredFormatter( + fmt="%(asctime)s - %(name)s - %(levelname)s - %(message)s", + datefmt="%Y-%m-%d %H:%M:%S", + ) + error_level = getattr(logging, cfg.loglevel.upper(), logging.INFO) + + for handler in self.access_log.handlers: + handler.setFormatter(app_like_formatter) + handler.setLevel(logging.INFO) + + for handler in self.error_log.handlers: + handler.setFormatter(app_like_formatter) + handler.setLevel(error_level) diff --git a/utils/logging_config.py b/utils/logging_config.py index b29af7ef..f7f36d0e 100644 --- a/utils/logging_config.py +++ b/utils/logging_config.py @@ -6,6 +6,8 @@ from pathlib import Path from datetime import datetime from typing import Optional +LOGGER_NAMESPACE = "soulsync" + class SafeFormatter(logging.Formatter): """Formatter that handles Unicode characters safely on Windows""" @@ -52,7 +54,7 @@ class ColoredFormatter(SafeFormatter): def setup_logging(level: str = "INFO", log_file: Optional[str] = None) -> logging.Logger: log_level = getattr(logging, level.upper(), logging.INFO) - logger = logging.getLogger("newmusic") + logger = logging.getLogger(LOGGER_NAMESPACE) logger.setLevel(log_level) if logger.handlers: @@ -91,15 +93,15 @@ def setup_logging(level: str = "INFO", log_file: Optional[str] = None) -> loggin return logger def get_logger(name: str) -> logging.Logger: - return logging.getLogger(f"newmusic.{name}") + return logging.getLogger(f"{LOGGER_NAMESPACE}.{name}") def set_log_level(level: str) -> bool: """Dynamically change the log level for all loggers without restart""" try: log_level = getattr(logging, level.upper(), logging.INFO) - # Get the root "newmusic" logger - root_logger = logging.getLogger("newmusic") + # Get the root "soulsync" logger + root_logger = logging.getLogger(LOGGER_NAMESPACE) root_logger.setLevel(log_level) # Update all handlers @@ -109,12 +111,12 @@ def set_log_level(level: str) -> bool: root_logger.info(f"Log level changed to: {level.upper()}") return True except Exception as e: - print(f"Error setting log level: {e}") + logging.getLogger(LOGGER_NAMESPACE).error(f"Error setting log level: {e}") return False def get_current_log_level() -> str: """Get the current log level""" - root_logger = logging.getLogger("newmusic") + root_logger = logging.getLogger(LOGGER_NAMESPACE) return logging.getLevelName(root_logger.level) -main_logger = get_logger("main") \ No newline at end of file +main_logger = get_logger("main") diff --git a/web_server.py b/web_server.py index 117c74c6..5366e503 100644 --- a/web_server.py +++ b/web_server.py @@ -33,31 +33,48 @@ from config.settings import config_manager # Setup logging early to avoid any import-time logs from being swallowed _log_level = config_manager.get('logging.level', 'INFO') _log_path = config_manager.get('logging.path', 'logs/app.log') +_log_dir = Path(_log_path).parent logger = setup_logging(_log_level, _log_path) # App version ā€” single source of truth for backup metadata, version-info endpoint, etc. -SOULSYNC_VERSION = "2.34" +_SOULSYNC_BASE_VERSION = "2.35" -# Dedicated source reuse logger ā€” writes to logs/source_reuse.log +def _build_version_string(): + """Append short commit hash to version when available (e.g. 2.35+abc1234).""" + sha = os.environ.get('SOULSYNC_COMMIT_SHA', '').strip() + if not sha: + try: + import subprocess + result = subprocess.run(['git', 'rev-parse', 'HEAD'], capture_output=True, text=True, cwd=os.path.dirname(__file__) or '.') + if result.returncode == 0: + sha = result.stdout.strip() + except Exception: + pass + if sha: + return f"{_SOULSYNC_BASE_VERSION}+{sha[:7]}" + return _SOULSYNC_BASE_VERSION + +SOULSYNC_VERSION = _build_version_string() + +# Dedicated source reuse logger ā€” writes alongside app.log in the configured log directory import logging as _logging import logging.handlers as _logging_handlers source_reuse_logger = _logging.getLogger("source_reuse") source_reuse_logger.setLevel(_logging.DEBUG) if not source_reuse_logger.handlers: - os.makedirs("logs", exist_ok=True) _sr_handler = _logging_handlers.RotatingFileHandler( - "logs/source_reuse.log", encoding="utf-8", maxBytes=5*1024*1024, backupCount=2 + _log_dir / "source_reuse.log", encoding="utf-8", maxBytes=5*1024*1024, backupCount=2 ) _sr_handler.setFormatter(_logging.Formatter("%(asctime)s - %(message)s", datefmt="%Y-%m-%d %H:%M:%S")) source_reuse_logger.addHandler(_sr_handler) source_reuse_logger.propagate = False -# Dedicated post-processing logger (failures only) ā€” writes to logs/post_processing.log +# Dedicated post-processing logger (failures only) ā€” writes alongside app.log in the configured log directory pp_logger = _logging.getLogger("post_processing") pp_logger.setLevel(_logging.DEBUG) if not pp_logger.handlers: _pp_handler = _logging_handlers.RotatingFileHandler( - "logs/post_processing.log", encoding="utf-8", maxBytes=5*1024*1024, backupCount=2 + _log_dir / "post_processing.log", encoding="utf-8", maxBytes=5*1024*1024, backupCount=2 ) _pp_handler.setFormatter(_logging.Formatter("%(asctime)s - %(message)s", datefmt="%Y-%m-%d %H:%M:%S")) pp_logger.addHandler(_pp_handler) @@ -82,17 +99,14 @@ from services.sync_service import PlaylistSyncService # Pre-v1.3 docker-compose files mounted soulsync_database:/app/database, which overlays # the Python package with stale volume contents. Detect this after import. if not hasattr(MusicDatabase, 'get_system_automation_by_action'): - print("=" * 70) - print("ERROR: Stale database module detected!") - print(" MusicDatabase is missing required methods. This usually means") - print(" your docker-compose.yml has an outdated volume mount:") - print("") - print(" FIX: Change your docker-compose.yml volume:") - print(" OLD: soulsync_database:/app/database") - print(" NEW: soulsync_database:/app/data") - print("") - print(" Then run: docker compose down && docker compose up -d") - print("=" * 70) + logger.error( + "Stale database module detected!\n" + "MusicDatabase is missing required methods. This usually means your docker-compose.yml has an outdated volume mount.\n" + "Fix:\n" + " OLD: soulsync_database:/app/database\n" + " NEW: soulsync_database:/app/data\n" + "Then run: docker compose down && docker compose up -d" + ) from datetime import datetime, timezone import yt_dlp from core.matching_engine import MusicMatchingEngine @@ -120,7 +134,7 @@ DEV_STATIC_NO_CACHE = os.environ.get('SOULSYNC_WEB_DEV_NO_CACHE', '0').lower() i env_config_path = os.environ.get('SOULSYNC_CONFIG_PATH') if env_config_path: config_path = env_config_path - print(f"Using config path from environment: {config_path}") + logger.info(f"Using config path from environment: {config_path}") else: config_path = os.path.join(project_root, 'config', 'config.json') @@ -134,20 +148,20 @@ if os.path.exists(config_path): current_loaded_path = current_loaded_path.resolve() if current_loaded_path == target_path and config_manager.config_data: - print(f"Web server configuration already loaded from: {config_path}") + logger.info(f"Web server configuration already loaded from: {config_path}") else: - print(f"Found config file at: {config_path}") + logger.info(f"Found config file at: {config_path}") # Load configuration into the existing singleton instance if hasattr(config_manager, 'load_config'): config_manager.load_config(config_path) else: # Fallback for older settings.py in Docker volumes - print("Legacy configuration detected: using fallback loading method") + logger.warning("Legacy configuration detected: using fallback loading method") config_manager.config_path = Path(config_path) config_manager._load_config() - print("Web server configuration loaded successfully.") + logger.info("Web server configuration loaded successfully.") else: - print(f"WARNING: config.json not found at {config_path}. Using default settings.") + logger.warning(f"config.json not found at {config_path}. Using default settings.") # Correctly point to the 'webui' directory for templates and static files app = Flask( __name__, @@ -370,78 +384,78 @@ def _make_context_key(username, filename): # --- Initialize Core Application Components --- # Each client is initialized independently so one failure doesn't take down everything. # Previously, a single exception set ALL clients to None, breaking the entire app. -print("Initializing SoulSync services for Web UI...") +logger.info("Initializing SoulSync services for Web UI...") spotify_client = plex_client = jellyfin_client = navidrome_client = soulsync_library_client = soulseek_client = tidal_client = matching_engine = sync_service = web_scan_manager = None try: spotify_client = SpotifyClient() - print(" Spotify client initialized") + logger.info(" Spotify client initialized") except Exception as e: - print(f" Spotify client failed to initialize: {e}") + logger.error(f" Spotify client failed to initialize: {e}") try: plex_client = PlexClient() - print(" Plex client initialized") + logger.info(" Plex client initialized") except Exception as e: - print(f" Plex client failed to initialize: {e}") + logger.error(f" Plex client failed to initialize: {e}") try: jellyfin_client = JellyfinClient() - print(" Jellyfin client initialized") + logger.info(" Jellyfin client initialized") except Exception as e: - print(f" Jellyfin client failed to initialize: {e}") + logger.error(f" Jellyfin client failed to initialize: {e}") try: navidrome_client = NavidromeClient() - print(" Navidrome client initialized") + logger.info(" Navidrome client initialized") except Exception as e: - print(f" Navidrome client failed to initialize: {e}") + logger.error(f" Navidrome client failed to initialize: {e}") try: from core.soulsync_client import SoulSyncClient soulsync_library_client = SoulSyncClient() - print(" SoulSync library client initialized") + logger.info(" SoulSync library client initialized") except Exception as e: - print(f" SoulSync library client failed to initialize: {e}") + logger.error(f" SoulSync library client failed to initialize: {e}") try: soulseek_client = DownloadOrchestrator() - print(" Download orchestrator initialized") + logger.info(" Download orchestrator initialized") except Exception as e: - print(f" Download orchestrator failed to initialize: {e}") + logger.error(f" Download orchestrator failed to initialize: {e}") try: tidal_client = TidalClient() - print(" Tidal client initialized") + logger.info(" Tidal client initialized") except Exception as e: - print(f" Tidal client failed to initialize: {e}") + logger.error(f" Tidal client failed to initialize: {e}") try: matching_engine = MusicMatchingEngine() - print(" Matching engine initialized") + logger.info(" Matching engine initialized") except Exception as e: - print(f" Matching engine failed to initialize: {e}") + logger.error(f" Matching engine failed to initialize: {e}") try: sync_service = PlaylistSyncService(spotify_client, plex_client, soulseek_client, jellyfin_client, navidrome_client) - print(" Playlist sync service initialized") + logger.info(" Playlist sync service initialized") except Exception as e: - print(f" Playlist sync service failed to initialize: {e}") + logger.error(f" Playlist sync service failed to initialize: {e}") # Inject shutdown check callback into YouTube and Tidal clients (avoids circular imports) if soulseek_client: if hasattr(soulseek_client, 'youtube'): soulseek_client.youtube.set_shutdown_check(lambda: IS_SHUTTING_DOWN) - print(" Configured YouTube client shutdown callback") + logger.info(" Configured YouTube client shutdown callback") if hasattr(soulseek_client, 'tidal'): soulseek_client.tidal.set_shutdown_check(lambda: IS_SHUTTING_DOWN) - print(" Configured Tidal download client shutdown callback") + logger.info(" Configured Tidal download client shutdown callback") if hasattr(soulseek_client, 'qobuz'): soulseek_client.qobuz.set_shutdown_check(lambda: IS_SHUTTING_DOWN) - print(" Configured Qobuz client shutdown callback") + logger.info(" Configured Qobuz client shutdown callback") if hasattr(soulseek_client, 'hifi'): soulseek_client.hifi.set_shutdown_check(lambda: IS_SHUTTING_DOWN) - print(" Configured HiFi client shutdown callback") + logger.info(" Configured HiFi client shutdown callback") # Initialize web scan manager for automatic post-download scanning try: @@ -452,18 +466,18 @@ try: 'soulsync_library_client': soulsync_library_client, } web_scan_manager = WebScanManager(media_clients, delay_seconds=60) - print(" Web scan manager initialized") + logger.info(" Web scan manager initialized") except Exception as e: - print(f" Web scan manager failed to initialize: {e}") + logger.error(f" Web scan manager failed to initialize: {e}") -print("Core service initialization complete.") +logger.info("Core service initialization complete.") # --- Automation Engine --- try: automation_engine = AutomationEngine(get_database()) - print("Automation engine initialized.") + logger.info("Automation engine initialized.") except Exception as e: - print(f"Automation engine failed to initialize: {e}") + logger.error(f"Automation engine failed to initialize: {e}") automation_engine = None def _register_automation_handlers(): @@ -830,7 +844,7 @@ def _register_automation_handlers(): if old_ids != new_ids: added_count = len(new_ids - old_ids) removed_count = len(old_ids - new_ids) - print(f"[AUTOMATION] Playlist changed: '{pl.get('name', '')}' ā€” {added_count} added, {removed_count} removed (old={len(old_ids)}, new={len(new_ids)})") + logger.info(f"[AUTOMATION] Playlist changed: '{pl.get('name', '')}' ā€” {added_count} added, {removed_count} removed (old={len(old_ids)}, new={len(new_ids)})") _update_automation_progress(auto_id, log_line=f'"{pl.get("name", "")}" ā€” {added_count} added, {removed_count} removed', log_type='success') try: @@ -846,7 +860,7 @@ def _register_automation_handlers(): except Exception: pass else: - print(f"[AUTOMATION] No changes: '{pl.get('name', '')}' (tracks={len(old_ids)})") + logger.warning(f"[AUTOMATION] No changes: '{pl.get('name', '')}' (tracks={len(old_ids)})") _update_automation_progress(auto_id, log_line=f'No changes: "{pl.get("name", "")}"', log_type='skip') except Exception as e: @@ -1124,7 +1138,7 @@ def _register_automation_handlers(): # but we pass None so it doesn't conflict with our pipeline progress _run_playlist_discovery_worker(pls, automation_id=None) except Exception as e: - print(f"[Pipeline] Discovery error: {e}") + logger.error(f"[Pipeline] Discovery error: {e}") finally: disc_done.set() @@ -2019,7 +2033,7 @@ def _register_automation_handlers(): }) web_scan_manager.add_scan_completion_callback(_on_library_scan_completed) - print("Automation action handlers registered") + logger.info("Automation action handlers registered") def _emit_track_downloaded(context): @@ -2355,7 +2369,7 @@ def _record_soulsync_library_entry(context, spotify_artist, album_info): pass conn.commit() - print(f"[SoulSync Library] Added: {artist_name} / {album_name} / {track_name}") + logger.info(f"[SoulSync Library] Added: {artist_name} / {album_name} / {track_name}") except Exception as e: logger.debug(f"[SoulSync Library] Non-critical error: {e}") @@ -2377,9 +2391,9 @@ try: 'hydrabase_client': None, # updated after Hydrabase init 'hydrabase_worker': None, # updated after Hydrabase init } - print("Public REST API v1 registered at /api/v1") + logger.info("Public REST API v1 registered at /api/v1") except Exception as e: - print(f"Public REST API v1 failed to register: {e}") + logger.error(f"Public REST API v1 failed to register: {e}") # --- Global Streaming State Management --- # Thread-safe state tracking for streaming functionality @@ -2658,14 +2672,14 @@ def get_cached_transfer_data(): 'averageSpeed': download.speed, } except Exception as e: - print(f"Could not fetch streaming source downloads: {e}") + logger.error(f"Could not fetch streaming source downloads: {e}") # Update cache transfer_data_cache['data'] = live_transfers_lookup transfer_data_cache['last_update'] = current_time except Exception as e: - print(f"Could not fetch live transfers (cached): {e}") + logger.error(f"Could not fetch live transfers (cached): {e}") # Return empty dict on error, but don't update cache timestamp # This way we'll retry on the next request return {} @@ -2724,14 +2738,14 @@ def get_cached_beatport_data(section_type, data_key, genre_slug=None): # Check if cache is still valid age = current_time - cache_entry['timestamp'] if age < cache_entry['ttl'] and cache_entry['data'] is not None: - print(f"Cache HIT for {section_type}/{data_key} (age: {age:.1f}s)") + logger.debug(f"Cache HIT for {section_type}/{data_key} (age: {age:.1f}s)") return cache_entry['data'] else: - print(f"ā° Cache MISS for {section_type}/{data_key} (age: {age:.1f}s, ttl: {cache_entry['ttl']}s)") + logger.debug(f"ā° Cache MISS for {section_type}/{data_key} (age: {age:.1f}s, ttl: {cache_entry['ttl']}s)") return None except Exception as e: - print(f"Cache lookup error for {section_type}/{data_key}: {e}") + logger.error(f"Cache lookup error for {section_type}/{data_key}: {e}") return None def set_cached_beatport_data(section_type, data_key, data, genre_slug=None): @@ -2752,7 +2766,7 @@ def set_cached_beatport_data(section_type, data_key, data, genre_slug=None): if data_key in beatport_data_cache['homepage']: beatport_data_cache['homepage'][data_key]['data'] = data beatport_data_cache['homepage'][data_key]['timestamp'] = current_time - print(f"Cached {section_type}/{data_key} (ttl: {beatport_data_cache['homepage'][data_key]['ttl']}s)") + logger.info(f"Cached {section_type}/{data_key} (ttl: {beatport_data_cache['homepage'][data_key]['ttl']}s)") elif section_type == 'genre' and genre_slug: # Initialize genre cache if not exists if genre_slug not in beatport_data_cache['genre']: @@ -2766,10 +2780,10 @@ def set_cached_beatport_data(section_type, data_key, data, genre_slug=None): beatport_data_cache['genre'][genre_slug][data_key]['data'] = data beatport_data_cache['genre'][genre_slug][data_key]['timestamp'] = current_time - print(f"Cached {section_type}/{genre_slug}/{data_key}") + logger.info(f"Cached {section_type}/{genre_slug}/{data_key}") except Exception as e: - print(f"Cache storage error for {section_type}/{data_key}: {e}") + logger.error(f"Cache storage error for {section_type}/{data_key}: {e}") def add_cache_headers(response, cache_duration=300): """ @@ -2860,7 +2874,7 @@ class WebUIDownloadMonitor: self.monitoring = True self.monitor_thread = threading.Thread(target=self._monitor_loop, daemon=True) self.monitor_thread.start() - print(f"Started download monitor for batch {batch_id}") + logger.info(f"Started download monitor for batch {batch_id}") def stop_monitoring(self, batch_id): """Stop monitoring a specific batch""" @@ -2868,7 +2882,7 @@ class WebUIDownloadMonitor: self.monitored_batches.discard(batch_id) if not self.monitored_batches: self.monitoring = False - print(f"Stopped download monitor (no active batches)") + logger.debug(f"Stopped download monitor (no active batches)") def shutdown(self): """Stop the monitor loop and clear active batch tracking.""" @@ -2876,7 +2890,7 @@ class WebUIDownloadMonitor: self.monitoring = False self.monitored_batches.clear() self.monitor_thread = None - print("Download monitor shutdown requested") + logger.info("Download monitor shutdown requested") def _monitor_loop(self): """Main monitoring loop - checks downloads every 1 second for responsive web UX""" @@ -2890,12 +2904,12 @@ class WebUIDownloadMonitor: except Exception as e: # If we get shutdown errors, stop monitoring gracefully if "interpreter shutdown" in str(e) or "cannot schedule new futures" in str(e): - print(f"Monitor detected shutdown, stopping gracefully") + logger.info(f"Monitor detected shutdown, stopping gracefully") self.monitoring = False break - print(f"Download monitor error: {e}") + logger.error(f"Download monitor error: {e}") - print(f"Download monitor loop ended") + logger.info(f"Download monitor loop ended") def _check_all_downloads(self): """Check all active downloads for timeouts and failures""" @@ -2953,7 +2967,7 @@ class WebUIDownloadMonitor: transferred = live_info.get('bytesTransferred', 0) if expected_size > 0 and transferred < expected_size: if not task.get('_incomplete_warned'): - print(f"Monitor: {task_id} state={state} but bytes incomplete ({transferred}/{expected_size}) ā€” waiting") + logger.debug(f"Monitor: {task_id} state={state} but bytes incomplete ({transferred}/{expected_size}) ā€” waiting") task['_incomplete_warned'] = True continue if has_completion and not has_error and task['status'] == 'downloading': @@ -2965,7 +2979,7 @@ class WebUIDownloadMonitor: # left tasks stuck in 'downloading' forever. task['status'] = 'post_processing' task['status_change_time'] = current_time - print(f"Monitor detected completed download for {task_id} ({state}) - submitting post-processing") + logger.info(f"Monitor detected completed download for {task_id} ({state}) - submitting post-processing") # Collect for handling outside the lock to prevent deadlock. # _on_download_completed acquires tasks_lock which is non-reentrant. completed_tasks.append((batch_id, task_id)) @@ -2979,21 +2993,21 @@ class WebUIDownloadMonitor: try: if op[0] == 'cancel_download': _, download_id, username = op - print(f"[Deferred] Cancelling download: {download_id} from {username}") + logger.debug(f"[Deferred] Cancelling download: {download_id} from {username}") run_async(soulseek_client.cancel_download(download_id, username, remove=True)) - print(f"[Deferred] Successfully cancelled download {download_id}") + logger.debug(f"[Deferred] Successfully cancelled download {download_id}") elif op[0] == 'cleanup_orphan': _, context_key = op with matched_context_lock: matched_downloads_context.pop(context_key, None) - print(f"[Deferred] Cleaned up orphaned download context: {context_key}") + logger.debug(f"[Deferred] Cleaned up orphaned download context: {context_key}") elif op[0] == 'restart_worker': _, task_id, batch_id = op - print(f"[Deferred] Restarting worker for task {task_id}") + logger.debug(f"[Deferred] Restarting worker for task {task_id}") missing_download_executor.submit(_download_track_worker, task_id, batch_id) - print(f"[Deferred] Successfully restarted worker for task {task_id}") + logger.debug(f"[Deferred] Successfully restarted worker for task {task_id}") except Exception as e: - print(f"[Deferred] Error executing deferred operation {op[0]}: {e}") + logger.error(f"[Deferred] Error executing deferred operation {op[0]}: {e}") # Handle completed downloads outside the lock to prevent deadlock # (_on_download_completed acquires tasks_lock internally) @@ -3001,19 +3015,19 @@ class WebUIDownloadMonitor: try: # Submit post-processing worker (file move, tagging, AcoustID verification) # This makes batch downloads fully independent of browser polling. - print(f"[Monitor] Submitting post-processing worker for task {task_id}") + logger.info(f"[Monitor] Submitting post-processing worker for task {task_id}") missing_download_executor.submit(_run_post_processing_worker, task_id, batch_id) # Chain to next download in the batch queue _on_download_completed(batch_id, task_id, success=True) except Exception as e: - print(f"[Monitor] Error handling completed task {task_id}: {e}") + logger.error(f"[Monitor] Error handling completed task {task_id}: {e}") # Handle exhausted retry tasks outside the lock to prevent deadlock for batch_id, task_id in exhausted_tasks: try: - print(f"[Monitor] Calling completion callback for exhausted task {task_id}") + logger.info(f"[Monitor] Calling completion callback for exhausted task {task_id}") _on_download_completed(batch_id, task_id, success=False) except Exception as e: - print(f"[Monitor] Error handling exhausted task {task_id}: {e}") + logger.error(f"[Monitor] Error handling exhausted task {task_id}: {e}") # ENHANCED: Add worker count validation to detect ghost workers self._validate_worker_counts() @@ -3072,7 +3086,7 @@ class WebUIDownloadMonitor: 'averageSpeed': download.speed, } except Exception as yt_error: - print(f"Monitor: Could not fetch streaming source downloads: {yt_error}") + logger.error(f"Monitor: Could not fetch streaming source downloads: {yt_error}") return live_transfers except Exception as e: @@ -3080,11 +3094,11 @@ class WebUIDownloadMonitor: if ("interpreter shutdown" in str(e) or "cannot schedule new futures" in str(e) or "Event loop is closed" in str(e)): - print(f"Monitor detected shutdown, stopping immediately") + logger.info(f"Monitor detected shutdown, stopping immediately") self.monitoring = False return {} else: - print(f"Monitor: Could not fetch live transfers: {e}") + logger.error(f"Monitor: Could not fetch live transfers: {e}") return {} def _should_retry_task(self, task_id, task, live_transfers_lookup, current_time, deferred_ops): @@ -3114,7 +3128,7 @@ class WebUIDownloadMonitor: last_retry = task.get('last_retry_time', 0) if retry_count < 3 and (current_time - last_retry) > 30: - print(f"Task not in live transfers for >90s - retry {retry_count + 1}/3") + logger.warning(f"Task not in live transfers for >90s - retry {retry_count + 1}/3") task['stuck_retry_count'] = retry_count + 1 task['last_retry_time'] = current_time @@ -3130,7 +3144,7 @@ class WebUIDownloadMonitor: source_key = f"{task_username}_{task_filename}" used_sources.add(source_key) task['used_sources'] = used_sources - print(f"Marked missing-transfer source as used: {source_key}") + logger.warning(f"Marked missing-transfer source as used: {source_key}") # Defer orphan cleanup if task_username and task_filename: @@ -3145,7 +3159,7 @@ class WebUIDownloadMonitor: task.pop('queued_start_time', None) task.pop('downloading_start_time', None) task['status_change_time'] = current_time - print(f"Task {task.get('track_info', {}).get('name', 'Unknown')} reset for missing-transfer retry") + logger.warning(f"Task {task.get('track_info', {}).get('name', 'Unknown')} reset for missing-transfer retry") batch_id = task.get('batch_id') if task_id and batch_id: @@ -3157,7 +3171,7 @@ class WebUIDownloadMonitor: track_label = task.get('track_info', {}).get('name', 'Unknown') tried_sources = task.get('used_sources', set()) sources_str = f' (tried {len(tried_sources)} source{"s" if len(tried_sources) != 1 else ""})' if tried_sources else '' - print(f"Task failed after 3 retry attempts (not in live transfers)") + logger.error(f"Task failed after 3 retry attempts (not in live transfers)") task['status'] = 'failed' task['error_message'] = f'Download disappeared from transfer list 3 times for "{track_label}"{sources_str} ā€” source may be unavailable' @@ -3177,7 +3191,7 @@ class WebUIDownloadMonitor: # Don't retry too frequently (wait at least 5 seconds between error retries) if retry_count < 3 and (current_time - last_retry) > 5: # Max 3 error retry attempts - print(f"Task errored (state: {state_str}) - immediate retry {retry_count + 1}/3") + logger.error(f"Task errored (state: {state_str}) - immediate retry {retry_count + 1}/3") task['error_retry_count'] = retry_count + 1 task['last_error_retry_time'] = current_time @@ -3197,7 +3211,7 @@ class WebUIDownloadMonitor: source_key = f"{username}_{filename}" used_sources.add(source_key) task['used_sources'] = used_sources - print(f"Marked errored source as used: {source_key}") + logger.error(f"Marked errored source as used: {source_key}") # Defer orphan cleanup to outside the lock (needs matched_context_lock) if username and filename: @@ -3215,7 +3229,7 @@ class WebUIDownloadMonitor: task.pop('queued_start_time', None) task.pop('downloading_start_time', None) task['status_change_time'] = current_time - print(f"Task {task.get('track_info', {}).get('name', 'Unknown')} reset for error retry") + logger.error(f"Task {task.get('track_info', {}).get('name', 'Unknown')} reset for error retry") # Defer worker restart to outside the lock batch_id = task.get('batch_id') @@ -3230,7 +3244,7 @@ class WebUIDownloadMonitor: track_label = task.get('track_info', {}).get('name', 'Unknown') tried_sources = task.get('used_sources', set()) sources_str = f' (tried {len(tried_sources)} source{"s" if len(tried_sources) != 1 else ""})' if tried_sources else '' - print(f"Task failed after 3 error retry attempts") + logger.error(f"Task failed after 3 error retry attempts") task['status'] = 'failed' # Tidal-specific error: check if this was a quality issue. # task['username'] is popped on error-retry (line ~2866) so we can't rely on it; @@ -3255,7 +3269,7 @@ class WebUIDownloadMonitor: # CRITICAL: Notify batch manager so track is added to permanently_failed_tracks batch_id = task.get('batch_id') if batch_id: - print(f"[Retry Exhausted] Notifying batch manager of permanent failure for task {task_id}") + logger.error(f"[Retry Exhausted] Notifying batch manager of permanent failure for task {task_id}") return True # Signal that we need to call completion outside the lock return False @@ -3280,7 +3294,7 @@ class WebUIDownloadMonitor: # Don't retry too frequently (wait at least 30 seconds between retries) if retry_count < 3 and (current_time - last_retry) > 30: # Max 3 retry attempts - print(f"Task stuck in queue for {queue_time:.1f}s - immediate retry {retry_count + 1}/3") + logger.warning(f"Task stuck in queue for {queue_time:.1f}s - immediate retry {retry_count + 1}/3") task['stuck_retry_count'] = retry_count + 1 task['last_retry_time'] = current_time @@ -3301,7 +3315,7 @@ class WebUIDownloadMonitor: source_key = f"{username}_{filename}" used_sources.add(source_key) task['used_sources'] = used_sources - print(f"Marked timeout source as used: {source_key}") + logger.error(f"Marked timeout source as used: {source_key}") # Defer orphan cleanup to outside the lock (needs matched_context_lock) if username and filename: @@ -3319,7 +3333,7 @@ class WebUIDownloadMonitor: task.pop('queued_start_time', None) task.pop('downloading_start_time', None) task['status_change_time'] = current_time - print(f"Task {task.get('track_info', {}).get('name', 'Unknown')} reset for timeout retry") + logger.error(f"Task {task.get('track_info', {}).get('name', 'Unknown')} reset for timeout retry") # Defer worker restart to outside the lock batch_id = task.get('batch_id') @@ -3334,7 +3348,7 @@ class WebUIDownloadMonitor: track_label = task.get('track_info', {}).get('name', 'Unknown') tried_sources = task.get('used_sources', set()) sources_str = f' (tried {len(tried_sources)} source{"s" if len(tried_sources) != 1 else ""})' if tried_sources else '' - print(f"Task failed after 3 retry attempts (queue timeout)") + logger.error(f"Task failed after 3 retry attempts (queue timeout)") task['status'] = 'failed' task['error_message'] = f'Download stayed queued too long 3 times for "{track_label}"{sources_str} ā€” peers may be offline or have full queues' # Clear timers to prevent further retry loops @@ -3344,7 +3358,7 @@ class WebUIDownloadMonitor: # CRITICAL: Notify batch manager so track is added to permanently_failed_tracks batch_id = task.get('batch_id') if batch_id: - print(f"[Retry Exhausted] Notifying batch manager of permanent failure for task {task_id}") + logger.error(f"[Retry Exhausted] Notifying batch manager of permanent failure for task {task_id}") return True # Signal that we need to call completion outside the lock return False @@ -3368,7 +3382,7 @@ class WebUIDownloadMonitor: # Don't retry too frequently (wait at least 30 seconds between retries) if retry_count < 3 and (current_time - last_retry) > 30: # Max 3 retry attempts - print(f"Task stuck at 0% for {download_time:.1f}s - immediate retry {retry_count + 1}/3") + logger.warning(f"Task stuck at 0% for {download_time:.1f}s - immediate retry {retry_count + 1}/3") task['stuck_retry_count'] = retry_count + 1 task['last_retry_time'] = current_time @@ -3389,7 +3403,7 @@ class WebUIDownloadMonitor: source_key = f"{username}_{filename}" used_sources.add(source_key) task['used_sources'] = used_sources - print(f"Marked 0% progress source as used: {source_key}") + logger.info(f"Marked 0% progress source as used: {source_key}") # Defer orphan cleanup to outside the lock (needs matched_context_lock) if username and filename: @@ -3407,7 +3421,7 @@ class WebUIDownloadMonitor: task.pop('queued_start_time', None) task.pop('downloading_start_time', None) task['status_change_time'] = current_time - print(f"Task {task.get('track_info', {}).get('name', 'Unknown')} reset for 0% retry") + logger.warning(f"Task {task.get('track_info', {}).get('name', 'Unknown')} reset for 0% retry") # Defer worker restart to outside the lock batch_id = task.get('batch_id') @@ -3421,7 +3435,7 @@ class WebUIDownloadMonitor: track_label = task.get('track_info', {}).get('name', 'Unknown') tried_sources = task.get('used_sources', set()) sources_str = f' (tried {len(tried_sources)} source{"s" if len(tried_sources) != 1 else ""})' if tried_sources else '' - print(f"Task failed after 3 retry attempts (0% progress timeout)") + logger.error(f"Task failed after 3 retry attempts (0% progress timeout)") task['status'] = 'failed' task['error_message'] = f'Download stuck at 0% three times for "{track_label}"{sources_str} ā€” peers may have connection issues' # Clear timers to prevent further retry loops @@ -3431,7 +3445,7 @@ class WebUIDownloadMonitor: # CRITICAL: Notify batch manager so track is added to permanently_failed_tracks batch_id = task.get('batch_id') if batch_id: - print(f"[Retry Exhausted] Notifying batch manager of permanent failure for task {task_id}") + logger.error(f"[Retry Exhausted] Notifying batch manager of permanent failure for task {task_id}") return True # Signal that we need to call completion outside the lock return False else: @@ -3458,7 +3472,7 @@ class WebUIDownloadMonitor: last_retry = task.get('last_retry_time', 0) if retry_count < 3 and (current_time - last_retry) > 30: - print(f"Task stuck in unknown state '{state_str}' with 0 progress for {download_time:.1f}s - retry {retry_count + 1}/3") + logger.warning(f"Task stuck in unknown state '{state_str}' with 0 progress for {download_time:.1f}s - retry {retry_count + 1}/3") task['stuck_retry_count'] = retry_count + 1 task['last_retry_time'] = current_time @@ -3475,7 +3489,7 @@ class WebUIDownloadMonitor: source_key = f"{username}_{filename}" used_sources.add(source_key) task['used_sources'] = used_sources - print(f"Marked unknown-state source as used: {source_key}") + logger.info(f"Marked unknown-state source as used: {source_key}") if username and filename: old_context_key = _make_context_key(username, filename) @@ -3498,7 +3512,7 @@ class WebUIDownloadMonitor: track_label = task.get('track_info', {}).get('name', 'Unknown') tried_sources = task.get('used_sources', set()) sources_str = f' (tried {len(tried_sources)} source{"s" if len(tried_sources) != 1 else ""})' if tried_sources else '' - print(f"Task failed after 3 retry attempts (unknown state '{state_str}')") + logger.error(f"Task failed after 3 retry attempts (unknown state '{state_str}')") task['status'] = 'failed' task['error_message'] = f'Download stuck in "{state_str}" state 3 times for "{track_label}"{sources_str}' task.pop('queued_start_time', None) @@ -3552,16 +3566,16 @@ class WebUIDownloadMonitor: # Check for discrepancies if reported_active != actually_active or orphaned_tasks: - print(f"[Worker Validation] Batch {batch_id}: reported={reported_active}, actual={actually_active}, orphaned={len(orphaned_tasks)}") + logger.warning(f"[Worker Validation] Batch {batch_id}: reported={reported_active}, actual={actually_active}, orphaned={len(orphaned_tasks)}") if orphaned_tasks: - print(f"[Worker Validation] Found {len(orphaned_tasks)} orphaned tasks to cleanup") + logger.warning(f"[Worker Validation] Found {len(orphaned_tasks)} orphaned tasks to cleanup") # Fix the active count if it's wrong if reported_active != actually_active: old_count = batch['active_count'] batch['active_count'] = actually_active - print(f"[Worker Validation] Fixed active count: {old_count} ā†’ {actually_active}") + logger.info(f"[Worker Validation] Fixed active count: {old_count} ā†’ {actually_active}") # Defer starting workers to outside the lock if actually_active < max_concurrent and queue_index < len(queue): @@ -3570,13 +3584,13 @@ class WebUIDownloadMonitor: # Start replacement workers outside the lock for batch_id in batches_needing_workers: try: - print(f"[Worker Validation] Starting replacement workers for {batch_id}") + logger.info(f"[Worker Validation] Starting replacement workers for {batch_id}") _start_next_batch_of_downloads(batch_id) except Exception as e: - print(f"[Worker Validation] Error starting workers for {batch_id}: {e}") + logger.error(f"[Worker Validation] Error starting workers for {batch_id}: {e}") except Exception as validation_error: - print(f"Error in worker count validation: {validation_error}") + logger.error(f"Error in worker count validation: {validation_error}") # Global download monitor instance download_monitor = WebUIDownloadMonitor() @@ -3616,7 +3630,7 @@ def validate_and_heal_batch_states(): # Check if batch has been complete for >5 minutes time_since_completion = current_time - completion_time if time_since_completion > 300: # 5 minutes - print(f"[Auto-Cleanup] Removing stale completed batch {batch_id} (completed {time_since_completion:.0f}s ago)") + logger.warning(f"[Auto-Cleanup] Removing stale completed batch {batch_id} (completed {time_since_completion:.0f}s ago)") batches_to_cleanup.append(batch_id) continue # Skip other healing logic for this batch @@ -3640,7 +3654,7 @@ def validate_and_heal_batch_states(): # Check for inconsistencies if active_count != actually_active: - print(f"[Batch Healing] {batch_id}: fixing active count {active_count} ā†’ {actually_active}") + logger.info(f"[Batch Healing] {batch_id}: fixing active count {active_count} ā†’ {actually_active}") batch_data['active_count'] = actually_active healed_batches.append(batch_id) @@ -3652,7 +3666,7 @@ def validate_and_heal_batch_states(): # Clean up orphaned tasks that are blocking progress if orphaned_tasks and phase == 'downloading': - print(f"[Batch Healing] Found {len(orphaned_tasks)} orphaned tasks in active batch {batch_id}") + logger.warning(f"[Batch Healing] Found {len(orphaned_tasks)} orphaned tasks in active batch {batch_id}") batches_needing_completion_check.append(batch_id) # Cleanup stale batches inside the lock (safe - just dict mutations) @@ -3665,31 +3679,31 @@ def validate_and_heal_batch_states(): del download_tasks[task_id] if batches_to_cleanup: - print(f"[Auto-Cleanup] Removed {len(batches_to_cleanup)} stale completed batches") + logger.warning(f"[Auto-Cleanup] Removed {len(batches_to_cleanup)} stale completed batches") if healed_batches: - print(f"[Batch Healing] Healed {len(healed_batches)} batches: {healed_batches}") + logger.info(f"[Batch Healing] Healed {len(healed_batches)} batches: {healed_batches}") # ---- All work below runs WITHOUT tasks_lock held ---- # Start replacement workers for healed batches for batch_id in batches_needing_workers: try: - print(f"[Batch Healing] Starting replacement workers for {batch_id}") + logger.info(f"[Batch Healing] Starting replacement workers for {batch_id}") _start_next_batch_of_downloads(batch_id) except Exception as e: - print(f"[Batch Healing] Error starting workers for {batch_id}: {e}") + logger.error(f"[Batch Healing] Error starting workers for {batch_id}: {e}") # Trigger completion checks for batches with orphaned tasks for batch_id in batches_needing_completion_check: try: - print(f"[Batch Healing] Triggering completion check for batch with orphaned tasks") + logger.warning(f"[Batch Healing] Triggering completion check for batch with orphaned tasks") _check_batch_completion_v2(batch_id) except Exception as e: - print(f"[Batch Healing] Error checking completion for {batch_id}: {e}") + logger.error(f"[Batch Healing] Error checking completion for {batch_id}: {e}") except Exception as healing_error: - print(f"[Batch Healing] Error during validation: {healing_error}") + logger.error(f"[Batch Healing] Error during validation: {healing_error}") # Start periodic batch healing (every 30 seconds) import threading @@ -3724,7 +3738,7 @@ def start_batch_healing_timer(): return validate_and_heal_batch_states() except Exception as e: - print(f"[Batch Healing Timer] Error: {e}") + logger.error(f"[Batch Healing Timer] {e}") finally: # Schedule next healing cycle _schedule_batch_healing_timer(30.0) @@ -3740,7 +3754,7 @@ import sys def cleanup_monitor(): """Clean up background monitor on shutdown""" if download_monitor.monitoring: - print("Flask shutdown detected, stopping download monitor...") + logger.info("Flask shutdown detected, stopping download monitor...") download_monitor.shutdown() # Give the thread a moment to exit cleanly time.sleep(0.5) @@ -3751,13 +3765,13 @@ def cleanup_monitor(): if acquired: try: batch_locks.clear() - print("Cleaned up batch locks") + logger.info("Cleaned up batch locks") finally: tasks_lock.release() else: - print("Skipped batch lock cleanup - tasks_lock busy") + logger.warning("Skipped batch lock cleanup - tasks_lock busy") except Exception as e: - print(f"Error cleaning up batch locks: {e}") + logger.error(f"Error cleaning up batch locks: {e}") # Global shutdown flag IS_SHUTTING_DOWN = False @@ -3767,10 +3781,10 @@ def _shutdown_executor(executor, name): if executor is None: return try: - print(f"Shutting down {name}...") + logger.info(f"Shutting down {name}...") executor.shutdown(wait=False, cancel_futures=True) except Exception as e: - print(f"Error shutting down {name}: {e}") + logger.error(f"Error shutting down {name}: {e}") def _stop_component(component, name, method_names=("stop", "shutdown")): """Call a best-effort stop method on a component if it has one.""" @@ -3780,10 +3794,10 @@ def _stop_component(component, name, method_names=("stop", "shutdown")): method = getattr(component, method_name, None) if callable(method): try: - print(f"Stopping {name}...") + logger.info(f"Stopping {name}...") method() except Exception as e: - print(f"Error stopping {name}: {e}") + logger.error(f"Error stopping {name}: {e}") return def _stop_components_parallel(components): @@ -3823,9 +3837,9 @@ def _shutdown_runtime_components(): try: from core.api_call_tracker import api_call_tracker api_call_tracker.save() - print("API call history saved") + logger.info("API call history saved") except Exception as e: - print(f"Error saving API call history: {e}") + logger.error(f"Error saving API call history: {e}") # Stop the active DB update worker before tearing down the executor it runs on. # This lets an in-flight update observe should_stop and exit cleanly. @@ -3876,7 +3890,7 @@ def _shutdown_runtime_components(): def signal_handler(signum, frame): """Handle SIGINT (Ctrl+C) and SIGTERM""" - print(f"Signal {signum} received, cleaning up...") + logger.info(f"Signal {signum} received, cleaning up...") _shutdown_runtime_components() sys.exit(0) @@ -3912,20 +3926,20 @@ def _handle_failed_download(batch_id, task_id, task, task_status): if task['retry_count'] > 2: # Max 3 attempts total (matches GUI) # All retries exhausted, mark as permanently failed - print(f"Task {task_id} failed after 3 retry attempts") + logger.error(f"Task {task_id} failed after 3 retry attempts") task_status['status'] = 'failed' task['status'] = 'failed' return # Show retrying status while we process retry task_status['status'] = 'pending' # Will show as pending until retry kicks in - print(f"Triggering retry {task['retry_count']}/3 for failed task {task_id}") + logger.error(f"Triggering retry {task['retry_count']}/3 for failed task {task_id}") # Trigger retry with next candidate (matches GUI retry_parallel_download_with_fallback) missing_download_executor.submit(download_monitor._retry_task_with_fallback, batch_id, task_id, task) except Exception as e: - print(f"Error handling failed download {task_id}: {e}") + logger.error(f"Error handling failed download {task_id}: {e}") task_status['status'] = 'failed' task['status'] = 'failed' @@ -3994,7 +4008,7 @@ def _prepare_stream_task(track_data): last_progress_sent = 0.0 try: - print(f"Starting stream preparation for: {track_data.get('filename')}") + logger.info(f"Starting stream preparation for: {track_data.get('filename')}") # Update state to loading with stream_lock: @@ -4021,9 +4035,9 @@ def _prepare_stream_task(track_data): os.remove(existing_file) elif os.path.isdir(existing_file): shutil.rmtree(existing_file) - print(f"Cleared old stream file: {existing_file}") + logger.info(f"Cleared old stream file: {existing_file}") except Exception as e: - print(f"Could not remove existing stream file: {e}") + logger.error(f"Could not remove existing stream file: {e}") # Start the download using the same mechanism as regular downloads loop = asyncio.new_event_loop() @@ -4044,7 +4058,7 @@ def _prepare_stream_task(track_data): }) return - print(f"Download initiated for streaming") + logger.info(f"Download initiated for streaming") # Enhanced monitoring with queue timeout detection (matching GUI) max_wait_time = 60 # Increased timeout @@ -4070,7 +4084,7 @@ def _prepare_stream_task(track_data): download_state = download_status.get('state', '').lower() original_state = download_status.get('state', '') - print(f"API Download - State: {original_state}, Progress: {api_progress:.1f}%") + logger.info(f"API Download - State: {original_state}, Progress: {api_progress:.1f}%") # Track queue state timing (matching GUI logic) is_queued = ('queued' in download_state or 'initializing' in download_state) @@ -4084,13 +4098,13 @@ def _prepare_stream_task(track_data): # Handle queue state timing if is_queued and queue_start_time is None: queue_start_time = time.time() - print(f"Download entered queue state: {original_state}") + logger.info(f"Download entered queue state: {original_state}") with stream_lock: stream_state["status"] = "queued" elif is_downloading and not actively_downloading: actively_downloading = True queue_start_time = None # Reset queue timer - print(f"Download started actively downloading: {original_state}") + logger.info(f"Download started actively downloading: {original_state}") with stream_lock: stream_state["status"] = "loading" @@ -4098,7 +4112,7 @@ def _prepare_stream_task(track_data): if is_queued and queue_start_time: queue_elapsed = time.time() - queue_start_time if queue_elapsed > queue_timeout: - print(f"ā° Queue timeout after {queue_elapsed:.1f}s - download stuck in queue") + logger.error(f"ā° Queue timeout after {queue_elapsed:.1f}s - download stuck in queue") with stream_lock: stream_state.update({ "status": "error", @@ -4114,7 +4128,7 @@ def _prepare_stream_task(track_data): # Check if download is complete if is_completed: - print(f"Download completed via API status: {original_state}") + logger.info(f"Download completed via API status: {original_state}") # Wait for file to stabilise on disk before moving found_file = _find_downloaded_file(download_path, track_data) @@ -4139,12 +4153,12 @@ def _prepare_stream_task(track_data): for attempt in range(retry_attempts): if found_file: break - print(f"File not found yet, attempt {attempt + 1}/{retry_attempts}") + logger.warning(f"File not found yet, attempt {attempt + 1}/{retry_attempts}") time.sleep(1) found_file = _find_downloaded_file(download_path, track_data) if found_file: - print(f"Found downloaded file: {found_file}") + logger.debug(f"Found downloaded file: {found_file}") # Move file to Stream folder original_filename = extract_filename(found_file) @@ -4152,7 +4166,7 @@ def _prepare_stream_task(track_data): try: shutil.move(found_file, stream_path) - print(f"Moved file to stream folder: {stream_path}") + logger.debug(f"Moved file to stream folder: {stream_path}") # Clean up empty directories (matching GUI) _cleanup_empty_directories(download_path, found_file) @@ -4174,15 +4188,15 @@ def _prepare_stream_task(track_data): download_id, track_data.get('username'), remove=True) ) if success: - print(f"Cleaned up download {download_id} from API") + logger.debug(f"Cleaned up download {download_id} from API") except Exception as e: - print(f"Error cleaning up download: {e}") + logger.error(f"Error cleaning up download: {e}") - print(f"Stream file ready for playback: {stream_path}") + logger.info(f"Stream file ready for playback: {stream_path}") return # Success! except Exception as e: - print(f"Error moving file to stream folder: {e}") + logger.error(f"Error moving file to stream folder: {e}") with stream_lock: stream_state.update({ "status": "error", @@ -4190,7 +4204,7 @@ def _prepare_stream_task(track_data): }) return else: - print("Could not find downloaded file after completion") + logger.error("Could not find downloaded file after completion") with stream_lock: stream_state.update({ "status": "error", @@ -4199,17 +4213,17 @@ def _prepare_stream_task(track_data): return else: # No transfer found in API - may still be initializing - print(f"No transfer found in API yet... (elapsed: {wait_count * poll_interval}s)") + logger.debug(f"No transfer found in API yet... (elapsed: {wait_count * poll_interval}s)") except Exception as e: - print(f"Error checking download progress: {e}") + logger.error(f"Error checking download progress: {e}") # Continue to next iteration if API call fails # Wait before next poll time.sleep(poll_interval) # If we get here, download timed out - print(f"Download timed out after {max_wait_time}s") + logger.warning(f"Download timed out after {max_wait_time}s") with stream_lock: stream_state.update({ "status": "error", @@ -4217,7 +4231,7 @@ def _prepare_stream_task(track_data): }) except asyncio.CancelledError: - print("Stream task cancelled") + logger.warning("Stream task cancelled") with stream_lock: stream_state.update({ "status": "stopped", @@ -4232,10 +4246,10 @@ def _prepare_stream_task(track_data): loop.run_until_complete(asyncio.gather(*pending, return_exceptions=True)) loop.close() except Exception as e: - print(f"Error cleaning up streaming event loop: {e}") + logger.error(f"Error cleaning up streaming event loop: {e}") except Exception as e: - print(f"Stream preparation failed: {e}") + logger.error(f"Stream preparation failed: {e}") with stream_lock: stream_state.update({ "status": "error", @@ -4272,7 +4286,7 @@ def _find_streaming_download_in_all_downloads(all_downloads, track_data): return None except Exception as e: - print(f"Error finding streaming download: {e}") + logger.error(f"Error finding streaming download: {e}") return None def _find_downloaded_file(download_path, track_data): @@ -4298,15 +4312,15 @@ def _find_downloaded_file(download_path, track_data): safe_title = re.sub(r'[<>:"/\\|?*]', '_', title) target_filename_youtube = safe_title # Extension-less for flexible matching source_name = 'HiFi' if is_hifi else ('Qobuz' if is_qobuz else 'Tidal') - print(f"[{source_name} Stream] Looking for file starting with: {target_filename_youtube}") + logger.debug(f"[{source_name} Stream] Looking for file starting with: {target_filename_youtube}") else: # yt-dlp will create "Title.mp3" from "Title" target_filename_youtube = f"{title}.mp3" - print(f"[YouTube Stream] Looking for file: {target_filename_youtube}") + logger.debug(f"[YouTube Stream] Looking for file: {target_filename_youtube}") elif is_streaming_source: # Fallback: if streaming source but no encoded format, use as-is target_filename_youtube = target_filename - print(f"[Stream] Using direct filename: {target_filename_youtube}") + logger.debug(f"[Stream] Using direct filename: {target_filename_youtube}") try: # Walk through the downloads directory to find the file @@ -4340,7 +4354,7 @@ def _find_downloaded_file(download_path, track_data): similarity = SequenceMatcher(None, compare_file, compare_target).ratio() source_label = 'HiFi' if is_hifi else ('Qobuz' if is_qobuz else ('Tidal' if is_tidal else 'YouTube')) - print(f"[{source_label} Stream] Comparing: '{file}' vs '{target_filename_youtube}' = {similarity:.2f}") + logger.debug(f"[{source_label} Stream] Comparing: '{file}' vs '{target_filename_youtube}' = {similarity:.2f}") # Keep track of best match if similarity > best_similarity: @@ -4349,28 +4363,28 @@ def _find_downloaded_file(download_path, track_data): # If we have a very good match (95%+), use it immediately if similarity >= 0.95: - print(f"Found excellent match for streaming file: {file_path}") + logger.debug(f"Found excellent match for streaming file: {file_path}") return file_path else: # For Soulseek, exact match if file == target_filename: - print(f"Found streaming file: {file_path}") + logger.debug(f"Found streaming file: {file_path}") return file_path # For YouTube/Tidal, if we found a good enough match (80%+), use it if is_streaming_source and best_match and best_similarity >= 0.80: source_label = 'Qobuz' if is_qobuz else ('Tidal' if is_tidal else 'YouTube') - print(f"Found good match ({best_similarity:.2f}) for {source_label} streaming file: {best_match}") + logger.debug(f"Found good match ({best_similarity:.2f}) for {source_label} streaming file: {best_match}") return best_match - print(f"Could not find downloaded file: {target_filename}") + logger.error(f"Could not find downloaded file: {target_filename}") if is_streaming_source: - print(f" Looking for: {target_filename_youtube}") - print(f" Best similarity: {best_similarity:.2f}") + logger.debug(f" Looking for: {target_filename_youtube}") + logger.debug(f" Best similarity: {best_similarity:.2f}") return None except Exception as e: - print(f"Error searching for downloaded file: {e}") + logger.error(f"Error searching for downloaded file: {e}") return None # --- Refactored Logic from GUI Threads --- @@ -4661,7 +4675,7 @@ def run_service_test(service, test_config): if original_config: for key, value in original_config.items(): config_manager.set(f"{service}.{key}", value) - print(f"Restored original config for '{service}' after test.") + logger.debug(f"Restored original config for '{service}' after test.") def run_detection(server_type): @@ -4669,7 +4683,7 @@ def run_detection(server_type): Performs comprehensive network detection for a given server type (plex, jellyfin, slskd). This implements the same scanning logic as the GUI's detection threads. """ - print(f"Running comprehensive detection for {server_type}...") + logger.info(f"Running comprehensive detection for {server_type}...") def get_network_info(): """Get comprehensive network information with subnet detection""" @@ -4818,36 +4832,36 @@ def run_detection(server_type): return None # Priority 1: Test localhost first - print(f"Testing localhost for {server_type}...") + logger.debug(f"Testing localhost for {server_type}...") localhost_result = test_func("localhost") if localhost_result: - print(f"Found {server_type} at localhost!") + logger.info(f"Found {server_type} at localhost!") return localhost_result # Priority 1.5: In Docker, try Docker host IP import os if os.path.exists('/.dockerenv'): - print(f"Docker detected, testing Docker host for {server_type}...") + logger.info(f"Docker detected, testing Docker host for {server_type}...") try: # Try host.docker.internal (Windows/Mac) host_result = test_func("host.docker.internal") if host_result: - print(f"Found {server_type} at Docker host!") + logger.info(f"Found {server_type} at Docker host!") return host_result.replace("host.docker.internal", "localhost") # Convert back to localhost for config # Try Docker bridge gateway (Linux) gateway_result = test_func("172.17.0.1") if gateway_result: - print(f"Found {server_type} at Docker gateway!") + logger.info(f"Found {server_type} at Docker gateway!") return gateway_result.replace("172.17.0.1", "localhost") # Convert back to localhost for config except Exception as e: - print(f"Docker host detection failed: {e}") + logger.error(f"Docker host detection failed: {e}") # Priority 2: Test local IP - print(f"Testing local IP {local_ip} for {server_type}...") + logger.debug(f"Testing local IP {local_ip} for {server_type}...") local_result = test_func(local_ip) if local_result: - print(f"Found {server_type} at {local_ip}!") + logger.info(f"Found {server_type} at {local_ip}!") return local_result # Priority 3: Test common IPs (router gateway, etc.) @@ -4857,12 +4871,12 @@ def run_detection(server_type): local_ip.rsplit('.', 1)[0] + '.100', # Common static IP ] - print(f"Testing common IPs for {server_type}...") + logger.debug(f"Testing common IPs for {server_type}...") for ip in common_ips: - print(f" Checking {ip}...") + logger.info(f" Checking {ip}...") result = test_func(ip) if result: - print(f"Found {server_type} at {ip}!") + logger.info(f"Found {server_type} at {ip}!") return result # Priority 4: Scan the network range (limited to reasonable size) @@ -4872,7 +4886,7 @@ def run_detection(server_type): step = max(1, len(network_hosts) // 50) network_hosts = network_hosts[::step] - print(f"Scanning network range for {server_type} ({len(network_hosts)} hosts)...") + logger.debug(f"Scanning network range for {server_type} ({len(network_hosts)} hosts)...") # Use ThreadPoolExecutor for concurrent scanning (limited for web context) with ThreadPoolExecutor(max_workers=5) as executor: @@ -4886,23 +4900,23 @@ def run_detection(server_type): try: result = future.result() if result: - print(f"Found {server_type} at {ip}!") + logger.info(f"Found {server_type} at {ip}!") # Cancel all pending futures before returning for f in future_to_ip: if not f.done(): f.cancel() return result except Exception as e: - print(f"Error testing {ip}: {e}") + logger.error(f"Error testing {ip}: {e}") continue except Exception as e: - print(f"Error in concurrent scanning: {e}") + logger.error(f"Error in concurrent scanning: {e}") - print(f"No {server_type} server found on network") + logger.warning(f"No {server_type} server found on network") return None except Exception as e: - print(f"Error during {server_type} detection: {e}") + logger.error(f"Error during {server_type} detection: {e}") return None # --- Web UI Routes --- @@ -5314,9 +5328,9 @@ def _regenerate_batch_m3u(batch, tracks): m3u_path = os.path.join(m3u_folder, f'{safe_fn}.m3u') with open(m3u_path, 'w', encoding='utf-8') as f: f.write(m3u_content) - print(f"[M3U] Regenerated M3U on batch complete: {m3u_path} ({found}/{len(tracks)} resolved)") + logger.info(f"[M3U] Regenerated M3U on batch complete: {m3u_path} ({found}/{len(tracks)} resolved)") except Exception as e: - print(f"[M3U] Error in _regenerate_batch_m3u: {e}") + logger.error(f"[M3U] Error in _regenerate_batch_m3u: {e}") @app.route('/api/save-playlist-m3u', methods=['POST']) @@ -5578,7 +5592,7 @@ def _build_system_stats(): if isinstance(speed, (int, float)) and speed > 0: total_download_speed += float(speed) except Exception as e: - print(f"Warning: Could not fetch download speeds: {e}") + logger.error(f"Could not fetch download speeds: {e}") # Convert bytes/sec to KB/s and format if total_download_speed > 0: @@ -5861,10 +5875,10 @@ def get_debug_info(): # Log lines log_map = { - 'app': os.path.join('logs', 'app.log'), - 'acoustid': os.path.join('logs', 'acoustid.log'), - 'post_processing': os.path.join('logs', 'post_processing.log'), - 'source_reuse': os.path.join('logs', 'source_reuse.log'), + 'app': Path(_log_path), + 'acoustid': _log_dir / 'acoustid.log', + 'post_processing': _log_dir / 'post_processing.log', + 'source_reuse': _log_dir / 'source_reuse.log', } log_path = log_map.get(log_source, log_map['app']) info['log_source'] = log_source @@ -5994,9 +6008,9 @@ def add_activity_item(icon: str, title: str, subtitle: str, time_ago: str = "Now except Exception: pass - print(f"Activity: {icon} {title} - {subtitle}") + logger.info(f"Activity: {icon} {title} - {subtitle}") except Exception as e: - print(f"Error adding activity item: {e}") + logger.error(f"Error adding activity item: {e}") # --- Internal API Key Management (browser-only, no auth) --- @app.route('/api/v1/api-keys-internal', methods=['GET']) @@ -6064,7 +6078,7 @@ def handle_settings(): for key, value in new_settings[service].items(): config_manager.set(f'{service}.{key}', value) - print("Settings saved successfully via Web UI.") + logger.info("Settings saved successfully via Web UI.") # Add activity for settings save changed_services = list(new_settings.keys()) @@ -6102,7 +6116,7 @@ def handle_settings(): tidal_enrichment_worker.client = tidal_client # Invalidate status cache so next poll reflects new settings (e.g. fallback source change) _status_cache_timestamps['spotify'] = 0 - print("Service clients re-initialized with new settings.") + logger.info("Service clients re-initialized with new settings.") return jsonify({"success": True, "message": "Settings saved successfully."}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @@ -6127,7 +6141,7 @@ def handle_dev_mode(): data = request.get_json() if data.get('password') == 'hydratest': dev_mode_enabled = True - print("Dev mode activated") + logger.info("Dev mode activated") return jsonify({"success": True, "enabled": True}) return jsonify({"success": False, "error": "Invalid password"}), 401 return jsonify({"enabled": dev_mode_enabled}) @@ -6252,10 +6266,10 @@ def hydrabase_connect(): config_manager.set('hydrabase.url', url) config_manager.set('hydrabase.api_key', api_key) config_manager.set('hydrabase.auto_connect', True) - print(f"[Hydrabase] Connected to {url}") + logger.info(f"[Hydrabase] Connected to {url}") return jsonify({"success": True, "message": "Connected"}) except Exception as e: - print(f"[Hydrabase] Connection failed: {e}") + logger.error(f"[Hydrabase] Connection failed: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/hydrabase/disconnect', methods=['POST']) @@ -6273,7 +6287,7 @@ def hydrabase_disconnect(): # Only disable dev mode if not using Hydrabase as a regular fallback source if _get_metadata_fallback_source() != 'hydrabase': dev_mode_enabled = False - print("[Hydrabase] Disconnected") + logger.info("[Hydrabase] Disconnected") return jsonify({"success": True}) @app.route('/api/hydrabase/status') @@ -6331,10 +6345,10 @@ def hydrabase_send(): result = json.loads(response) except json.JSONDecodeError: result = response - print(f"[Hydrabase] Sent payload ā€” got response") + logger.info(f"[Hydrabase] Sent payload ā€” got response") return jsonify({"success": True, "data": result}) except Exception as e: - print(f"[Hydrabase] Send failed: {e}") + logger.error(f"[Hydrabase] Send failed: {e}") with _hydrabase_lock: try: _hydrabase_ws.close() @@ -6403,10 +6417,10 @@ def get_log_tail(): level_filter = request.args.get('level', '').upper() # DEBUG, INFO, WARNING, ERROR or empty log_map = { - 'app': os.path.join('logs', 'app.log'), - 'post_processing': os.path.join('logs', 'post_processing.log'), - 'acoustid': os.path.join('logs', 'acoustid.log'), - 'source_reuse': os.path.join('logs', 'source_reuse.log'), + 'app': Path(_log_path), + 'acoustid': _log_dir / 'acoustid.log', + 'post_processing': _log_dir / 'post_processing.log', + 'source_reuse': _log_dir / 'source_reuse.log', } log_path = log_map.get(log_source, log_map['app']) @@ -6418,7 +6432,7 @@ def get_log_tail(): if ' - INFO - ' in line: return 'INFO' if ' - WARNING - ' in line: return 'WARNING' if ' - ERROR - ' in line or ' - CRITICAL - ' in line: return 'ERROR' - # Heuristic for print() output and non-logger lines + # Heuristic for plain-text output and non-logger lines ll = line.lower() if 'error' in ll or 'traceback' in ll or 'exception' in ll or 'failed' in ll: return 'ERROR' if 'warning' in ll or 'warn' in ll: return 'WARNING' @@ -7159,7 +7173,7 @@ def test_connection_endpoint(): if not service: return jsonify({"success": False, "error": "No service specified."}), 400 - print(f"Received test connection request for: {service}") + logger.info(f"Received test connection request for: {service}") # Get the current settings from the main config manager to test with test_config = config_manager.get(service, {}) @@ -7180,18 +7194,18 @@ def test_connection_endpoint(): _status_cache['spotify']['connected'] = True _status_cache['spotify']['source'] = _get_metadata_fallback_source() _status_cache_timestamps['spotify'] = current_time - print("Updated Spotify status cache after successful test") + logger.info("Updated Spotify status cache after successful test") elif service in ['plex', 'jellyfin', 'navidrome', 'soulsync']: _status_cache['media_server']['connected'] = True _status_cache['media_server']['type'] = service _status_cache_timestamps['media_server'] = current_time - print(f"Updated {service} status cache after successful test") + logger.info(f"Updated {service} status cache after successful test") elif service == 'soulseek': _status_cache['soulseek']['connected'] = True _status_cache_timestamps['soulseek'] = current_time - print("Updated Soulseek status cache after successful test") + logger.info("Updated Soulseek status cache after successful test") elif service == 'listenbrainz': - print("ListenBrainz test successful") + logger.info("ListenBrainz test successful") # Add activity for connection test if success: @@ -7209,7 +7223,7 @@ def test_dashboard_connection_endpoint(): if not service: return jsonify({"success": False, "error": "No service specified."}), 400 - print(f"Received dashboard test connection request for: {service}") + logger.info(f"Received dashboard test connection request for: {service}") # Get the current settings from the main config manager to test with test_config = config_manager.get(service, {}) @@ -7230,16 +7244,16 @@ def test_dashboard_connection_endpoint(): _status_cache['spotify']['connected'] = True _status_cache['spotify']['source'] = _get_metadata_fallback_source() _status_cache_timestamps['spotify'] = current_time - print("Updated Spotify status cache after successful dashboard test") + logger.info("Updated Spotify status cache after successful dashboard test") elif service in ['plex', 'jellyfin', 'navidrome', 'soulsync']: _status_cache['media_server']['connected'] = True _status_cache['media_server']['type'] = service _status_cache_timestamps['media_server'] = current_time - print(f"Updated {service} status cache after successful dashboard test") + logger.info(f"Updated {service} status cache after successful dashboard test") elif service == 'soulseek': _status_cache['soulseek']['connected'] = True _status_cache_timestamps['soulseek'] = current_time - print("Updated Soulseek status cache after successful dashboard test") + logger.info("Updated Soulseek status cache after successful dashboard test") # Add activity for dashboard connection test (different from settings test) if success: @@ -7253,7 +7267,7 @@ def test_dashboard_connection_endpoint(): def detect_media_server_endpoint(): data = request.get_json() server_type = data.get('server_type') - print(f"Received auto-detect request for: {server_type}") + logger.info(f"Received auto-detect request for: {server_type}") # Add activity for auto-detect start add_activity_item("", "Auto-Detect Started", f"Searching for {server_type} server", "Now") @@ -7689,7 +7703,7 @@ def apply_quality_preset(preset_name): @app.route('/api/detect-soulseek', methods=['POST']) def detect_soulseek_endpoint(): - print("Received auto-detect request for slskd") + logger.info("Received auto-detect request for slskd") # Add activity for soulseek auto-detect start add_activity_item("", "Auto-Detect Started", "Searching for slskd server", "Now") @@ -7730,10 +7744,10 @@ def auth_spotify(): state=f'profile_{profile_id_int}' ) auth_url = auth_manager.get_authorize_url() - print(f"Per-profile Spotify auth initiated for profile {profile_id_int}") + logger.info(f"Per-profile Spotify auth initiated for profile {profile_id_int}") return redirect(auth_url) except (ValueError, Exception) as e: - print(f"Per-profile Spotify auth failed, falling back to global: {e}") + logger.error(f"Per-profile Spotify auth failed, falling back to global: {e}") # Global auth (admin or fallback) temp_spotify_client = SpotifyClient() @@ -7741,7 +7755,7 @@ def auth_spotify(): # Get the authorization URL auth_url = temp_spotify_client.sp.auth_manager.get_authorize_url() configured_uri = config_manager.get_spotify_config().get('redirect_uri', 'http://127.0.0.1:8888/callback') - print(f"Spotify auth initiated ā€” redirect_uri: {configured_uri}") + logger.info(f"Spotify auth initiated ā€” redirect_uri: {configured_uri}") add_activity_item("", "Spotify Auth Started", "Please complete OAuth in browser", "Now") # Detect if accessing remotely @@ -7858,7 +7872,7 @@ def auth_spotify(): else: return "

    Spotify Authentication Failed

    Could not initialize Spotify client. Check your credentials.

    ", 400 except Exception as e: - print(f"Error starting Spotify auth: {e}") + logger.error(f"Error starting Spotify auth: {e}") return f"

    Spotify Authentication Error

    {str(e)}

    ", 500 @app.route('/auth/tidal') @@ -7866,7 +7880,7 @@ def auth_tidal(): """ Initiates Tidal OAuth authentication flow """ - print("TIDAL AUTH ROUTE CALLED ") + logger.info("TIDAL AUTH ROUTE CALLED ") try: # Create a fresh tidal client to get OAuth URL from core.tidal_client import TidalClient @@ -7889,20 +7903,20 @@ def auth_tidal(): configured_redirect = config_manager.get('tidal.redirect_uri', '') if configured_redirect: temp_tidal_client.redirect_uri = configured_redirect - print(f"Using configured Tidal redirect_uri: {configured_redirect}") + logger.info(f"Using configured Tidal redirect_uri: {configured_redirect}") else: # Fallback: dynamically set based on request host (non-Docker local access) request_host = request.host.split(':')[0] if request_host not in ('127.0.0.1', 'localhost'): dynamic_redirect = f"http://{request_host}:8889/tidal/callback" temp_tidal_client.redirect_uri = dynamic_redirect - print(f"Tidal redirect_uri set from request host: {dynamic_redirect}") + logger.info(f"Tidal redirect_uri set from request host: {dynamic_redirect}") # Store PKCE + redirect_uri for callback to use the same values with tidal_oauth_lock: tidal_oauth_state["redirect_uri"] = temp_tidal_client.redirect_uri - print(f"Stored PKCE - verifier: {temp_tidal_client.code_verifier[:20]}... challenge: {temp_tidal_client.code_challenge[:20]}...") + logger.info(f"Stored PKCE - verifier: {temp_tidal_client.code_verifier[:20]}... challenge: {temp_tidal_client.code_challenge[:20]}...") # Store profile_id for per-profile auth profile_id = request.args.get('profile_id', '') @@ -7922,8 +7936,8 @@ def auth_tidal(): auth_url = f"{temp_tidal_client.auth_url}?" + urllib.parse.urlencode(params) - print(f"Generated Tidal OAuth URL: {auth_url}") - print(f"Redirect URI in URL: {params['redirect_uri']}") + logger.info(f"Generated Tidal OAuth URL: {auth_url}") + logger.info(f"Redirect URI in URL: {params['redirect_uri']}") add_activity_item("", "Tidal Auth Started", "Please complete OAuth in browser", "Now") @@ -7995,9 +8009,9 @@ def auth_tidal(): return f'

    Tidal Authentication

    Please visit this URL to authenticate:

    {auth_url}

    After authentication, return to the app.

    ' except Exception as e: - print(f"Error starting Tidal auth: {e}") + logger.error(f"Error starting Tidal auth: {e}") import traceback - print(f"Full traceback: {traceback.format_exc()}") + logger.error(f"Full traceback: {traceback.format_exc()}") return f"

    Tidal Authentication Error

    {str(e)}

    ", 500 @@ -8014,19 +8028,19 @@ def spotify_callback(): if not auth_code: error = request.args.get('error') if error: - print(f"Spotify OAuth error on port 8008: Spotify returned error: {error}") + logger.error(f"Spotify OAuth error on port 8008: Spotify returned error: {error}") add_activity_item("", "Spotify Auth Failed", f"Spotify returned error: {error}", "Now") return f"

    Spotify Authentication Failed

    Spotify returned error: {error}

    ", 400 # No code AND no error ā€” check if query params were stripped if request.args: - print(f"Spotify callback on port 8008 received unexpected params: {dict(request.args)}") + logger.info(f"Spotify callback on port 8008 received unexpected params: {dict(request.args)}") else: # Completely empty ā€” likely a healthcheck or spurious request pass return '', 204 - print(f"Spotify callback received on port 8008 with authorization code") + logger.info(f"Spotify callback received on port 8008 with authorization code") # Check for per-profile state parameter state = request.args.get('state', '') @@ -8034,7 +8048,7 @@ def spotify_callback(): if state and state.startswith('profile_'): try: profile_id_from_state = int(state.replace('profile_', '')) - print(f"Per-profile callback detected for profile {profile_id_from_state}") + logger.info(f"Per-profile callback detected for profile {profile_id_from_state}") except ValueError: pass @@ -8070,7 +8084,7 @@ def spotify_callback(): # Global callback (admin) config = config_manager.get_spotify_config() configured_uri = config.get('redirect_uri', "http://127.0.0.1:8888/callback") - print(f"Using redirect_uri for token exchange: {configured_uri}") + logger.info(f"Using redirect_uri for token exchange: {configured_uri}") auth_manager = SpotifyOAuth( client_id=config['client_id'], @@ -8105,7 +8119,7 @@ def spotify_callback(): else: raise Exception("Failed to exchange authorization code for access token") except Exception as e: - print(f"Spotify OAuth callback error on port 8008: {e}") + logger.error(f"Spotify OAuth callback error on port 8008: {e}") add_activity_item("", "Spotify Auth Failed", f"Token processing failed: {str(e)}", "Now") return f"

    Spotify Authentication Failed

    {str(e)}

    ", 400 @@ -8208,7 +8222,7 @@ def tidal_callback(): add_activity_item("", "Tidal Auth Complete", f"Profile {profile_id_int} authenticated with Tidal", "Now") return "

    Tidal Authentication Successful!

    Your personal Tidal account is now connected. You can close this window.

    " except Exception as profile_err: - print(f"Per-profile Tidal auth failed, falling back to global: {profile_err}") + logger.error(f"Per-profile Tidal auth failed, falling back to global: {profile_err}") # Global: Re-initialize the main global tidal_client instance with the new token tidal_client = TidalClient() @@ -8218,7 +8232,7 @@ def tidal_callback(): else: return "

    Tidal Authentication Failed

    Could not exchange authorization code for a token. Please try again.

    ", 400 except Exception as e: - print(f"Error during Tidal token exchange: {e}") + logger.error(f"Error during Tidal token exchange: {e}") return f"

    An Error Occurred

    An unexpected error occurred during the authentication process: {e}

    ", 500 @@ -8339,14 +8353,9 @@ def get_beatport_hero_tracks(): # SMART FILTERING - Remove duplicates and invalid tracks valid_tracks = [] seen_urls = set() - - logger.info(f"Processing {len(tracks)} raw tracks from scraper (SMART FILTERING)...") + filtered_reasons = collections.Counter() for i, track in enumerate(tracks): - logger.info(f" Track {i+1}: {track.get('title', 'NO_TITLE')} - {track.get('artist', 'NO_ARTIST')}") - logger.info(f" URL: {track.get('url', 'NO_URL')}") - logger.info(f" Image: {'YES' if track.get('image_url') else 'NO'}") - # Extract and clean basic data title = track.get('title', '').strip() artist = track.get('artist', '').strip() @@ -8391,7 +8400,7 @@ def get_beatport_hero_tracks(): skip_reasons.append("Duplicate URL") if not is_valid: - logger.info(f" Track {i+1} filtered out: {', '.join(skip_reasons)}") + filtered_reasons.update(skip_reasons) continue # Mark URL as seen for deduplication @@ -8434,7 +8443,16 @@ def get_beatport_hero_tracks(): break valid_tracks.append(track_data) - logger.info(f" Track {i+1} added: {title} - {artist}") + + sample_titles = [f"{t['title']} - {t['artist']}" for t in valid_tracks[:3]] + logger.debug( + "Beatport smart filter summary: raw=%s valid=%s filtered=%s reasons=%s sample=%s", + len(tracks), + len(valid_tracks), + len(tracks) - len(valid_tracks), + dict(filtered_reasons), + sample_titles, + ) logger.info(f"Retrieved {len(valid_tracks)} valid unique Beatport tracks (SMART FILTERING)") @@ -8620,17 +8638,17 @@ def get_beatport_featured_charts(): gridsliders = soup.select('[class*="GridSlider-style__Wrapper"]') featured_container = None - logger.info(f"Checking {len(gridsliders)} GridSlider containers for featured charts...") + logger.debug(f"Checking {len(gridsliders)} GridSlider containers for featured charts...") for container in gridsliders: h2 = container.select_one('h2') if h2: title = h2.get_text(strip=True).lower() - logger.info(f"Found section: '{h2.get_text(strip=True)}'") + logger.debug(f"Found section: '{h2.get_text(strip=True)}'") if 'featured' in title and 'chart' in title: featured_container = container - logger.info(f"FOUND FEATURED CHARTS: '{h2.get_text(strip=True)}'") + logger.debug(f"FOUND FEATURED CHARTS: '{h2.get_text(strip=True)}'") break if not featured_container: @@ -8645,7 +8663,7 @@ def get_beatport_featured_charts(): charts = [] chart_links = featured_container.select('a[href*="/chart/"]') - logger.info(f"Found {len(chart_links)} chart links in Featured Charts section") + logger.debug(f"Found {len(chart_links)} chart links in Featured Charts section") for i, link in enumerate(chart_links[:100]): # Limit to 100 for 10 slides chart_data = {} @@ -8713,7 +8731,7 @@ def get_beatport_featured_charts(): # Only add if we have meaningful data if 'name' in chart_data and 'url' in chart_data: charts.append(chart_data) - logger.info(f"Chart {len(charts)}: {chart_data['name']} by {chart_data['creator']}") + logger.debug(f"Chart {len(charts)}: {chart_data['name']} by {chart_data['creator']}") logger.info(f"Successfully extracted {len(charts)} featured charts") @@ -8769,12 +8787,12 @@ def get_beatport_dj_charts(): carousels = soup.select('[class*="Carousel-style__Wrapper"]') dj_container = None - logger.info(f"Checking {len(carousels)} Carousel containers for DJ charts...") + logger.debug(f"Checking {len(carousels)} Carousel containers for DJ charts...") # Based on test results, DJ charts are in the second carousel (index 1) with ~9 chart links for i, container in enumerate(carousels): chart_links = container.select('a[href*="/chart/"]') - logger.info(f"Carousel {i+1}: {len(chart_links)} chart links") + logger.debug(f"Carousel {i+1}: {len(chart_links)} chart links") # DJ charts container typically has 8-12 chart links (not 99+ like featured charts) if 5 <= len(chart_links) <= 15: @@ -8949,7 +8967,7 @@ def search_music(): return jsonify({"results": all_results}) except Exception as e: - print(f"Search error: {e}") + logger.error(f"Search error: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/enhanced-search', methods=['POST']) @@ -9633,16 +9651,16 @@ def download_music_video(): track_title = best.name if hasattr(best, 'release_date') and best.release_date: year = str(best.release_date)[:4] - print(f"[Music Video] Matched to: {artist_name} - {track_title} (confidence: {best_score:.2f})") + logger.info(f"[Music Video] Matched to: {artist_name} - {track_title} (confidence: {best_score:.2f})") else: # Parse artist from video title: "Artist - Title" pattern if ' - ' in raw_title: parts = raw_title.split(' - ', 1) artist_name = parts[0].strip() track_title = _re.sub(r'\s*[\(\[].*?[\)\]]', '', parts[1]).strip() - print(f"[Music Video] No metadata match, using parsed: {artist_name} - {track_title}") + logger.warning(f"[Music Video] No metadata match, using parsed: {artist_name} - {track_title}") except Exception as e: - print(f"[Music Video] Metadata lookup failed: {e}") + logger.error(f"[Music Video] Metadata lookup failed: {e}") if ' - ' in raw_title: parts = raw_title.split(' - ', 1) artist_name = parts[0].strip() @@ -9688,17 +9706,17 @@ def download_music_video(): _music_video_downloads[video_id]['status'] = 'completed' _music_video_downloads[video_id]['progress'] = 100 _music_video_downloads[video_id]['path'] = final_path - print(f"[Music Video] Downloaded: {artist_name} - {track_title} ā†’ {final_path}") + logger.info(f"[Music Video] Downloaded: {artist_name} - {track_title} ā†’ {final_path}") add_activity_item("", "Music Video Downloaded", f"{artist_name} - {track_title}", "Now") else: _music_video_downloads[video_id]['status'] = 'error' _music_video_downloads[video_id]['error'] = 'Download failed ā€” file not found' - print(f"[Music Video] Download failed for: {artist_name} - {track_title}") + logger.error(f"[Music Video] Download failed for: {artist_name} - {track_title}") except Exception as e: _music_video_downloads[video_id]['status'] = 'error' _music_video_downloads[video_id]['error'] = str(e) - print(f"[Music Video] Error: {e}") + logger.error(f"[Music Video] {e}") # Run in background thread import threading @@ -9891,11 +9909,11 @@ def _find_completed_file_robust(download_dir, api_filename, transfer_dir=None): file_path = os.path.join(root, file) # Fast path: if path aligns with expected directory structure, return now if api_dir_parts and _path_matches_api_dirs(file_path): - print(f"Found path-confirmed match in {location_name}: {file_path}") + logger.info(f"Found path-confirmed match in {location_name}: {file_path}") return file_path, 1.0 if not api_dir_parts: # No directory info to disambiguate ā€” return first match (original behavior) - print(f"Found exact match in {location_name}: {file_path}") + logger.info(f"Found exact match in {location_name}: {file_path}") return file_path, 1.0 exact_matches.append(file_path) continue @@ -9907,10 +9925,10 @@ def _find_completed_file_robust(download_dir, api_filename, transfer_dir=None): if stripped_stem != file_stem and stripped_stem + file_ext_part == target_basename: file_path = os.path.join(root, file) if api_dir_parts and _path_matches_api_dirs(file_path): - print(f"Found path-confirmed dedup match in {location_name}: {file_path}") + logger.info(f"Found path-confirmed dedup match in {location_name}: {file_path}") return file_path, 1.0 if not api_dir_parts: - print(f"Found dedup-suffix match in {location_name}: {file_path}") + logger.info(f"Found dedup-suffix match in {location_name}: {file_path}") return file_path, 1.0 exact_matches.append(file_path) continue @@ -9926,7 +9944,7 @@ def _find_completed_file_robust(download_dir, api_filename, transfer_dir=None): # Return best exact match (disambiguated by path), or fall back to fuzzy if exact_matches: if len(exact_matches) == 1: - print(f"Found exact match in {location_name}: {exact_matches[0]}") + logger.info(f"Found exact match in {location_name}: {exact_matches[0]}") return exact_matches[0], 1.0 # Multiple files share the basename ā€” pick the one whose path best # matches the expected directory structure from the Soulseek remote path @@ -9938,7 +9956,7 @@ def _find_completed_file_robust(download_dir, api_filename, transfer_dir=None): if score > best_score: best_score = score best = m - print(f"Found {len(exact_matches)} files named '{target_basename}' in {location_name}, picked best path match: {best}") + logger.info(f"Found {len(exact_matches)} files named '{target_basename}' in {location_name}, picked best path match: {best}") return best, 1.0 return best_fuzzy_path, highest_fuzzy_similarity @@ -9960,7 +9978,7 @@ def _find_completed_file_robust(download_dir, api_filename, transfer_dir=None): if downloads_similarity > 0.85: location = 'downloads' if downloads_similarity < 1.0: - print(f"Found fuzzy match in downloads ({downloads_similarity:.2f}): {best_downloads_path}") + logger.info(f"Found fuzzy match in downloads ({downloads_similarity:.2f}): {best_downloads_path}") return (best_downloads_path, location) # If not found in downloads and transfer_dir is provided, search there @@ -9971,7 +9989,7 @@ def _find_completed_file_robust(download_dir, api_filename, transfer_dir=None): if transfer_similarity > 0.85: location = 'transfer' if transfer_similarity < 1.0: - print(f"Found fuzzy match in transfer ({transfer_similarity:.2f}): {best_transfer_path}") + logger.info(f"Found fuzzy match in transfer ({transfer_similarity:.2f}): {best_transfer_path}") return (best_transfer_path, location) # Don't spam logs - file not found is common for completed/processed downloads @@ -10040,7 +10058,7 @@ def get_download_status(): with matched_context_lock: has_active_context = context_key in matched_downloads_context if has_active_context: - print(f"Orphaned key {context_key} has active context ā€” retry re-used same source, treating as active") + logger.warning(f"Orphaned key {context_key} has active context ā€” retry re-used same source, treating as active") _orphaned_download_keys.discard(context_key) # Fall through to normal processing below else: @@ -10051,10 +10069,10 @@ def get_download_status(): if found_path: try: os.remove(found_path) - print(f"Deleted orphaned download: {os.path.basename(found_path)}") + logger.warning(f"Deleted orphaned download: {os.path.basename(found_path)}") orphan_cleaned = True except Exception as e: - print(f"Failed to delete orphaned file (will retry next poll): {e}") + logger.error(f"Failed to delete orphaned file (will retry next poll): {e}") else: # File not on disk (already gone or never written) ā€” nothing to clean orphan_cleaned = True @@ -10078,11 +10096,11 @@ def get_download_status(): available_keys = list(matched_downloads_context.keys())[:5] if not context else None if context: - print(f"[Context Lookup] Found context for key: {context_key}") + logger.info(f"[Context Lookup] Found context for key: {context_key}") elif context_key not in _stale_transfer_keys: # Only log once per stale key to avoid spamming every poll cycle - print(f"[Context Lookup] No context found for key: {context_key}") - print(f" Available keys: {available_keys}...") + logger.warning(f"[Context Lookup] No context found for key: {context_key}") + logger.info(f" Available keys: {available_keys}...") _stale_transfer_keys.add(context_key) if context: @@ -10095,10 +10113,10 @@ def get_download_status(): # Prevent two contexts from claiming the same physical file _norm_path = os.path.normpath(found_path) if _norm_path in _files_claimed_this_cycle: - print(f"File already claimed by another context this cycle: {os.path.basename(found_path)} ā€” deferring to next poll") + logger.info(f"File already claimed by another context this cycle: {os.path.basename(found_path)} ā€” deferring to next poll") else: _files_claimed_this_cycle.add(_norm_path) - print(f"Found completed matched file on disk: {found_path}") + logger.info(f"Found completed matched file on disk: {found_path}") completed_matched_downloads.append((context_key, context, found_path)) # Don't add to _processed_download_ids yet - wait until thread starts successfully @@ -10107,7 +10125,7 @@ def get_download_status(): if context_key in _download_retry_attempts: retry_count = _download_retry_attempts[context_key]['count'] elapsed = time.time() - _download_retry_attempts[context_key]['first_attempt'] - print(f"File found after {retry_count} retry attempt(s) ({elapsed:.1f}s): {os.path.basename(filename_from_api)}") + logger.warning(f"File found after {retry_count} retry attempt(s) ({elapsed:.1f}s): {os.path.basename(filename_from_api)}") del _download_retry_attempts[context_key] else: # File not found yet - implement retry logic instead of immediate give-up @@ -10119,7 +10137,7 @@ def get_download_status(): 'count': 1, 'first_attempt': time.time() } - print(f"File not found yet: '{os.path.basename(filename_from_api)}' - Will retry (attempt 1/{_download_retry_max})") + logger.warning(f"File not found yet: '{os.path.basename(filename_from_api)}' - Will retry (attempt 1/{_download_retry_max})") else: # Increment retry count _download_retry_attempts[context_key]['count'] += 1 @@ -10128,19 +10146,19 @@ def get_download_status(): if retry_count >= _download_retry_max: # Max retries reached, give up - print(f"CRITICAL: Could not find '{os.path.basename(filename_from_api)}' after {retry_count} attempts over {elapsed:.1f}s. Giving up.") + logger.error(f"CRITICAL: Could not find '{os.path.basename(filename_from_api)}' after {retry_count} attempts over {elapsed:.1f}s. Giving up.") _processed_download_ids.add(context_key) # Clean up retry tracking del _download_retry_attempts[context_key] else: - print(f"File not found yet: '{os.path.basename(filename_from_api)}' - Will retry (attempt {retry_count}/{_download_retry_max}, elapsed: {elapsed:.1f}s)") + logger.warning(f"File not found yet: '{os.path.basename(filename_from_api)}' - Will retry (attempt {retry_count}/{_download_retry_max}, elapsed: {elapsed:.1f}s)") # If we found completed matched downloads, start processing them in background threads if completed_matched_downloads: def process_completed_downloads(): for context_key, context, found_path in completed_matched_downloads: try: - print(f"Starting post-processing thread for: {context_key}") + logger.info(f"Starting post-processing thread for: {context_key}") # Use verification wrapper if context has task tracking IDs, # otherwise call directly (race guard flag still gets set on context) _pp_task_id = context.get('task_id') @@ -10157,16 +10175,16 @@ def get_download_status(): # Only mark as processed AFTER thread starts successfully _processed_download_ids.add(context_key) - print(f"Marked as processed: {context_key}") + logger.info(f"Marked as processed: {context_key}") # DON'T remove context immediately - verification worker needs it # Context will be cleaned up by verification worker after both processors complete - print(f"Keeping context for verification worker: {context_key}") + logger.info(f"Keeping context for verification worker: {context_key}") except Exception as e: - print(f"Error starting post-processing thread for {context_key}: {e}") + logger.error(f"Error starting post-processing thread for {context_key}: {e}") # Don't add to processed set if thread failed to start - print(f"Will retry {context_key} on next check") + logger.warning(f"Will retry {context_key} on next check") # Start a single thread to manage the launching of all processing threads processing_thread = threading.Thread(target=process_completed_downloads) @@ -10212,14 +10230,14 @@ def get_download_status(): # Prevent two contexts from claiming the same physical file _st_norm = os.path.normpath(found_path) if _st_norm in _files_claimed_this_cycle: - print(f"[{source_label}] File already claimed this cycle: {os.path.basename(found_path)} ā€” deferring") + logger.info(f"[{source_label}] File already claimed this cycle: {os.path.basename(found_path)} ā€” deferring") continue _files_claimed_this_cycle.add(_st_norm) - print(f"[{source_label}] Found completed matched file on disk: {found_path}") + logger.info(f"[{source_label}] Found completed matched file on disk: {found_path}") # Start post-processing thread def process_streaming_download(_ctx_key=context_key, _ctx=context, _path=found_path, _label=source_label): try: - print(f"[{_label}] Starting post-processing thread for: {_ctx_key}") + logger.info(f"[{_label}] Starting post-processing thread for: {_ctx_key}") # Use verification wrapper if context has task tracking IDs _st_task_id = _ctx.get('task_id') _st_batch_id = _ctx.get('batch_id') @@ -10233,9 +10251,9 @@ def get_download_status(): thread.daemon = True thread.start() _processed_download_ids.add(_ctx_key) - print(f"[{_label}] Marked as processed: {_ctx_key}") + logger.info(f"[{_label}] Marked as processed: {_ctx_key}") except Exception as e: - print(f"[{_label}] Error starting post-processing thread for {_ctx_key}: {e}") + logger.error(f"[{_label}] Error starting post-processing thread for {_ctx_key}: {e}") processing_thread = threading.Thread(target=process_streaming_download) processing_thread.daemon = True @@ -10246,13 +10264,31 @@ def get_download_status(): _processed_download_ids.add(context_key) except Exception as streaming_error: import traceback - print(f"Could not fetch YouTube/Tidal downloads for status: {streaming_error}") + logger.error(f"Could not fetch YouTube/Tidal downloads for status: {streaming_error}") traceback.print_exc() + # Enrich transfers with metadata from download context (artist, album, artwork) + with matched_context_lock: + for transfer in all_transfers: + ctx_key = _make_context_key(transfer.get('username', ''), transfer.get('filename', '')) + ctx = matched_downloads_context.get(ctx_key) + if ctx: + _sp_artist = ctx.get('spotify_artist') or {} + _sp_album = ctx.get('spotify_album') or {} + _sp_track = ctx.get('track_info') or {} + _sp_images = _sp_album.get('images') or [] + transfer['_meta'] = { + 'artist': _sp_artist.get('name', ''), + 'album': _sp_album.get('name', ''), + 'artwork_url': _sp_images[0].get('url', '') if _sp_images and isinstance(_sp_images[0], dict) else '', + 'track_number': _sp_track.get('track_number'), + 'quality': ctx.get('_audio_quality', ''), + } + return jsonify({"transfers": all_transfers}) except Exception as e: - print(f"Error fetching download status: {e}") + logger.error(f"Error fetching download status: {e}") return jsonify({"error": str(e)}), 500 @@ -10282,7 +10318,7 @@ def cancel_download(): else: return jsonify({"success": False, "error": "Failed to cancel download via slskd."}), 500 except Exception as e: - print(f"Error cancelling download: {e}") + logger.error(f"Error cancelling download: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/downloads/cancel-all', methods=['POST']) @@ -10304,7 +10340,7 @@ def cancel_all_downloads(): return jsonify({"success": True, "message": "All downloads cancelled and cleared."}) except Exception as e: - print(f"Error cancelling all downloads: {e}") + logger.error(f"Error cancelling all downloads: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/downloads/clear-finished', methods=['POST']) @@ -10322,7 +10358,7 @@ def clear_finished_downloads(): else: return jsonify({"success": False, "error": "Backend failed to clear downloads."}), 500 except Exception as e: - print(f"Error clearing finished downloads: {e}") + logger.error(f"Error clearing finished downloads: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/downloads/task//candidates', methods=['GET']) @@ -10369,7 +10405,7 @@ def get_task_candidates(task_id): "candidate_count": len(serialized), }) except Exception as e: - print(f"[Candidates] Error fetching candidates for task {task_id}: {e}") + logger.error(f"[Candidates] Error fetching candidates for task {task_id}: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/downloads/task//download-candidate', methods=['POST']) @@ -10477,11 +10513,11 @@ def download_selected_candidate(task_id): missing_download_executor.submit(_run_manual_download) track_name = track_info.get('name', 'Unknown') - print(f"[Manual Download] User selected candidate for '{track_name}' from {username}") + logger.info(f"[Manual Download] User selected candidate for '{track_name}' from {username}") return jsonify({"success": True, "message": f"Download initiated for '{track_name}'"}) except Exception as e: - print(f"[Manual Download] Error: {e}") + logger.error(f"[Manual Download] {e}") import traceback traceback.print_exc() return jsonify({"error": str(e)}), 500 @@ -10508,12 +10544,12 @@ def clear_quarantine(): shutil.rmtree(entry_path) removed_files += 1 except Exception as e: - print(f"[Quarantine] Failed to remove {entry}: {e}") + logger.error(f"[Quarantine] Failed to remove {entry}: {e}") - print(f"[Quarantine] Cleared {removed_files} item(s) from quarantine folder") + logger.info(f"[Quarantine] Cleared {removed_files} item(s) from quarantine folder") return jsonify({"success": True, "message": f"Quarantine cleared ({removed_files} item{'s' if removed_files != 1 else ''} removed)."}) except Exception as e: - print(f"[Quarantine] Error clearing quarantine: {e}") + logger.error(f"[Quarantine] Error clearing quarantine: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/scan/request', methods=['POST']) @@ -10710,7 +10746,7 @@ def clear_all_searches(): else: return jsonify({"success": False, "error": "Backend failed to clear searches."}), 500 except Exception as e: - print(f"Error clearing searches: {e}") + logger.error(f"Error clearing searches: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/searches/maintain', methods=['POST']) @@ -10732,7 +10768,7 @@ def maintain_search_history(): else: return jsonify({"success": False, "error": "Backend failed to maintain search history."}), 500 except Exception as e: - print(f"Error maintaining search history: {e}") + logger.error(f"Error maintaining search history: {e}") return jsonify({"success": False, "error": str(e)}), 500 def fix_artist_image_url(thumb_url): @@ -10753,13 +10789,13 @@ def fix_artist_image_url(thumb_url): if needs_fixing: active_server = config_manager.get_active_media_server() - print(f"Fixing URL: {thumb_url}, Active server: {active_server}") + logger.debug(f"Fixing URL: {thumb_url}, Active server: {active_server}") if active_server == 'plex': plex_config = config_manager.get_plex_config() plex_base_url = plex_config.get('base_url', '') plex_token = plex_config.get('token', '') - print(f"Plex config - base_url: {plex_base_url}, token: {plex_token[:10]}...") + logger.info(f"Plex config - base_url: {plex_base_url}, token: {plex_token[:10]}...") if plex_base_url and plex_token: # Extract the path from URL @@ -10774,14 +10810,14 @@ def fix_artist_image_url(thumb_url): # Construct proper Plex URL with token fixed_url = f"{plex_base_url.rstrip('/')}{path}?X-Plex-Token={plex_token}" - print(f"Fixed URL: {fixed_url}") + logger.info(f"Fixed URL: {fixed_url}") return fixed_url elif active_server == 'jellyfin': jellyfin_config = config_manager.get_jellyfin_config() jellyfin_base_url = jellyfin_config.get('base_url', '') jellyfin_token = jellyfin_config.get('api_key', '') - print(f"Jellyfin config - base_url: {jellyfin_base_url}, token: {jellyfin_token[:10] if jellyfin_token else 'None'}...") + logger.info(f"Jellyfin config - base_url: {jellyfin_base_url}, token: {jellyfin_token[:10] if jellyfin_token else 'None'}...") if jellyfin_base_url: # Extract the path from URL @@ -10800,7 +10836,7 @@ def fix_artist_image_url(thumb_url): fixed_url = f"{jellyfin_base_url.rstrip('/')}{path}{separator}X-Emby-Token={jellyfin_token}" else: fixed_url = f"{jellyfin_base_url.rstrip('/')}{path}" - print(f"Fixed URL: {fixed_url}") + logger.info(f"Fixed URL: {fixed_url}") return fixed_url elif active_server == 'navidrome': @@ -10808,7 +10844,7 @@ def fix_artist_image_url(thumb_url): navidrome_base_url = navidrome_config.get('base_url', '') navidrome_username = navidrome_config.get('username', '') navidrome_password = navidrome_config.get('password', '') - print(f"Navidrome config - base_url: {navidrome_base_url}, username: {navidrome_username}") + logger.info(f"Navidrome config - base_url: {navidrome_base_url}, username: {navidrome_username}") if navidrome_base_url and navidrome_username and navidrome_password: # Extract the path from URL @@ -10833,16 +10869,16 @@ def fix_artist_image_url(thumb_url): # Construct proper Navidrome Subsonic URL fixed_url = f"{navidrome_base_url.rstrip('/')}{path}{separator}{auth_params}" - print(f"Fixed URL: {fixed_url}") + logger.info(f"Fixed URL: {fixed_url}") return fixed_url - print(f"No configuration found for {active_server} or unsupported server type") + logger.warning(f"No configuration found for {active_server} or unsupported server type") # Return original URL if no fixing needed/possible return thumb_url except Exception as e: - print(f"Error fixing image URL '{thumb_url}': {e}") + logger.error(f"Error fixing image URL '{thumb_url}': {e}") return thumb_url @app.route('/api/library/history') @@ -10909,7 +10945,7 @@ def get_library_artists(): }) except Exception as e: - print(f"Error fetching library artists: {e}") + logger.error(f"Error fetching library artists: {e}") import traceback traceback.print_exc() return jsonify({ @@ -10938,7 +10974,7 @@ def test_artist_endpoint(artist_id): def get_artist_detail(artist_id): """Get artist detail data""" try: - print(f"Getting artist detail for ID: {artist_id}") + logger.info(f"Getting artist detail for ID: {artist_id}") # Get database instance database = get_database() @@ -10947,7 +10983,7 @@ def get_artist_detail(artist_id): db_result = database.get_artist_discography(artist_id) if not db_result.get('success'): - print(f"Database returned error: {db_result}") + logger.error(f"Database returned error: {db_result}") return jsonify({ "success": False, "error": db_result.get('error', 'Artist not found') @@ -10956,18 +10992,18 @@ def get_artist_detail(artist_id): artist_info = db_result['artist'] owned_releases = db_result['owned_releases'] - print(f"Found artist: {artist_info['name']} with {len(owned_releases['albums'])} albums") + logger.info(f"Found artist: {artist_info['name']} with {len(owned_releases['albums'])} albums") # Fix artist image URL - print(f"Artist image before fix: '{artist_info.get('image_url')}'") + logger.info(f"Artist image before fix: '{artist_info.get('image_url')}'") if artist_info.get('image_url'): artist_info['image_url'] = fix_artist_image_url(artist_info['image_url']) - print(f"Artist image after fix: '{artist_info['image_url']}'") + logger.info(f"Artist image after fix: '{artist_info['image_url']}'") else: - print(f"No artist image URL found for {artist_info['name']}") + logger.warning(f"No artist image URL found for {artist_info['name']}") # Debug final artist data being sent - print(f"Final artist data being sent: {artist_info}") + logger.info(f"Final artist data being sent: {artist_info}") # Fix image URLs for all albums for album in owned_releases['albums']: @@ -11009,7 +11045,7 @@ def get_artist_detail(artist_id): ) if artist_detail_discography['success']: - print( + logger.debug( "Source-priority discography found - " f"Albums: {len(artist_detail_discography['albums'])}, " f"EPs: {len(artist_detail_discography['eps'])}, " @@ -11017,10 +11053,10 @@ def get_artist_detail(artist_id): ) merged_discography = artist_detail_discography else: - print(f"Source-priority discography not found: {artist_detail_discography.get('error', 'Unknown error')}") + logger.debug(f"Source-priority discography not found: {artist_detail_discography.get('error', 'Unknown error')}") merged_discography = owned_releases except Exception as detail_error: - print(f"Error fetching source-priority discography: {detail_error}") + logger.error(f"Error fetching source-priority discography: {detail_error}") merged_discography = owned_releases spotify_artist_data = None @@ -11081,7 +11117,7 @@ def get_artist_detail(artist_id): return jsonify(response_data) except Exception as e: - print(f"Error in get_artist_detail: {e}") + logger.error(f"Error in get_artist_detail: {e}") import traceback traceback.print_exc() return jsonify({ @@ -11130,298 +11166,45 @@ def debug_library_photos(): @app.route('/api/artist/similar//stream') def get_similar_artists_stream(artist_name): - """ - Stream similar artists from MusicMap and match them to Spotify one by one + """Stream MusicMap similar artists using source-priority metadata matching.""" + from core.metadata_service import iter_musicmap_similar_artist_events - Args: - artist_name: The artist name to find similar artists for - - Returns: - Server-Sent Events stream with each matched artist - """ def generate(): - try: - print(f"Streaming similar artists for: {artist_name}") - - # Import required libraries - from bs4 import BeautifulSoup - - # Construct MusicMap URL - url_artist = artist_name.lower().replace(' ', '+') - musicmap_url = f'https://www.music-map.com/{url_artist}' - - print(f"Fetching MusicMap: {musicmap_url}") - - # Set headers to mimic a browser - headers = { - 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36', - 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8', - 'Accept-Language': 'en-US,en;q=0.5', - } - - # Fetch MusicMap page - response = requests.get(musicmap_url, headers=headers, timeout=10) - response.raise_for_status() - - # Parse HTML - soup = BeautifulSoup(response.text, 'html.parser') - gnod_map = soup.find(id='gnodMap') - - if not gnod_map: - yield f"data: {json.dumps({'error': 'Could not find artist map on MusicMap'})}\n\n" - return - - # Extract similar artist names - all_anchors = gnod_map.find_all('a') - searched_artist_lower = artist_name.lower().strip() - - similar_artist_names = [] - for anchor in all_anchors: - artist_text = anchor.get_text(strip=True) - - # Skip if this is the searched artist - if artist_text.lower() == searched_artist_lower: - continue - - similar_artist_names.append(artist_text) - - print(f"Found {len(similar_artist_names)} similar artists from MusicMap") - - # Determine metadata source - use_hydrabase = _is_hydrabase_active() - - if not use_hydrabase: - if not spotify_client or not spotify_client.is_authenticated(): - yield f"data: {json.dumps({'error': 'Spotify not authenticated'})}\n\n" - return - - # Get the searched artist's ID to exclude them - searched_artist_id = None - try: - if use_hydrabase: - searched_results = hydrabase_client.search_artists(artist_name, limit=1) - else: - searched_results = spotify_client.search_artists(artist_name, limit=1) - if searched_results and len(searched_results) > 0: - searched_artist_id = searched_results[0].id - print(f"Searched artist ID: {searched_artist_id}") - except Exception as e: - print(f"Could not get searched artist ID: {e}") - - # Match each artist one by one and stream results - max_artists = 20 - matched_count = 0 - seen_artist_ids = set() # Track seen artist IDs to prevent duplicates - - for artist_name_to_match in similar_artist_names[:max_artists]: - try: - print(f"Matching: {artist_name_to_match}") - - # Search for the artist via active metadata source - if use_hydrabase: - results = hydrabase_client.search_artists(artist_name_to_match, limit=1) - else: - results = spotify_client.search_artists(artist_name_to_match, limit=1) - - if results and len(results) > 0: - spotify_artist = results[0] - - # Skip if this is the searched artist - if spotify_artist.id == searched_artist_id: - print(f"Skipping searched artist: {spotify_artist.name}") - continue - - # Skip if we've already seen this artist ID (deduplication) - if spotify_artist.id in seen_artist_ids: - print(f"Skipping duplicate artist: {spotify_artist.name}") - continue - - seen_artist_ids.add(spotify_artist.id) - - artist_data = { - 'id': spotify_artist.id, - 'name': spotify_artist.name, - 'image_url': spotify_artist.image_url if hasattr(spotify_artist, 'image_url') else None, - 'genres': spotify_artist.genres if hasattr(spotify_artist, 'genres') else [], - 'popularity': spotify_artist.popularity if hasattr(spotify_artist, 'popularity') else 0 - } - - # Stream this matched artist immediately - yield f"data: {json.dumps({'artist': artist_data})}\n\n" - matched_count += 1 - - print(f"Matched and streamed: {spotify_artist.name}") - else: - print(f"No Spotify match found for: {artist_name_to_match}") - - except Exception as match_error: - print(f"Error matching {artist_name_to_match}: {match_error}") - continue - - # Send completion message - yield f"data: {json.dumps({'complete': True, 'total': matched_count})}\n\n" - print(f"Streaming complete: {matched_count} artists matched") - - except requests.exceptions.RequestException as e: - print(f"Error fetching MusicMap: {e}") - yield f"data: {json.dumps({'error': f'Failed to fetch from MusicMap: {str(e)}'})}\n\n" - - except Exception as e: - print(f"Error streaming similar artists: {e}") - import traceback - traceback.print_exc() - yield f"data: {json.dumps({'error': str(e)})}\n\n" + logger.info(f"Streaming similar artists for: {artist_name}") + for event in iter_musicmap_similar_artist_events(artist_name, limit=20): + yield f"data: {json.dumps(event)}\n\n" + if event.get('artist'): + time.sleep(0.1) return Response(generate(), mimetype='text/event-stream') @app.route('/api/artist/similar/') def get_similar_artists(artist_name): - """ - Get similar artists from MusicMap and match them to Spotify (legacy batch endpoint) + """Get MusicMap similar artists using source-priority metadata matching.""" + from core.metadata_service import get_musicmap_similar_artists - Args: - artist_name: The artist name to find similar artists for - - Returns: - JSON with similar artists matched to Spotify data - """ try: - print(f"Getting similar artists for: {artist_name}") - - # Import required libraries - from bs4 import BeautifulSoup - - # Construct MusicMap URL - url_artist = artist_name.lower().replace(' ', '+') - musicmap_url = f'https://www.music-map.com/{url_artist}' - - print(f"Fetching MusicMap: {musicmap_url}") - - # Set headers to mimic a browser - headers = { - 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36', - 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8', - 'Accept-Language': 'en-US,en;q=0.5', - } - - # Fetch MusicMap page - response = requests.get(musicmap_url, headers=headers, timeout=10) - response.raise_for_status() - - # Parse HTML - soup = BeautifulSoup(response.text, 'html.parser') - gnod_map = soup.find(id='gnodMap') - - if not gnod_map: + logger.info(f"Getting similar artists for: {artist_name}") + result = get_musicmap_similar_artists(artist_name, limit=20) + if not result.get('success'): + error = result.get('error', 'Failed to fetch similar artists') + status_code = int(result.get('status_code') or 500) return jsonify({ "success": False, - "error": "Could not find artist map on MusicMap" - }), 404 - - # Extract similar artist names - all_anchors = gnod_map.find_all('a') - searched_artist_lower = artist_name.lower().strip() - - similar_artist_names = [] - for anchor in all_anchors: - artist_text = anchor.get_text(strip=True) - - # Skip if this is the searched artist - if artist_text.lower() == searched_artist_lower: - continue - - similar_artist_names.append(artist_text) - - print(f"Found {len(similar_artist_names)} similar artists from MusicMap") - - # Determine metadata source - use_hydrabase = _is_hydrabase_active() - - if not use_hydrabase: - if not spotify_client or not spotify_client.is_authenticated(): - return jsonify({ - "success": False, - "error": "Spotify not authenticated" - }), 401 - - # Get the searched artist's ID to exclude them - searched_artist_id = None - try: - if use_hydrabase: - searched_results = hydrabase_client.search_artists(artist_name, limit=1) - else: - searched_results = spotify_client.search_artists(artist_name, limit=1) - if searched_results and len(searched_results) > 0: - searched_artist_id = searched_results[0].id - print(f"Searched artist ID: {searched_artist_id}") - except Exception as e: - print(f"Could not get searched artist ID: {e}") - - # Match each artist (limit to first 20 for performance) - matched_artists = [] - max_artists = 20 - seen_artist_ids = set() # Track seen artist IDs to prevent duplicates - - for artist_name_to_match in similar_artist_names[:max_artists]: - try: - print(f"Matching: {artist_name_to_match}") - - # Search for the artist via active metadata source - if use_hydrabase: - results = hydrabase_client.search_artists(artist_name_to_match, limit=1) - else: - results = spotify_client.search_artists(artist_name_to_match, limit=1) - - if results and len(results) > 0: - spotify_artist = results[0] - - # Skip if this is the searched artist - if spotify_artist.id == searched_artist_id: - print(f"Skipping searched artist: {spotify_artist.name}") - continue - - # Skip if we've already seen this artist ID (deduplication) - if spotify_artist.id in seen_artist_ids: - print(f"Skipping duplicate artist: {spotify_artist.name}") - continue - - seen_artist_ids.add(spotify_artist.id) - - matched_artists.append({ - 'id': spotify_artist.id, - 'name': spotify_artist.name, - 'image_url': spotify_artist.image_url if hasattr(spotify_artist, 'image_url') else None, - 'genres': spotify_artist.genres if hasattr(spotify_artist, 'genres') else [], - 'popularity': spotify_artist.popularity if hasattr(spotify_artist, 'popularity') else 0 - }) - - print(f"Matched: {spotify_artist.name}") - else: - print(f"No Spotify match found for: {artist_name_to_match}") - - except Exception as match_error: - print(f"Error matching {artist_name_to_match}: {match_error}") - continue - - print(f"Successfully matched {len(matched_artists)} artists to Spotify") + "error": error + }), status_code return jsonify({ "success": True, "artist": artist_name, - "similar_artists": matched_artists, - "total_found": len(similar_artist_names), - "total_matched": len(matched_artists) + "similar_artists": result.get('similar_artists', []), + "total_found": result.get('total_found', 0), + "total_matched": result.get('total_matched', 0), + "source_priority": result.get('source_priority', []), }) - except requests.exceptions.RequestException as e: - print(f"Error fetching MusicMap: {e}") - return jsonify({ - "success": False, - "error": f"Failed to fetch from MusicMap: {str(e)}" - }), 500 - except Exception as e: - print(f"Error getting similar artists: {e}") + logger.error(f"Error getting similar artists: {e}") import traceback traceback.print_exc() return jsonify({ @@ -11431,59 +11214,20 @@ def get_similar_artists(artist_name): @app.route('/api/artist//image', methods=['GET']) def get_artist_image(artist_id): - """Get artist image URL - used for lazy loading in search results. - - For iTunes, this fetches the artist's first album artwork as a fallback. - For Spotify, returns the artist's image directly. - """ + """Get an artist image URL using source-aware metadata resolution.""" try: - # Soul IDs from Hydrabase can't be looked up on Spotify/iTunes - if artist_id.startswith('soul_'): - return jsonify({"success": True, "image_url": None}) + from core.metadata_service import get_artist_image_url as _get_artist_image_url - # Source override from multi-source search tabs - source_override = request.args.get('source', '') - - if source_override == 'itunes': - client = _get_itunes_client() - image_url = client._get_artist_image_from_albums(artist_id) - return jsonify({"success": True, "image_url": image_url}) - elif source_override == 'deezer': - client = _get_deezer_client() - image_url = client._get_artist_image_from_albums(artist_id) - return jsonify({"success": True, "image_url": image_url}) - elif source_override == 'discogs': - client = _get_discogs_client() - image_url = client._get_artist_image_from_albums(artist_id) - return jsonify({"success": True, "image_url": image_url}) - elif source_override == 'hydrabase': - # Route to the plugin that sourced the data - plugin = request.args.get('plugin', '').lower() - if plugin == 'deezer': - client = _get_deezer_client() - image_url = client._get_artist_image_from_albums(artist_id) - elif plugin == 'itunes' or artist_id.isdigit(): - client = _get_itunes_client() - image_url = client._get_artist_image_from_albums(artist_id) - else: - image_url = None - return jsonify({"success": True, "image_url": image_url}) - elif spotify_client and spotify_client.is_spotify_authenticated() and source_override != 'itunes': - # Use Spotify directly - from core.api_call_tracker import api_call_tracker - api_call_tracker.record_call('spotify', endpoint='artist') - artist_data = spotify_client.sp.artist(artist_id) - if artist_data and artist_data.get('images'): - image_url = artist_data['images'][0]['url'] if artist_data['images'] else None - return jsonify({"success": True, "image_url": image_url}) - return jsonify({"success": True, "image_url": None}) - else: - # Use fallback source - fetch album art - fallback = _get_metadata_fallback_client() - image_url = fallback._get_artist_image_from_albums(artist_id) - return jsonify({"success": True, "image_url": image_url}) + source_override = request.args.get('source', '').strip().lower() or None + plugin = request.args.get('plugin', '').strip().lower() or None + image_url = _get_artist_image_url( + artist_id, + source_override=source_override, + plugin=plugin, + ) + return jsonify({"success": True, "image_url": image_url}) except Exception as e: - print(f"Error fetching artist image: {e}") + logger.error(f"Error fetching artist image: {e}") return jsonify({"success": False, "image_url": None, "error": str(e)}) @app.route('/api/artist//discography', methods=['GET']) @@ -11804,7 +11548,7 @@ def download_discography(artist_id): total_added += added total_skipped += skipped - print(f"[Discography] {album_name}: {added} added, {skipped} skipped") + logger.warning(f"[Discography] {album_name}: {added} added, {skipped} skipped") yield json.dumps({ "album_id": album_id, "name": album_name, "status": "done", "tracks_added": added, "tracks_skipped": skipped, "tracks_total": len(tracks) @@ -11813,13 +11557,13 @@ def download_discography(artist_id): except Exception as album_err: yield json.dumps({"album_id": album_id, "status": "error", "message": str(album_err)}) + '\n' - print(f"[Discography] Complete for {artist_name}: {total_added} tracks added, {total_skipped} skipped across {len(album_ids)} albums") + logger.warning(f"[Discography] Complete for {artist_name}: {total_added} tracks added, {total_skipped} skipped across {len(album_ids)} albums") yield json.dumps({"status": "complete", "total_added": total_added, "total_skipped": total_skipped, "total_albums": len(album_ids)}) + '\n' return app.response_class(generate_ndjson(), mimetype='application/x-ndjson', headers={'X-Accel-Buffering': 'no'}) except Exception as e: - print(f"Error in download discography: {e}") + logger.error(f"Error in download discography: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/artist//completion', methods=['POST']) @@ -11840,7 +11584,7 @@ def check_artist_discography_completion(artist_id): ) return jsonify(result) except Exception as e: - print(f"Error checking discography completion: {e}") + logger.error(f"Error checking discography completion: {e}") import traceback traceback.print_exc() return jsonify({"error": str(e)}), 500 @@ -11864,7 +11608,7 @@ def check_artist_discography_completion_stream(artist_id): def generate_completion_stream(): try: - print(f"Starting streaming completion check for artist: {artist_name}") + logger.info(f"Starting streaming completion check for artist: {artist_name}") for event in iter_artist_discography_completion_events( discography, artist_name=artist_name, @@ -11875,7 +11619,7 @@ def check_artist_discography_completion_stream(artist_id): # Small delay to make the streaming effect visible time.sleep(0.1) # 100ms delay between items except Exception as e: - print(f"Error in streaming completion check: {e}") + logger.error(f"Error in streaming completion check: {e}") import traceback traceback.print_exc() yield f"data: {json.dumps({'type': 'error', 'error': str(e)})}\n\n" @@ -11915,8 +11659,35 @@ def library_completion_stream(): for item in data.get(cat, []): all_items.append((cat, item)) + # Pre-fetch the artist's library albums AND tracks ONCE so per-item + # matching runs in-memory instead of firing per-item SQL searches. + # Turns N*K queries into 2 broad fetches + N track-count lookups. + from config.settings import config_manager as _cm_cs + _active_server = _cm_cs.get_active_media_server() + candidate_albums = None + candidate_tracks = None + _t0 = time.perf_counter() + try: + candidate_albums = db.get_candidate_albums_for_artist(artist_name, server_source=_active_server) + except Exception as _cand_err: + print(f"[completion-stream] Failed to pre-fetch album candidates for '{artist_name}': {_cand_err}") + candidate_albums = None + _t1 = time.perf_counter() + print(f"[completion-stream] Pre-fetched {len(candidate_albums) if candidate_albums is not None else 0} library albums for '{artist_name}' in {(_t1 - _t0) * 1000:.0f}ms") + + if candidate_albums: + _t2 = time.perf_counter() + try: + candidate_tracks = db.get_candidate_tracks_for_albums([a.id for a in candidate_albums]) + except Exception as _tr_err: + print(f"[completion-stream] Failed to pre-fetch track candidates for '{artist_name}': {_tr_err}") + candidate_tracks = None + _t3 = time.perf_counter() + print(f"[completion-stream] Pre-fetched {len(candidate_tracks) if candidate_tracks is not None else 0} library tracks in {(_t3 - _t2) * 1000:.0f}ms") + yield f"data: {json.dumps({'type': 'start', 'total_items': len(all_items)})}\n\n" + _loop_start = time.perf_counter() for i, (category, item) in enumerate(all_items): try: # Map Library field names to helper field names @@ -11928,9 +11699,9 @@ def library_completion_stream(): } if category == 'singles': - result = check_single_completion(db, mapped, artist_name, source_override=source_override) + result = check_single_completion(db, mapped, artist_name, source_override=source_override, candidate_albums=candidate_albums, candidate_tracks=candidate_tracks) else: - result = check_album_completion(db, mapped, artist_name, source_override=source_override) + result = check_album_completion(db, mapped, artist_name, source_override=source_override, candidate_albums=candidate_albums) result['id'] = item['id'] result['category'] = category @@ -11941,10 +11712,14 @@ def library_completion_stream(): time.sleep(0.05) # 50ms between items for visible streaming + _loop_elapsed = time.perf_counter() - _loop_start + _sleep_floor = 0.05 * len(all_items) + print(f"[completion-stream] Processed {len(all_items)} items for '{artist_name}' in {_loop_elapsed * 1000:.0f}ms (sleep floor: {_sleep_floor * 1000:.0f}ms)") + yield f"data: {json.dumps({'type': 'complete', 'processed_count': len(all_items)})}\n\n" except Exception as e: - print(f"Error in library completion stream: {e}") + logger.error(f"Error in library completion stream: {e}") import traceback traceback.print_exc() yield f"data: {json.dumps({'type': 'error', 'error': str(e)})}\n\n" @@ -12075,7 +11850,7 @@ def library_check_tracks(): return jsonify({"success": True, "owned_tracks": owned_map}) except Exception as e: - print(f"Error checking track ownership: {e}") + logger.error(f"Error checking track ownership: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -12284,7 +12059,7 @@ def enhance_artist_quality(artist_id): 'external_urls': {}, } except Exception as e: - print(f"[Enhance] Spotify lookup failed for {spotify_tid}: {e}") + logger.error(f"[Enhance] Spotify lookup failed for {spotify_tid}: {e}") if not matched_track_data and spotify_client: # Fallback: Spotify search matching ā€” need full track data for wishlist @@ -12358,7 +12133,7 @@ def enhance_artist_quality(artist_id): 'external_urls': best_match.external_urls or {}, } except Exception as e: - print(f"[Enhance] Search match failed for {title}: {e}") + logger.error(f"[Enhance] Search match failed for {title}: {e}") # Fallback source when Spotify unavailable or no match found if not matched_track_data: @@ -12427,9 +12202,9 @@ def enhance_artist_quality(artist_id): 'preview_url': itunes_best.preview_url, 'external_urls': itunes_best.external_urls or {}, } - print(f"[Enhance] Fallback match for {title}: {itunes_best.artists[0]} - {itunes_best.name} (conf: {itunes_best_conf:.3f})") + logger.warning(f"[Enhance] Fallback match for {title}: {itunes_best.artists[0]} - {itunes_best.name} (conf: {itunes_best_conf:.3f})") except Exception as e: - print(f"[Enhance] Fallback source failed for {title}: {e}") + logger.error(f"[Enhance] Fallback source failed for {title}: {e}") if not matched_track_data: failed_count += 1 @@ -12456,7 +12231,7 @@ def enhance_artist_quality(artist_id): if success: enhanced_count += 1 - print(f"[Enhance] Queued for upgrade: {artist_name} - {title} ({tier_name})") + logger.info(f"[Enhance] Queued for upgrade: {artist_name} - {title} ({tier_name})") else: failed_count += 1 failed_tracks.append({'track_id': track_id, 'title': title, 'reason': 'Wishlist add failed'}) @@ -12468,7 +12243,7 @@ def enhance_artist_quality(artist_id): 'failed_tracks': failed_tracks }) except Exception as e: - print(f"[Enhance] Error: {e}") + logger.error(f"[Enhance] {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -13384,6 +13159,10 @@ def reorganize_album_preview(album_id): 'disc_number': disc_number, 'year': year_val, 'quality': quality, + 'albumtype': _get_album_type_display( + album_data.get('record_type'), + album_data.get('track_count') or len(tracks) + ), } # Build new path using the template @@ -13538,6 +13317,10 @@ def reorganize_album_files(album_id): 'disc_number': disc_number, 'year': year_val, 'quality': quality, + 'albumtype': _get_album_type_display( + album_data.get('record_type'), + album_data.get('track_count') or len(tracks) + ), } folder_path, filename = _get_file_path_from_template_raw(template, context) @@ -13667,9 +13450,9 @@ def reorganize_album_files(album_id): if not os.path.exists(sidecar_dst): try: shutil.move(sidecar_src, sidecar_dst) - print(f"[Reorganize] Moved {sidecar} to {dest_dir}") + logger.info(f"[Reorganize] Moved {sidecar} to {dest_dir}") except Exception as sc_err: - print(f"[Reorganize] Failed to move {sidecar}: {sc_err}") + logger.error(f"[Reorganize] Failed to move {sidecar}: {sc_err}") # Clean up empty directories left behind (after sidecars moved) for src_dir in moved_dirs: @@ -14182,7 +13965,7 @@ def library_play_track(): else: return jsonify({"success": False, "error": _get_file_not_found_error(file_path)}), 404 - print(f"Library play request: {os.path.basename(file_path)}") + logger.info(f"Library play request: {os.path.basename(file_path)}") # Set stream state to ready with the library file path directly with stream_lock: @@ -14202,7 +13985,7 @@ def library_play_track(): return jsonify({"success": True, "message": "Library track ready for playback"}) except Exception as e: - print(f"Error playing library track: {e}") + logger.error(f"Error playing library track: {e}") return jsonify({"success": False, "error": str(e)}), 500 _enrichment_locks = {svc: threading.Lock() for svc in ('audiodb', 'deezer', 'musicbrainz', 'spotify', 'itunes', 'lastfm', 'genius', 'tidal', 'qobuz', 'discogs')} @@ -14276,7 +14059,7 @@ def library_enrich_entity(): }) except Exception as e: - print(f"Error enriching entity: {e}") + logger.error(f"Error enriching entity: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -14433,7 +14216,7 @@ def library_search_service(): return jsonify({"success": True, "results": results}) except Exception as e: - print(f"Error searching service: {e}") + logger.error(f"Error searching service: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -14757,7 +14540,7 @@ def library_manual_match(): }) except Exception as e: - print(f"Error manual matching: {e}") + logger.error(f"Error manual matching: {e}") @app.route('/api/library/clear-match', methods=['PUT']) def library_clear_match(): @@ -14815,7 +14598,7 @@ def library_clear_match(): }) except Exception as e: - print(f"Error clearing match: {e}") + logger.error(f"Error clearing match: {e}") return jsonify({"success": False, "error": str(e)}), 500 import traceback @@ -14899,7 +14682,7 @@ def library_delete_track(track_id): result["file_error"] = file_error return jsonify(result) except Exception as e: - print(f"Error deleting track {track_id}: {e}") + logger.error(f"Error deleting track {track_id}: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -15541,24 +15324,24 @@ def sync_artist_library(artist_id): # Fetch the artist object from the server server_artist = None - print(f"[Artist Sync] Fetching artist {db_artist_id} from {server_source}...") + logger.info(f"[Artist Sync] Fetching artist {db_artist_id} from {server_source}...") if server_source == 'plex' and hasattr(media_client, 'server'): try: server_artist = media_client.server.fetchItem(int(db_artist_id)) - print(f"[Artist Sync] Plex returned: {getattr(server_artist, 'title', 'None')}") + logger.info(f"[Artist Sync] Plex returned: {getattr(server_artist, 'title', 'None')}") except Exception as e: - print(f"[Artist Sync] Plex fetchItem failed: {e}") + logger.error(f"[Artist Sync] Plex fetchItem failed: {e}") elif hasattr(media_client, 'get_artist_by_id'): try: server_artist = media_client.get_artist_by_id(str(db_artist_id)) - print(f"[Artist Sync] Server returned: {getattr(server_artist, 'title', None) or server_artist}") + logger.info(f"[Artist Sync] Server returned: {getattr(server_artist, 'title', None) or server_artist}") except Exception as e: - print(f"[Artist Sync] get_artist_by_id failed: {e}") + logger.error(f"[Artist Sync] get_artist_by_id failed: {e}") else: - print(f"[Artist Sync] No get_artist_by_id method on {type(media_client).__name__}") + logger.warning(f"[Artist Sync] No get_artist_by_id method on {type(media_client).__name__}") if not server_artist: - print(f"[Artist Sync] Could not fetch artist from server ā€” skipping pull phase") + logger.error(f"[Artist Sync] Could not fetch artist from server ā€” skipping pull phase") if server_artist: # Check for name change @@ -15568,7 +15351,7 @@ def sync_artist_library(artist_id): "UPDATE artists SET name = ?, updated_at = CURRENT_TIMESTAMP WHERE id = ?", (new_name, db_artist_id) ) - print(f"[Artist Sync] Name updated: '{artist_name}' ā†’ '{new_name}'") + logger.info(f"[Artist Sync] Name updated: '{artist_name}' ā†’ '{new_name}'") artist_name = new_name name_updated = True @@ -15576,10 +15359,10 @@ def sync_artist_library(artist_id): success, details, new_albums, new_tracks = worker._process_artist_with_content( server_artist, skip_existing_tracks=True ) - print(f"[Artist Sync] Server pull for {artist_name}: {details}") + logger.info(f"[Artist Sync] Server pull for {artist_name}: {details}") except Exception as e: - print(f"[Artist Sync] Server pull failed for {artist_name}: {e}") + logger.error(f"[Artist Sync] Server pull failed for {artist_name}: {e}") # ā”€ā”€ Phase 2: Remove stale entries (files no longer on disk) ā”€ā”€ stale_removed = 0 @@ -15619,7 +15402,7 @@ def sync_artist_library(artist_id): conn.commit() - print(f"[Artist Sync] {artist_name}: +{new_albums} albums, +{new_tracks} tracks, " + logger.warning(f"[Artist Sync] {artist_name}: +{new_albums} albums, +{new_tracks} tracks, " f"-{stale_removed} stale, -{empty_albums_removed} empty albums") return jsonify({ @@ -15633,7 +15416,7 @@ def sync_artist_library(artist_id): }) except Exception as e: - print(f"Error syncing artist {artist_id}: {e}") + logger.error(f"Error syncing artist {artist_id}: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -15709,7 +15492,7 @@ def library_delete_album(album_id): "files_failed": files_failed }) except Exception as e: - print(f"Error deleting album {album_id}: {e}") + logger.error(f"Error deleting album {album_id}: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -15734,7 +15517,7 @@ def library_delete_tracks_batch(): conn.commit() return jsonify({"success": True, "deleted_count": cursor.rowcount}) except Exception as e: - print(f"Error batch deleting tracks: {e}") + logger.error(f"Error batch deleting tracks: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -15765,7 +15548,7 @@ def library_radio(): return jsonify(result) except Exception as e: - print(f"Error getting radio tracks: {e}") + logger.error(f"Error getting radio tracks: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -15782,7 +15565,7 @@ def stream_start(): if not data: return jsonify({"success": False, "error": "No track data provided"}), 400 - print(f"Web UI Stream request for: {data.get('filename')}") + logger.info(f"Web UI Stream request for: {data.get('filename')}") try: # Stop any existing streaming task @@ -15806,7 +15589,7 @@ def stream_start(): return jsonify({"success": True, "message": "Streaming started"}) except Exception as e: - print(f"Error starting stream: {e}") + logger.error(f"Error starting stream: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/stream/status') @@ -15822,7 +15605,7 @@ def stream_status(): "error_message": stream_state["error_message"] }) except Exception as e: - print(f"Error getting stream status: {e}") + logger.error(f"Error getting stream status: {e}") return jsonify({ "status": "error", "progress": 0, @@ -15843,7 +15626,7 @@ def stream_audio(): if not os.path.exists(file_path): return jsonify({"error": "Audio file not found"}), 404 - print(f"Serving audio file: {os.path.basename(file_path)}") + logger.info(f"Serving audio file: {os.path.basename(file_path)}") # Determine MIME type based on file extension file_ext = os.path.splitext(file_path)[1].lower() @@ -15925,7 +15708,7 @@ def stream_audio(): return response except Exception as e: - print(f"Error serving audio file: {e}") + logger.error(f"Error serving audio file: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/stream/stop', methods=['POST']) @@ -15951,9 +15734,9 @@ def stream_stop(): file_path = os.path.join(stream_folder, filename) if os.path.isfile(file_path): os.remove(file_path) - print(f"Removed stream file: {filename}") + logger.info(f"Removed stream file: {filename}") else: - print(f"Library playback stopped - skipping file deletion") + logger.info(f"Library playback stopped - skipping file deletion") # Reset stream state with stream_lock: @@ -15969,7 +15752,7 @@ def stream_stop(): return jsonify({"success": True, "message": "Stream stopped"}) except Exception as e: - print(f"Error stopping stream: {e}") + logger.error(f"Error stopping stream: {e}") return jsonify({"success": False, "error": str(e)}), 500 # --- Matched Downloads API Endpoints --- @@ -15983,22 +15766,22 @@ def _generate_artist_suggestions(search_result, is_album=False, album_result=Non return [] try: - print(f"Generating artist suggestions for: {search_result.get('artist', '')} - {search_result.get('title', '')}") + logger.info(f"Generating artist suggestions for: {search_result.get('artist', '')} - {search_result.get('title', '')}") suggestions = [] # Special handling for albums - use album title to find artist if is_album and album_result and album_result.get('album_title'): - print(f"Album mode detected - using album title for artist search") + logger.info(f"Album mode detected - using album title for artist search") album_title = album_result.get('album_title', '') # Clean album title (remove year prefixes like "(2005)") import re clean_album_title = re.sub(r'^\(\d{4}\)\s*', '', album_title).strip() - print(f" clean_album_title: '{clean_album_title}'") + logger.info(f" clean_album_title: '{clean_album_title}'") # Search tracks using album title to find the artist tracks = spotify_client.search_tracks(clean_album_title, limit=10) - print(f"Found {len(tracks)} tracks from album search") + logger.info(f"Found {len(tracks)} tracks from album search") # Collect unique artists and their associated tracks/albums unique_artists = {} # artist_name -> list of (track, album) tuples @@ -16018,7 +15801,7 @@ def _generate_artist_suggestions(search_result, is_album=False, album_result=Non if matches: return artist_name, matches[0] except Exception as e: - print(f"Error fetching artist '{artist_name}': {e}") + logger.error(f"Error fetching artist '{artist_name}': {e}") return artist_name, None # Use limited concurrency to respect rate limits @@ -16069,7 +15852,7 @@ def _generate_artist_suggestions(search_result, is_album=False, album_result=Non if not search_artist: return [] - print(f"Single track mode - searching for artist: '{search_artist}'") + logger.info(f"Single track mode - searching for artist: '{search_artist}'") # Search for artists directly artist_matches = spotify_client.search_artists(search_artist, limit=10) @@ -16097,7 +15880,7 @@ def _generate_artist_suggestions(search_result, is_album=False, album_result=Non return suggestions[:4] except Exception as e: - print(f"Error generating artist suggestions: {e}") + logger.error(f"Error generating artist suggestions: {e}") return [] def _generate_album_suggestions(selected_artist, search_result): @@ -16109,22 +15892,22 @@ def _generate_album_suggestions(selected_artist, search_result): return [] try: - print(f"Generating album suggestions for artist: {selected_artist['name']}") + logger.info(f"Generating album suggestions for artist: {selected_artist['name']}") # Determine target album name from search result target_album_name = search_result.get('album', '') or search_result.get('album_title', '') if not target_album_name: - print("No album name found in search result") + logger.warning("No album name found in search result") return [] # Clean target album name import re clean_target = re.sub(r'^\(\d{4}\)\s*', '', target_album_name).strip() - print(f" target_album: '{clean_target}'") + logger.info(f" target_album: '{clean_target}'") # Get artist's albums from Spotify artist_albums = spotify_client.get_artist_albums(selected_artist['id']) - print(f"Found {len(artist_albums)} albums for artist") + logger.info(f"Found {len(artist_albums)} albums for artist") album_matches = [] for album in artist_albums: @@ -16151,7 +15934,7 @@ def _generate_album_suggestions(selected_artist, search_result): return album_matches[:4] except Exception as e: - print(f"Error generating album suggestions: {e}") + logger.error(f"Error generating album suggestions: {e}") return [] @app.route('/api/match/suggestions', methods=['POST']) @@ -16175,7 +15958,7 @@ def get_match_suggestions(): return jsonify({"suggestions": suggestions}) except Exception as e: - print(f"Error in match suggestions: {e}") + logger.error(f"Error in match suggestions: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/match/search', methods=['POST']) @@ -16273,7 +16056,7 @@ def search_match(): return jsonify({"error": "Invalid context. Must be 'artist' or 'album'"}), 400 except Exception as e: - print(f"Error in match search: {e}") + logger.error(f"Error in match search: {e}") return jsonify({"error": str(e)}), 500 @@ -16323,10 +16106,10 @@ def _start_enhanced_album_download(enhanced_tracks, unmatched_tracks, spotify_ar _mb_release_cache[(spotify_album['name'].lower().strip(), _pf_artist_key)] = _pf_mbid with _mb_release_detail_cache_lock: _mb_release_detail_cache[_pf_mbid] = _pf_release - print(f"[Preflight] Pre-cached MB release for '{spotify_album['name']}': " + logger.info(f"[Preflight] Pre-cached MB release for '{spotify_album['name']}': " f"'{_pf_release.get('title', '')}' ({_pf_mbid[:8]}...)") except Exception as pf_err: - print(f"[Preflight] MB release preflight failed: {pf_err}") + logger.error(f"[Preflight] MB release preflight failed: {pf_err}") # Process matched tracks with full Spotify metadata for matched_item in enhanced_tracks: @@ -16372,10 +16155,14 @@ def _start_enhanced_album_download(enhanced_tracks, unmatched_tracks, spotify_ar "has_full_spotify_metadata": True # Flag for robust processing } - logger.info(f"Queued matched track: '{spotify_track['name']}' (track #{spotify_track['track_number']})") + logger.info( + "Queued matched track: title=%r track_number=%s", + spotify_track['name'], + spotify_track['track_number'], + ) started_count += 1 else: - logger.error(f"Failed to queue track: {filename}") + logger.error("Failed to queue track: filename=%s", filename) except Exception as e: logger.error(f"Error processing matched track: {e}") @@ -16425,18 +16212,18 @@ def _start_album_download_tasks(album_result, spotify_artist, spotify_album): match and correct the metadata for each individual track before downloading, ensuring perfect tagging and naming. """ - print(f"Processing matched album download for '{spotify_album['name']}' with {len(album_result.get('tracks', []))} tracks.") + logger.info(f"Processing matched album download for '{spotify_album['name']}' with {len(album_result.get('tracks', []))} tracks.") tracks_to_download = album_result.get('tracks', []) if not tracks_to_download: - print("Album result contained no tracks. Aborting.") + logger.warning("Album result contained no tracks. Aborting.") return 0 # --- THIS IS THE NEW LOGIC --- # Fetch the official tracklist from Spotify ONCE for the entire album. official_spotify_tracks = _get_spotify_album_tracks(spotify_album) if not official_spotify_tracks: - print("Could not fetch official tracklist from Spotify. Metadata may be inaccurate.") + logger.error("Could not fetch official tracklist from Spotify. Metadata may be inaccurate.") # --- END OF NEW LOGIC --- # Compute total_discs for multi-disc album subfolder support @@ -16460,10 +16247,10 @@ def _start_album_download_tasks(album_result, spotify_artist, spotify_album): _mb_release_cache[(spotify_album['name'].lower().strip(), _pf_artist_key)] = _pf_mbid with _mb_release_detail_cache_lock: _mb_release_detail_cache[_pf_mbid] = _pf_release - print(f"[Preflight] Pre-cached MB release for '{spotify_album['name']}': " + logger.info(f"[Preflight] Pre-cached MB release for '{spotify_album['name']}': " f"'{_pf_release.get('title', '')}' ({_pf_mbid[:8]}...)") except Exception as pf_err: - print(f"[Preflight] MB release preflight failed: {pf_err}") + logger.error(f"[Preflight] MB release preflight failed: {pf_err}") started_count = 0 for track_data in tracks_to_download: @@ -16484,7 +16271,7 @@ def _start_album_download_tasks(album_result, spotify_artist, spotify_album): # --- END OF CRITICAL STEP --- if _is_explicit_blocked(corrected_meta): - print(f"[Content Filter] Skipping explicit track: '{corrected_meta.get('title')}'") + logger.info(f"[Content Filter] Skipping explicit track: '{corrected_meta.get('title')}'") continue # Create a clean context object using the CORRECTED metadata @@ -16514,13 +16301,17 @@ def _start_album_download_tasks(album_result, spotify_artist, spotify_album): "original_search_result": enhanced_context, # Contains corrected data + clean title "is_album_download": True } - print(f" + Queued track: {filename} (Matched to: '{corrected_meta.get('title')}')") + logger.info( + "Queued track: filename=%s matched_title=%r", + filename, + corrected_meta.get('title'), + ) started_count += 1 else: - print(f" - Failed to queue track: {filename}") + logger.error("Failed to queue track: filename=%s", filename) except Exception as e: - print(f"Error processing track in album batch: {track_data.get('filename')}. Error: {e}") + logger.error(f"Error processing track in album batch: {track_data.get('filename')}: {e}") continue return started_count @@ -16725,7 +16516,7 @@ def _parse_filename_metadata(filename: str) -> dict: cleaned_album = re.sub(r'^\d{4}\s*-\s*', '', potential_album).strip() metadata['album'] = cleaned_album - print(f"Parsed Filename '{base_name}': Artist='{metadata['artist']}', Title='{metadata['title']}', Album='{metadata['album']}', Track#='{metadata['track_number']}'") + logger.info(f"Parsed Filename '{base_name}': Artist='{metadata['artist']}', Title='{metadata['title']}', Album='{metadata['album']}', Track#='{metadata['track_number']}'") return metadata @@ -16895,7 +16686,7 @@ def _search_track_in_album_context(original_search: dict, artist: dict) -> dict: matching_engine.normalize_string(track_data['name']) ) if similarity > 0.7: - print(f"Found track in album context: '{track_data['name']}'") + logger.info(f"Found track in album context: '{track_data['name']}'") return { 'is_album': True, 'album_name': spotify_album.name, @@ -16905,7 +16696,7 @@ def _search_track_in_album_context(original_search: dict, artist: dict) -> dict: } return None except Exception as e: - print(f"Error in _search_track_in_album_context: {e}") + logger.error(f"Error in _search_track_in_album_context: {e}") return None @@ -16919,35 +16710,44 @@ def _detect_album_info_web(context: dict, artist: dict) -> dict: try: # Log available data for debugging (GUI PARITY) original_search = context.get("original_search_result", {}) - print(f"\n[Album Detection] Starting for track: '{original_search.get('title', 'Unknown')}'") - print(f"[Data Available]:") - print(f" - Clean Spotify title: '{original_search.get('spotify_clean_title', 'None')}'") - print(f" - Clean Spotify album: '{original_search.get('spotify_clean_album', 'None')}'") - print(f" - Filename album: '{original_search.get('album', 'None')}'") - print(f" - Artist: '{artist.get('name', 'Unknown')}'") - print(f" - Context has clean data: {context.get('has_clean_spotify_data', False)}") - print(f" - Is album download: {context.get('is_album_download', False)}") + logger.info( + "[Album Detection] start: track=%r clean_spotify_title=%r clean_spotify_album=%r " + "filename_album=%r artist=%r clean_data=%s album_download=%s", + original_search.get('title', 'Unknown'), + original_search.get('spotify_clean_title', 'None'), + original_search.get('spotify_clean_album', 'None'), + original_search.get('album', 'None'), + artist.get('name', 'Unknown'), + context.get('has_clean_spotify_data', False), + context.get('is_album_download', False), + ) spotify_album_context = context.get("spotify_album") is_album_download = context.get("is_album_download", False) artist_name = artist['name'] - print(f"Album detection for '{original_search.get('title', 'Unknown')}' by '{artist_name}':") - print(f" Has album attr: {bool(original_search.get('album'))}") - if original_search.get('album'): - print(f" Album value: '{original_search.get('album')}'") + logger.info( + "[Album Detection] track=%r artist=%r has_album_attr=%s album=%r", + original_search.get('title', 'Unknown'), + artist_name, + bool(original_search.get('album')), + original_search.get('album'), + ) # --- THIS IS THE CRITICAL FIX --- # If this is part of a matched album download, we TRUST the context data completely. # This is the exact logic from downloads.py. if is_album_download and spotify_album_context: - print("Matched Album context found. Prioritizing pre-matched Spotify data.") - # We exclusively use the track number and title that were matched # *before* the download started. We do not try to re-parse the filename. track_number = original_search.get('track_number', 1) clean_track_name = original_search.get('title', 'Unknown Track') - print(f" -> Using pre-matched Track #{track_number} and Title '{clean_track_name}'") + logger.info( + "[Album Detection] using matched context: track_number=%s title=%r album=%r", + track_number, + clean_track_name, + spotify_album_context['name'], + ) return { 'is_album': True, @@ -16974,7 +16774,7 @@ def _detect_album_info_web(context: dict, artist: dict) -> dict: if album_name_to_use: track_title = original_search.get('spotify_clean_title') or original_search.get('title', 'Unknown') - print(f"ALBUM-AWARE SEARCH ({album_source}): Looking for '{track_title}' in album '{album_name_to_use}'") + logger.info(f"ALBUM-AWARE SEARCH ({album_source}): Looking for '{track_title}' in album '{album_name_to_use}'") # Temporarily set the album for the search original_album = original_search.get('album') @@ -16983,10 +16783,10 @@ def _detect_album_info_web(context: dict, artist: dict) -> dict: try: album_result = _search_track_in_album_context_web(context, artist) if album_result: - print(f"PRIORITY 1 SUCCESS: Found track using {album_source} album name - FORCING album classification") + logger.info(f"PRIORITY 1 SUCCESS: Found track using {album_source} album name - FORCING album classification") return album_result else: - print(f"PRIORITY 1 FAILED: Track not found using {album_source} album name") + logger.error(f"PRIORITY 1 FAILED: Track not found using {album_source} album name") finally: # Restore original album value if original_album is not None: @@ -16995,13 +16795,13 @@ def _detect_album_info_web(context: dict, artist: dict) -> dict: original_search.pop('album', None) # PRIORITY 2: Fallback to individual track search for clean metadata - print(f"Searching Spotify for individual track info (PRIORITY 2)...") + logger.info(f"Searching Spotify for individual track info (PRIORITY 2)...") # Clean the track title before searching - remove artist prefix # Prioritize clean Spotify title over filename-parsed title track_title_to_use = original_search.get('spotify_clean_title') or original_search.get('title', '') clean_title = _clean_track_title_web(track_title_to_use, artist_name) - print(f"Cleaned title: '{track_title_to_use}' -> '{clean_title}'") + logger.info(f"Cleaned title: '{track_title_to_use}' -> '{clean_title}'") # Search for the track by artist and cleaned title query = f"artist:{artist_name} track:{clean_title}" @@ -17040,25 +16840,25 @@ def _detect_album_info_web(context: dict, artist: dict) -> dict: # If we found a good Spotify match, use it for clean metadata if best_match and best_confidence > 0.75: - print(f"Found matching Spotify track: '{best_match.name}' - Album: '{best_match.album}' (confidence: {best_confidence:.2f})") + logger.info(f"Found matching Spotify track: '{best_match.name}' - Album: '{best_match.album}' (confidence: {best_confidence:.2f})") # Get detailed track information using Spotify's track API detailed_track = None if hasattr(best_match, 'id') and best_match.id: - print(f"Getting detailed track info from Spotify API for track ID: {best_match.id}") + logger.info(f"Getting detailed track info from Spotify API for track ID: {best_match.id}") detailed_track = spotify_client.get_track_details(best_match.id) # Use detailed track data if available if detailed_track: - print(f"Got detailed track data from Spotify API") + logger.info(f"Got detailed track data from Spotify API") album_name = _clean_album_title_web(detailed_track['album']['name'], artist_name) clean_track_name = detailed_track['name'] # Use Spotify's clean track name album_type = detailed_track['album'].get('album_type', 'album') total_tracks = detailed_track['album'].get('total_tracks', 1) spotify_track_number = detailed_track.get('track_number', 1) - print(f"Spotify album info: '{album_name}' (type: {album_type}, total_tracks: {total_tracks}, track#: {spotify_track_number})") - print(f"Clean track name from Spotify: '{clean_track_name}'") + logger.info(f"Spotify album info: '{album_name}' (type: {album_type}, total_tracks: {total_tracks}, track#: {spotify_track_number})") + logger.info(f"Clean track name from Spotify: '{clean_track_name}'") # Enhanced album detection using detailed API data (GUI PARITY) is_album = ( @@ -17076,7 +16876,7 @@ def _detect_album_info_web(context: dict, artist: dict) -> dict: if detailed_track['album'].get('images'): album_image_url = detailed_track['album']['images'][0].get('url') - print(f"Album classification: {is_album} (type={album_type}, tracks={total_tracks})") + logger.info(f"Album classification: {is_album} (type={album_type}, tracks={total_tracks})") return { 'is_album': is_album, @@ -17089,7 +16889,7 @@ def _detect_album_info_web(context: dict, artist: dict) -> dict: } # Fallback: Use original data with basic cleaning - print("No good Spotify match found, using original data") + logger.warning("No good Spotify match found, using original data") fallback_title = _clean_track_title_web(original_search.get('title', 'Unknown Track'), artist_name) # Preserve track_number from context if available (playlist sync tracks have it) @@ -17107,7 +16907,7 @@ def _detect_album_info_web(context: dict, artist: dict) -> dict: } except Exception as e: - print(f"Error in _detect_album_info_web: {e}") + logger.error(f"Error in _detect_album_info_web: {e}") clean_title = _clean_track_title_web(context.get("original_search_result", {}).get('title', 'Unknown'), artist.get('name', '')) _err_tn = (context.get("original_search_result", {}).get('track_number') or context.get('track_info', {}).get('track_number') @@ -17125,13 +16925,13 @@ def _cleanup_empty_directories(download_path, moved_file_path): while current_dir != download_path and current_dir.startswith(download_path): is_empty = not any(not f.startswith('.') for f in os.listdir(current_dir)) if is_empty: - print(f"Removing empty directory: {current_dir}") + logger.warning(f"Removing empty directory: {current_dir}") os.rmdir(current_dir) current_dir = os.path.dirname(current_dir) else: break except Exception as e: - print(f"Warning: An error occurred during directory cleanup: {e}") + logger.error(f"An error occurred during directory cleanup: {e}") def _sweep_empty_download_directories(): @@ -17173,10 +16973,10 @@ def _sweep_empty_download_directories(): pass # Directory not actually empty or locked ā€” skip silently if removed > 0: - print(f"[Folder Cleanup] Removed {removed} empty director{'y' if removed == 1 else 'ies'} from downloads folder") + logger.warning(f"[Folder Cleanup] Removed {removed} empty director{'y' if removed == 1 else 'ies'} from downloads folder") return removed except Exception as e: - print(f"[Folder Cleanup] Error sweeping empty directories: {e}") + logger.error(f"[Folder Cleanup] Error sweeping empty directories: {e}") return 0 @@ -17236,7 +17036,7 @@ def _detect_deluxe_edition(album_name: str) -> bool: for indicator in deluxe_indicators: if indicator in album_lower: - print(f"Detected deluxe edition: '{album_name}' contains '{indicator}'") + logger.info(f"Detected deluxe edition: '{album_name}' contains '{indicator}'") return True return False @@ -17259,7 +17059,7 @@ def _normalize_base_album_name(base_album: str, artist_name: str) -> str: # Check for exact matches in our corrections for variant, correction in known_corrections.items(): if normalized_lower == variant.lower(): - print(f"Album correction applied: '{base_album}' -> '{correction}'") + logger.info(f"Album correction applied: '{base_album}' -> '{correction}'") return correction # Handle punctuation variations @@ -17270,7 +17070,7 @@ def _normalize_base_album_name(base_album: str, artist_name: str) -> str: normalized = re.sub(r'\s+', ' ', normalized) # Clean multiple spaces normalized = normalized.strip() - print(f"Album variant normalization: '{base_album}' -> '{normalized}'") + logger.info(f"Album variant normalization: '{base_album}' -> '{normalized}'") return normalized def _resolve_album_group(spotify_artist: dict, album_info: dict, original_album: str = None) -> str: @@ -17303,10 +17103,10 @@ def _resolve_album_group(spotify_artist: dict, album_info: dict, original_album: # Check if we already have a cached result for this album if album_key in album_name_cache: cached_name = album_name_cache[album_key] - print(f"Using cached album name for '{album_key}': '{cached_name}'") + logger.info(f"Using cached album name for '{album_key}': '{cached_name}'") return cached_name - print(f"Album grouping - Key: '{album_key}', Detected: '{detected_album}'") + logger.info(f"Album grouping - Key: '{album_key}', Detected: '{detected_album}'") # Check if this track indicates a deluxe edition is_deluxe_track = False @@ -17320,7 +17120,7 @@ def _resolve_album_group(spotify_artist: dict, album_info: dict, original_album: # SMART ALGORITHM: Upgrade to deluxe if this track is deluxe if is_deluxe_track and current_edition == "standard": - print(f"UPGRADE: Album '{base_album}' upgraded from standard to deluxe!") + logger.info(f"UPGRADE: Album '{base_album}' upgraded from standard to deluxe!") album_editions[album_key] = "deluxe" current_edition = "deluxe" @@ -17335,12 +17135,12 @@ def _resolve_album_group(spotify_artist: dict, album_info: dict, original_album: album_name_cache[album_key] = final_album_name album_artists[album_key] = artist_name - print(f"Album resolution: '{detected_album}' -> '{final_album_name}' (edition: {current_edition})") + logger.info(f"Album resolution: '{detected_album}' -> '{final_album_name}' (edition: {current_edition})") return final_album_name except Exception as e: - print(f"Error resolving album group: {e}") + logger.error(f"Error resolving album group: {e}") return album_info.get('album_name', 'Unknown Album') def _clean_album_title_web(album_title: str, artist_name: str) -> str: @@ -17350,7 +17150,7 @@ def _clean_album_title_web(album_title: str, artist_name: str) -> str: # Start with the original title original = album_title.strip() cleaned = original - print(f"Album Title Cleaning: '{original}' (artist: '{artist_name}')") + logger.info(f"Album Title Cleaning: '{original}' (artist: '{artist_name}')") # Remove "Album - " prefix cleaned = re.sub(r'^Album\s*-\s*', '', cleaned, flags=re.IGNORECASE) @@ -17389,7 +17189,7 @@ def _clean_album_title_web(album_title: str, artist_name: str) -> str: # Remove leading/trailing punctuation cleaned = re.sub(r'^[-\s]+|[-\s]+$', '', cleaned) - print(f"Album Title Result: '{original}' -> '{cleaned}'") + logger.info(f"Album Title Result: '{original}' -> '{cleaned}'") return cleaned if cleaned else original def _search_track_in_album_context_web(context: dict, spotify_artist: dict) -> dict: @@ -17408,10 +17208,10 @@ def _search_track_in_album_context_web(context: dict, spotify_artist: dict) -> d artist_name = spotify_artist["name"] if not album_name or not track_title: - print(f"Album-aware search failed: Missing album ({album_name}) or track ({track_title})") + logger.error(f"Album-aware search failed: Missing album ({album_name}) or track ({track_title})") return None - print(f"Album-aware search: '{track_title}' in album '{album_name}' by '{artist_name}'") + logger.info(f"Album-aware search: '{track_title}' in album '{album_name}' by '{artist_name}'") # Clean the album name for better search results clean_album = _clean_album_title_web(album_name, artist_name) @@ -17419,21 +17219,21 @@ def _search_track_in_album_context_web(context: dict, spotify_artist: dict) -> d # Search for the specific album first album_query = f"album:{clean_album} artist:{artist_name}" - print(f"Searching albums: {album_query}") + logger.info(f"Searching albums: {album_query}") albums = spotify_client.search_albums(album_query, limit=5) if not albums: - print(f"No albums found for query: {album_query}") + logger.warning(f"No albums found for query: {album_query}") return None # Check each album to see if our track is in it for album in albums: - print(f"Checking album: '{album.name}' ({album.total_tracks} tracks)") + logger.info(f"Checking album: '{album.name}' ({album.total_tracks} tracks)") # Get tracks from this album album_tracks_data = spotify_client.get_album_tracks(album.id) if not album_tracks_data or 'items' not in album_tracks_data: - print(f"Could not get tracks for album: {album.name}") + logger.error(f"Could not get tracks for album: {album.name}") continue # Check if our track is in this album @@ -17452,7 +17252,7 @@ def _search_track_in_album_context_web(context: dict, spotify_artist: dict) -> d threshold = 0.9 if is_remix else 0.65 # Lower threshold to favor album matches over singles if similarity > threshold: - print(f"FOUND: '{track_name}' (track #{track_number}) matches '{clean_track}' (similarity: {similarity:.2f})") + logger.info(f"FOUND: '{track_name}' (track #{track_number}) matches '{clean_track}' (similarity: {similarity:.2f})") # Classify as album vs single using same logic as _detect_album_info_web ctx_album_type = getattr(album, 'album_type', 'album') or 'album' @@ -17463,7 +17263,7 @@ def _search_track_in_album_context_web(context: dict, spotify_artist: dict) -> d matching_engine.normalize_string(album.name) != matching_engine.normalize_string(clean_track) and matching_engine.normalize_string(album.name) != matching_engine.normalize_string(artist_name) ) - print(f"Album context classification: is_album={ctx_is_album} (type={ctx_album_type}, tracks={ctx_total_tracks})") + logger.info(f"Album context classification: is_album={ctx_is_album} (type={ctx_album_type}, tracks={ctx_total_tracks})") return { 'is_album': ctx_is_album, @@ -17475,13 +17275,13 @@ def _search_track_in_album_context_web(context: dict, spotify_artist: dict) -> d 'source': 'album_context_search' } - print(f"Track '{clean_track}' not found in album '{album.name}'") + logger.warning(f"Track '{clean_track}' not found in album '{album.name}'") - print(f"Track '{clean_track}' not found in any matching albums") + logger.warning(f"Track '{clean_track}' not found in any matching albums") return None except Exception as e: - print(f"Error in album-aware search: {e}") + logger.error(f"Error in album-aware search: {e}") return None def _clean_track_title_web(track_title: str, artist_name: str) -> str: @@ -17491,7 +17291,7 @@ def _clean_track_title_web(track_title: str, artist_name: str) -> str: # Start with the original title original = track_title.strip() cleaned = original - print(f"Track Title Cleaning: '{original}' (artist: '{artist_name}')") + logger.info(f"Track Title Cleaning: '{original}' (artist: '{artist_name}')") # Remove artist name prefix if it appears at the beginning # This handles cases like "Kendrick Lamar - HUMBLE." @@ -17520,7 +17320,7 @@ def _clean_track_title_web(track_title: str, artist_name: str) -> str: # Remove leading/trailing punctuation cleaned = re.sub(r'^[-\s]+|[-\s]+$', '', cleaned) - print(f"Track Title Result: '{original}' -> '{cleaned}'") + logger.info(f"Track Title Result: '{original}' -> '{cleaned}'") return cleaned if cleaned else original @@ -17556,7 +17356,7 @@ def clean_youtube_track_title(title, artist_name=None): cleaned_title = re.sub(artist_pattern, '', title, flags=re.IGNORECASE).strip() if cleaned_title != title: - print(f"Removed artist from start: '{title}' -> '{cleaned_title}' (artist: '{artist_name}')") + logger.info(f"Removed artist from start: '{title}' -> '{cleaned_title}' (artist: '{artist_name}')") title = cleaned_title artist_removed = True else: @@ -17566,7 +17366,7 @@ def clean_youtube_track_title(title, artist_name=None): cleaned_title = re.sub(artist_end_pattern, '', title, flags=re.IGNORECASE).strip() if cleaned_title != title: - print(f"Removed artist from end: '{title}' -> '{cleaned_title}' (artist: '{artist_name}')") + logger.info(f"Removed artist from end: '{title}' -> '{cleaned_title}' (artist: '{artist_name}')") title = cleaned_title artist_removed = True @@ -17628,7 +17428,7 @@ def clean_youtube_track_title(title, artist_name=None): title = re.sub(rf'\b{re.escape(artist_name)}\s*[-ā€“ā€”:]\s*', '', title, flags=re.IGNORECASE) title = re.sub(rf'^{re.escape(artist_name)}\s*[-ā€“ā€”:]\s*', '', title, flags=re.IGNORECASE) else: - print(f"Skipping artist removal - collaboration detected: '{title}'") + logger.info(f"Skipping artist removal - collaboration detected: '{title}'") # Remove "prod. Producer" patterns title = re.sub(r'\s+prod\.?\s+\S+', '', title, flags=re.IGNORECASE) @@ -17656,7 +17456,7 @@ def clean_youtube_track_title(title, artist_name=None): title = original_title if title != original_title: - print(f"YouTube title cleaned: '{original_title}' ā†’ '{title}'") + logger.info(f"YouTube title cleaned: '{original_title}' ā†’ '{title}'") return title @@ -17721,7 +17521,7 @@ def clean_youtube_artist(artist_string): artist_string = original_artist if artist_string != original_artist: - print(f"YouTube artist cleaned: '{original_artist}' ā†’ '{artist_string}'") + logger.info(f"YouTube artist cleaned: '{original_artist}' ā†’ '{artist_string}'") return artist_string @@ -17748,14 +17548,14 @@ def parse_youtube_playlist(url): playlist_info = ydl.extract_info(url, download=False) if not playlist_info: - print("Could not extract playlist information") + logger.error("Could not extract playlist information") return None playlist_name = playlist_info.get('title', 'Unknown Playlist') playlist_id = playlist_info.get('id', 'unknown_id') entries = list(playlist_info.get('entries', []) or []) - print(f"Found YouTube playlist: '{playlist_name}' with {len(entries)} entries") + logger.info(f"Found YouTube playlist: '{playlist_name}' with {len(entries)} entries") for entry in entries: if not entry: @@ -17795,11 +17595,11 @@ def parse_youtube_playlist(url): 'image_url': playlist_info.get('thumbnail', '') or '', } - print(f"Successfully parsed YouTube playlist: {len(tracks)} tracks extracted") + logger.info(f"Successfully parsed YouTube playlist: {len(tracks)} tracks extracted") return playlist_data except Exception as e: - print(f"Error parsing YouTube playlist: {e}") + logger.error(f"Error parsing YouTube playlist: {e}") return None @@ -17879,7 +17679,7 @@ def _build_final_path_for_track(context, spotify_artist, album_info, file_ext): original_stem = os.path.splitext(os.path.basename(original_path))[0] final_path = os.path.join(original_dir, original_stem + file_ext) os.makedirs(original_dir, exist_ok=True) - print(f"[Enhance] Using original file location: {final_path}") + logger.info(f"[Enhance] Using original file location: {final_path}") return final_path, True # Extract year and album_type from spotify_album for template use (safe for all modes) @@ -18051,9 +17851,9 @@ def _build_final_path_for_track(context, spotify_artist, album_info, file_ext): total_discs = max((t.get('disc_number', 1) for t in _atd['items']), default=1) if total_discs > 1: spotify_album['total_discs'] = total_discs - print(f"[Multi-Disc] Resolved {total_discs} discs for single-track download of '{spotify_album.get('name')}'") + logger.info(f"[Multi-Disc] Resolved {total_discs} discs for single-track download of '{spotify_album.get('name')}'") except Exception as _disc_err: - print(f"[Multi-Disc] Could not resolve total_discs: {_disc_err}") + logger.warning(f"[Multi-Disc] Could not resolve total_discs: {_disc_err}") # Check if user controls disc structure via $disc in their template album_template = config_manager.get('file_organization.templates.album_path', '') @@ -18278,13 +18078,13 @@ def _downsample_hires_flac(final_path, context): original_bits = audio.info.bits_per_sample original_rate = audio.info.sample_rate except Exception as e: - print(f"[Downsample] Could not read FLAC info: {e}") + logger.error(f"[Downsample] Could not read FLAC info: {e}") return None if original_bits <= 16 and original_rate <= 44100: return None # Already CD quality or below - print(f"[Downsample] Converting {original_bits}-bit/{original_rate}Hz ā†’ 16-bit/44100Hz: {os.path.basename(final_path)}") + logger.info(f"[Downsample] Converting {original_bits}-bit/{original_rate}Hz ā†’ 16-bit/44100Hz: {os.path.basename(final_path)}") ffmpeg_bin = shutil.which('ffmpeg') if not ffmpeg_bin: @@ -18292,7 +18092,7 @@ def _downsample_hires_flac(final_path, context): if os.path.isfile(local): ffmpeg_bin = local else: - print("[Downsample] ffmpeg not found ā€” skipping hi-res conversion") + logger.warning("[Downsample] ffmpeg not found ā€” skipping hi-res conversion") return None temp_path = final_path + '.tmp.flac' @@ -18307,27 +18107,27 @@ def _downsample_hires_flac(final_path, context): ], capture_output=True, text=True, timeout=300) if result.returncode != 0: - print(f"[Downsample] ffmpeg failed: {result.stderr[:200]}") + logger.error(f"[Downsample] ffmpeg failed: {result.stderr[:200]}") if os.path.exists(temp_path): os.remove(temp_path) return None # Verify the output is a valid 16-bit FLAC if not os.path.isfile(temp_path) or os.path.getsize(temp_path) == 0: - print(f"[Downsample] Output file missing or empty") + logger.warning(f"[Downsample] Output file missing or empty") if os.path.exists(temp_path): os.remove(temp_path) return None verify_audio = FLAC(temp_path) if verify_audio.info.bits_per_sample != 16: - print(f"[Downsample] Output not 16-bit ({verify_audio.info.bits_per_sample}-bit), aborting") + logger.info(f"[Downsample] Output not 16-bit ({verify_audio.info.bits_per_sample}-bit), aborting") os.remove(temp_path) return None # Atomic swap ā€” replace original with downsampled version os.replace(temp_path, final_path) - print(f"[Downsample] Converted to 16-bit/44.1kHz: {os.path.basename(final_path)}") + logger.info(f"[Downsample] Converted to 16-bit/44.1kHz: {os.path.basename(final_path)}") # Update QUALITY tag in the new file new_quality = 'FLAC 16bit' @@ -18336,7 +18136,7 @@ def _downsample_hires_flac(final_path, context): updated_audio['QUALITY'] = new_quality updated_audio.save() except Exception as tag_err: - print(f"[Downsample] Could not update QUALITY tag: {tag_err}") + logger.error(f"[Downsample] Could not update QUALITY tag: {tag_err}") # Update context so downstream (lossy copy, metadata) reflects new quality old_quality = context.get('_audio_quality', '') @@ -18348,7 +18148,7 @@ def _downsample_hires_flac(final_path, context): new_path = os.path.join(os.path.dirname(final_path), new_basename) try: os.rename(final_path, new_path) - print(f"[Downsample] Renamed: {os.path.basename(final_path)} ā†’ {new_basename}") + logger.info(f"[Downsample] Renamed: {os.path.basename(final_path)} ā†’ {new_basename}") # Rename matching lyrics sidecar file if it exists (.lrc or .txt) for lyrics_ext in ('.lrc', '.txt'): old_lyrics = os.path.splitext(final_path)[0] + lyrics_ext @@ -18357,16 +18157,16 @@ def _downsample_hires_flac(final_path, context): os.rename(old_lyrics, new_lyrics) return new_path except Exception as rename_err: - print(f"[Downsample] Could not rename file: {rename_err}") + logger.error(f"[Downsample] Could not rename file: {rename_err}") return final_path except subprocess.TimeoutExpired: - print(f"[Downsample] Conversion timed out for: {os.path.basename(final_path)}") + logger.info(f"[Downsample] Conversion timed out for: {os.path.basename(final_path)}") if os.path.exists(temp_path): os.remove(temp_path) except Exception as e: - print(f"[Downsample] Conversion error: {e}") + logger.error(f"[Downsample] Conversion error: {e}") if os.path.exists(temp_path): try: os.remove(temp_path) @@ -18408,7 +18208,7 @@ def _create_lossy_copy(final_path): } if codec not in codec_map: - print(f"[Lossy Copy] Unknown codec '{codec}' ā€” skipping conversion") + logger.info(f"[Lossy Copy] Unknown codec '{codec}' ā€” skipping conversion") return None ffmpeg_codec, out_ext, quality_label, extra_args = codec_map[codec] @@ -18428,11 +18228,11 @@ def _create_lossy_copy(final_path): if os.path.isfile(local): ffmpeg_bin = local else: - print(f"[Lossy Copy] ffmpeg not found ā€” skipping {codec.upper()} conversion") + logger.warning(f"[Lossy Copy] ffmpeg not found ā€” skipping {codec.upper()} conversion") return None try: - print(f"[Lossy Copy] Converting to {quality_label}: {os.path.basename(final_path)}") + logger.info(f"[Lossy Copy] Converting to {quality_label}: {os.path.basename(final_path)}") cmd = [ ffmpeg_bin, '-i', final_path, '-codec:a', ffmpeg_codec, @@ -18443,7 +18243,7 @@ def _create_lossy_copy(final_path): result = subprocess.run(cmd, capture_output=True, text=True, timeout=120) if result.returncode == 0: - print(f"[Lossy Copy] Created {quality_label} copy: {os.path.basename(out_path)}") + logger.info(f"[Lossy Copy] Created {quality_label} copy: {os.path.basename(out_path)}") # Fix QUALITY tag ā€” the FLAC's tag was copied verbatim by ffmpeg try: @@ -18460,7 +18260,7 @@ def _create_lossy_copy(final_path): audio['----:com.apple.iTunes:QUALITY'] = [MP4FreeForm(quality_label.encode('utf-8'))] audio.save() except Exception as tag_err: - print(f"[Lossy Copy] Could not update QUALITY tag: {tag_err}") + logger.error(f"[Lossy Copy] Could not update QUALITY tag: {tag_err}") # Embed cover art from source FLAC into the lossy copy # Opus/OGG can't inherit FLAC cover art via ffmpeg -map_metadata alone @@ -18490,7 +18290,7 @@ def _create_lossy_copy(final_path): pic.depth = 0 pic.colors = 0 pic.data = img_data - print(f"[Lossy Copy] Using cover.jpg as art source (FLAC had no embedded art)") + logger.warning(f"[Lossy Copy] Using cover.jpg as art source (FLAC had no embedded art)") except Exception: pass @@ -18515,15 +18315,15 @@ def _create_lossy_copy(final_path): ) dest_audio['METADATA_BLOCK_PICTURE'] = [base64.b64encode(picture_data).decode('ascii')] dest_audio.save() - print(f"[Lossy Copy] Embedded cover art in Opus file") + logger.info(f"[Lossy Copy] Embedded cover art in Opus file") elif codec == 'aac': from mutagen.mp4 import MP4Cover fmt = MP4Cover.FORMAT_JPEG if 'jpeg' in pic.mime else MP4Cover.FORMAT_PNG dest_audio['covr'] = [MP4Cover(pic.data, imageformat=fmt)] dest_audio.save() - print(f"[Lossy Copy] Embedded cover art in M4A file") + logger.info(f"[Lossy Copy] Embedded cover art in M4A file") except Exception as art_err: - print(f"[Lossy Copy] Could not embed cover art: {art_err}") + logger.error(f"[Lossy Copy] Could not embed cover art: {art_err}") # Blasphemy Mode: delete original FLAC if enabled and output is verified if config_manager.get('lossy_copy.delete_original', False): @@ -18539,7 +18339,7 @@ def _create_lossy_copy(final_path): except Exception: pass os.remove(final_path) - print(f"[Blasphemy Mode] Deleted original: {os.path.basename(final_path)}") + logger.info(f"[Blasphemy Mode] Deleted original: {os.path.basename(final_path)}") # Rename lyrics sidecar file to match the output filename for lyrics_ext in ('.lrc', '.txt'): src_lyrics = os.path.splitext(final_path)[0] + lyrics_ext @@ -18547,16 +18347,16 @@ def _create_lossy_copy(final_path): dst_lyrics = os.path.splitext(out_path)[0] + lyrics_ext try: os.rename(src_lyrics, dst_lyrics) - print(f"[Blasphemy Mode] Renamed {lyrics_ext}: {os.path.basename(src_lyrics)} -> {os.path.basename(dst_lyrics)}") + logger.info(f"[Blasphemy Mode] Renamed {lyrics_ext}: {os.path.basename(src_lyrics)} -> {os.path.basename(dst_lyrics)}") except Exception as lrc_err: - print(f"[Blasphemy Mode] Could not rename {lyrics_ext}: {lrc_err}") + logger.error(f"[Blasphemy Mode] Could not rename {lyrics_ext}: {lrc_err}") return out_path else: - print(f"[Blasphemy Mode] Output failed audio validation, keeping original: {os.path.basename(final_path)}") + logger.error(f"[Blasphemy Mode] Output failed audio validation, keeping original: {os.path.basename(final_path)}") else: - print(f"[Blasphemy Mode] Output missing or empty, keeping original: {os.path.basename(final_path)}") + logger.warning(f"[Blasphemy Mode] Output missing or empty, keeping original: {os.path.basename(final_path)}") except Exception as del_err: - print(f"[Blasphemy Mode] Error during original deletion, keeping original: {del_err}") + logger.error(f"[Blasphemy Mode] Error during original deletion, keeping original: {del_err}") else: # ffmpeg always prints its version banner to stderr (~300 chars). # Strip it so the actual error is visible, and show more than 200 chars. @@ -18571,19 +18371,60 @@ def _create_lossy_copy(final_path): elif line.strip() == '': past_banner = True error_msg = '\n'.join(error_lines).strip() if error_lines else stderr[-500:] - print(f"[Lossy Copy] ffmpeg failed (exit code {result.returncode}): {error_msg[:500]}") + logger.error(f"[Lossy Copy] ffmpeg failed (exit code {result.returncode}): {error_msg[:500]}") # Clean up empty/broken output file if os.path.isfile(out_path) and os.path.getsize(out_path) == 0: os.remove(out_path) - print(f"[Lossy Copy] Removed empty output file: {os.path.basename(out_path)}") + logger.warning(f"[Lossy Copy] Removed empty output file: {os.path.basename(out_path)}") except subprocess.TimeoutExpired: - print(f"[Lossy Copy] Conversion timed out for: {os.path.basename(final_path)}") + logger.info(f"[Lossy Copy] Conversion timed out for: {os.path.basename(final_path)}") if os.path.isfile(out_path) and os.path.getsize(out_path) == 0: os.remove(out_path) except Exception as e: - print(f"[Lossy Copy] Conversion error: {e}") + logger.error(f"[Lossy Copy] Conversion error: {e}") return None +def _get_album_type_display(raw_type, track_count) -> str: + """ + Return the display form of an album's type for the $albumtype template variable. + + Mirrors the inference used in the download pipeline so reorganize output + matches initial placement. Values: 'Album', 'Single', 'EP', 'Compilation'. + """ + raw = (raw_type or '').strip().lower() + try: + tc = int(track_count or 0) + except (TypeError, ValueError): + tc = 0 + + # Deezer's raw API returns 'compile' (only mapped to 'compilation' in the + # Album dataclass path); the Deezer enrichment worker writes the raw value, + # so both need to match here. + if raw in ('compilation', 'compile'): + return 'Compilation' + if raw == 'album': + return 'Album' + if raw in ('single', 'ep'): + # Match download-pipeline logic: Spotify labels both singles and EPs + # as 'single', so final classification is by track count. Applying the + # same rule to explicit 'ep' keeps reorganize consistent with where + # the files were first placed. + if tc <= 3: + return 'Single' + if tc <= 6: + return 'EP' + return 'Album' + + # Unknown/missing ā€” infer from track count + if tc <= 0: + return 'Album' + if tc <= 3: + return 'Single' + if tc <= 6: + return 'EP' + return 'Album' + + def _apply_path_template(template: str, context: dict) -> str: """ Apply template to build file path. @@ -18628,6 +18469,25 @@ def _apply_path_template(template: str, context: dict) -> str: album_artist_value = resolved except Exception: pass + # Support ${var} delimited syntax (e.g. ${albumtype}s ā†’ Albums) + # Must run before $var replacements to prevent partial matching + _bracket_map = { + 'albumartist': album_artist_value, + 'albumtype': clean_context.get('albumtype', 'Album'), + 'playlist': clean_context.get('playlist_name', ''), + 'artistletter': (clean_context.get('artist', 'U') or 'U')[0].upper(), + 'artist': clean_context.get('artist', 'Unknown Artist'), + 'album': clean_context.get('album', 'Unknown Album'), + 'title': clean_context.get('title', 'Unknown Track'), + 'track': f"{clean_context.get('track_number', 1):02d}", + 'disc': str(clean_context.get('disc_number', 1)), + 'discnum': str(clean_context.get('disc_number', 1)), + 'year': str(clean_context.get('year', '')), + 'quality': clean_context.get('quality', ''), + } + for var_name, val in _bracket_map.items(): + result = result.replace('${' + var_name + '}', val) + result = result.replace('$albumartist', album_artist_value) result = result.replace('$albumtype', clean_context.get('albumtype', 'Album')) result = result.replace('$playlist', clean_context.get('playlist_name', '')) @@ -18779,10 +18639,10 @@ def _wipe_source_tags(file_path: str) -> bool: else: audio.save() if tag_count > 0: - print(f"[Tag Wipe] Stripped {tag_count} source tags from: {os.path.basename(file_path)}") + logger.info(f"[Tag Wipe] Stripped {tag_count} source tags from: {os.path.basename(file_path)}") return True except Exception as e: - print(f"[Tag Wipe] Failed (non-fatal): {e}") + logger.error(f"[Tag Wipe] Failed (non-fatal): {e}") return False @@ -18804,11 +18664,11 @@ def _strip_all_non_audio_tags(file_path: str) -> dict: apev2_tags.delete(file_path) summary['apev2_stripped'] = True summary['apev2_tag_count'] = tag_count - print(f"Stripped {tag_count} APEv2 tags: {', '.join(tag_keys[:10])}") + logger.info(f"Stripped {tag_count} APEv2 tags: {', '.join(tag_keys[:10])}") except APENoHeaderError: pass # No APEv2 tags ā€” common case except Exception as e: - print(f"Could not strip APEv2 tags (non-fatal): {e}") + logger.error(f"Could not strip APEv2 tags (non-fatal): {e}") return summary def _verify_metadata_written(file_path: str) -> bool: @@ -18816,7 +18676,7 @@ def _verify_metadata_written(file_path: str) -> bool: try: check = MutagenFile(file_path) if check is None or check.tags is None: - print(f"[VERIFY] Tags are None after save: {file_path}") + logger.info(f"[VERIFY] Tags are None after save: {file_path}") return False title_found = False artist_found = False @@ -18826,7 +18686,7 @@ def _verify_metadata_written(file_path: str) -> bool: # Confirm APEv2 is gone try: APEv2(file_path) - print(f"[VERIFY] APEv2 tags still present after processing!") + logger.info(f"[VERIFY] APEv2 tags still present after processing!") return False except APENoHeaderError: pass @@ -18837,12 +18697,12 @@ def _verify_metadata_written(file_path: str) -> bool: title_found = bool(check.get('\xa9nam')) artist_found = bool(check.get('\xa9ART')) if not title_found or not artist_found: - print(f"[VERIFY] Missing metadata - title:{title_found} artist:{artist_found}") + logger.warning(f"[VERIFY] Missing metadata - title:{title_found} artist:{artist_found}") return False - print(f"[VERIFY] Metadata verified OK") + logger.info(f"[VERIFY] Metadata verified OK") return True except Exception as e: - print(f"[VERIFY] Verification error (non-fatal): {e}") + logger.error(f"[VERIFY] Verification error (non-fatal): {e}") return False def _is_ogg_opus(audio_file): @@ -18860,7 +18720,7 @@ def _enhance_file_metadata(file_path: str, context: dict, artist: dict, album_in which stripped the ID3v2 header from MP3 files, leaving them tagless. """ if not config_manager.get('metadata_enhancement.enabled', True): - print("Metadata enhancement disabled in config.") + logger.warning("Metadata enhancement disabled in config.") return True # Normalize None album_info to empty dict to prevent AttributeError on .get() calls @@ -18870,14 +18730,14 @@ def _enhance_file_metadata(file_path: str, context: dict, artist: dict, album_in # Acquire per-file lock to prevent concurrent metadata writes to the same file file_lock = _get_file_lock(file_path) with file_lock: - print(f"Enhancing metadata for: {os.path.basename(file_path)}") + logger.info(f"Enhancing metadata for: {os.path.basename(file_path)}") try: # Strip APEv2 tags from MP3 (invisible to ID3 handler) strip_summary = _strip_all_non_audio_tags(file_path) audio_file = MutagenFile(file_path) if audio_file is None: - print(f"Could not load audio file with Mutagen: {file_path}") + logger.error(f"Could not load audio file with Mutagen: {file_path}") return False # ā”€ā”€ Wipe ALL existing tags and save immediately ā”€ā”€ @@ -18892,7 +18752,7 @@ def _enhance_file_metadata(file_path: str, context: dict, artist: dict, album_in if audio_file.tags is not None: if len(audio_file.tags) > 0: tag_keys = list(audio_file.tags.keys())[:15] - print(f"Clearing {len(audio_file.tags)} existing tags: " + logger.info(f"Clearing {len(audio_file.tags)} existing tags: " f"{', '.join(str(k) for k in tag_keys)}") audio_file.tags.clear() else: @@ -18908,7 +18768,7 @@ def _enhance_file_metadata(file_path: str, context: dict, artist: dict, album_in metadata = _extract_spotify_metadata(context, artist, album_info) if not metadata: - print("Could not extract Spotify metadata, saving with cleared tags.") + logger.error("Could not extract Spotify metadata, saving with cleared tags.") if isinstance(audio_file.tags, ID3): audio_file.save(v1=0, v2_version=4) elif isinstance(audio_file, FLAC): @@ -18920,12 +18780,18 @@ def _enhance_file_metadata(file_path: str, context: dict, artist: dict, album_in # ā”€ā”€ Write standard tags using format-specific API ā”€ā”€ track_num_str = f"{metadata.get('track_number', 1)}/{metadata.get('total_tracks', 1)}" + _write_multi = config_manager.get('metadata_enhancement.tags.write_multi_artist', False) + _artists_list = metadata.get('_artists_list', []) + if isinstance(audio_file.tags, ID3): # MP3: write ID3 frames directly if metadata.get('title'): audio_file.tags.add(TIT2(encoding=3, text=[metadata['title']])) if metadata.get('artist'): audio_file.tags.add(TPE1(encoding=3, text=[metadata['artist']])) + # Multi-value: write each artist as separate TPE1 text value + if _write_multi and len(_artists_list) > 1: + audio_file.tags.add(TPE1(encoding=3, text=_artists_list)) if metadata.get('album_artist'): audio_file.tags.add(TPE2(encoding=3, text=[metadata['album_artist']])) if metadata.get('album'): @@ -18944,6 +18810,9 @@ def _enhance_file_metadata(file_path: str, context: dict, artist: dict, album_in audio_file['title'] = [metadata['title']] if metadata.get('artist'): audio_file['artist'] = [metadata['artist']] + # Multi-value: write ARTISTS tag with individual values + if _write_multi and len(_artists_list) > 1: + audio_file['artists'] = _artists_list if metadata.get('album_artist'): audio_file['albumartist'] = [metadata['album_artist']] if metadata.get('album'): @@ -18961,7 +18830,11 @@ def _enhance_file_metadata(file_path: str, context: dict, artist: dict, album_in if metadata.get('title'): audio_file['\xa9nam'] = [metadata['title']] if metadata.get('artist'): - audio_file['\xa9ART'] = [metadata['artist']] + # Multi-value: write each artist as separate list entry + if _write_multi and len(_artists_list) > 1: + audio_file['\xa9ART'] = _artists_list + else: + audio_file['\xa9ART'] = [metadata['artist']] if metadata.get('album_artist'): audio_file['aART'] = [metadata['album_artist']] if metadata.get('album'): @@ -19011,18 +18884,18 @@ def _enhance_file_metadata(file_path: str, context: dict, artist: dict, album_in # Verify metadata was written verified = _verify_metadata_written(file_path) if verified: - print("Metadata enhanced successfully.") + logger.info("Metadata enhanced successfully.") else: - print("Metadata saved but verification found issues (see above).") + logger.info("Metadata saved but verification found issues (see above).") return True except Exception as e: import traceback - print(f"Error enhancing metadata for {file_path}: {e}") - print(f"[Metadata Debug] Exception type: {type(e).__name__}") - print(f"[Metadata Debug] File exists: {os.path.exists(file_path)}") - print(f"[Metadata Debug] Artist: {artist.get('name', 'MISSING') if artist else 'None'}") - print(f"[Metadata Debug] Album info: {album_info.get('album_name', 'MISSING') if album_info else 'None'}") - print(f"[Metadata Debug] Traceback:\n{traceback.format_exc()}") + logger.error(f"Error enhancing metadata for {file_path}: {e}") + logger.error(f"[Metadata Debug] Exception type: {type(e).__name__}") + logger.info(f"[Metadata Debug] File exists: {os.path.exists(file_path)}") + logger.warning(f"[Metadata Debug] Artist: {artist.get('name', 'MISSING') if artist else 'None'}") + logger.warning(f"[Metadata Debug] Album info: {album_info.get('album_name', 'MISSING') if album_info else 'None'}") + logger.error(f"[Metadata Debug] Traceback:\n{traceback.format_exc()}") return False def _generate_lrc_file(file_path: str, context: dict, artist: dict, album_info: dict) -> bool: @@ -19071,14 +18944,14 @@ def _generate_lrc_file(file_path: str, context: dict, artist: dict, album_info: ) if success: - print(f"LRC file generated for: {track_name}") + logger.info(f"LRC file generated for: {track_name}") else: - print(f"No lyrics found for: {track_name}") + logger.warning(f"No lyrics found for: {track_name}") return success except Exception as e: - print(f"Error generating LRC file for {file_path}: {e}") + logger.error(f"Error generating LRC file for {file_path}: {e}") return False def _extract_spotify_metadata(context: dict, artist: dict, album_info: dict) -> dict: @@ -19092,19 +18965,18 @@ def _extract_spotify_metadata(context: dict, artist: dict, album_info: dict) -> # Priority 1: Spotify clean title from context if original_search.get('spotify_clean_title'): metadata['title'] = original_search['spotify_clean_title'] - print(f"Metadata: Using Spotify clean title: '{metadata['title']}'") + logger.info(f"Metadata: Using Spotify clean title: '{metadata['title']}'") # Priority 2: Album info clean name elif album_info.get('clean_track_name'): metadata['title'] = album_info['clean_track_name'] - print(f"Metadata: Using album info clean name: '{metadata['title']}'") + logger.info(f"Metadata: Using album info clean name: '{metadata['title']}'") # Priority 3: Original title as fallback else: metadata['title'] = original_search.get('title', '') - print(f"Metadata: Using original title as fallback: '{metadata['title']}'") + logger.warning(f"Metadata: Using original title as fallback: '{metadata['title']}'") # Handle multiple artists from Spotify data original_search = context.get("original_search_result", {}) if 'artists' in original_search and isinstance(original_search['artists'], list) and len(original_search['artists']) > 0: - # Join all artists with semicolon separator (standard format) all_artists = [] for a in original_search['artists']: if isinstance(a, dict) and 'name' in a: @@ -19114,11 +18986,11 @@ def _extract_spotify_metadata(context: dict, artist: dict, album_info: dict) -> else: all_artists.append(str(a)) metadata['artist'] = ', '.join(all_artists) - print(f"Metadata: Using all artists: '{metadata['artist']}'") + logger.info(f"Metadata: Using all artists: '{metadata['artist']}'") else: # Fallback to single artist metadata['artist'] = artist.get('name', '') - print(f"Metadata: Using primary artist: '{metadata['artist']}'") + logger.info(f"Metadata: Using primary artist: '{metadata['artist']}'") # Resolve album_artist for consistent tagging across all tracks in an album. # Priority: 1) explicit batch artist context (same artist for whole album) @@ -19178,18 +19050,18 @@ def _extract_spotify_metadata(context: dict, artist: dict, album_info: dict) -> track_num = album_info.get('track_number', 1) metadata['track_number'] = track_num metadata['total_tracks'] = spotify_album.get('total_tracks', 1) if spotify_album else 1 - print(f"[METADATA] Album track - track_number: {track_num}, album: {metadata['album']}") + logger.info(f"[METADATA] Album track - track_number: {track_num}, album: {metadata['album']}") else: # SAFEGUARD: If we have spotify_album context, never use track title as album name # This prevents album tracks from being tagged as singles due to classification errors if spotify_album and spotify_album.get('name'): - print(f"[SAFEGUARD] Using spotify_album name instead of track title for album metadata") + logger.info(f"[SAFEGUARD] Using spotify_album name instead of track title for album metadata") metadata['album'] = spotify_album['name'] # Use corrected track_number from album_info (which should be updated by post-processing) corrected_track_number = album_info.get('track_number', 1) if album_info else 1 metadata['track_number'] = corrected_track_number metadata['total_tracks'] = spotify_album.get('total_tracks', 1) - print(f"[SAFEGUARD] Using track_number: {corrected_track_number}") + logger.info(f"[SAFEGUARD] Using track_number: {corrected_track_number}") else: metadata['album'] = metadata['title'] # For true singles, album is the title metadata['track_number'] = 1 @@ -19250,7 +19122,7 @@ def _extract_spotify_metadata(context: dict, artist: dict, album_info: dict) -> metadata['spotify_album_id'] = album_id # Summary log for debugging metadata issues (e.g. wrong album_artist / track_number) - print(f"[Metadata Summary] title='{metadata.get('title')}' | artist='{metadata.get('artist')}' | album_artist='{metadata.get('album_artist')}' | album='{metadata.get('album')}' | track={metadata.get('track_number')}/{metadata.get('total_tracks')} | disc={metadata.get('disc_number')}") + logger.info(f"[Metadata Summary] title='{metadata.get('title')}' | artist='{metadata.get('artist')}' | album_artist='{metadata.get('album_artist')}' | album='{metadata.get('album')}' | track={metadata.get('track_number')}/{metadata.get('total_tracks')} | disc={metadata.get('disc_number')}") return metadata @@ -19297,7 +19169,7 @@ def _embed_album_art_metadata(audio_file, metadata: dict): image_data = response.read() mime_type = response.info().get_content_type() or 'image/jpeg' if image_data and len(image_data) > 1000: - print(f"Cover art from Cover Art Archive ({len(image_data) // 1024}KB)") + logger.info(f"Cover art from Cover Art Archive ({len(image_data) // 1024}KB)") else: image_data = None # Too small, likely an error page except Exception: @@ -19307,14 +19179,14 @@ def _embed_album_art_metadata(audio_file, metadata: dict): if not image_data: art_url = metadata.get('album_art_url') if not art_url: - print("No album art URL available for embedding.") + logger.warning("No album art URL available for embedding.") return with urllib.request.urlopen(art_url, timeout=10) as response: image_data = response.read() mime_type = response.info().get_content_type() if not image_data: - print("Failed to download album art data.") + logger.error("Failed to download album art data.") return # MP3 (ID3) @@ -19337,9 +19209,9 @@ def _embed_album_art_metadata(audio_file, metadata: dict): fmt = MP4Cover.FORMAT_JPEG if 'jpeg' in mime_type else MP4Cover.FORMAT_PNG audio_file['covr'] = [MP4Cover(image_data, imageformat=fmt)] - print("Album art successfully embedded.") + logger.info("Album art successfully embedded.") except Exception as e: - print(f"Error embedding album art: {e}") + logger.error(f"Error embedding album art: {e}") def _embed_source_ids(audio_file, metadata: dict, context: dict = None): """ @@ -19543,13 +19415,13 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): """, (int(release_year), _pp_album_name, _pp_artist_name)) if cursor.rowcount > 0: conn.commit() - print(f"Updated album year to {release_year} in database") + logger.info(f"Updated album year to {release_year} in database") else: conn.rollback() finally: conn.close() except Exception as e: - print(f"Could not update album year in DB: {e}") + logger.error(f"Could not update album year in DB: {e}") # (All source lookups now handled by _pp_lookup_* functions called via configurable order above) if False: # Dead code ā€” old inline blocks preserved for reference during transition @@ -19621,10 +19493,10 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): break except (ValueError, TypeError): pass - print(f"MusicBrainz release details: type={primary_type or '?'}, " + logger.info(f"MusicBrainz release details: type={primary_type or '?'}, " f"country={country or '?'}, media={id_tags.get('MEDIA', '?')}") except Exception as e: - print(f"MusicBrainz release detail lookup failed (non-fatal): {e}") + logger.error(f"MusicBrainz release detail lookup failed (non-fatal): {e}") # ā”€ā”€ 2b. Deezer lookup for BPM, ISRC fallback, and source IDs ā”€ā”€ deezer_bpm = None @@ -19643,7 +19515,7 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): dz_artist_id = dz_result.get('artist', {}).get('id') if dz_artist_id: id_tags['DEEZER_ARTIST_ID'] = str(dz_artist_id) - print(f"Deezer track matched: {dz_track_id}") + logger.info(f"Deezer track matched: {dz_track_id}") # Get full track details for BPM and ISRC dz_details = dz_client.get_track_details(dz_track_id) @@ -19655,9 +19527,9 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): if dz_isrc: deezer_isrc = dz_isrc else: - print("Deezer worker not available, skipping Deezer lookup") + logger.info("Deezer worker not available, skipping Deezer lookup") except Exception as e: - print(f"Deezer lookup failed (non-fatal): {e}") + logger.error(f"Deezer lookup failed (non-fatal): {e}") # ā”€ā”€ 2c. AudioDB lookup for mood, style, genre, and source ID ā”€ā”€ audiodb_mood = None @@ -19675,13 +19547,13 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): adb_track_id = adb_result.get('idTrack') if adb_track_id: id_tags['AUDIODB_TRACK_ID'] = str(adb_track_id) - print(f"AudioDB track matched: {adb_track_id}") + logger.info(f"AudioDB track matched: {adb_track_id}") # Use AudioDB's MusicBrainz IDs as fallbacks for any missing from MB lookup adb_mb_track = adb_result.get('strMusicBrainzID') if adb_mb_track and 'MUSICBRAINZ_RECORDING_ID' not in id_tags: id_tags['MUSICBRAINZ_RECORDING_ID'] = adb_mb_track recording_mbid = adb_mb_track - print(f"MusicBrainz recording ID from AudioDB fallback: {adb_mb_track}") + logger.warning(f"MusicBrainz recording ID from AudioDB fallback: {adb_mb_track}") # NOTE: AudioDB's strMusicBrainzAlbumID is intentionally # NOT used as a fallback for MUSICBRAINZ_RELEASE_ID. # AudioDB links each track to its original album in MB, @@ -19692,14 +19564,14 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): if adb_mb_artist and 'MUSICBRAINZ_ARTIST_ID' not in id_tags: id_tags['MUSICBRAINZ_ARTIST_ID'] = adb_mb_artist artist_mbid = adb_mb_artist - print(f"MusicBrainz artist ID from AudioDB fallback: {adb_mb_artist}") + logger.warning(f"MusicBrainz artist ID from AudioDB fallback: {adb_mb_artist}") audiodb_mood = adb_result.get('strMood') or None audiodb_style = adb_result.get('strStyle') or None audiodb_genre = adb_result.get('strGenre') or None else: - print("AudioDB worker not available, skipping AudioDB lookup") + logger.info("AudioDB worker not available, skipping AudioDB lookup") except Exception as e: - print(f"AudioDB lookup failed (non-fatal): {e}") + logger.error(f"AudioDB lookup failed (non-fatal): {e}") # ā”€ā”€ 2d. Tidal lookup for ISRC fallback, copyright, and source IDs ā”€ā”€ tidal_isrc = None @@ -19714,7 +19586,7 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): td_track_id = td_result.get('id') if td_track_id: id_tags['TIDAL_TRACK_ID'] = str(td_track_id) - print(f"Tidal track matched: {td_track_id}") + logger.info(f"Tidal track matched: {td_track_id}") td_artist = td_result.get('artist', {}) if isinstance(td_artist, dict) and td_artist.get('id'): id_tags['TIDAL_ARTIST_ID'] = str(td_artist['id']) @@ -19731,7 +19603,7 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): if td_copyright: tidal_copyright = td_copyright except Exception as e: - print(f"Tidal lookup failed (non-fatal): {e}") + logger.error(f"Tidal lookup failed (non-fatal): {e}") # ā”€ā”€ 2e. Qobuz lookup for ISRC fallback, copyright, label, and source IDs ā”€ā”€ qobuz_isrc = None @@ -19754,7 +19626,7 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): qz_track_id = qz_result.get('id') if qz_track_id: id_tags['QOBUZ_TRACK_ID'] = str(qz_track_id) - print(f"Qobuz track matched: {qz_track_id}") + logger.info(f"Qobuz track matched: {qz_track_id}") if isinstance(qz_performer, dict) and qz_performer.get('id'): id_tags['QOBUZ_ARTIST_ID'] = str(qz_performer['id']) qz_isrc = qz_result.get('isrc') @@ -19773,7 +19645,7 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): if isinstance(qz_label_info, dict) and qz_label_info.get('name'): qobuz_label = qz_label_info['name'] except Exception as e: - print(f"Qobuz lookup failed (non-fatal): {e}") + logger.error(f"Qobuz lookup failed (non-fatal): {e}") # ā”€ā”€ 2f. Last.fm lookup for tags (genre merge) and URL ā”€ā”€ lastfm_tags = [] @@ -19796,9 +19668,9 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): lastfm_tags = [t.get('name', '') for t in tag_list if isinstance(t, dict) and t.get('name')] elif isinstance(tag_list, dict) and tag_list.get('name'): lastfm_tags = [tag_list['name']] - print(f"Last.fm track info found: {len(lastfm_tags)} tags") + logger.info(f"Last.fm track info found: {len(lastfm_tags)} tags") except Exception as e: - print(f"Last.fm lookup failed (non-fatal): {e}") + logger.error(f"Last.fm lookup failed (non-fatal): {e}") # ā”€ā”€ 2g. Genius lookup for source ID and URL ā”€ā”€ # Genius has an aggressive global rate limiter (30ā†’60ā†’120s backoff) that @@ -19812,7 +19684,7 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): try: import core.genius_client as _genius_module if time.time() < _genius_module._rate_limit_until: - print("Genius rate-limited, skipping (non-blocking)") + logger.info("Genius rate-limited, skipping (non-blocking)") else: g_client = genius_worker.client if genius_worker else None if g_client: @@ -19821,12 +19693,12 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): g_id = g_result.get('id') if g_id: id_tags['GENIUS_TRACK_ID'] = str(g_id) - print(f"Genius song matched: {g_id}") + logger.info(f"Genius song matched: {g_id}") g_url = g_result.get('url') if g_url: genius_url = g_url except Exception as e: - print(f"Genius lookup failed (non-fatal): {e}") + logger.error(f"Genius lookup failed (non-fatal): {e}") if not id_tags and not deezer_bpm and not deezer_isrc and not audiodb_mood and not audiodb_style: return @@ -19914,7 +19786,7 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): written.append(key) if written: - print(f"Embedded IDs: {', '.join(written)}") + logger.info(f"Embedded IDs: {', '.join(written)}") # ā”€ā”€ 3aĀ½. Write date tag if discovered during lookups (initial write had no date) ā”€ā”€ if _needs_date_tag and release_year: @@ -19924,7 +19796,7 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): audio_file['date'] = [release_year] elif isinstance(audio_file, MP4): audio_file['\xa9day'] = [release_year] - print(f"Date tag: {release_year}") + logger.info(f"Date tag: {release_year}") # ā”€ā”€ 3b. Write BPM tag (from Deezer) ā”€ā”€ if _tag_enabled('deezer.tags.bpm') and deezer_bpm and deezer_bpm > 0: @@ -19935,7 +19807,7 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): audio_file['BPM'] = [str(bpm_int)] elif isinstance(audio_file, MP4): audio_file['tmpo'] = [bpm_int] - print(f"BPM: {bpm_int}") + logger.info(f"BPM: {bpm_int}") # ā”€ā”€ 3c. Write mood tag (from AudioDB) ā”€ā”€ if _tag_enabled('audiodb.tags.mood') and audiodb_mood: @@ -19945,7 +19817,7 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): audio_file['MOOD'] = [audiodb_mood] elif isinstance(audio_file, MP4): audio_file['----:com.apple.iTunes:MOOD'] = [MP4FreeForm(audiodb_mood.encode('utf-8'))] - print(f"Mood: {audiodb_mood}") + logger.info(f"Mood: {audiodb_mood}") # ā”€ā”€ 3d. Write style tag (from AudioDB) ā”€ā”€ if _tag_enabled('audiodb.tags.style') and audiodb_style: @@ -19955,7 +19827,7 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): audio_file['STYLE'] = [audiodb_style] elif isinstance(audio_file, MP4): audio_file['----:com.apple.iTunes:STYLE'] = [MP4FreeForm(audiodb_style.encode('utf-8'))] - print(f"Style: {audiodb_style}") + logger.info(f"Style: {audiodb_style}") # ā”€ā”€ 4. Merge genres (Spotify + MusicBrainz + AudioDB + Last.fm) and overwrite tag ā”€ā”€ if _tag_enabled('metadata_enhancement.tags.genre_merge'): @@ -19984,7 +19856,7 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): audio_file['GENRE'] = [genre_string] elif isinstance(audio_file, MP4): audio_file['\xa9gen'] = [genre_string] - print(f"Genres merged: {genre_string}") + logger.info(f"Genres merged: {genre_string}") # ā”€ā”€ 5. Write ISRC if available (per-source fallback chain) ā”€ā”€ _isrc_candidates = [] @@ -20004,7 +19876,7 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): audio_file['ISRC'] = [final_isrc] elif isinstance(audio_file, MP4): audio_file['----:com.apple.iTunes:ISRC'] = [MP4FreeForm(final_isrc.encode('utf-8'))] - print(f"ISRC ({source}): {final_isrc}") + logger.info(f"ISRC ({source}): {final_isrc}") # ā”€ā”€ 6. Write copyright tag (Tidal ā†’ Qobuz fallback) ā”€ā”€ _copyright_candidates = [] @@ -20020,7 +19892,7 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): audio_file['COPYRIGHT'] = [final_copyright] elif isinstance(audio_file, MP4): audio_file['cprt'] = [final_copyright] - print(f"Ā©ļø Copyright ({source}): {final_copyright[:60]}") + logger.info(f"Ā©ļø Copyright ({source}): {final_copyright[:60]}") # ā”€ā”€ 7. Write label/publisher tag (from Qobuz) ā”€ā”€ if _tag_enabled('qobuz.tags.label') and qobuz_label: @@ -20030,7 +19902,7 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): audio_file['LABEL'] = [qobuz_label] elif isinstance(audio_file, MP4): audio_file['----:com.apple.iTunes:LABEL'] = [MP4FreeForm(qobuz_label.encode('utf-8'))] - print(f"Label (Qobuz): {qobuz_label}") + logger.info(f"Label (Qobuz): {qobuz_label}") # ā”€ā”€ 8. Write Last.fm and Genius URLs as custom tags ā”€ā”€ if _tag_enabled('lastfm.tags.url') and lastfm_url: @@ -20050,7 +19922,7 @@ def _embed_source_ids(audio_file, metadata: dict, context: dict = None): audio_file['----:com.apple.iTunes:GENIUS_URL'] = [MP4FreeForm(genius_url.encode('utf-8'))] except Exception as e: - print(f"Error embedding source IDs (non-fatal): {e}") + logger.error(f"Error embedding source IDs (non-fatal): {e}") def _download_cover_art(album_info: dict, target_dir: str, context: dict = None): """Downloads cover.jpg into the specified directory. @@ -20075,7 +19947,7 @@ def _download_cover_art(album_info: dict, target_dir: str, context: dict = None) return # Already high-res, skip # Low-res cover exists ā€” try to upgrade from CAA is_upgrade = True - print(f"Existing cover.jpg is {existing_size // 1024}KB ā€” attempting CAA upgrade...") + logger.info(f"Existing cover.jpg is {existing_size // 1024}KB ā€” attempting CAA upgrade...") except Exception: return else: @@ -20094,7 +19966,7 @@ def _download_cover_art(album_info: dict, target_dir: str, context: dict = None) with urllib.request.urlopen(req, timeout=10) as response: image_data = response.read() if image_data and len(image_data) > 1000: - print(f"Cover art from Cover Art Archive ({len(image_data) // 1024}KB)") + logger.info(f"Cover art from Cover Art Archive ({len(image_data) // 1024}KB)") else: image_data = None except Exception: @@ -20102,7 +19974,7 @@ def _download_cover_art(album_info: dict, target_dir: str, context: dict = None) # If upgrading and CAA failed, keep existing cover ā€” don't overwrite with same low-res if is_upgrade and not image_data: - print(f"CAA upgrade failed ā€” keeping existing cover.jpg") + logger.error(f"CAA upgrade failed ā€” keeping existing cover.jpg") return # Fallback to Spotify/iTunes/Deezer URL @@ -20118,7 +19990,7 @@ def _download_cover_art(album_info: dict, target_dir: str, context: dict = None) if images and isinstance(images, list) and len(images) > 0: art_url = images[0].get('url') if isinstance(images[0], dict) else None if art_url: - print(f"Using cover art URL from spotify_album context") + logger.info(f"Using cover art URL from spotify_album context") # Upgrade to highest available resolution before fetching if art_url and 'i.scdn.co' in art_url: from core.spotify_client import _upgrade_spotify_image_url @@ -20127,7 +19999,7 @@ def _download_cover_art(album_info: dict, target_dir: str, context: dict = None) import re as _re art_url = _re.sub(r'\d+x\d+bb', '3000x3000bb', art_url) if not art_url: - print("No cover art URL available for download.") + logger.warning("No cover art URL available for download.") return with urllib.request.urlopen(art_url, timeout=10) as response: image_data = response.read() @@ -20138,9 +20010,9 @@ def _download_cover_art(album_info: dict, target_dir: str, context: dict = None) with open(cover_path, 'wb') as f: f.write(image_data) - print(f"Cover art downloaded to: {cover_path}") + logger.info(f"Cover art downloaded to: {cover_path}") except Exception as e: - print(f"Error downloading cover.jpg: {e}") + logger.error(f"Error downloading cover.jpg: {e}") @@ -20161,7 +20033,7 @@ def _get_spotify_album_tracks(spotify_album: dict) -> list: } for item in tracks_data['items']] return [] except Exception as e: - print(f"Error fetching Spotify album tracks: {e}") + logger.error(f"Error fetching Spotify album tracks: {e}") return [] def _match_track_to_spotify_title(slsk_track_meta: dict, spotify_tracks: list) -> dict: @@ -20177,7 +20049,7 @@ def _match_track_to_spotify_title(slsk_track_meta: dict, spotify_tracks: list) - track_num = slsk_track_meta['track_number'] for sp_track in spotify_tracks: if sp_track.get('track_number') == track_num: - print(f"Matched track by number ({track_num}): '{slsk_track_meta['title']}' -> '{sp_track['name']}'") + logger.info(f"Matched track by number ({track_num}): '{slsk_track_meta['title']}' -> '{sp_track['name']}'") # Return a new dict with the corrected title and number return { 'title': sp_track['name'], @@ -20201,7 +20073,7 @@ def _match_track_to_spotify_title(slsk_track_meta: dict, spotify_tracks: list) - best_match = sp_track if best_match: - print(f"Matched track by title similarity ({best_score:.2f}): '{slsk_track_meta['title']}' -> '{best_match['name']}'") + logger.info(f"Matched track by title similarity ({best_score:.2f}): '{slsk_track_meta['title']}' -> '{best_match['name']}'") return { 'title': best_match['name'], 'artist': slsk_track_meta.get('artist'), @@ -20211,7 +20083,7 @@ def _match_track_to_spotify_title(slsk_track_meta: dict, spotify_tracks: list) - 'explicit': best_match.get('explicit', False) } - print(f"Could not confidently match track '{slsk_track_meta['title']}'. Using original metadata.") + logger.error(f"Could not confidently match track '{slsk_track_meta['title']}'. Using original metadata.") return slsk_track_meta # Fallback to original @@ -20234,13 +20106,13 @@ def _pp_lookup_musicbrainz(pp, _names_match): try: mb_service = mb_worker.mb_service if mb_worker else None if not mb_service: - print("MusicBrainz worker not available, skipping MBID lookup") + logger.info("MusicBrainz worker not available, skipping MBID lookup") return result = mb_service.match_recording(track_title, artist_name) if result and result.get('mbid'): pp['recording_mbid'] = result['mbid'] id_tags['MUSICBRAINZ_RECORDING_ID'] = pp['recording_mbid'] - print(f"MusicBrainz recording matched: {pp['recording_mbid']}") + logger.info(f"MusicBrainz recording matched: {pp['recording_mbid']}") details = mb_service.mb_client.get_recording(pp['recording_mbid'], includes=['isrcs', 'genres']) if details: isrcs = details.get('isrcs', []) @@ -20345,13 +20217,13 @@ def _pp_lookup_musicbrainz(pp, _names_match): if _release_recording.get('id'): pp['recording_mbid'] = _release_recording['id'] id_tags['MUSICBRAINZ_RECORDING_ID'] = _release_recording['id'] - print(f"MusicBrainz recording from release tracklist: {_release_recording['id']}") + logger.info(f"MusicBrainz recording from release tracklist: {_release_recording['id']}") break break except (ValueError, TypeError): pass except Exception as e: - print(f"MusicBrainz lookup failed (non-fatal): {e}") + logger.error(f"MusicBrainz lookup failed (non-fatal): {e}") def _pp_lookup_deezer(pp, _names_match): @@ -20365,7 +20237,7 @@ def _pp_lookup_deezer(pp, _names_match): try: dz_client = deezer_worker.client if deezer_worker else None if not dz_client: - print("Deezer worker not available, skipping Deezer lookup") + logger.info("Deezer worker not available, skipping Deezer lookup") return dz_result = dz_client.search_track(artist_name, track_title) if dz_result and _names_match(dz_result.get('title', ''), track_title) and \ @@ -20375,7 +20247,7 @@ def _pp_lookup_deezer(pp, _names_match): dz_artist_id = dz_result.get('artist', {}).get('id') if dz_artist_id: id_tags['DEEZER_ARTIST_ID'] = str(dz_artist_id) - print(f"Deezer track matched: {dz_track_id}") + logger.info(f"Deezer track matched: {dz_track_id}") dz_details = dz_client.get_track_details(dz_track_id) if dz_details: bpm_val = dz_details.get('bpm') @@ -20391,7 +20263,7 @@ def _pp_lookup_deezer(pp, _names_match): if len(dz_release) >= 4 and dz_release[:4].isdigit(): pp['release_year'] = dz_release[:4] except Exception as e: - print(f"Deezer lookup failed (non-fatal): {e}") + logger.error(f"Deezer lookup failed (non-fatal): {e}") def _pp_lookup_audiodb(pp, _names_match): @@ -20405,7 +20277,7 @@ def _pp_lookup_audiodb(pp, _names_match): try: adb_client = audiodb_worker.client if audiodb_worker else None if not adb_client: - print("AudioDB worker not available, skipping AudioDB lookup") + logger.info("AudioDB worker not available, skipping AudioDB lookup") return adb_result = adb_client.search_track(artist_name, track_title) if adb_result and _names_match(adb_result.get('strTrack', ''), track_title) and \ @@ -20413,22 +20285,22 @@ def _pp_lookup_audiodb(pp, _names_match): adb_track_id = adb_result.get('idTrack') if adb_track_id: id_tags['AUDIODB_TRACK_ID'] = str(adb_track_id) - print(f"AudioDB track matched: {adb_track_id}") + logger.info(f"AudioDB track matched: {adb_track_id}") adb_mb_track = adb_result.get('strMusicBrainzID') if adb_mb_track and 'MUSICBRAINZ_RECORDING_ID' not in id_tags: id_tags['MUSICBRAINZ_RECORDING_ID'] = adb_mb_track pp['recording_mbid'] = adb_mb_track - print(f"MusicBrainz recording ID from AudioDB fallback: {adb_mb_track}") + logger.warning(f"MusicBrainz recording ID from AudioDB fallback: {adb_mb_track}") adb_mb_artist = adb_result.get('strMusicBrainzArtistID') if adb_mb_artist and 'MUSICBRAINZ_ARTIST_ID' not in id_tags: id_tags['MUSICBRAINZ_ARTIST_ID'] = adb_mb_artist pp['artist_mbid'] = adb_mb_artist - print(f"MusicBrainz artist ID from AudioDB fallback: {adb_mb_artist}") + logger.warning(f"MusicBrainz artist ID from AudioDB fallback: {adb_mb_artist}") pp['audiodb_mood'] = adb_result.get('strMood') or None pp['audiodb_style'] = adb_result.get('strStyle') or None pp['audiodb_genre'] = adb_result.get('strGenre') or None except Exception as e: - print(f"AudioDB lookup failed (non-fatal): {e}") + logger.error(f"AudioDB lookup failed (non-fatal): {e}") def _pp_lookup_tidal(pp, _names_match): @@ -20447,7 +20319,7 @@ def _pp_lookup_tidal(pp, _names_match): td_track_id = td_result.get('id') if td_track_id: id_tags['TIDAL_TRACK_ID'] = str(td_track_id) - print(f"Tidal track matched: {td_track_id}") + logger.info(f"Tidal track matched: {td_track_id}") td_artist = td_result.get('artist', {}) if isinstance(td_artist, dict) and td_artist.get('id'): id_tags['TIDAL_ARTIST_ID'] = str(td_artist['id']) @@ -20471,7 +20343,7 @@ def _pp_lookup_tidal(pp, _names_match): if len(td_release) >= 4 and td_release[:4].isdigit(): pp['release_year'] = td_release[:4] except Exception as e: - print(f"Tidal lookup failed (non-fatal): {e}") + logger.error(f"Tidal lookup failed (non-fatal): {e}") def _pp_lookup_qobuz(pp, _names_match): @@ -20497,7 +20369,7 @@ def _pp_lookup_qobuz(pp, _names_match): qz_track_id = qz_result.get('id') if qz_track_id: id_tags['QOBUZ_TRACK_ID'] = str(qz_track_id) - print(f"Qobuz track matched: {qz_track_id}") + logger.info(f"Qobuz track matched: {qz_track_id}") if isinstance(qz_performer, dict) and qz_performer.get('id'): id_tags['QOBUZ_ARTIST_ID'] = str(qz_performer['id']) qz_isrc = qz_result.get('isrc') @@ -20527,7 +20399,7 @@ def _pp_lookup_qobuz(pp, _names_match): if len(qz_release) >= 4 and qz_release[:4].isdigit(): pp['release_year'] = qz_release[:4] except Exception as e: - print(f"Qobuz lookup failed (non-fatal): {e}") + logger.error(f"Qobuz lookup failed (non-fatal): {e}") def _pp_lookup_lastfm(pp, _names_match): @@ -20553,9 +20425,9 @@ def _pp_lookup_lastfm(pp, _names_match): pp['lastfm_tags'] = [t.get('name', '') for t in tag_list if isinstance(t, dict) and t.get('name')] elif isinstance(tag_list, dict) and tag_list.get('name'): pp['lastfm_tags'] = [tag_list['name']] - print(f"Last.fm track info found: {len(pp['lastfm_tags'])} tags") + logger.info(f"Last.fm track info found: {len(pp['lastfm_tags'])} tags") except Exception as e: - print(f"Last.fm lookup failed (non-fatal): {e}") + logger.error(f"Last.fm lookup failed (non-fatal): {e}") def _pp_lookup_genius(pp, _names_match): @@ -20569,7 +20441,7 @@ def _pp_lookup_genius(pp, _names_match): try: import core.genius_client as _genius_module if time.time() < _genius_module._rate_limit_until: - print("Genius rate-limited, skipping (non-blocking)") + logger.info("Genius rate-limited, skipping (non-blocking)") return g_client = genius_worker.client if genius_worker else None if not g_client: @@ -20579,12 +20451,12 @@ def _pp_lookup_genius(pp, _names_match): g_id = g_result.get('id') if g_id: id_tags['GENIUS_TRACK_ID'] = str(g_id) - print(f"Genius song matched: {g_id}") + logger.info(f"Genius song matched: {g_id}") g_url = g_result.get('url') if g_url: pp['genius_url'] = g_url except Exception as e: - print(f"Genius lookup failed (non-fatal): {e}") + logger.error(f"Genius lookup failed (non-fatal): {e}") def _post_process_matched_download_with_verification(context_key, context, file_path, task_id, batch_id): @@ -20788,16 +20660,16 @@ def _check_flac_bit_depth(file_path, context, context_key): track_info = context.get('track_info', {}) track_name = track_info.get('name', os.path.basename(file_path)) if _downsample_enabled: - print(f"[FLAC Downsample] Accepted {_actual_bits}-bit FLAC (will be downsampled to {_flac_pref}-bit): {track_name}") + logger.info(f"[FLAC Downsample] Accepted {_actual_bits}-bit FLAC (will be downsampled to {_flac_pref}-bit): {track_name}") else: - print(f"[FLAC Fallback] Accepted {_actual_bits}-bit FLAC (preferred {_flac_pref}-bit): {track_name}") + logger.warning(f"[FLAC Fallback] Accepted {_actual_bits}-bit FLAC (preferred {_flac_pref}-bit): {track_name}") return False # Strict mode ā€” reject and quarantine rejection_msg = f"FLAC bit depth mismatch: file is {_actual_bits}-bit, preference is {_flac_pref}-bit" try: quarantine_path = _move_to_quarantine(file_path, context, rejection_msg) - print(f"File quarantined due to bit depth filter: {quarantine_path}") + logger.info(f"File quarantined due to bit depth filter: {quarantine_path}") except Exception as quarantine_error: logger.error(f"Quarantine failed ({quarantine_error}), deleting file: {file_path}") try: @@ -21034,9 +20906,9 @@ def _post_process_matched_download(context_key, context, file_path): if not os.path.exists(file_path): existing_final = context.get('_final_processed_path') if existing_final and os.path.exists(existing_final): - print(f"[Race Guard] Source gone but destination exists ā€” already processed by another thread: {os.path.basename(existing_final)}") + logger.info(f"[Race Guard] Source gone but destination exists ā€” already processed by another thread: {os.path.basename(existing_final)}") return - print(f"[Race Guard] Source file gone and no known destination ā€” marking as failed: {os.path.basename(file_path)}") + logger.error(f"[Race Guard] Source file gone and no known destination ā€” marking as failed: {os.path.basename(file_path)}") context['_race_guard_failed'] = True return # --- END RACE CONDITION GUARD --- @@ -21057,10 +20929,10 @@ def _post_process_matched_download(context_key, context, file_path): break _prev_size = _cur_size if _stability_check == 0: - print(f"Waiting for file to stabilise: {_basename} ({_cur_size} bytes)") + logger.info(f"Waiting for file to stabilise: {_basename} ({_cur_size} bytes)") time.sleep(1.5) else: - print(f"File may still be writing after stability checks: {_basename} ({_prev_size} bytes)") + logger.info(f"File may still be writing after stability checks: {_basename} ({_prev_size} bytes)") # --- END FILE STABILITY CHECK --- # --- ACOUSTID VERIFICATION --- @@ -21104,26 +20976,26 @@ def _post_process_matched_download(context_key, context, file_path): expected_artist = spotify_artist.get('name', '') if expected_track and expected_artist: - print(f"Running AcoustID verification for: '{expected_track}' by '{expected_artist}'") + logger.info(f"Running AcoustID verification for: '{expected_track}' by '{expected_artist}'") verification_result, verification_msg = verifier.verify_audio_file( file_path, expected_track, expected_artist, context ) - print(f"AcoustID verification result: {verification_result.value} - {verification_msg}") + logger.info(f"AcoustID verification result: {verification_result.value} - {verification_msg}") context['_acoustid_result'] = verification_result.value if verification_result == VerificationResult.FAIL: # Move to quarantine instead of Transfer try: quarantine_path = _move_to_quarantine(file_path, context, verification_msg) - print(f"File quarantined due to verification failure: {quarantine_path}") + logger.error(f"File quarantined due to verification failure: {quarantine_path}") except Exception as quarantine_error: # Quarantine failed ā€” delete the known-wrong file instead # NEVER save a file we've confirmed is wrong logger.error(f"Quarantine failed ({quarantine_error}), deleting wrong file: {file_path}") - print(f"Quarantine failed, deleting wrong file: {file_path}") + logger.error(f"Quarantine failed, deleting wrong file: {file_path}") try: os.remove(file_path) except Exception as del_error: @@ -21153,14 +21025,14 @@ def _post_process_matched_download(context_key, context, file_path): return # NEVER continue processing a known-wrong file else: - print(f"AcoustID verification skipped: missing track/artist info") + logger.warning(f"AcoustID verification skipped: missing track/artist info") context['_acoustid_result'] = 'skip' else: - print(f"ā„¹ļø AcoustID verification not available: {available_reason}") + logger.info(f"ā„¹ļø AcoustID verification not available: {available_reason}") context['_acoustid_result'] = 'disabled' except Exception as verify_error: # Any verification error should NOT block the download - fail open - print(f"AcoustID verification error (continuing normally): {verify_error}") + logger.error(f"AcoustID verification error (continuing normally): {verify_error}") context['_acoustid_result'] = 'error' # --- END ACOUSTID VERIFICATION --- @@ -21233,11 +21105,11 @@ def _post_process_matched_download(context_key, context, file_path): return # --- END SIMPLE DOWNLOAD HANDLING --- - print(f"Starting robust post-processing for: {context_key}") + logger.info(f"Starting robust post-processing for: {context_key}") spotify_artist = context.get("spotify_artist") if not spotify_artist: - print(f"Post-processing failed: Missing spotify_artist context.") + logger.error(f"Post-processing failed: Missing spotify_artist context.") return # ā”€ā”€ UNKNOWN ARTIST GUARD ā”€ā”€ @@ -21246,7 +21118,7 @@ def _post_process_matched_download(context_key, context, file_path): _junk_artist_names = {'', 'unknown', 'unknown artist', 'various artists', 'none', 'null'} _artist_name = (spotify_artist.get('name', '') if isinstance(spotify_artist, dict) else '').strip() if _artist_name.lower() in _junk_artist_names: - print(f"[Unknown Artist Guard] Artist name is '{_artist_name}' ā€” attempting to resolve") + logger.info(f"[Unknown Artist Guard] Artist name is '{_artist_name}' ā€” attempting to resolve") _resolved = False track_info_guard = context.get("track_info", {}) or {} original_search_guard = context.get("original_search_result", {}) or {} @@ -21258,7 +21130,7 @@ def _post_process_matched_download(context_key, context, file_path): _name = _first.get('name', '') if isinstance(_first, dict) else str(_first) if _name and _name.strip().lower() not in _junk_artist_names: spotify_artist['name'] = _name.strip() - print(f"[Unknown Artist Guard] Resolved from track_info.artists: '{_name}'") + logger.info(f"[Unknown Artist Guard] Resolved from track_info.artists: '{_name}'") _resolved = True # Try 2: Pull from original_search_result @@ -21266,7 +21138,7 @@ def _post_process_matched_download(context_key, context, file_path): _os_artist = original_search_guard.get('artist') or original_search_guard.get('artist_name') or '' if isinstance(_os_artist, str) and _os_artist.strip().lower() not in _junk_artist_names: spotify_artist['name'] = _os_artist.strip() - print(f"[Unknown Artist Guard] Resolved from original_search_result: '{_os_artist}'") + logger.info(f"[Unknown Artist Guard] Resolved from original_search_result: '{_os_artist}'") _resolved = True # Try 3: Re-fetch from metadata source using track ID @@ -21284,13 +21156,13 @@ def _post_process_matched_download(context_key, context, file_path): _d_name = _d_first.get('name', '') if isinstance(_d_first, dict) else str(_d_first) if _d_name and _d_name.strip().lower() not in _junk_artist_names: spotify_artist['name'] = _d_name.strip() - print(f"[Unknown Artist Guard] Resolved from metadata API: '{_d_name}'") + logger.info(f"[Unknown Artist Guard] Resolved from metadata API: '{_d_name}'") _resolved = True except Exception as _guard_err: - print(f"[Unknown Artist Guard] Metadata re-fetch failed: {_guard_err}") + logger.error(f"[Unknown Artist Guard] Metadata re-fetch failed: {_guard_err}") if not _resolved: - print(f"[Unknown Artist Guard] Could not resolve artist ā€” proceeding with '{_artist_name}'") + logger.error(f"[Unknown Artist Guard] Could not resolve artist ā€” proceeding with '{_artist_name}'") context['spotify_artist'] = spotify_artist # ā”€ā”€ END UNKNOWN ARTIST GUARD ā”€ā”€ @@ -21299,28 +21171,28 @@ def _post_process_matched_download(context_key, context, file_path): track_info = context.get("track_info", {}) playlist_folder_mode = track_info.get("_playlist_folder_mode", False) - print(f"[Debug] Post-processing - track_info type: {type(track_info)}, is None: {track_info is None}, is empty: {not track_info}") - print(f"[Debug] Post-processing - playlist_folder_mode: {playlist_folder_mode}") + logger.debug(f"[Debug] Post-processing - track_info type: {type(track_info)}, is None: {track_info is None}, is empty: {not track_info}") + logger.debug(f"[Debug] Post-processing - playlist_folder_mode: {playlist_folder_mode}") if track_info: - print(f"[Debug] Post-processing - track_info keys: {list(track_info.keys())}") + logger.debug(f"[Debug] Post-processing - track_info keys: {list(track_info.keys())}") if playlist_folder_mode: # Use shared path builder for playlist mode playlist_name = track_info.get("_playlist_name", "Unknown Playlist") - print(f"[Playlist Folder Mode] Organizing in playlist folder: {playlist_name}") + logger.info(f"[Playlist Folder Mode] Organizing in playlist folder: {playlist_name}") file_ext = os.path.splitext(file_path)[1] # Build final path FIRST so we can check for already-processed files final_path, _ = _build_final_path_for_track(context, spotify_artist, None, file_ext) - print(f"Playlist mode final path: '{final_path}'") + logger.info(f"Playlist mode final path: '{final_path}'") # RACE CONDITION GUARD: If source file is gone but destination exists, # another thread (stream processor or verification worker) already moved it. # Return early to avoid deleting the successfully processed file. if not os.path.exists(file_path): if os.path.exists(final_path): - print(f"[Playlist Folder Mode] Source gone but destination exists ā€” already processed by another thread: {os.path.basename(final_path)}") + logger.info(f"[Playlist Folder Mode] Source gone but destination exists ā€” already processed by another thread: {os.path.basename(final_path)}") context['_final_processed_path'] = final_path return else: @@ -21329,7 +21201,7 @@ def _post_process_matched_download(context_key, context, file_path): context['_audio_quality'] = _get_audio_quality_string(file_path) if context['_audio_quality']: - print(f"Audio quality detected: {context['_audio_quality']}") + logger.info(f"Audio quality detected: {context['_audio_quality']}") # FLAC bit depth filter if _check_flac_bit_depth(file_path, context, context_key): @@ -21337,7 +21209,7 @@ def _post_process_matched_download(context_key, context, file_path): # Enhance metadata before moving try: - print(f"[Metadata Input] Playlist mode - artist: '{spotify_artist.get('name', 'MISSING')}' (id: {spotify_artist.get('id', 'MISSING')})") + logger.warning(f"[Metadata Input] Playlist mode - artist: '{spotify_artist.get('name', 'MISSING')}' (id: {spotify_artist.get('id', 'MISSING')})") _enhance_file_metadata(file_path, context, spotify_artist, None) except Exception as meta_err: import traceback @@ -21345,7 +21217,7 @@ def _post_process_matched_download(context_key, context, file_path): _wipe_source_tags(file_path) # Move file to playlist folder - print(f"Moving '{os.path.basename(file_path)}' to '{final_path}'") + logger.info(f"Moving '{os.path.basename(file_path)}' to '{final_path}'") _safe_move_file(file_path, final_path) # Store final path for verification wrapper (before conversions may override) @@ -21378,13 +21250,13 @@ def _post_process_matched_download(context_key, context, file_path): downloads_path = docker_resolve_path(config_manager.get('soulseek.download_path', './downloads')) _cleanup_empty_directories(downloads_path, file_path) - print(f"[Playlist Folder Mode] Post-processing complete: {final_path}") + logger.info(f"[Playlist Folder Mode] Post-processing complete: {final_path}") # WISHLIST REMOVAL: Check if this track should be removed from wishlist try: _check_and_remove_from_wishlist(context) except Exception as wishlist_error: - print(f"[Playlist Folder] Error checking wishlist removal: {wishlist_error}") + logger.error(f"[Playlist Folder] Error checking wishlist removal: {wishlist_error}") _emit_track_downloaded(context) _record_library_history_download(context) @@ -21399,7 +21271,7 @@ def _post_process_matched_download(context_key, context, file_path): if task_id in download_tasks: download_tasks[task_id]['stream_processed'] = True download_tasks[task_id]['status'] = 'completed' - print(f"[Playlist Folder Mode] Marked task {task_id} as completed") + logger.info(f"[Playlist Folder Mode] Marked task {task_id} as completed") _on_download_completed(batch_id, task_id, success=True) return # Skip normal album/artist folder structure processing @@ -21409,7 +21281,7 @@ def _post_process_matched_download(context_key, context, file_path): if is_album_download and has_clean_spotify_data: # Build album_info directly from clean Spotify metadata (GUI PARITY) - print("Album context with clean Spotify data found - using direct album info") + logger.info("Album context with clean Spotify data found - using direct album info") original_search = context.get("original_search_result", {}) spotify_album = context.get("spotify_album", {}) @@ -21417,11 +21289,12 @@ def _post_process_matched_download(context_key, context, file_path): clean_track_name = original_search.get('spotify_clean_title', 'Unknown Track') clean_album_name = original_search.get('spotify_clean_album', 'Unknown Album') - # DEBUG: Check what's in original_search - print(f"[DEBUG] Path 1 - Clean Spotify data path:") - print(f" original_search keys: {list(original_search.keys())}") - print(f" track_number in original_search: {'track_number' in original_search}") - print(f" track_number value: {original_search.get('track_number', 'NOT_FOUND')}") + logger.debug( + "Path 1 - Clean Spotify data path: keys=%s has_track_number=%s track_number=%s", + list(original_search.keys()), + 'track_number' in original_search, + original_search.get('track_number', 'NOT_FOUND'), + ) album_info = { 'is_album': True, @@ -21434,20 +21307,21 @@ def _post_process_matched_download(context_key, context, file_path): 'source': 'clean_spotify_metadata' } - print(f"Using clean Spotify album: '{clean_album_name}' for track: '{clean_track_name}'") + logger.info(f"Using clean Spotify album: '{clean_album_name}' for track: '{clean_track_name}'") elif is_album_download: # CRITICAL FIX: Album context without clean Spotify data - still force album treatment - print("Album context found but no clean Spotify data - using enhanced fallback") + logger.warning("Album context found but no clean Spotify data - using enhanced fallback") original_search = context.get("original_search_result", {}) spotify_album = context.get("spotify_album", {}) clean_track_name = original_search.get('spotify_clean_title') or original_search.get('title', 'Unknown Track') - # DEBUG: Check what's in original_search for path 2 - print(f"[DEBUG] Path 2 - Enhanced fallback album context path:") - print(f" original_search keys: {list(original_search.keys())}") - print(f" track_number in original_search: {'track_number' in original_search}") - print(f" track_number value: {original_search.get('track_number', 'NOT_FOUND')}") - print(f" spotify_album name: {spotify_album.get('name', 'NOT_FOUND')}") + logger.debug( + "Path 2 - Enhanced fallback album context path: keys=%s has_track_number=%s track_number=%s spotify_album=%s", + list(original_search.keys()), + 'track_number' in original_search, + original_search.get('track_number', 'NOT_FOUND'), + spotify_album.get('name', 'NOT_FOUND'), + ) # ENHANCEMENT: Use spotify_clean_album if available for consistency album_name = (original_search.get('spotify_clean_album') or @@ -21464,10 +21338,10 @@ def _post_process_matched_download(context_key, context, file_path): 'confidence': 0.9, # Higher confidence - user explicitly chose album 'source': 'enhanced_fallback_album_context' } - print(f"[FORCED ALBUM] Using album: '{album_name}' for track: '{clean_track_name}'") + logger.info(f"[FORCED ALBUM] Using album: '{album_name}' for track: '{clean_track_name}'") else: # For singles, we still need to detect if they belong to an album. - print("Single track download - attempting album detection") + logger.info("Single track download - attempting album detection") album_info = _detect_album_info_web(context, spotify_artist) # --- Album grouping resolution --- @@ -21475,8 +21349,11 @@ def _post_process_matched_download(context_key, context, file_path): # Explicit album downloads already have the correct Spotify album name ā€” # re-grouping would mangle names like "(Reworked and Remastered)" into "(Deluxe Edition)". if album_info and album_info['is_album'] and not is_album_download: - print(f"\nSMART ALBUM GROUPING for track: '{album_info.get('clean_track_name', 'Unknown')}'") - print(f" Original album: '{album_info.get('album_name', 'None')}'") + logger.info( + "SMART ALBUM GROUPING for track=%r original_album=%r", + album_info.get('clean_track_name', 'Unknown'), + album_info.get('album_name', 'None'), + ) # Get original album name from context if available original_album = None @@ -21487,17 +21364,18 @@ def _post_process_matched_download(context_key, context, file_path): consistent_album_name = _resolve_album_group(spotify_artist, album_info, original_album) album_info['album_name'] = consistent_album_name - print(f" Final album name: '{consistent_album_name}'") - print(f"Album grouping complete!\n") + logger.info("Album grouping complete: final_album=%r", consistent_album_name) elif album_info and album_info['is_album'] and is_album_download: - print(f"\nEXPLICIT ALBUM DOWNLOAD - preserving Spotify album name: '{album_info.get('album_name', 'None')}'") - print(f" Skipping smart grouping (not needed for explicit album downloads)\n") + logger.info( + "EXPLICIT ALBUM DOWNLOAD - preserving Spotify album name=%r; skipping smart grouping", + album_info.get('album_name', 'None'), + ) # 1. Get transfer path (directory creation handled by _build_final_path_for_track) file_ext = os.path.splitext(file_path)[1] context['_audio_quality'] = _get_audio_quality_string(file_path) if context['_audio_quality']: - print(f"Audio quality detected: {context['_audio_quality']}") + logger.info(f"Audio quality detected: {context['_audio_quality']}") # FLAC bit depth filter if _check_flac_bit_depth(file_path, context, context_key): @@ -21514,46 +21392,50 @@ def _post_process_matched_download(context_key, context, file_path): # Priority 1: Spotify clean title from context if original_search.get('spotify_clean_title'): clean_track_name = original_search['spotify_clean_title'] - print(f"Using Spotify clean title: '{clean_track_name}'") + logger.info(f"Using Spotify clean title: '{clean_track_name}'") # Priority 2: Album info clean name elif album_info.get('clean_track_name'): clean_track_name = album_info['clean_track_name'] - print(f"Using album info clean name: '{clean_track_name}'") + logger.info(f"Using album info clean name: '{clean_track_name}'") # Priority 3: Original title as fallback else: clean_track_name = original_search.get('title', 'Unknown Track') - print(f"Using original title as fallback: '{clean_track_name}'") + logger.warning(f"Using original title as fallback: '{clean_track_name}'") final_track_name_sanitized = _sanitize_filename(clean_track_name) track_number = album_info['track_number'] - # DEBUG: Check final track_number values - print(f"[DEBUG] Final track_number processing:") - print(f" album_info source: {album_info.get('source', 'unknown')}") - print(f" album_info track_number: {album_info.get('track_number', 'NOT_FOUND')}") - print(f" track_number variable: {track_number}") + logger.debug( + "Final track_number processing: source=%s album_info_track_number=%s track_number=%s", + album_info.get('source', 'unknown'), + album_info.get('track_number', 'NOT_FOUND'), + track_number, + ) # Fix: Handle None track_number if track_number is None: - print(f"Track number is None, extracting from filename: {os.path.basename(file_path)}") track_number = _extract_track_number_from_filename(file_path) - print(f" -> Extracted track number: {track_number}") + logger.info( + "Track number was None; extracted from filename=%r -> %s", + os.path.basename(file_path), + track_number, + ) # Ensure track_number is valid if not isinstance(track_number, int) or track_number < 1: - print(f"Invalid track number ({track_number}), defaulting to 1") + logger.error(f"Invalid track number ({track_number}), defaulting to 1") track_number = 1 - print(f"[DEBUG] FINAL track_number used for filename: {track_number}") + logger.debug(f"FINAL track_number used for filename: {track_number}") # CRITICAL FIX: Update album_info with corrected track_number for metadata enhancement album_info['track_number'] = track_number album_info['clean_track_name'] = clean_track_name # Ensure clean name is in album_info - print(f"[FIX] Updated album_info track_number to {track_number} for consistent metadata") + logger.info(f"[FIX] Updated album_info track_number to {track_number} for consistent metadata") # Use shared path builder for album mode final_path, _ = _build_final_path_for_track(context, spotify_artist, album_info, file_ext) - print(f"Album path: '{final_path}'") + logger.info(f"Album path: '{final_path}'") else: # Single track structure: Transfer/ARTIST/ARTIST - SINGLE/SINGLE.ext # --- GUI PARITY: Use multiple sources for clean track name --- @@ -21563,15 +21445,15 @@ def _post_process_matched_download(context_key, context, file_path): # Priority 1: Spotify clean title from context if original_search.get('spotify_clean_title'): clean_track_name = original_search['spotify_clean_title'] - print(f"Using Spotify clean title: '{clean_track_name}'") + logger.info(f"Using Spotify clean title: '{clean_track_name}'") # Priority 2: Album info clean name elif album_info and album_info.get('clean_track_name'): clean_track_name = album_info['clean_track_name'] - print(f"Using album info clean name: '{clean_track_name}'") + logger.info(f"Using album info clean name: '{clean_track_name}'") # Priority 3: Original title as fallback else: clean_track_name = original_search.get('title', 'Unknown Track') - print(f"Using original title as fallback: '{clean_track_name}'") + logger.warning(f"Using original title as fallback: '{clean_track_name}'") # Ensure clean name is in album_info for path builder if album_info: @@ -21579,7 +21461,7 @@ def _post_process_matched_download(context_key, context, file_path): # Use shared path builder for single mode final_path, _ = _build_final_path_for_track(context, spotify_artist, album_info, file_ext) - print(f"Single path: '{final_path}'") + logger.info(f"Single path: '{final_path}'") # Store the actual computed path so verification uses this exact path # instead of recomputing independently (which can produce mismatches) @@ -21587,11 +21469,11 @@ def _post_process_matched_download(context_key, context, file_path): # 3. Enhance metadata, move file, download art, and cleanup try: - print(f"[Metadata Input] artist: '{spotify_artist.get('name', 'MISSING')}' (id: {spotify_artist.get('id', 'MISSING')})") + logger.warning(f"[Metadata Input] artist: '{spotify_artist.get('name', 'MISSING')}' (id: {spotify_artist.get('id', 'MISSING')})") if album_info: - print(f"[Metadata Input] album: '{album_info.get('album_name', 'MISSING')}', track#: {album_info.get('track_number', 'MISSING')}, disc#: {album_info.get('disc_number', 'MISSING')}, source: {album_info.get('source', 'unknown')}") + logger.warning(f"[Metadata Input] album: '{album_info.get('album_name', 'MISSING')}', track#: {album_info.get('track_number', 'MISSING')}, disc#: {album_info.get('disc_number', 'MISSING')}, source: {album_info.get('source', 'unknown')}") else: - print(f"[Metadata Input] album_info: None (single track)") + logger.info(f"[Metadata Input] album_info: None (single track)") _enhance_file_metadata(file_path, context, spotify_artist, album_info) except Exception as meta_err: import traceback @@ -21609,12 +21491,12 @@ def _post_process_matched_download(context_key, context, file_path): _enhance_source_info = {} is_enhance_download = _enhance_source_info.get('enhance', False) - print(f"Moving '{os.path.basename(file_path)}' to '{final_path}'") + logger.info(f"Moving '{os.path.basename(file_path)}' to '{final_path}'") if os.path.exists(final_path): # PROTECTION: If destination already exists, check before overwriting # If the source file is gone, another thread already handled this - don't delete the destination if not os.path.exists(file_path): - print(f"[Protection] Destination exists and source already gone - file already transferred: {os.path.basename(final_path)}") + logger.info(f"[Protection] Destination exists and source already gone - file already transferred: {os.path.basename(final_path)}") return try: from mutagen import File as MutagenFile @@ -21629,50 +21511,50 @@ def _post_process_matched_download(context_key, context, file_path): _incoming_tier = _get_quality_tier_from_extension(file_path) if _incoming_tier[1] < _existing_tier[1]: # Incoming is higher quality (lower tier number) ā€” replace - print(f"[Quality Replace] Replacing {_existing_tier[0]} with {_incoming_tier[0]}: {os.path.basename(final_path)}") + logger.info(f"[Quality Replace] Replacing {_existing_tier[0]} with {_incoming_tier[0]}: {os.path.basename(final_path)}") try: os.remove(final_path) except Exception as e: - print(f"[Quality Replace] Could not remove existing file: {e}") + logger.error(f"[Quality Replace] Could not remove existing file: {e}") else: - print(f"[Protection] Existing file is same or better quality ({_existing_tier[0]} vs {_incoming_tier[0]}) - skipping: {os.path.basename(final_path)}") + logger.info(f"[Protection] Existing file is same or better quality ({_existing_tier[0]} vs {_incoming_tier[0]}) - skipping: {os.path.basename(final_path)}") try: os.remove(file_path) except FileNotFoundError: pass except Exception as e: - print(f"[Protection] Error removing redundant file: {e}") + logger.error(f"[Protection] Error removing redundant file: {e}") return else: - print(f"[Protection] Existing file already has metadata enhancement - skipping overwrite: {os.path.basename(final_path)}") - print(f"[Protection] Removing redundant download file: {os.path.basename(file_path)}") + logger.info(f"[Protection] Existing file already has metadata enhancement - skipping overwrite: {os.path.basename(final_path)}") + logger.info(f"[Protection] Removing redundant download file: {os.path.basename(file_path)}") try: os.remove(file_path) except FileNotFoundError: - print(f"[Protection] Could not remove redundant file (already gone): {file_path}") + logger.error(f"[Protection] Could not remove redundant file (already gone): {file_path}") except Exception as e: - print(f"[Protection] Error removing redundant file: {e}") + logger.error(f"[Protection] Error removing redundant file: {e}") return # Don't overwrite the good file elif is_enhance_download: # ENHANCE BYPASS: Allow overwrite ā€” backup original, then remove to allow move - print(f"[Enhance] Quality enhance mode ā€” replacing existing file: {os.path.basename(final_path)}") + logger.info(f"[Enhance] Quality enhance mode ā€” replacing existing file: {os.path.basename(final_path)}") try: os.remove(final_path) except Exception as e: - print(f"[Enhance] Could not remove existing file for replacement: {e}") + logger.error(f"[Enhance] Could not remove existing file for replacement: {e}") else: - print(f"[Protection] Existing file lacks metadata - safe to overwrite: {os.path.basename(final_path)}") + logger.info(f"[Protection] Existing file lacks metadata - safe to overwrite: {os.path.basename(final_path)}") try: os.remove(final_path) except FileNotFoundError: pass # It was just there, but now gone? except Exception as check_error: - print(f"[Protection] Error checking existing file metadata, proceeding with overwrite: {check_error}") + logger.error(f"[Protection] Error checking existing file metadata, proceeding with overwrite: {check_error}") try: if os.path.exists(final_path): os.remove(final_path) except Exception as e: - print(f"[Protection] Failed to remove existing file for overwrite: {e}") + logger.error(f"[Protection] Failed to remove existing file for overwrite: {e}") # --- PRE-MOVE SOURCE CHECK --- # Right before moving, verify the source file still exists. @@ -21680,7 +21562,7 @@ def _post_process_matched_download(context_key, context, file_path): # already moved this file during the sleep + metadata enhancement window. if not os.path.exists(file_path): if os.path.exists(final_path): - print(f"[Pre-Move] Source already gone and destination exists - another thread completed transfer: {os.path.basename(final_path)}") + logger.info(f"[Pre-Move] Source already gone and destination exists - another thread completed transfer: {os.path.basename(final_path)}") # Still do cover art + lyrics since the other thread might not have finished those _download_cover_art(album_info, os.path.dirname(final_path), context) _generate_lrc_file(final_path, context, spotify_artist, album_info) @@ -21708,13 +21590,13 @@ def _post_process_matched_download(context_key, context, file_path): found_variant = os.path.join(expected_dir, f) break if found_variant: - print(f"[Pre-Move] Source gone but found variant in destination (stream processor handled it): {os.path.basename(found_variant)}") + logger.debug(f"[Pre-Move] Source gone but found variant in destination (stream processor handled it): {os.path.basename(found_variant)}") context['_final_processed_path'] = found_variant _download_cover_art(album_info, expected_dir, context) _generate_lrc_file(found_variant, context, spotify_artist, album_info) return else: - print(f"[Pre-Move] Source file gone and no matching file in destination: {os.path.basename(file_path)}") + logger.warning(f"[Pre-Move] Source file gone and no matching file in destination: {os.path.basename(file_path)}") raise FileNotFoundError(f"Source file vanished before move and destination does not exist: {file_path}") _safe_move_file(file_path, final_path) @@ -21727,13 +21609,13 @@ def _post_process_matched_download(context_key, context, file_path): os.remove(original_enhance_path) old_fmt = os.path.splitext(original_enhance_path)[1] new_fmt = os.path.splitext(final_path)[1] - print(f"[Enhance] Upgraded {old_fmt} ā†’ {new_fmt}: {os.path.basename(final_path)}") + logger.info(f"[Enhance] Upgraded {old_fmt} ā†’ {new_fmt}: {os.path.basename(final_path)}") except Exception as e: - print(f"[Enhance] Could not remove old-format file: {e}") + logger.error(f"[Enhance] Could not remove old-format file: {e}") elif is_enhance_download: old_fmt = _enhance_source_info.get('original_format', 'unknown') new_fmt = os.path.splitext(final_path)[1] - print(f"[Enhance] Replaced in-place ({old_fmt} ā†’ {new_fmt}): {os.path.basename(final_path)}") + logger.info(f"[Enhance] Replaced in-place ({old_fmt} ā†’ {new_fmt}): {os.path.basename(final_path)}") _download_cover_art(album_info, os.path.dirname(final_path), context) @@ -21766,7 +21648,7 @@ def _post_process_matched_download(context_key, context, file_path): downloads_path = docker_resolve_path(config_manager.get('soulseek.download_path', './downloads')) _cleanup_empty_directories(downloads_path, file_path) - print(f"Post-processing complete for: {context.get('_final_processed_path', final_path)}") + logger.info(f"Post-processing complete for: {context.get('_final_processed_path', final_path)}") _emit_track_downloaded(context) _record_library_history_download(context) @@ -21779,7 +21661,7 @@ def _post_process_matched_download(context_key, context, file_path): completed_path = context.get('_final_processed_path', final_path) _record_retag_download(context, spotify_artist, album_info, completed_path) except Exception as retag_err: - print(f"[Post-Process] Retag data capture failed (non-fatal): {retag_err}") + logger.error(f"[Post-Process] Retag data capture failed (non-fatal): {retag_err}") # REPAIR: Register album folder for repair scanning when batch completes try: @@ -21790,7 +21672,7 @@ def _post_process_matched_download(context_key, context, file_path): if album_folder: repair_worker.register_folder(batch_id_for_repair, album_folder) except Exception as repair_err: - print(f"[Post-Process] Repair folder registration failed: {repair_err}") + logger.error(f"[Post-Process] Repair folder registration failed: {repair_err}") # ALBUM CONSISTENCY: Register completed file for post-batch MB tag reconciliation try: @@ -21808,19 +21690,19 @@ def _post_process_matched_download(context_key, context, file_path): if batch_id_for_consistency in download_batches: download_batches[batch_id_for_consistency].setdefault('_consistency_files', []).append(_file_info) except Exception as cons_err: - print(f"[Post-Process] Album consistency registration failed: {cons_err}") + logger.error(f"[Post-Process] Album consistency registration failed: {cons_err}") # WISHLIST REMOVAL: Check if this track should be removed from wishlist after successful download try: _check_and_remove_from_wishlist(context) except Exception as wishlist_error: - print(f"[Post-Process] Error checking wishlist removal: {wishlist_error}") + logger.error(f"[Post-Process] Error checking wishlist removal: {wishlist_error}") # Call completion callback for missing downloads tasks to start next batch task_id = context.get('task_id') batch_id = context.get('batch_id') if task_id and batch_id: - print(f"[Post-Process] Calling completion callback for task {task_id} in batch {batch_id}") + logger.info(f"[Post-Process] Calling completion callback for task {task_id} in batch {batch_id}") # Mark task as stream processed and set terminal status so # _validate_worker_counts won't count this task as active @@ -21832,7 +21714,7 @@ def _post_process_matched_download(context_key, context, file_path): if task_id in download_tasks: download_tasks[task_id]['stream_processed'] = True download_tasks[task_id]['status'] = 'completed' - print(f"[Post-Process] Marked task {task_id} as completed") + logger.info(f"[Post-Process] Marked task {task_id} as completed") _on_download_completed(batch_id, task_id, success=True) @@ -21840,7 +21722,7 @@ def _post_process_matched_download(context_key, context, file_path): import traceback pp_logger.info(f"[inner] EXCEPTION in post-processing for {context_key}: {e}") pp_logger.info(traceback.format_exc()) - print(f"\nCRITICAL ERROR in post-processing for {context_key}: {e}") + logger.error(f"\nCRITICAL ERROR in post-processing for {context_key}: {e}") traceback.print_exc() # Only retry if the source file still exists - otherwise retrying is pointless @@ -21851,15 +21733,15 @@ def _post_process_matched_download(context_key, context, file_path): # Remove from processed set so it can be retried if context_key in _processed_download_ids: _processed_download_ids.remove(context_key) - print(f"Removed {context_key} from processed set - will retry on next check") + logger.warning(f"Removed {context_key} from processed set - will retry on next check") # Re-add to matched context for retry with matched_context_lock: if context_key not in matched_downloads_context: matched_downloads_context[context_key] = context - print(f"Re-added {context_key} to context for retry") + logger.warning(f"Re-added {context_key} to context for retry") else: - print(f"Source file gone, not retrying: {context_key}") + logger.warning(f"Source file gone, not retrying: {context_key}") finally: file_lock.release() # Clean up the lock entry to prevent unbounded memory growth @@ -21957,7 +21839,7 @@ def _record_retag_download(context, spotify_artist, album_info, final_path): title=title, file_path=str(final_path), file_format=file_format, spotify_track_id=spotify_track_id, itunes_track_id=itunes_track_id ) - print(f"[Retag] Recorded track for retag: '{title}' in '{album_name}'") + logger.info(f"[Retag] Recorded track for retag: '{title}' in '{album_name}'") # Cap retag groups at 100, remove oldest db.trim_retag_groups(100) @@ -22056,7 +21938,7 @@ def _execute_retag(group_id, album_id): if best_match: matched_pairs.append((existing_track, best_match)) else: - print(f"[Retag] No match found for track: '{existing_track.get('title')}'") + logger.warning(f"[Retag] No match found for track: '{existing_track.get('title')}'") matched_pairs.append((existing_track, None)) with retag_lock: @@ -22078,7 +21960,7 @@ def _execute_retag(group_id, album_id): # Verify file exists if not os.path.exists(current_file_path): - print(f"[Retag] File not found, skipping: {current_file_path}") + logger.warning(f"[Retag] File not found, skipping: {current_file_path}") with retag_lock: retag_state['processed'] += 1 retag_state['progress'] = int(retag_state['processed'] / retag_state['total_tracks'] * 100) @@ -22120,9 +22002,9 @@ def _execute_retag(group_id, album_id): # Re-write metadata tags try: _enhance_file_metadata(current_file_path, context, new_artist, album_info) - print(f"[Retag] Re-tagged: '{track_title}'") + logger.info(f"[Retag] Re-tagged: '{track_title}'") except Exception as meta_err: - print(f"[Retag] Metadata write failed for '{track_title}': {meta_err}") + logger.error(f"[Retag] Metadata write failed for '{track_title}': {meta_err}") # Compute new path and move if different file_ext = os.path.splitext(current_file_path)[1] @@ -22130,7 +22012,7 @@ def _execute_retag(group_id, album_id): new_path, _ = _build_final_path_for_track(context, new_artist, album_info, file_ext) if os.path.normpath(current_file_path) != os.path.normpath(new_path): - print(f"[Retag] Moving '{os.path.basename(current_file_path)}' -> '{new_path}'") + logger.info(f"[Retag] Moving '{os.path.basename(current_file_path)}' -> '{new_path}'") old_dir = os.path.dirname(current_file_path) os.makedirs(os.path.dirname(new_path), exist_ok=True) _safe_move_file(current_file_path, new_path) @@ -22142,9 +22024,9 @@ def _execute_retag(group_id, album_id): new_lyrics = os.path.splitext(new_path)[0] + lyrics_ext try: _safe_move_file(old_lyrics, new_lyrics) - print(f"[Retag] Moved {lyrics_ext} file alongside audio") + logger.info(f"[Retag] Moved {lyrics_ext} file alongside audio") except Exception as lrc_err: - print(f"[Retag] Failed to move {lyrics_ext} file: {lrc_err}") + logger.error(f"[Retag] Failed to move {lyrics_ext} file: {lrc_err}") # Remove old cover.jpg if directory changed and old dir is now empty of audio new_dir = os.path.dirname(new_path) @@ -22158,7 +22040,7 @@ def _execute_retag(group_id, album_id): if not remaining_audio: try: os.remove(old_cover) - print(f"[Retag] Removed orphaned cover.jpg from old directory") + logger.warning(f"[Retag] Removed orphaned cover.jpg from old directory") except Exception: pass @@ -22170,15 +22052,15 @@ def _execute_retag(group_id, album_id): db.update_retag_track_path(existing_track['id'], str(new_path)) current_file_path = new_path else: - print(f"[Retag] Path unchanged for '{track_title}', no move needed") + logger.warning(f"[Retag] Path unchanged for '{track_title}', no move needed") except Exception as move_err: - print(f"[Retag] Path/move failed for '{track_title}': {move_err}") + logger.error(f"[Retag] Path/move failed for '{track_title}': {move_err}") # Download cover art to album directory try: _download_cover_art(album_info, os.path.dirname(current_file_path), context) except Exception as cover_err: - print(f"[Retag] Cover art download failed: {cover_err}") + logger.error(f"[Retag] Cover art download failed: {cover_err}") with retag_lock: retag_state['processed'] += 1 @@ -22209,12 +22091,12 @@ def _execute_retag(group_id, album_id): "progress": 100, "current_track": "" }) - print(f"[Retag] Retag operation complete for group {group_id}") + logger.info(f"[Retag] Retag operation complete for group {group_id}") except Exception as e: import traceback - print(f"[Retag] Error during retag: {e}") - print(traceback.format_exc()) + logger.error(f"[Retag] Error during retag: {e}") + logger.error(traceback.format_exc()) with retag_lock: retag_state.update({ "status": "error", @@ -22239,17 +22121,17 @@ def _check_and_remove_from_wishlist(context): track_info = context.get('track_info', {}) if track_info.get('id'): spotify_track_id = track_info['id'] - print(f"[Wishlist] Found Spotify ID from track_info: {spotify_track_id}") + logger.info(f"[Wishlist] Found Spotify ID from track_info: {spotify_track_id}") # Method 2: From original search result elif context.get('original_search_result', {}).get('id'): spotify_track_id = context['original_search_result']['id'] - print(f"[Wishlist] Found Spotify ID from original_search_result: {spotify_track_id}") + logger.info(f"[Wishlist] Found Spotify ID from original_search_result: {spotify_track_id}") # Method 3: Check if this is a wishlist download (context has wishlist_id) elif 'wishlist_id' in track_info: wishlist_id = track_info['wishlist_id'] - print(f"[Wishlist] Found wishlist_id in context: {wishlist_id}") + logger.info(f"[Wishlist] Found wishlist_id in context: {wishlist_id}") # Get the Spotify track ID from the wishlist entry (search all profiles) database = get_database() @@ -22260,7 +22142,7 @@ def _check_and_remove_from_wishlist(context): for wl_track in wishlist_tracks: if wl_track.get('wishlist_id') == wishlist_id: spotify_track_id = wl_track.get('spotify_track_id') or wl_track.get('id') - print(f"[Wishlist] Found Spotify ID from wishlist entry: {spotify_track_id}") + logger.info(f"[Wishlist] Found Spotify ID from wishlist entry: {spotify_track_id}") break # Method 4: Try to construct ID from track metadata for fuzzy matching @@ -22269,7 +22151,7 @@ def _check_and_remove_from_wishlist(context): artist_name = _get_track_artist_name(track_info) or _get_track_artist_name(context.get('original_search_result', {})) if track_name and artist_name: - print(f"[Wishlist] No Spotify ID found, checking for fuzzy match: '{track_name}' by '{artist_name}'") + logger.warning(f"[Wishlist] No Spotify ID found, checking for fuzzy match: '{track_name}' by '{artist_name}'") # Get all wishlist tracks and find potential matches (search all profiles) if not wishlist_tracks: @@ -22293,22 +22175,22 @@ def _check_and_remove_from_wishlist(context): # Simple fuzzy matching if (wl_name == track_name.lower() and wl_artist_name == artist_name.lower()): spotify_track_id = wl_track.get('spotify_track_id') or wl_track.get('id') - print(f"[Wishlist] Found fuzzy match - Spotify ID: {spotify_track_id}") + logger.info(f"[Wishlist] Found fuzzy match - Spotify ID: {spotify_track_id}") break # If we found a Spotify track ID, remove it from wishlist if spotify_track_id: - print(f"[Wishlist] Attempting to remove track from wishlist: {spotify_track_id}") + logger.info(f"[Wishlist] Attempting to remove track from wishlist: {spotify_track_id}") removed = wishlist_service.mark_track_download_result(spotify_track_id, success=True) if removed: - print(f"[Wishlist] Successfully removed track from wishlist: {spotify_track_id}") + logger.info(f"[Wishlist] Successfully removed track from wishlist: {spotify_track_id}") else: - print(f"ā„¹ļø [Wishlist] Track not found in wishlist or already removed: {spotify_track_id}") + logger.warning(f"ā„¹ļø [Wishlist] Track not found in wishlist or already removed: {spotify_track_id}") else: - print(f"ā„¹ļø [Wishlist] No Spotify track ID found for wishlist removal check") + logger.warning(f"ā„¹ļø [Wishlist] No Spotify track ID found for wishlist removal check") except Exception as e: - print(f"[Wishlist] Error in wishlist removal check: {e}") + logger.error(f"[Wishlist] Error in wishlist removal check: {e}") import traceback traceback.print_exc() @@ -22326,13 +22208,13 @@ def _check_and_remove_track_from_wishlist_by_metadata(track_data): track_id = track_data.get('id', '') artists = track_data.get('artists', []) - print(f"[Analysis] Checking if track should be removed from wishlist: '{track_name}' (ID: {track_id})") + logger.info(f"[Analysis] Checking if track should be removed from wishlist: '{track_name}' (ID: {track_id})") # Method 1: Direct Spotify ID match if track_id: removed = wishlist_service.mark_track_download_result(track_id, success=True) if removed: - print(f"[Analysis] Removed track from wishlist via direct ID match: {track_id}") + logger.info(f"[Analysis] Removed track from wishlist via direct ID match: {track_id}") return True # Method 2: Fuzzy matching by name and artist if no direct ID match @@ -22346,7 +22228,7 @@ def _check_and_remove_track_from_wishlist_by_metadata(track_data): else: primary_artist = str(artists[0]) - print(f"[Analysis] No direct ID match, trying fuzzy match: '{track_name}' by '{primary_artist}'") + logger.warning(f"[Analysis] No direct ID match, trying fuzzy match: '{track_name}' by '{primary_artist}'") # Get all wishlist tracks and find matches (search all profiles) database = get_database() @@ -22372,14 +22254,14 @@ def _check_and_remove_track_from_wishlist_by_metadata(track_data): if spotify_track_id: removed = wishlist_service.mark_track_download_result(spotify_track_id, success=True) if removed: - print(f"[Analysis] Removed track from wishlist via fuzzy match: {spotify_track_id}") + logger.info(f"[Analysis] Removed track from wishlist via fuzzy match: {spotify_track_id}") return True - print(f"ā„¹ļø [Analysis] Track not found in wishlist or already removed: '{track_name}'") + logger.warning(f"ā„¹ļø [Analysis] Track not found in wishlist or already removed: '{track_name}'") return False except Exception as e: - print(f"[Analysis] Error checking wishlist removal by metadata: {e}") + logger.error(f"[Analysis] Error checking wishlist removal by metadata: {e}") import traceback traceback.print_exc() return False @@ -22397,7 +22279,7 @@ def _automatic_wishlist_cleanup_after_db_update(): db = MusicDatabase() active_server = config_manager.get_active_media_server() - print("[Auto Cleanup] Starting automatic wishlist cleanup after database update...") + logger.info("[Auto Cleanup] Starting automatic wishlist cleanup after database update...") # Get all wishlist tracks (across all profiles - cleanup is global) database = get_database() @@ -22406,10 +22288,10 @@ def _automatic_wishlist_cleanup_after_db_update(): for p in all_profiles: wishlist_tracks.extend(wishlist_service.get_wishlist_tracks_for_download(profile_id=p['id'])) if not wishlist_tracks: - print("[Auto Cleanup] No tracks in wishlist to clean up") + logger.warning("[Auto Cleanup] No tracks in wishlist to clean up") return - print(f"[Auto Cleanup] Found {len(wishlist_tracks)} tracks in wishlist") + logger.info(f"[Auto Cleanup] Found {len(wishlist_tracks)} tracks in wishlist") removed_count = 0 @@ -22444,11 +22326,11 @@ def _automatic_wishlist_cleanup_after_db_update(): if db_track and confidence >= 0.7: found_in_db = True - print(f"[Auto Cleanup] Track found in database: '{track_name}' by {artist_name} (confidence: {confidence:.2f})") + logger.info(f"[Auto Cleanup] Track found in database: '{track_name}' by {artist_name} (confidence: {confidence:.2f})") break except Exception as db_error: - print(f"[Auto Cleanup] Error checking database for track '{track_name}': {db_error}") + logger.error(f"[Auto Cleanup] Error checking database for track '{track_name}': {db_error}") continue # If found in database, remove from wishlist @@ -22457,14 +22339,14 @@ def _automatic_wishlist_cleanup_after_db_update(): removed = wishlist_service.mark_track_download_result(spotify_track_id, success=True) if removed: removed_count += 1 - print(f"[Auto Cleanup] Removed track from wishlist: '{track_name}' ({spotify_track_id})") + logger.info(f"[Auto Cleanup] Removed track from wishlist: '{track_name}' ({spotify_track_id})") except Exception as remove_error: - print(f"[Auto Cleanup] Error removing track from wishlist: {remove_error}") + logger.error(f"[Auto Cleanup] Error removing track from wishlist: {remove_error}") - print(f"[Auto Cleanup] Completed automatic cleanup: {removed_count} tracks removed from wishlist") + logger.info(f"[Auto Cleanup] Completed automatic cleanup: {removed_count} tracks removed from wishlist") except Exception as e: - print(f"[Auto Cleanup] Error in automatic wishlist cleanup: {e}") + logger.error(f"[Auto Cleanup] Error in automatic wishlist cleanup: {e}") import traceback traceback.print_exc() @@ -22539,16 +22421,54 @@ def get_version_info(): "subtitle": f"Version {SOULSYNC_VERSION} ā€” Latest Changes", "sections": [ { - "title": "MusicBrainz Search Tab", - "description": "Find tracks and albums on MusicBrainz's community database ā€” covers obscure music that Spotify/Deezer/iTunes miss", + "title": "Discography Backfill", + "description": "New maintenance job that fills gaps in your library ā€” scans each artist's full discography and finds what you're missing", "features": [ - "ā€¢ New tab in Enhanced Search and Global Search alongside existing sources", - "ā€¢ Searches recordings, releases, and artists on MusicBrainz", - "ā€¢ Cover art from Cover Art Archive (free, linked by release ID)", - "ā€¢ Click results to open download modal with full tracklist ā€” same flow as other sources", - "ā€¢ Smart query parsing splits 'Artist Title' into structured artist + title search", - "ā€¢ Deduplicates album results (keeps best version with date and art)", - "ā€¢ Always available ā€” public API, no authentication needed", + "ā€¢ Scans each artist in your library against metadata source discographies", + "ā€¢ Creates findings for missing tracks ā€” review and click 'Add to Wishlist' to queue downloads", + "ā€¢ Respects all content filters (live, remix, acoustic, compilation, instrumental)", + "ā€¢ Release type filters (album, EP, single) with configurable defaults", + "ā€¢ Opt-in, disabled by default ā€” runs weekly, processes up to 50 artists per run", + "ā€¢ Rate-limited to avoid hammering metadata APIs", + ], + }, + { + "title": "Multi-Artist Tagging", + "description": "Enhanced control over how multiple artists are written to audio file tags", + "features": [ + "ā€¢ Configurable artist separator: comma, semicolon, or slash", + "ā€¢ Multi-value ARTISTS tag for Navidrome/Jellyfin multi-artist linking", + "ā€¢ 'Move featured artists to title' mode ā€” primary artist in ARTIST tag, others as (feat. ...) in title", + "ā€¢ All opt-in with defaults matching current behavior", + ], + }, + { + "title": "Enriched Downloads Page", + "description": "Download cards now show rich metadata instead of just filenames", + "features": [ + "ā€¢ Album artwork thumbnail on each download card", + "ā€¢ Artist name, album name, and source badge", + "ā€¢ Quality badge appears after post-processing", + "ā€¢ Falls back gracefully for transfers without metadata context", + ], + }, + { + "title": "Template Variable Delimiters", + "description": "Use ${var} syntax to append literal text to template variables", + "features": [ + "ā€¢ ${albumtype}s produces 'Albums', 'Singles', 'EPs'", + "ā€¢ Both $var and ${var} syntaxes work in all templates", + "ā€¢ Validation updated to accept delimited variables", + ], + }, + { + "title": "Reorganize All Albums", + "description": "Bulk reorganize all albums for an artist from the enhanced library view", + "features": [ + "ā€¢ New 'Reorganize All' button in the artist header", + "ā€¢ Processes albums sequentially with progress toasts", + "ā€¢ Continues on error ā€” one failed album doesn't block the rest", + "ā€¢ Uses the same template and endpoint as per-album reorganize", ], }, { @@ -23923,7 +23843,7 @@ _OLD_V2_NOTES = r""" def _simple_monitor_task(): """The actual monitoring task that runs in the background thread. Search cleanup and download cleanup are now handled by system automations.""" - print("Simple background monitor started") + logger.info("Simple background monitor started") while not globals().get('IS_SHUTTING_DOWN', False): try: @@ -23944,15 +23864,15 @@ def _simple_monitor_task(): if current_time - data['first_attempt'] > 60 ] for key in stale_keys: - print(f"Cleaning up stale retry attempt: {key}") + logger.warning(f"Cleaning up stale retry attempt: {key}") del _download_retry_attempts[key] time.sleep(1) except Exception as e: - print(f"Simple monitor error: {e}") + logger.error(f"Simple monitor error: {e}") time.sleep(10) - print("Simple background monitor stopped") + logger.info("Simple background monitor stopped") def start_simple_background_monitor(): """Starts the simple background monitor thread.""" @@ -23970,7 +23890,7 @@ def _sanitize_track_data_for_processing(track_data): Preserves album dict to retain full metadata (images, id, etc.) and normalizes artist field. """ if not isinstance(track_data, dict): - print(f"[Sanitize] Unexpected track data type: {type(track_data)}") + logger.info(f"[Sanitize] Unexpected track data type: {type(track_data)}") return track_data # Create a copy to avoid modifying original data @@ -23995,7 +23915,7 @@ def _sanitize_track_data_for_processing(track_data): processed_artists.append(str(artist)) sanitized['artists'] = processed_artists else: - print(f"[Sanitize] Unexpected artists format: {type(raw_artists)}") + logger.info(f"[Sanitize] Unexpected artists format: {type(raw_artists)}") sanitized['artists'] = [str(raw_artists)] if raw_artists else [] return sanitized @@ -24018,7 +23938,7 @@ def check_and_recover_stuck_flags(): time_stuck = current_time - wishlist_auto_processing_timestamp if time_stuck > stuck_timeout: stuck_minutes = time_stuck / 60 - print(f"[Stuck Detection] Wishlist auto-processing flag has been stuck for {stuck_minutes:.1f} minutes - RESETTING") + logger.info(f"[Stuck Detection] Wishlist auto-processing flag has been stuck for {stuck_minutes:.1f} minutes - RESETTING") with wishlist_timer_lock: wishlist_auto_processing = False wishlist_auto_processing_timestamp = 0 @@ -24030,7 +23950,7 @@ def check_and_recover_stuck_flags(): time_stuck = current_time - watchlist_auto_scanning_timestamp if time_stuck > stuck_timeout: stuck_minutes = time_stuck / 60 - print(f"[Stuck Detection] Watchlist auto-scanning flag has been stuck for {stuck_minutes:.1f} minutes - RESETTING") + logger.info(f"[Stuck Detection] Watchlist auto-scanning flag has been stuck for {stuck_minutes:.1f} minutes - RESETTING") with watchlist_timer_lock: watchlist_auto_scanning = False watchlist_auto_scanning_timestamp = 0 @@ -24055,7 +23975,7 @@ def is_wishlist_actually_processing(): # If more than 15 minutes, flag is stuck - auto-recover and return False if time_since_start > 900: # 15 minutes stuck_minutes = time_since_start / 60 - print(f"[Stuck Detection] Wishlist flag stuck for {stuck_minutes:.1f} minutes - auto-recovering") + logger.warning(f"[Stuck Detection] Wishlist flag stuck for {stuck_minutes:.1f} minutes - auto-recovering") check_and_recover_stuck_flags() return False @@ -24078,7 +23998,7 @@ def is_watchlist_actually_scanning(): # If more than 15 minutes, flag is stuck - auto-recover and return False if time_since_start > 900: # 15 minutes stuck_minutes = time_since_start / 60 - print(f"[Stuck Detection] Watchlist flag stuck for {stuck_minutes:.1f} minutes - auto-recovering") + logger.warning(f"[Stuck Detection] Watchlist flag stuck for {stuck_minutes:.1f} minutes - auto-recovering") check_and_recover_stuck_flags() return False @@ -24125,13 +24045,13 @@ def _process_wishlist_automatically(automation_id=None): """Main automatic processing logic that runs in background thread.""" global wishlist_auto_processing, wishlist_auto_processing_timestamp - print("[Auto-Wishlist] Timer triggered - starting automatic wishlist processing...") + logger.info("[Auto-Wishlist] Timer triggered - starting automatic wishlist processing...") try: # CRITICAL FIX: Use smart stuck detection BEFORE acquiring lock # This prevents deadlock and handles stuck flags (2-hour timeout) if is_wishlist_actually_processing(): - print("[Auto-Wishlist] Already processing (verified with stuck detection), skipping.") + logger.info("[Auto-Wishlist] Already processing (verified with stuck detection), skipping.") return # Check conditions and set flag @@ -24140,7 +24060,7 @@ def _process_wishlist_automatically(automation_id=None): with wishlist_timer_lock: # Re-check inside lock to handle race conditions if wishlist_auto_processing: - print("[Auto-Wishlist] Already processing (race condition check), skipping.") + logger.info("[Auto-Wishlist] Already processing (race condition check), skipping.") should_skip_already_running = True else: @@ -24148,7 +24068,7 @@ def _process_wishlist_automatically(automation_id=None): import time wishlist_auto_processing = True wishlist_auto_processing_timestamp = time.time() - print(f"[Auto-Wishlist] Flag set at timestamp {wishlist_auto_processing_timestamp}") + logger.info(f"[Auto-Wishlist] Flag set at timestamp {wishlist_auto_processing_timestamp}") if should_skip_already_running: return @@ -24162,17 +24082,17 @@ def _process_wishlist_automatically(automation_id=None): database = get_database() all_profiles = database.get_all_profiles() count = sum(wishlist_service.get_wishlist_count(profile_id=p['id']) for p in all_profiles) - print(f"[Auto-Wishlist] Wishlist count check: {count} tracks found across {len(all_profiles)} profiles") + logger.info(f"[Auto-Wishlist] Wishlist count check: {count} tracks found across {len(all_profiles)} profiles") _update_automation_progress(automation_id, progress=10, phase='Checking wishlist', log_line=f'{count} tracks across {len(all_profiles)} profiles', log_type='info') if count == 0: - print("ā„¹ļø [Auto-Wishlist] No tracks in wishlist for auto-processing.") + logger.warning("ā„¹ļø [Auto-Wishlist] No tracks in wishlist for auto-processing.") with wishlist_timer_lock: wishlist_auto_processing = False wishlist_auto_processing_timestamp = 0 return - print(f"[Auto-Wishlist] Found {count} tracks in wishlist, starting automatic processing...") + logger.info(f"[Auto-Wishlist] Found {count} tracks in wishlist, starting automatic processing...") # Check if wishlist processing is already active (auto or manual) playlist_id = "wishlist" @@ -24182,7 +24102,7 @@ def _process_wishlist_automatically(automation_id=None): # Check for both auto ('wishlist') and manual ('wishlist_manual') batches if (batch_playlist_id in ['wishlist', 'wishlist_manual'] and batch_data.get('phase') not in ['complete', 'error', 'cancelled']): - print(f"Wishlist processing already active in another batch ({batch_playlist_id}), skipping automatic start") + logger.info(f"Wishlist processing already active in another batch ({batch_playlist_id}), skipping automatic start") with wishlist_timer_lock: wishlist_auto_processing = False return @@ -24192,15 +24112,15 @@ def _process_wishlist_automatically(automation_id=None): from database.music_database import MusicDatabase db = MusicDatabase() - print("[Auto-Wishlist] Cleaning duplicate tracks before processing...") + logger.warning("[Auto-Wishlist] Cleaning duplicate tracks before processing...") for p in all_profiles: duplicates_removed = db.remove_wishlist_duplicates(profile_id=p['id']) if duplicates_removed > 0: - print(f"[Auto-Wishlist] Removed {duplicates_removed} duplicate tracks from profile {p['id']}") + logger.warning(f"[Auto-Wishlist] Removed {duplicates_removed} duplicate tracks from profile {p['id']}") # CLEANUP: Remove tracks from wishlist that already exist in library # This prevents wasting bandwidth on tracks we already have - print("[Auto-Wishlist] Checking wishlist against library for already-owned tracks...") + logger.debug("[Auto-Wishlist] Checking wishlist against library for already-owned tracks...") cleanup_tracks = [] for p in all_profiles: cleanup_tracks.extend(wishlist_service.get_wishlist_tracks_for_download(profile_id=p['id'])) @@ -24245,12 +24165,12 @@ def _process_wishlist_automatically(automation_id=None): removed = wishlist_service.mark_track_download_result(spotify_track_id, success=True) if removed: cleanup_removed += 1 - print(f"[Auto-Wishlist] Removed already-owned track: '{track_name}' by {artist_name}") + logger.info(f"[Auto-Wishlist] Removed already-owned track: '{track_name}' by {artist_name}") except Exception as remove_error: - print(f"[Auto-Wishlist] Error removing track from wishlist: {remove_error}") + logger.error(f"[Auto-Wishlist] Error removing track from wishlist: {remove_error}") if cleanup_removed > 0: - print(f"[Auto-Wishlist] Cleaned up {cleanup_removed} already-owned tracks from wishlist") + logger.info(f"[Auto-Wishlist] Cleaned up {cleanup_removed} already-owned tracks from wishlist") _update_automation_progress(automation_id, progress=25, phase='Cleaned up duplicates', log_line=f'Removed {cleanup_removed} already-owned tracks', log_type='success') else: @@ -24262,7 +24182,7 @@ def _process_wishlist_automatically(automation_id=None): for p in all_profiles: raw_wishlist_tracks.extend(wishlist_service.get_wishlist_tracks_for_download(profile_id=p['id'])) if not raw_wishlist_tracks: - print("No tracks returned from wishlist service.") + logger.warning("No tracks returned from wishlist service.") with wishlist_timer_lock: wishlist_auto_processing = False wishlist_auto_processing_timestamp = 0 @@ -24286,8 +24206,8 @@ def _process_wishlist_automatically(automation_id=None): seen_track_ids_sanitation.add(spotify_track_id) if duplicates_found > 0: - print(f"[Auto-Wishlist] Found and removed {duplicates_found} duplicate tracks during sanitization") - print(f"[Auto-Wishlist] Sanitized {len(wishlist_tracks)} tracks from wishlist service") + logger.warning(f"[Auto-Wishlist] Found and removed {duplicates_found} duplicate tracks during sanitization") + logger.info(f"[Auto-Wishlist] Sanitized {len(wishlist_tracks)} tracks from wishlist service") # CYCLE FILTERING: Get current cycle and filter tracks by category with db._get_connection() as conn: @@ -24325,14 +24245,14 @@ def _process_wishlist_automatically(automation_id=None): # No ID - can't deduplicate safely, always add filtered_tracks.append(track) - print(f"[Auto-Wishlist] Current cycle: {current_cycle}") - print(f"[Auto-Wishlist] Filtered {len(filtered_tracks)}/{len(wishlist_tracks)} tracks for '{current_cycle}' category") + logger.info(f"[Auto-Wishlist] Current cycle: {current_cycle}") + logger.info(f"[Auto-Wishlist] Filtered {len(filtered_tracks)}/{len(wishlist_tracks)} tracks for '{current_cycle}' category") _update_automation_progress(automation_id, progress=40, phase=f'Processing {current_cycle}', log_line=f'Cycle: {current_cycle} ā€” {len(filtered_tracks)} tracks to process', log_type='info') # If no tracks in this category, skip to next cycle immediately if len(filtered_tracks) == 0: - print(f"ā„¹ļø [Auto-Wishlist] No {current_cycle} tracks in wishlist, toggling cycle and scheduling next run") + logger.warning(f"ā„¹ļø [Auto-Wishlist] No {current_cycle} tracks in wishlist, toggling cycle and scheduling next run") # Toggle cycle next_cycle = 'singles' if current_cycle == 'albums' else 'albums' @@ -24343,7 +24263,7 @@ def _process_wishlist_automatically(automation_id=None): VALUES ('wishlist_cycle', ?, CURRENT_TIMESTAMP) """, (next_cycle,)) conn.commit() - print(f"[Auto-Wishlist] Cycle toggled: {current_cycle} ā†’ {next_cycle}") + logger.info(f"[Auto-Wishlist] Cycle toggled: {current_cycle} ā†’ {next_cycle}") with wishlist_timer_lock: wishlist_auto_processing = False @@ -24386,7 +24306,7 @@ def _process_wishlist_automatically(automation_id=None): 'profile_id': 1 } - print(f"Starting automatic wishlist batch {batch_id} with {len(wishlist_tracks)} tracks") + logger.info(f"Starting automatic wishlist batch {batch_id} with {len(wishlist_tracks)} tracks") _update_automation_progress(automation_id, progress=50, phase=f'Downloading {len(wishlist_tracks)} tracks', log_line=f'Started batch: {len(wishlist_tracks)} {current_cycle}', log_type='success') @@ -24396,7 +24316,7 @@ def _process_wishlist_automatically(automation_id=None): # Don't mark auto_processing as False here - let completion handler do it except Exception as e: - print(f"Error in automatic wishlist processing: {e}") + logger.error(f"Error in automatic wishlist processing: {e}") import traceback traceback.print_exc() _update_automation_progress(automation_id, log_line=f'Error: {str(e)}', log_type='error') @@ -24411,7 +24331,7 @@ def _process_wishlist_automatically(automation_id=None): # =============================== def _db_update_progress_callback(current_item, processed, total, percentage): - print(f"[DB Progress] {current_item} - {processed}/{total} ({percentage:.1f}%)") + logger.info(f"[DB Progress] {current_item} - {processed}/{total} ({percentage:.1f}%)") with db_update_lock: db_update_state.update({ "current_item": current_item, @@ -24424,7 +24344,7 @@ def _db_update_progress_callback(current_item, processed, total, percentage): current_item=current_item) def _db_update_phase_callback(phase): - print(f"[DB Phase] {phase}") + logger.info(f"[DB Phase] {phase}") with db_update_lock: db_update_state["phase"] = phase _update_automation_progress(_db_update_automation_id, phase=phase) @@ -24526,11 +24446,11 @@ def _db_update_finished_callback(total_artists, total_albums, total_tracks, succ # WISHLIST CLEANUP: Automatically clean up wishlist after database update try: - print("[DB Update] Database update completed, starting automatic wishlist cleanup...") + logger.info("[DB Update] Database update completed, starting automatic wishlist cleanup...") # Run cleanup in background to avoid blocking the UI missing_download_executor.submit(_automatic_wishlist_cleanup_after_db_update) except Exception as cleanup_error: - print(f"[DB Update] Error starting automatic wishlist cleanup: {cleanup_error}") + logger.error(f"[DB Update] Error starting automatic wishlist cleanup: {cleanup_error}") def _db_update_error_callback(error_message): global _db_update_automation_id @@ -24564,7 +24484,7 @@ def _pause_workers_for_scan(): w.pause() _workers_paused_by_scan.add(name) if _workers_paused_by_scan: - print(f"Paused {len(_workers_paused_by_scan)} workers during database scan: {', '.join(_workers_paused_by_scan)}") + logger.warning(f"Paused {len(_workers_paused_by_scan)} workers during database scan: {', '.join(_workers_paused_by_scan)}") def _resume_workers_after_scan(): """Resume only the workers that WE paused (don't resume manually-paused ones).""" @@ -24581,7 +24501,7 @@ def _resume_workers_after_scan(): w.resume() resumed += 1 if resumed: - print(f"Resumed {resumed} workers after database scan") + logger.info(f"Resumed {resumed} workers after database scan") _workers_paused_by_scan = set() def _run_soulsync_full_refresh(): @@ -24594,7 +24514,7 @@ def _run_soulsync_full_refresh(): _db_update_error_callback(f"Output folder not found: {transfer_path}") return - print(f"[SoulSync Full Refresh] Starting ā€” clearing soulsync data, re-scanning: {transfer_path}") + logger.info(f"[SoulSync Full Refresh] Starting ā€” clearing soulsync data, re-scanning: {transfer_path}") _db_update_phase_callback('Clearing library...') db = get_database() @@ -24610,7 +24530,7 @@ def _run_soulsync_full_refresh(): audio_files.append(os.path.join(root, fname)) total = len(audio_files) - print(f"[SoulSync Full Refresh] Found {total} audio files, rebuilding library...") + logger.info(f"[SoulSync Full Refresh] Found {total} audio files, rebuilding library...") if total == 0: _db_update_finished_callback(0, 0, 0, 0, 0) return @@ -24690,11 +24610,11 @@ def _run_soulsync_full_refresh(): successful += 1 except Exception as e: failed += 1 - print(f"[SoulSync Full Refresh] Track insert error: {e}") + logger.error(f"[SoulSync Full Refresh] Track insert error: {e}") conn.commit() except Exception as e: - print(f"[SoulSync Full Refresh] DB error: {e}") + logger.error(f"[SoulSync Full Refresh] DB error: {e}") _db_update_error_callback(f"Database error: {e}") return @@ -24703,12 +24623,12 @@ def _run_soulsync_full_refresh(): summary = f"Full refresh complete: {successful} tracks from {album_count} albums by {artist_count} artists" if failed > 0: summary += f" ({failed} failed)" - print(f"[SoulSync Full Refresh] {summary}") + logger.info(f"[SoulSync Full Refresh] {summary}") add_activity_item("", "SoulSync Full Refresh", summary, "Now") _db_update_finished_callback(artist_count, album_count, total, successful, failed) except Exception as e: - print(f"[SoulSync Full Refresh] Error: {e}") + logger.error(f"[SoulSync Full Refresh] {e}") import traceback traceback.print_exc() _db_update_error_callback(f"Full refresh failed: {e}") @@ -24731,7 +24651,7 @@ def _run_soulsync_deep_scan(): _db_update_error_callback(f"Output folder not found: {transfer_path}") return - print(f"[SoulSync Deep Scan] Starting ā€” Transfer: {transfer_path}") + logger.info(f"[SoulSync Deep Scan] Starting ā€” Transfer: {transfer_path}") _db_update_phase_callback('scanning') # Phase 1: Collect all audio files in Transfer @@ -24742,7 +24662,7 @@ def _run_soulsync_deep_scan(): if os.path.splitext(filename)[1].lower() in audio_extensions: transfer_files.add(os.path.join(root, filename)) - print(f"[SoulSync Deep Scan] Found {len(transfer_files)} audio files in Transfer") + logger.info(f"[SoulSync Deep Scan] Found {len(transfer_files)} audio files in Transfer") # Phase 2: Get all soulsync file paths from DB db = get_database() @@ -24755,9 +24675,9 @@ def _run_soulsync_deep_scan(): if row['file_path']: db_paths.add(row['file_path']) except Exception as e: - print(f"[SoulSync Deep Scan] Error reading DB paths: {e}") + logger.error(f"[SoulSync Deep Scan] Error reading DB paths: {e}") - print(f"[SoulSync Deep Scan] {len(db_paths)} tracks in soulsync DB") + logger.info(f"[SoulSync Deep Scan] {len(db_paths)} tracks in soulsync DB") # Phase 3: Find untracked files (in Transfer but not in DB) untracked = transfer_files - db_paths @@ -24779,7 +24699,7 @@ def _run_soulsync_deep_scan(): shutil.move(file_path, dest_path) moved_count += 1 except Exception as e: - print(f"[SoulSync Deep Scan] Could not move {os.path.basename(file_path)}: {e}") + logger.error(f"[SoulSync Deep Scan] Could not move {os.path.basename(file_path)}: {e}") # Clean up empty directories in Transfer after moving files for root, dirs, files in os.walk(transfer_path, topdown=False): @@ -24825,9 +24745,9 @@ def _run_soulsync_deep_scan(): conn.commit() if orphan_albums > 0 or orphan_artists > 0: - print(f"[SoulSync Deep Scan] Cleaned up {orphan_albums} orphaned albums, {orphan_artists} orphaned artists") + logger.warning(f"[SoulSync Deep Scan] Cleaned up {orphan_albums} orphaned albums, {orphan_artists} orphaned artists") except Exception as e: - print(f"[SoulSync Deep Scan] Error cleaning stale records: {e}") + logger.error(f"[SoulSync Deep Scan] Error cleaning stale records: {e}") summary = f"Deep scan complete: {len(transfer_files)} files scanned" if moved_count > 0: @@ -24837,12 +24757,12 @@ def _run_soulsync_deep_scan(): if moved_count == 0 and stale_count == 0: summary += " ā€” library is clean" - print(f"[SoulSync Deep Scan] {summary}") + logger.info(f"[SoulSync Deep Scan] {summary}") add_activity_item("", "SoulSync Deep Scan", summary, "Now") _db_update_finished_callback(0, 0, len(transfer_files), moved_count + stale_count, 0) except Exception as e: - print(f"[SoulSync Deep Scan] Error: {e}") + logger.error(f"[SoulSync Deep Scan] {e}") import traceback traceback.print_exc() _db_update_error_callback(f"Deep scan failed: {e}") @@ -24858,7 +24778,7 @@ def _run_db_update_task(full_refresh, server_type): _run_soulsync_full_refresh() else: # Incremental: library updates at download/import time, nothing to do - print("[SoulSync Standalone] Incremental scan skipped ā€” library updates at download time. Use Deep Scan or Full Refresh.") + logger.warning("[SoulSync Standalone] Incremental scan skipped ā€” library updates at download time. Use Deep Scan or Full Refresh.") _db_update_finished_callback(0, 0, 0, 0, 0) return @@ -24962,7 +24882,7 @@ def get_database_stats(): stats = db.get_database_info_for_server() return jsonify(stats) except Exception as e: - print(f"Error getting database stats: {e}") + logger.error(f"Error getting database stats: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/wishlist/process', methods=['POST']) @@ -24990,7 +24910,7 @@ def get_wishlist_count(): count = wishlist_service.get_wishlist_count(profile_id=get_current_profile_id()) return jsonify({"count": count}) except Exception as e: - print(f"Error getting wishlist count: {e}") + logger.error(f"Error getting wishlist count: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/wishlist/stats', methods=['GET']) @@ -25059,7 +24979,7 @@ def get_wishlist_stats(): }) except Exception as e: - print(f"Error getting wishlist stats: {e}") + logger.error(f"Error getting wishlist stats: {e}") import traceback traceback.print_exc() return jsonify({"error": str(e)}), 500 @@ -25096,7 +25016,7 @@ def get_wishlist_cycle(): return jsonify({"cycle": cycle}) except Exception as e: - print(f"Error getting wishlist cycle: {e}") + logger.error(f"Error getting wishlist cycle: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/wishlist/cycle', methods=['POST']) @@ -25126,11 +25046,11 @@ def set_wishlist_cycle(): """, (cycle,)) conn.commit() - print(f"Wishlist cycle set to: {cycle}") + logger.info(f"Wishlist cycle set to: {cycle}") return jsonify({"success": True, "cycle": cycle}) except Exception as e: - print(f"Error setting wishlist cycle: {e}") + logger.error(f"Error setting wishlist cycle: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/discovery/lookback-period', methods=['GET']) @@ -25165,7 +25085,7 @@ def get_discovery_lookback_period(): return jsonify({"period": period}) except Exception as e: - print(f"Error getting discovery lookback period: {e}") + logger.error(f"Error getting discovery lookback period: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/discovery/lookback-period', methods=['POST']) @@ -25213,11 +25133,11 @@ def set_discovery_lookback_period(): conn.commit() - print(f"Discovery lookback period set to: {period}") + logger.info(f"Discovery lookback period set to: {period}") return jsonify({"success": True, "period": period}) except Exception as e: - print(f"Error setting discovery lookback period: {e}") + logger.error(f"Error setting discovery lookback period: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/discovery/hemisphere', methods=['GET']) @@ -25293,9 +25213,9 @@ def get_wishlist_tracks(): db = MusicDatabase() duplicates_removed = db.remove_wishlist_duplicates(profile_id=get_current_profile_id()) if duplicates_removed > 0: - print(f"Cleaned {duplicates_removed} duplicate tracks from wishlist") + logger.warning(f"Cleaned {duplicates_removed} duplicate tracks from wishlist") else: - print(f"Skipping wishlist duplicate cleanup - download in progress") + logger.warning(f"Skipping wishlist duplicate cleanup - download in progress") wishlist_service = get_wishlist_service() raw_tracks = wishlist_service.get_wishlist_tracks_for_download(profile_id=get_current_profile_id()) @@ -25318,7 +25238,7 @@ def get_wishlist_tracks(): seen_track_ids_sanitation.add(spotify_track_id) if duplicates_found > 0: - print(f"[API-Wishlist-Tracks] Found and removed {duplicates_found} duplicate tracks during sanitization") + logger.warning(f"[API-Wishlist-Tracks] Found and removed {duplicates_found} duplicate tracks during sanitization") # FILTER by category if specified if category: @@ -25347,7 +25267,7 @@ def get_wishlist_tracks(): # Count total in category (quick scan ā€” no heavy processing, just classification) total_in_category = sum(1 for t in sanitized_tracks if _classify_wishlist_track(t) == category) - print(f"Wishlist filter: {len(filtered_tracks)}/{total_in_category} tracks in '{category}' category (limit: {limit or 'none'})") + logger.info(f"Wishlist filter: {len(filtered_tracks)}/{total_in_category} tracks in '{category}' category (limit: {limit or 'none'})") return jsonify({"tracks": filtered_tracks, "category": category, "total": total_in_category}) # Apply limit to non-filtered results @@ -25355,7 +25275,7 @@ def get_wishlist_tracks(): result_tracks = sanitized_tracks[:limit] if limit else sanitized_tracks return jsonify({"tracks": result_tracks, "total": total_count}) except Exception as e: - print(f"Error getting wishlist tracks: {e}") + logger.error(f"Error getting wishlist tracks: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/wishlist/download_missing', methods=['POST']) @@ -25387,16 +25307,16 @@ def start_wishlist_missing_downloads(): # CRITICAL: Clean duplicates BEFORE fetching tracks to prevent count mismatches # This prevents the "11 tracks shown but 12 counted" bug - print("[Manual-Wishlist] Cleaning duplicate tracks before download...") + logger.warning("[Manual-Wishlist] Cleaning duplicate tracks before download...") db = MusicDatabase() manual_profile_id = get_current_profile_id() duplicates_removed = db.remove_wishlist_duplicates(profile_id=manual_profile_id) if duplicates_removed > 0: - print(f"[Manual-Wishlist] Removed {duplicates_removed} duplicate tracks") + logger.warning(f"[Manual-Wishlist] Removed {duplicates_removed} duplicate tracks") # CLEANUP: Remove tracks from wishlist that already exist in library # This prevents wasting bandwidth on tracks we already have - print("[Manual-Wishlist] Checking wishlist against library for already-owned tracks...") + logger.info("[Manual-Wishlist] Checking wishlist against library for already-owned tracks...") cleanup_tracks = wishlist_service.get_wishlist_tracks_for_download(profile_id=manual_profile_id) cleanup_removed = 0 @@ -25443,12 +25363,12 @@ def start_wishlist_missing_downloads(): removed = wishlist_service.mark_track_download_result(spotify_track_id, success=True) if removed: cleanup_removed += 1 - print(f"[Manual-Wishlist] Removed already-owned track: '{track_name}' by {artist_name}") + logger.info(f"[Manual-Wishlist] Removed already-owned track: '{track_name}' by {artist_name}") except Exception as remove_error: - print(f"[Manual-Wishlist] Error removing track from wishlist: {remove_error}") + logger.error(f"[Manual-Wishlist] Error removing track from wishlist: {remove_error}") if cleanup_removed > 0: - print(f"[Manual-Wishlist] Cleaned up {cleanup_removed} already-owned tracks from wishlist") + logger.info(f"[Manual-Wishlist] Cleaned up {cleanup_removed} already-owned tracks from wishlist") # Get wishlist tracks formatted for download modal (after cleanup) raw_wishlist_tracks = wishlist_service.get_wishlist_tracks_for_download(profile_id=manual_profile_id) @@ -25473,8 +25393,8 @@ def start_wishlist_missing_downloads(): seen_track_ids_sanitation.add(spotify_track_id) if duplicates_found > 0: - print(f"[Manual-Wishlist] Found and removed {duplicates_found} duplicate tracks during sanitization") - print(f"[Manual-Wishlist] Sanitized {len(wishlist_tracks)} tracks from wishlist service") + logger.warning(f"[Manual-Wishlist] Found and removed {duplicates_found} duplicate tracks during sanitization") + logger.info(f"[Manual-Wishlist] Sanitized {len(wishlist_tracks)} tracks from wishlist service") # FILTER BY TRACK IDs if specified (prioritized - prevents race conditions) if track_ids: @@ -25498,7 +25418,7 @@ def start_wishlist_missing_downloads(): seen_track_ids.add(tid) wishlist_tracks = filtered_tracks - print(f"[Manual-Wishlist] Filtered to {len(wishlist_tracks)} specific tracks by ID (preserving frontend display order)") + logger.info(f"[Manual-Wishlist] Filtered to {len(wishlist_tracks)} specific tracks by ID (preserving frontend display order)") # FILTER BY CATEGORY if specified and no track_ids (backward compatibility) elif category: @@ -25549,7 +25469,7 @@ def start_wishlist_missing_downloads(): filtered_tracks.append(track) wishlist_tracks = filtered_tracks - print(f"[Manual-Wishlist] Filtered to {len(wishlist_tracks)} tracks for category: {category}") + logger.info(f"[Manual-Wishlist] Filtered to {len(wishlist_tracks)} tracks for category: {category}") # Stamp original index on each track so task indices match frontend row order for i, track in enumerate(wishlist_tracks): @@ -25596,7 +25516,7 @@ def start_wishlist_missing_downloads(): }) except Exception as e: - print(f"Error starting wishlist download process: {e}") + logger.error(f"Error starting wishlist download process: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/wishlist/clear', methods=['POST']) @@ -25627,7 +25547,7 @@ def clear_wishlist(): wishlist_auto_processing_timestamp = 0 if cancelled_count > 0: - print(f"[Wishlist Clear] Cancelled {cancelled_count} active wishlist downloads") + logger.warning(f"[Wishlist Clear] Cancelled {cancelled_count} active wishlist downloads") add_activity_item("", "Wishlist Cleared", f"Wishlist cleared and {cancelled_count} downloads cancelled", "Now") return jsonify({"success": True, "message": "Wishlist cleared successfully", "cancelled_downloads": cancelled_count}) @@ -25635,7 +25555,7 @@ def clear_wishlist(): return jsonify({"success": False, "error": "Failed to clear wishlist"}), 500 except Exception as e: - print(f"Error clearing wishlist: {e}") + logger.error(f"Error clearing wishlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/wishlist/cleanup', methods=['POST']) @@ -25649,7 +25569,7 @@ def cleanup_wishlist(): db = MusicDatabase() active_server = config_manager.get_active_media_server() - print("[Wishlist Cleanup] Starting wishlist cleanup process...") + logger.info("[Wishlist Cleanup] Starting wishlist cleanup process...") # Get wishlist tracks for current profile cleanup_profile_id = get_current_profile_id() @@ -25657,7 +25577,7 @@ def cleanup_wishlist(): if not wishlist_tracks: return jsonify({"success": True, "message": "No tracks in wishlist to clean up", "removed_count": 0}) - print(f"[Wishlist Cleanup] Found {len(wishlist_tracks)} tracks in wishlist") + logger.info(f"[Wishlist Cleanup] Found {len(wishlist_tracks)} tracks in wishlist") removed_count = 0 processed_count = 0 @@ -25673,7 +25593,7 @@ def cleanup_wishlist(): if not track_name or not artists or not spotify_track_id: continue - print(f"[Wishlist Cleanup] Checking track {processed_count}/{len(wishlist_tracks)}: '{track_name}'") + logger.info(f"[Wishlist Cleanup] Checking track {processed_count}/{len(wishlist_tracks)}: '{track_name}'") # Check each artist found_in_db = False @@ -25696,11 +25616,11 @@ def cleanup_wishlist(): if db_track and confidence >= 0.7: found_in_db = True - print(f"[Wishlist Cleanup] Track found in database: '{track_name}' by {artist_name} (confidence: {confidence:.2f})") + logger.info(f"[Wishlist Cleanup] Track found in database: '{track_name}' by {artist_name} (confidence: {confidence:.2f})") break except Exception as db_error: - print(f"[Wishlist Cleanup] Error checking database for track '{track_name}': {db_error}") + logger.error(f"[Wishlist Cleanup] Error checking database for track '{track_name}': {db_error}") continue # If found in database, remove from wishlist @@ -25709,13 +25629,13 @@ def cleanup_wishlist(): removed = wishlist_service.mark_track_download_result(spotify_track_id, success=True) if removed: removed_count += 1 - print(f"[Wishlist Cleanup] Removed track from wishlist: '{track_name}' ({spotify_track_id})") + logger.info(f"[Wishlist Cleanup] Removed track from wishlist: '{track_name}' ({spotify_track_id})") else: - print(f"[Wishlist Cleanup] Failed to remove track from wishlist: '{track_name}' ({spotify_track_id})") + logger.error(f"[Wishlist Cleanup] Failed to remove track from wishlist: '{track_name}' ({spotify_track_id})") except Exception as remove_error: - print(f"[Wishlist Cleanup] Error removing track from wishlist: {remove_error}") + logger.error(f"[Wishlist Cleanup] Error removing track from wishlist: {remove_error}") - print(f"[Wishlist Cleanup] Completed cleanup: {removed_count} tracks removed from wishlist") + logger.info(f"[Wishlist Cleanup] Completed cleanup: {removed_count} tracks removed from wishlist") return jsonify({ "success": True, @@ -25725,7 +25645,7 @@ def cleanup_wishlist(): }) except Exception as e: - print(f"Error in wishlist cleanup: {e}") + logger.error(f"Error in wishlist cleanup: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -25948,20 +25868,20 @@ def add_album_track_to_wishlist(): ) if success: - print(f"Added track '{track.get('name')}' by '{artist.get('name')}' to wishlist") + logger.info(f"Added track '{track.get('name')}' by '{artist.get('name')}' to wishlist") return jsonify({ "success": True, "message": f"Added '{track.get('name')}' to wishlist" }) else: - print(f"Failed to add track '{track.get('name')}' to wishlist") + logger.error(f"Failed to add track '{track.get('name')}' to wishlist") return jsonify({ "success": False, "error": "Failed to add track to wishlist" }) except Exception as e: - print(f"Error adding track to wishlist: {e}") + logger.error(f"Error adding track to wishlist: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -26004,7 +25924,7 @@ def get_database_update_status(): with db_update_lock: # Debug: Log current state occasionally if db_update_state["status"] == "running": - print(f"[Status Check] {db_update_state['processed']}/{db_update_state['total']} ({db_update_state['progress']:.1f}%) - {db_update_state['phase']}") + logger.info(f"[Status Check] {db_update_state['processed']}/{db_update_state['total']} ({db_update_state['progress']:.1f}%) - {db_update_state['phase']}") return jsonify(db_update_state) @app.route('/api/database/update/stop', methods=['POST']) @@ -26152,7 +26072,10 @@ def restore_backup_endpoint(filename): pass version_warning = None - if backup_version and backup_version != SOULSYNC_VERSION: + # Compare base versions only (strip +commit suffix) to avoid false mismatches + _backup_base = backup_version.split('+')[0] if backup_version else None + _current_base = SOULSYNC_VERSION.split('+')[0] + if _backup_base and _backup_base != _current_base: # Allow restore but warn ā€” the caller must pass force=true to confirm force = request.json.get('force', False) if request.is_json else False if not force: @@ -26735,7 +26658,7 @@ def _run_quality_scanner(scope='watchlist', profile_id=1): quality_scanner_state["results"] = [] quality_scanner_state["error_message"] = "" - print(f"[Quality Scanner] Starting scan with scope: {scope}") + logger.info(f"[Quality Scanner] Starting scan with scope: {scope}") # Get database instance db = MusicDatabase() @@ -26760,7 +26683,7 @@ def _run_quality_scanner(scope='watchlist', profile_id=1): tier_num = QUALITY_TIERS[tier_name]['tier'] min_acceptable_tier = min(min_acceptable_tier, tier_num) - print(f"[Quality Scanner] Minimum acceptable tier: {min_acceptable_tier}") + logger.info(f"[Quality Scanner] Minimum acceptable tier: {min_acceptable_tier}") # Get tracks to scan based on scope with quality_scanner_lock: @@ -26774,12 +26697,12 @@ def _run_quality_scanner(scope='watchlist', profile_id=1): quality_scanner_state["status"] = "finished" quality_scanner_state["phase"] = "No watchlist artists found" quality_scanner_state["error_message"] = "Please add artists to watchlist first" - print(f"[Quality Scanner] No watchlist artists found") + logger.warning(f"[Quality Scanner] No watchlist artists found") return # Get artist names from watchlist artist_names = [artist.artist_name for artist in watchlist_artists] - print(f"[Quality Scanner] Scanning {len(artist_names)} watchlist artists") + logger.info(f"[Quality Scanner] Scanning {len(artist_names)} watchlist artists") # Get all tracks for these artists by name conn = db._get_connection() @@ -26809,7 +26732,7 @@ def _run_quality_scanner(scope='watchlist', profile_id=1): conn.close() total_tracks = len(tracks_to_scan) - print(f"[Quality Scanner] Found {total_tracks} tracks to scan") + logger.info(f"[Quality Scanner] Found {total_tracks} tracks to scan") with quality_scanner_lock: quality_scanner_state["total"] = total_tracks @@ -26821,7 +26744,7 @@ def _run_quality_scanner(scope='watchlist', profile_id=1): quality_scanner_state["status"] = "error" quality_scanner_state["phase"] = "Spotify not authenticated" quality_scanner_state["error_message"] = "Please authenticate with Spotify first" - print(f"[Quality Scanner] Spotify not authenticated") + logger.info(f"[Quality Scanner] Spotify not authenticated") return wishlist_service = get_wishlist_service() @@ -26830,7 +26753,7 @@ def _run_quality_scanner(scope='watchlist', profile_id=1): for idx, track_row in enumerate(tracks_to_scan, 1): # Check for stop request if quality_scanner_state.get('status') != 'running': - print(f"[Quality Scanner] Stop requested, halting at track {idx}/{total_tracks}") + logger.info(f"[Quality Scanner] Stop requested, halting at track {idx}/{total_tracks}") break try: @@ -26856,7 +26779,7 @@ def _run_quality_scanner(scope='watchlist', profile_id=1): with quality_scanner_lock: quality_scanner_state["low_quality"] += 1 - print(f"[Quality Scanner] Low quality: {artist_name} - {title} ({tier_name}, {file_path})") + logger.info(f"[Quality Scanner] Low quality: {artist_name} - {title} ({tier_name}, {file_path})") # Attempt to match to Spotify using matching_engine matched = False @@ -26871,7 +26794,7 @@ def _run_quality_scanner(scope='watchlist', profile_id=1): })() search_queries = matching_engine.generate_download_queries(temp_track) - print(f"[Quality Scanner] Generated {len(search_queries)} search queries for {artist_name} - {title}") + logger.info(f"[Quality Scanner] Generated {len(search_queries)} search queries for {artist_name} - {title}") # Find best match using confidence scoring best_match = None @@ -26915,31 +26838,31 @@ def _run_quality_scanner(scope='watchlist', profile_id=1): elif _at == 'ep': combined_confidence += 0.01 - print(f"[Quality Scanner] Candidate: '{spotify_track.artists[0]}' - '{spotify_track.name}' (confidence: {combined_confidence:.3f})") + logger.info(f"[Quality Scanner] Candidate: '{spotify_track.artists[0]}' - '{spotify_track.name}' (confidence: {combined_confidence:.3f})") # Update best match if this is better if combined_confidence > best_confidence and combined_confidence >= min_confidence: best_confidence = combined_confidence best_match = spotify_track - print(f"[Quality Scanner] New best match: {spotify_track.artists[0]} - {spotify_track.name} (confidence: {combined_confidence:.3f})") + logger.info(f"[Quality Scanner] New best match: {spotify_track.artists[0]} - {spotify_track.name} (confidence: {combined_confidence:.3f})") except Exception as e: - print(f"[Quality Scanner] Error scoring result: {e}") + logger.error(f"[Quality Scanner] Error scoring result: {e}") continue # If we found a very high confidence match, stop searching if best_confidence >= 0.9: - print(f"[Quality Scanner] High confidence match found ({best_confidence:.3f}), stopping search") + logger.info(f"[Quality Scanner] High confidence match found ({best_confidence:.3f}), stopping search") break except Exception as e: - print(f"[Quality Scanner] Error searching with query '{search_query}': {e}") + logger.debug(f"[Quality Scanner] Error searching with query '{search_query}': {e}") continue # Process best match if best_match: matched = True - print(f"[Quality Scanner] Final match: {best_match.artists[0]} - {best_match.name} (confidence: {best_confidence:.3f})") + logger.info(f"[Quality Scanner] Final match: {best_match.artists[0]} - {best_match.name} (confidence: {best_confidence:.3f})") # Build full Spotify track data for wishlist matched_track_data = { @@ -26979,14 +26902,14 @@ def _run_quality_scanner(scope='watchlist', profile_id=1): if success: with quality_scanner_lock: quality_scanner_state["matched"] += 1 - print(f"[Quality Scanner] Matched and added to wishlist: {artist_name} - {title}") + logger.info(f"[Quality Scanner] Matched and added to wishlist: {artist_name} - {title}") else: - print(f"[Quality Scanner] Failed to add to wishlist: {artist_name} - {title}") + logger.error(f"[Quality Scanner] Failed to add to wishlist: {artist_name} - {title}") else: - print(f"[Quality Scanner] No suitable match found (best confidence: {best_confidence:.3f}, required: {min_confidence:.3f})") + logger.warning(f"[Quality Scanner] No suitable match found (best confidence: {best_confidence:.3f}, required: {min_confidence:.3f})") except Exception as matching_error: - print(f"[Quality Scanner] Matching error for {artist_name} - {title}: {matching_error}") + logger.error(f"[Quality Scanner] Matching error for {artist_name} - {title}: {matching_error}") # Store result result_entry = { @@ -27005,10 +26928,10 @@ def _run_quality_scanner(scope='watchlist', profile_id=1): quality_scanner_state["results"].append(result_entry) if not matched: - print(f"[Quality Scanner] No Spotify match found for: {artist_name} - {title}") + logger.warning(f"[Quality Scanner] No Spotify match found for: {artist_name} - {title}") except Exception as track_error: - print(f"[Quality Scanner] Error processing track: {track_error}") + logger.error(f"[Quality Scanner] Error processing track: {track_error}") continue # Scan complete (don't overwrite if already stopped by user) @@ -27019,7 +26942,7 @@ def _run_quality_scanner(scope='watchlist', profile_id=1): if not was_stopped: quality_scanner_state["phase"] = "Scan complete" - print(f"[Quality Scanner] Scan {'stopped' if was_stopped else 'complete'}: {quality_scanner_state['processed']} processed, " + logger.info(f"[Quality Scanner] Scan {'stopped' if was_stopped else 'complete'}: {quality_scanner_state['processed']} processed, " f"{quality_scanner_state['low_quality']} low quality, {quality_scanner_state['matched']} matched to Spotify") # Add activity @@ -27037,7 +26960,7 @@ def _run_quality_scanner(scope='watchlist', profile_id=1): pass except Exception as e: - print(f"[Quality Scanner] Critical error: {e}") + logger.error(f"[Quality Scanner] Critical error: {e}") import traceback traceback.print_exc() @@ -27066,7 +26989,7 @@ def _run_duplicate_cleaner(): duplicate_cleaner_state["space_freed"] = 0 duplicate_cleaner_state["error_message"] = "" - print(f"[Duplicate Cleaner] Starting duplicate scan...") + logger.warning(f"[Duplicate Cleaner] Starting duplicate scan...") # Get Transfer folder path from config transfer_folder = docker_resolve_path(config_manager.get('soulseek.transfer_path', './Transfer')) @@ -27075,13 +26998,13 @@ def _run_duplicate_cleaner(): duplicate_cleaner_state["status"] = "error" duplicate_cleaner_state["phase"] = "Output folder not configured or does not exist" duplicate_cleaner_state["error_message"] = "Please configure output folder in settings" - print(f"[Duplicate Cleaner] Transfer folder not found: {transfer_folder}") + logger.warning(f"[Duplicate Cleaner] Transfer folder not found: {transfer_folder}") return # Create deleted folder if it doesn't exist deleted_folder = os.path.join(transfer_folder, 'deleted') os.makedirs(deleted_folder, exist_ok=True) - print(f"[Duplicate Cleaner] Deleted folder: {deleted_folder}") + logger.warning(f"[Duplicate Cleaner] Deleted folder: {deleted_folder}") # Phase 1: Count total files for progress tracking with duplicate_cleaner_lock: @@ -27094,7 +27017,7 @@ def _run_duplicate_cleaner(): dirs.remove('deleted') total_files += len(files) - print(f"[Duplicate Cleaner] Found {total_files} total files to scan") + logger.warning(f"[Duplicate Cleaner] Found {total_files} total files to scan") with duplicate_cleaner_lock: duplicate_cleaner_state["total_files"] = total_files @@ -27161,7 +27084,7 @@ def _run_duplicate_cleaner(): continue duplicates_found += len(file_versions) - 1 # Count all but the one we keep - print(f"[Duplicate Cleaner] Found {len(file_versions)} versions of '{filename}' in {directory}") + logger.warning(f"[Duplicate Cleaner] Found {len(file_versions)} versions of '{filename}' in {directory}") # Sort by priority: best format first, then largest size def sort_key(f): @@ -27173,7 +27096,7 @@ def _run_duplicate_cleaner(): # Keep the first one (best quality), delete the rest best_version = sorted_versions[0] - print(f"[Duplicate Cleaner] Keeping: {os.path.basename(best_version['full_path'])} " + logger.warning(f"[Duplicate Cleaner] Keeping: {os.path.basename(best_version['full_path'])} " f"({best_version['extension']}, {best_version['size']} bytes)") for duplicate_file in sorted_versions[1:]: @@ -27192,7 +27115,7 @@ def _run_duplicate_cleaner(): deleted_count += 1 space_freed += duplicate_file['size'] - print(f"[Duplicate Cleaner] Moved to deleted: {os.path.basename(duplicate_file['full_path'])} " + logger.warning(f"[Duplicate Cleaner] Moved to deleted: {os.path.basename(duplicate_file['full_path'])} " f"({duplicate_file['extension']}, {duplicate_file['size']} bytes)") # Update stats @@ -27202,7 +27125,7 @@ def _run_duplicate_cleaner(): duplicate_cleaner_state["duplicates_found"] = duplicates_found except Exception as e: - print(f"[Duplicate Cleaner] Error moving file {duplicate_file['full_path']}: {e}") + logger.error(f"[Duplicate Cleaner] Error moving file {duplicate_file['full_path']}: {e}") continue # Scan complete @@ -27212,7 +27135,7 @@ def _run_duplicate_cleaner(): duplicate_cleaner_state["phase"] = "Cleaning complete" space_mb = space_freed / (1024 * 1024) - print(f"[Duplicate Cleaner] Scan complete: {files_scanned} files scanned, " + logger.warning(f"[Duplicate Cleaner] Scan complete: {files_scanned} files scanned, " f"{duplicates_found} duplicates found, {deleted_count} files moved to deleted folder, " f"{space_mb:.2f} MB freed") @@ -27231,7 +27154,7 @@ def _run_duplicate_cleaner(): pass except Exception as e: - print(f"[Duplicate Cleaner] Critical error: {e}") + logger.error(f"[Duplicate Cleaner] Critical error: {e}") import traceback traceback.print_exc() @@ -27250,7 +27173,7 @@ def start_quality_scan(): data = request.get_json() or {} scope = data.get('scope', 'watchlist') # 'watchlist' or 'all' - print(f"[Quality Scanner API] Starting scan with scope: {scope}") + logger.info(f"[Quality Scanner API] Starting scan with scope: {scope}") # Reset state quality_scanner_state["status"] = "running" @@ -27296,7 +27219,7 @@ def start_duplicate_cleaner(): if duplicate_cleaner_state["status"] == "running": return jsonify({"success": False, "error": "A scan is already in progress"}), 409 - print(f"[Duplicate Cleaner API] Starting duplicate cleaner...") + logger.warning(f"[Duplicate Cleaner API] Starting duplicate cleaner...") # Reset state duplicate_cleaner_state["status"] = "running" @@ -27387,7 +27310,7 @@ def search_retag_albums(): }) return jsonify({"success": True, "albums": albums}) except Exception as e: - print(f"[Retag] Album search error: {e}") + logger.error(f"[Retag] Album search error: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/retag/execute', methods=['POST']) @@ -27544,15 +27467,15 @@ def get_valid_candidates(results, spotify_track, query): # Sort by confidence (best match first) scored.sort(key=lambda x: x.confidence, reverse=True) best = scored[0] - print(f"[{source_label}] {len(scored)}/{len(results)} candidates passed validation " + logger.info(f"[{source_label}] {len(scored)}/{len(results)} candidates passed validation " f"(best: {best.confidence:.2f} '{best.artist} - {best.title}')") return scored else: if results[0].username == 'youtube': - print(f"[{source_label}] No streaming results passed validation ā€” falling through to filename matching") + logger.warning(f"[{source_label}] No streaming results passed validation ā€” falling through to filename matching") # YouTube artist data is unreliable, allow fallback to filename-based matching else: - print(f"[{source_label}] No streaming results passed validation (threshold: 0.60, artist gate: 0.40) ā€” rejecting all candidates") + logger.warning(f"[{source_label}] No streaming results passed validation (threshold: 0.60, artist gate: 0.40) ā€” rejecting all candidates") return [] # Tidal/Qobuz/HiFi/Deezer have structured metadata; don't fall back to filename matching # Uses the existing, powerful matching engine for scoring (Soulseek P2P results) @@ -27566,7 +27489,7 @@ def get_valid_candidates(results, spotify_track, query): if is_streaming_source: source_label = initial_candidates[0].username.title() - print(f"[{source_label}] Skipping quality filter - streaming source handles quality internally") + logger.info(f"[{source_label}] Skipping quality filter - streaming source handles quality internally") quality_filtered_candidates = initial_candidates else: # Filter by user's quality profile before artist verification (Soulseek only) @@ -27578,7 +27501,7 @@ def get_valid_candidates(results, spotify_track, query): # and no results match, we should fail the download rather than force a fallback. # The quality filter already has its own fallback logic controlled by the user's settings. if not quality_filtered_candidates: - print(f"[Quality Filter] No candidates match quality profile - download will fail per user preferences") + logger.error(f"[Quality Filter] No candidates match quality profile - download will fail per user preferences") return [] verified_candidates = [] @@ -27637,18 +27560,18 @@ def _recover_worker_slot(batch_id, task_id): This prevents permanent worker slot leaks that cause modal to show wrong worker counts. """ try: - print(f"[Worker Recovery] Attempting to recover worker slot for batch {batch_id}, task {task_id}") + logger.warning(f"[Worker Recovery] Attempting to recover worker slot for batch {batch_id}, task {task_id}") # Acquire lock with timeout to prevent deadlock lock_acquired = tasks_lock.acquire(timeout=3.0) if not lock_acquired: - print(f"[Worker Recovery] FATAL: Could not acquire lock for recovery - worker slot LEAKED") + logger.error(f"[Worker Recovery] FATAL: Could not acquire lock for recovery - worker slot LEAKED") return False try: # Verify batch still exists if batch_id not in download_batches: - print(f"[Worker Recovery] Batch {batch_id} not found - nothing to recover") + logger.warning(f"[Worker Recovery] Batch {batch_id} not found - nothing to recover") return True batch = download_batches[batch_id] @@ -27658,11 +27581,11 @@ def _recover_worker_slot(batch_id, task_id): if old_active > 0: batch['active_count'] -= 1 new_active = batch['active_count'] - print(f"[Worker Recovery] Recovered worker slot - Active count: {old_active} ā†’ {new_active}") + logger.warning(f"[Worker Recovery] Recovered worker slot - Active count: {old_active} ā†’ {new_active}") # Try to start next worker if queue isn't empty if batch['queue_index'] < len(batch['queue']) and new_active < batch['max_concurrent']: - print(f"[Worker Recovery] Attempting to start replacement worker") + logger.warning(f"[Worker Recovery] Attempting to start replacement worker") # Release lock temporarily to avoid deadlock in _start_next_batch_of_downloads tasks_lock.release() try: @@ -27673,14 +27596,14 @@ def _recover_worker_slot(batch_id, task_id): return True else: - print(f"[Worker Recovery] Active count already 0 - no recovery needed") + logger.warning(f"[Worker Recovery] Active count already 0 - no recovery needed") return True finally: tasks_lock.release() except Exception as recovery_error: - print(f"[Worker Recovery] FATAL ERROR in recovery: {recovery_error}") + logger.error(f"[Worker Recovery] FATAL ERROR in recovery: {recovery_error}") return False def _get_batch_lock(batch_id): @@ -27699,7 +27622,7 @@ def _start_next_batch_of_downloads(batch_id): with batch_lock: # Prevent starting new tasks if shutting down if IS_SHUTTING_DOWN: - print(f"[Batch Manager] Server shutting down - skipping new tasks for batch {batch_id}") + logger.info(f"[Batch Manager] Server shutting down - skipping new tasks for batch {batch_id}") return with tasks_lock: @@ -27712,7 +27635,7 @@ def _start_next_batch_of_downloads(batch_id): queue_index = batch['queue_index'] active_count = batch['active_count'] - print(f"[Batch Lock] Starting workers for {batch_id}: active={active_count}, max={max_concurrent}, queue_pos={queue_index}/{len(queue)}") + logger.info(f"[Batch Lock] Starting workers for {batch_id}: active={active_count}, max={max_concurrent}, queue_pos={queue_index}/{len(queue)}") # Start downloads up to the concurrent limit while active_count < max_concurrent and queue_index < len(queue): @@ -27722,7 +27645,7 @@ def _start_next_batch_of_downloads(batch_id): if task_id in download_tasks: current_status = download_tasks[task_id]['status'] if current_status == 'cancelled': - print(f"[Batch Lock] Skipping cancelled task {task_id} (queue position {queue_index + 1})") + logger.warning(f"[Batch Lock] Skipping cancelled task {task_id} (queue position {queue_index + 1})") download_batches[batch_id]['queue_index'] += 1 queue_index += 1 continue # Skip to next task without consuming worker slot @@ -27731,9 +27654,9 @@ def _start_next_batch_of_downloads(batch_id): # Must be done INSIDE the lock to prevent race conditions with status polling download_tasks[task_id]['status'] = 'searching' download_tasks[task_id]['status_change_time'] = time.time() - print(f"[Batch Manager] Set task {task_id} status to 'searching'") + logger.info(f"[Batch Manager] Set task {task_id} status to 'searching'") else: - print(f"[Batch Lock] Task {task_id} not found in download_tasks - skipping") + logger.warning(f"[Batch Lock] Task {task_id} not found in download_tasks - skipping") download_batches[batch_id]['queue_index'] += 1 queue_index += 1 continue @@ -27747,26 +27670,26 @@ def _start_next_batch_of_downloads(batch_id): download_batches[batch_id]['active_count'] += 1 download_batches[batch_id]['queue_index'] += 1 - print(f"[Batch Lock] Started download {queue_index + 1}/{len(queue)} - Active: {active_count + 1}/{max_concurrent}") + logger.info(f"[Batch Lock] Started download {queue_index + 1}/{len(queue)} - Active: {active_count + 1}/{max_concurrent}") # Update local counters for next iteration active_count += 1 queue_index += 1 except Exception as submit_error: - print(f"[Batch Lock] CRITICAL: Failed to submit task {task_id} to executor: {submit_error}") - print(f"[Batch Lock] Worker slot NOT consumed - preventing ghost worker") + logger.error(f"[Batch Lock] CRITICAL: Failed to submit task {task_id} to executor: {submit_error}") + logger.info(f"[Batch Lock] Worker slot NOT consumed - preventing ghost worker") # Reset task status since worker never started if task_id in download_tasks: download_tasks[task_id]['status'] = 'failed' - print(f"[Batch Lock] Set task {task_id} status to 'failed' due to submit failure") + logger.error(f"[Batch Lock] Set task {task_id} status to 'failed' due to submit failure") # Don't increment counters - no worker was actually started # This prevents the "ghost worker" issue where active_count is incremented but no actual worker runs break # Stop trying to start more workers if executor is failing - print(f"[Batch Lock] Finished starting workers for {batch_id}: final_active={download_batches[batch_id]['active_count']}, max={max_concurrent}") + logger.info(f"[Batch Lock] Finished starting workers for {batch_id}: final_active={download_batches[batch_id]['active_count']}, max={max_concurrent}") def _get_track_artist_name(track_info): """Extract artist name from track info, handling different data formats (replicating sync.py)""" @@ -27872,11 +27795,11 @@ def _process_failed_tracks_to_wishlist_exact(batch_id): from core.wishlist_service import get_wishlist_service from datetime import datetime - print(f"[Wishlist Processing] Starting wishlist processing for batch {batch_id}") + logger.info(f"[Wishlist Processing] Starting wishlist processing for batch {batch_id}") with tasks_lock: if batch_id not in download_batches: - print(f"[Wishlist Processing] Batch {batch_id} not found") + logger.warning(f"[Wishlist Processing] Batch {batch_id} not found") return {'tracks_added': 0, 'errors': 0} batch = download_batches[batch_id] @@ -27884,13 +27807,13 @@ def _process_failed_tracks_to_wishlist_exact(batch_id): # Wing It mode ā€” skip wishlist entirely for failed tracks if batch.get('wing_it'): failed_count = len(batch.get('permanently_failed_tracks', [])) - print(f"[Wing It] Skipping wishlist for {failed_count} failed tracks (wing it mode)") + logger.error(f"[Wing It] Skipping wishlist for {failed_count} failed tracks (wing it mode)") return {'tracks_added': 0, 'errors': 0} permanently_failed_tracks = batch.get('permanently_failed_tracks', []) cancelled_tracks = batch.get('cancelled_tracks', set()) # STEP 0: Remove completed tracks from wishlist (THIS WAS MISSING!) - print(f"[Wishlist Processing] Checking completed tracks for wishlist removal") + logger.info(f"[Wishlist Processing] Checking completed tracks for wishlist removal") for task_id in batch.get('queue', []): if task_id in download_tasks: task = download_tasks[task_id] @@ -27900,12 +27823,12 @@ def _process_failed_tracks_to_wishlist_exact(batch_id): context = {'track_info': track_info, 'original_search_result': track_info} _check_and_remove_from_wishlist(context) except Exception as e: - print(f"[Wishlist Processing] Error removing completed track from wishlist: {e}") + logger.error(f"[Wishlist Processing] Error removing completed track from wishlist: {e}") # STEP 1: Add cancelled tracks that were missing to permanently_failed_tracks (replicating sync.py) # This matches sync.py's logic for adding cancelled missing tracks to the failed list if cancelled_tracks: - print(f"[Wishlist Processing] Processing {len(cancelled_tracks)} cancelled tracks") + logger.warning(f"[Wishlist Processing] Processing {len(cancelled_tracks)} cancelled tracks") # Process cancelled tracks with safeguard to prevent infinite loops processed_count = 0 @@ -27939,9 +27862,9 @@ def _process_failed_tracks_to_wishlist_exact(batch_id): if not any(t.get('table_index') == track_index for t in permanently_failed_tracks): permanently_failed_tracks.append(cancelled_track_info) processed_count += 1 - print(f"[Wishlist Processing] Added cancelled missing track {cancelled_track_info['track_name']} to failed list for wishlist") + logger.error(f"[Wishlist Processing] Added cancelled missing track {cancelled_track_info['track_name']} to failed list for wishlist") - print(f"[Wishlist Processing] Processed {processed_count} cancelled tracks") + logger.warning(f"[Wishlist Processing] Processed {processed_count} cancelled tracks") # STEP 1.5: Recover any failed/not_found tasks not captured in permanently_failed_tracks. # Stuck detection (in _on_download_completed, _check_batch_completion_v2, and the Safety Valve) @@ -27967,14 +27890,14 @@ def _process_failed_tracks_to_wishlist_exact(batch_id): 'candidates': task.get('cached_candidates', []) } permanently_failed_tracks.append(recovered_track_info) - print(f"[Wishlist Processing] Recovered uncaptured failed track for wishlist: {recovered_track_info['track_name']}") + logger.error(f"[Wishlist Processing] Recovered uncaptured failed track for wishlist: {recovered_track_info['track_name']}") # STEP 2: Add permanently failed tracks to wishlist (exact sync.py logic) failed_count = len(permanently_failed_tracks) wishlist_added_count = 0 error_count = 0 - print(f"[Wishlist Processing] Processing {failed_count} failed tracks for wishlist") + logger.error(f"[Wishlist Processing] Processing {failed_count} failed tracks for wishlist") if permanently_failed_tracks: try: @@ -28002,10 +27925,10 @@ def _process_failed_tracks_to_wishlist_exact(batch_id): sp_id = sp_track.get('id', '') if isinstance(sp_track, dict) else '' if str(sp_id).startswith('wing_it_'): wing_it_skipped += 1 - print(f"[Wishlist Processing] Skipping wing-it track: {track_name}") + logger.info(f"[Wishlist Processing] Skipping wing-it track: {track_name}") continue - print(f"[Wishlist Processing] Adding track {i+1}/{max_failed_tracks}: {track_name}") + logger.error(f"[Wishlist Processing] Adding track {i+1}/{max_failed_tracks}: {track_name}") success = wishlist_service.add_failed_track_from_modal( track_info=failed_track_info, @@ -28015,7 +27938,7 @@ def _process_failed_tracks_to_wishlist_exact(batch_id): ) if success: wishlist_added_count += 1 - print(f"[Wishlist Processing] Added {track_name} to wishlist") + logger.info(f"[Wishlist Processing] Added {track_name} to wishlist") try: if automation_engine: automation_engine.emit('wishlist_item_added', { @@ -28026,23 +27949,23 @@ def _process_failed_tracks_to_wishlist_exact(batch_id): except Exception: pass else: - print(f"[Wishlist Processing] Failed to add {track_name} to wishlist") + logger.error(f"[Wishlist Processing] Failed to add {track_name} to wishlist") except Exception as e: error_count += 1 - print(f"[Wishlist Processing] Exception adding track to wishlist: {e}") + logger.error(f"[Wishlist Processing] Exception adding track to wishlist: {e}") if wing_it_skipped: - print(f"[Wishlist Processing] Skipped {wing_it_skipped} wing-it fallback tracks") - print(f"[Wishlist Processing] Added {wishlist_added_count}/{failed_count} failed tracks to wishlist (errors: {error_count})") + logger.warning(f"[Wishlist Processing] Skipped {wing_it_skipped} wing-it fallback tracks") + logger.error(f"[Wishlist Processing] Added {wishlist_added_count}/{failed_count} failed tracks to wishlist (errors: {error_count})") except Exception as e: error_count = len(permanently_failed_tracks) - print(f"[Wishlist Processing] Critical error adding failed tracks to wishlist: {e}") + logger.error(f"[Wishlist Processing] Critical error adding failed tracks to wishlist: {e}") import traceback traceback.print_exc() else: - print(f"ā„¹ļø [Wishlist Processing] No failed tracks to add to wishlist") + logger.error(f"ā„¹ļø [Wishlist Processing] No failed tracks to add to wishlist") # Store completion summary in batch for API response (matching sync.py pattern) completion_summary = { @@ -28057,7 +27980,7 @@ def _process_failed_tracks_to_wishlist_exact(batch_id): download_batches[batch_id]['wishlist_processing_complete'] = True # Phase already set to 'complete' in _on_download_completed - print(f"[Wishlist Processing] Completed wishlist processing for batch {batch_id}") + logger.info(f"[Wishlist Processing] Completed wishlist processing for batch {batch_id}") # Auto-cleanup: Clear completed downloads from slskd try: @@ -28076,7 +27999,7 @@ def _process_failed_tracks_to_wishlist_exact(batch_id): return completion_summary except Exception as e: - print(f"[Wishlist Processing] CRITICAL ERROR in wishlist processing: {e}") + logger.error(f"[Wishlist Processing] CRITICAL ERROR in wishlist processing: {e}") import traceback traceback.print_exc() @@ -28094,7 +28017,7 @@ def _process_failed_tracks_to_wishlist_exact(batch_id): } download_batches[batch_id]['wishlist_processing_complete'] = True except Exception as lock_error: - print(f"[Wishlist Processing] Failed to update batch after error: {lock_error}") + logger.error(f"[Wishlist Processing] Failed to update batch after error: {lock_error}") return {'tracks_added': 0, 'errors': 1, 'total_failed': 0} @@ -28106,7 +28029,7 @@ def _process_failed_tracks_to_wishlist_exact_with_auto_completion(batch_id): global wishlist_auto_processing try: - print(f"[Auto-Wishlist] Processing completion for auto-initiated batch {batch_id}") + logger.info(f"[Auto-Wishlist] Processing completion for auto-initiated batch {batch_id}") # Run standard wishlist processing completion_summary = _process_failed_tracks_to_wishlist_exact(batch_id) @@ -28114,7 +28037,7 @@ def _process_failed_tracks_to_wishlist_exact_with_auto_completion(batch_id): # Log auto-processing completion tracks_added = completion_summary.get('tracks_added', 0) total_failed = completion_summary.get('total_failed', 0) - print(f"[Auto-Wishlist] Background processing complete: {tracks_added} added to wishlist, {total_failed} failed") + logger.error(f"[Auto-Wishlist] Background processing complete: {tracks_added} added to wishlist, {total_failed} failed") # Add activity for wishlist processing if tracks_added > 0: @@ -28140,9 +28063,9 @@ def _process_failed_tracks_to_wishlist_exact_with_auto_completion(batch_id): """, (next_cycle,)) conn.commit() - print(f"[Auto-Wishlist] Cycle toggled after completion: {current_cycle} ā†’ {next_cycle}") + logger.info(f"[Auto-Wishlist] Cycle toggled after completion: {current_cycle} ā†’ {next_cycle}") except Exception as cycle_error: - print(f"[Auto-Wishlist] Error toggling cycle: {cycle_error}") + logger.error(f"[Auto-Wishlist] Error toggling cycle: {cycle_error}") # Mark auto-processing as complete and reset timestamp with wishlist_timer_lock: @@ -28162,7 +28085,7 @@ def _process_failed_tracks_to_wishlist_exact_with_auto_completion(batch_id): return completion_summary except Exception as e: - print(f"[Auto-Wishlist] Error in auto-completion processing: {e}") + logger.error(f"[Auto-Wishlist] Error in auto-completion processing: {e}") import traceback traceback.print_exc() @@ -28177,7 +28100,7 @@ def _on_download_completed(batch_id, task_id, success=True): """Called when a download completes to start the next one in queue""" with tasks_lock: if batch_id not in download_batches: - print(f"[Batch Manager] Batch {batch_id} not found for completed task {task_id}") + logger.warning(f"[Batch Manager] Batch {batch_id} not found for completed task {task_id}") return # Guard against double-calling: track which tasks have already been completed @@ -28190,7 +28113,7 @@ def _on_download_completed(batch_id, task_id, success=True): completed_tasks = download_batches[batch_id].setdefault('_completed_task_ids', set()) _is_duplicate_completion = task_id in completed_tasks if _is_duplicate_completion: - print(f"[Batch Manager] Task {task_id} already completed ā€” skipping decrement, still checking batch completion") + logger.info(f"[Batch Manager] Task {task_id} already completed ā€” skipping decrement, still checking batch completion") # Set terminal status so the monitor loop stops re-processing this task if task_id in download_tasks and download_tasks[task_id].get('status') in ('downloading', 'queued'): download_tasks[task_id]['status'] = 'completed' @@ -28223,15 +28146,15 @@ def _on_download_completed(batch_id, task_id, success=True): if task_status == 'cancelled': download_batches[batch_id]['cancelled_tracks'].add(task.get('track_index', 0)) - print(f"[Batch Manager] Added cancelled track to batch tracking: {track_info['track_name']}") + logger.warning(f"[Batch Manager] Added cancelled track to batch tracking: {track_info['track_name']}") add_activity_item("", "Download Cancelled", f"'{track_info['track_name']}'", "Now") elif task_status in ('failed', 'not_found'): download_batches[batch_id]['permanently_failed_tracks'].append(track_info) if task_status == 'not_found': - print(f"[Batch Manager] Added not-found track to batch tracking: {track_info['track_name']}") + logger.info(f"[Batch Manager] Added not-found track to batch tracking: {track_info['track_name']}") add_activity_item("", "Not Found", f"'{track_info['track_name']}'", "Now") else: - print(f"[Batch Manager] Added failed track to batch tracking: {track_info['track_name']}") + logger.error(f"[Batch Manager] Added failed track to batch tracking: {track_info['track_name']}") add_activity_item("", "Download Failed", f"'{track_info['track_name']}'", "Now") try: @@ -28249,7 +28172,7 @@ def _on_download_completed(batch_id, task_id, success=True): try: task = download_tasks[task_id] track_info = task.get('track_info', {}) - print(f"[Batch Manager] Successful download - checking wishlist removal for task {task_id}") + logger.info(f"[Batch Manager] Successful download - checking wishlist removal for task {task_id}") # Add activity for successful download track_name = track_info.get('name', 'Unknown Track') @@ -28275,18 +28198,18 @@ def _on_download_completed(batch_id, task_id, success=True): } _check_and_remove_from_wishlist(context) except Exception as wishlist_error: - print(f"[Batch Manager] Error checking wishlist removal for successful download: {wishlist_error}") + logger.error(f"[Batch Manager] Error checking wishlist removal for successful download: {wishlist_error}") # Decrement active count old_active = download_batches[batch_id]['active_count'] download_batches[batch_id]['active_count'] -= 1 new_active = download_batches[batch_id]['active_count'] - print(f"[Batch Manager] Task {task_id} completed ({'success' if success else 'failed/cancelled'}). Active workers: {old_active} ā†’ {new_active}/{download_batches[batch_id]['max_concurrent']}") + logger.error(f"[Batch Manager] Task {task_id} completed ({'success' if success else 'failed/cancelled'}). Active workers: {old_active} ā†’ {new_active}/{download_batches[batch_id]['max_concurrent']}") # ENHANCED: Always check batch completion after any task completes (including duplicate calls) # This ensures completion is detected even when mixing normal downloads with cancelled tasks - print(f"[Batch Manager] Checking batch completion after task {task_id} completed") + logger.info(f"[Batch Manager] Checking batch completion after task {task_id} completed") # FIXED: Check if batch is truly complete (all tasks finished, not just workers freed) batch = download_batches[batch_id] @@ -28309,7 +28232,7 @@ def _on_download_completed(batch_id, task_id, success=True): if task_status == 'searching': task_age = current_time - task.get('status_change_time', current_time) if task_age > 600: # 10 minutes - print(f"ā° [Stuck Detection] Task {task_id} stuck in searching for {task_age:.0f}s - forcing not_found") + logger.info(f"ā° [Stuck Detection] Task {task_id} stuck in searching for {task_age:.0f}s - forcing not_found") task['status'] = 'not_found' task['error_message'] = f'Search stuck for {int(task_age // 60)} minutes with no results ā€” timed out' finished_count += 1 @@ -28318,7 +28241,7 @@ def _on_download_completed(batch_id, task_id, success=True): elif task_status == 'post_processing': task_age = current_time - task.get('status_change_time', current_time) if task_age > 300: # 5 minutes (post-processing should be fast) - print(f"ā° [Stuck Detection] Task {task_id} stuck in post_processing for {task_age:.0f}s - forcing completion") + logger.info(f"ā° [Stuck Detection] Task {task_id} stuck in post_processing for {task_age:.0f}s - forcing completion") task['status'] = 'completed' # Assume it worked if file verification is taking too long finished_count += 1 else: @@ -28327,19 +28250,19 @@ def _on_download_completed(batch_id, task_id, success=True): finished_count += 1 else: # Task ID in queue but not in download_tasks - treat as completed to prevent blocking - print(f"[Orphaned Task] Task {task_id} in queue but not in download_tasks - counting as finished") + logger.warning(f"[Orphaned Task] Task {task_id} in queue but not in download_tasks - counting as finished") finished_count += 1 all_tasks_truly_finished = finished_count >= len(queue) has_retrying_tasks = retrying_count > 0 if all_tasks_started and no_active_workers and all_tasks_truly_finished and not has_retrying_tasks: - print(f"[Batch Manager] Batch {batch_id} truly complete - all {finished_count}/{len(queue)} tasks finished - processing failed tracks to wishlist") + logger.error(f"[Batch Manager] Batch {batch_id} truly complete - all {finished_count}/{len(queue)} tasks finished - processing failed tracks to wishlist") elif all_tasks_started and no_active_workers and has_retrying_tasks: - print(f"[Batch Manager] Batch {batch_id}: all workers free but {retrying_count} tasks retrying - continuing monitoring") + logger.warning(f"[Batch Manager] Batch {batch_id}: all workers free but {retrying_count} tasks retrying - continuing monitoring") elif all_tasks_started and no_active_workers: # This used to incorrectly mark batch as complete! - print(f"[Batch Manager] Batch {batch_id}: all workers free but only {finished_count}/{len(queue)} tasks finished - continuing monitoring") + logger.info(f"[Batch Manager] Batch {batch_id}: all workers free but only {finished_count}/{len(queue)} tasks finished - continuing monitoring") if all_tasks_started and no_active_workers and all_tasks_truly_finished and not has_retrying_tasks: @@ -28380,30 +28303,30 @@ def _on_download_completed(batch_id, task_id, success=True): url_hash = playlist_id.replace('youtube_', '') if url_hash in youtube_playlist_states: youtube_playlist_states[url_hash]['phase'] = 'download_complete' - print(f"Updated YouTube playlist {url_hash} to download_complete phase") + logger.info(f"Updated YouTube playlist {url_hash} to download_complete phase") # Update Tidal playlist phase to 'download_complete' if this is a Tidal playlist if playlist_id and playlist_id.startswith('tidal_'): tidal_playlist_id = playlist_id.replace('tidal_', '') if tidal_playlist_id in tidal_discovery_states: tidal_discovery_states[tidal_playlist_id]['phase'] = 'download_complete' - print(f"Updated Tidal playlist {tidal_playlist_id} to download_complete phase") + logger.info(f"Updated Tidal playlist {tidal_playlist_id} to download_complete phase") # Update Deezer playlist phase to 'download_complete' if this is a Deezer playlist if playlist_id and playlist_id.startswith('deezer_'): deezer_playlist_id = playlist_id.replace('deezer_', '') if deezer_playlist_id in deezer_discovery_states: deezer_discovery_states[deezer_playlist_id]['phase'] = 'download_complete' - print(f"Updated Deezer playlist {deezer_playlist_id} to download_complete phase") + logger.info(f"Updated Deezer playlist {deezer_playlist_id} to download_complete phase") # Update Spotify Public playlist phase to 'download_complete' if this is a Spotify Public playlist if playlist_id and playlist_id.startswith('spotify_public_'): spotify_public_url_hash = playlist_id.replace('spotify_public_', '') if spotify_public_url_hash in spotify_public_discovery_states: spotify_public_discovery_states[spotify_public_url_hash]['phase'] = 'download_complete' - print(f"Updated Spotify Public playlist {spotify_public_url_hash} to download_complete phase") + logger.info(f"Updated Spotify Public playlist {spotify_public_url_hash} to download_complete phase") - print(f"[Batch Manager] Batch {batch_id} complete - stopping monitor") + logger.info(f"[Batch Manager] Batch {batch_id} complete - stopping monitor") download_monitor.stop_monitoring(batch_id) # M3U REGENERATION: Regenerate M3U with real library paths now that @@ -28427,7 +28350,7 @@ def _on_download_completed(batch_id, task_id, success=True): if m3u_tracks: _regenerate_batch_m3u(batch, m3u_tracks) except Exception as m3u_err: - print(f"[M3U] Error regenerating M3U on batch complete: {m3u_err}") + logger.error(f"[M3U] Error regenerating M3U on batch complete: {m3u_err}") # REPAIR: Scan all album folders from this batch for track number issues if repair_worker: @@ -28458,12 +28381,12 @@ def _on_download_completed(batch_id, task_id, success=True): file_lock_fn=_get_file_lock, ) if _cons_result.get('success'): - print(f"[Album Consistency] {_cons_result['tags_written']}/{_cons_result['total_files']} files " + logger.info(f"[Album Consistency] {_cons_result['tags_written']}/{_cons_result['total_files']} files " f"harmonized to release {_cons_result.get('release_mbid', '')[:8]}...") elif _cons_result.get('error'): - print(f"[Album Consistency] Skipped: {_cons_result['error']}") + logger.error(f"[Album Consistency] Skipped: {_cons_result['error']}") except Exception as cons_err: - print(f"[Album Consistency] Failed (non-fatal): {cons_err}") + logger.error(f"[Album Consistency] Failed (non-fatal): {cons_err}") # Mark that wishlist processing is starting (prevents premature cleanup) batch['wishlist_processing_started'] = True @@ -28476,12 +28399,12 @@ def _on_download_completed(batch_id, task_id, success=True): # For manual batches, use standard wishlist processing missing_download_executor.submit(_process_failed_tracks_to_wishlist_exact, batch_id) else: - print(f"[Batch Manager] Batch {batch_id} already marked complete - skipping duplicate processing") + logger.warning(f"[Batch Manager] Batch {batch_id} already marked complete - skipping duplicate processing") return # Don't start next batch if we're done # Start next downloads in queue - print(f"[Batch Manager] Starting next batch for {batch_id}") + logger.info(f"[Batch Manager] Starting next batch for {batch_id}") _start_next_batch_of_downloads(batch_id) def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): @@ -28516,13 +28439,13 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): batch_artist_context = download_batches[batch_id].get('artist_context') if force_download_all: - print(f"[Force Download] Force download mode enabled for batch {batch_id} - treating all tracks as missing") + logger.warning(f"[Force Download] Force download mode enabled for batch {batch_id} - treating all tracks as missing") # Allow duplicate tracks across albums ā€” when enabled, only skip tracks already # owned in THIS album, not tracks owned in other albums allow_duplicates = config_manager.get('wishlist.allow_duplicate_tracks', True) if allow_duplicates and batch_is_album: - print(f"[Duplicates] Allow duplicate tracks enabled ā€” only checking ownership within target album") + logger.info(f"[Duplicates] Allow duplicate tracks enabled ā€” only checking ownership within target album") # PREFLIGHT: Pre-populate MusicBrainz release cache for album downloads. # This ensures ALL tracks in the album use the same release MBID during @@ -28547,12 +28470,12 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): # Also cache the full release detail for tag extraction with _mb_release_detail_cache_lock: _mb_release_detail_cache[release_mbid] = release - print(f"[Preflight] Pre-cached MB release for '{album_name_pf}': " + logger.info(f"[Preflight] Pre-cached MB release for '{album_name_pf}': " f"'{release.get('title', '')}' ({release_mbid[:8]}...)") else: - print(f"[Preflight] No MB release found for '{album_name_pf}' ā€” per-track lookup will be used") + logger.warning(f"[Preflight] No MB release found for '{album_name_pf}' ā€” per-track lookup will be used") except Exception as pf_err: - print(f"[Preflight] MB release preflight failed: {pf_err}") + logger.error(f"[Preflight] MB release preflight failed: {pf_err}") # ALBUM FAST PATH: If this is an album download, try to find the album in the DB first # and match tracks within it ā€” faster and more accurate than N global searches @@ -28573,11 +28496,11 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): db_album_tracks = db.get_tracks_by_album(db_album.id) for t in db_album_tracks: album_tracks_map[t.title.lower().strip()] = t - print(f"[Album Analysis] Found album '{db_album.title}' in DB with {len(db_album_tracks)} tracks (confidence: {album_confidence:.2f})") + logger.info(f"[Album Analysis] Found album '{db_album.title}' in DB with {len(db_album_tracks)} tracks (confidence: {album_confidence:.2f})") else: - print(f"[Album Analysis] Album '{album_name}' not found in DB ā€” falling back to per-track search") + logger.warning(f"[Album Analysis] Album '{album_name}' not found in DB ā€” falling back to per-track search") except Exception as album_err: - print(f"[Album Analysis] Album lookup error: {album_err} ā€” falling back to per-track search") + logger.error(f"[Album Analysis] Album lookup error: {album_err} ā€” falling back to per-track search") for i, track_data in enumerate(tracks_json): # Use original table index if provided (for partial track selection), @@ -28589,7 +28512,7 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): # Skip database check if force download is enabled if force_download_all: - print(f"[Force Download] Skipping database check for '{track_name}' - treating as missing") + logger.warning(f"[Force Download] Skipping database check for '{track_name}' - treating as missing") found, confidence = False, 0.0 elif album_tracks_map: # Album-scoped matching: check against known album tracks first @@ -28656,7 +28579,7 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): try: _check_and_remove_track_from_wishlist_by_metadata(track_data) except Exception as wishlist_error: - print(f"[Analysis] Error checking wishlist removal for found track: {wishlist_error}") + logger.error(f"[Analysis] Error checking wishlist removal for found track: {wishlist_error}") with tasks_lock: if batch_id in download_batches: @@ -28672,7 +28595,7 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): missing_tracks = [res for res in missing_tracks if not _is_explicit_blocked(res.get('track', {}))] skipped = before_count - len(missing_tracks) if skipped > 0: - print(f"[Content Filter] Filtered out {skipped} explicit track(s) from download queue") + logger.warning(f"[Content Filter] Filtered out {skipped} explicit track(s) from download queue") with tasks_lock: if batch_id in download_batches: @@ -28680,7 +28603,7 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): # PHASE 2: TRANSITION TO DOWNLOAD (if necessary) if not missing_tracks: - print(f"Analysis for batch {batch_id} complete. No missing tracks.") + logger.warning(f"Analysis for batch {batch_id} complete. No missing tracks.") # Record sync history ā€” all tracks found, nothing to download tracks_found = sum(1 for r in analysis_results if r.get('found')) @@ -28731,37 +28654,37 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): url_hash = playlist_id.replace('youtube_', '') if url_hash in youtube_playlist_states: youtube_playlist_states[url_hash]['phase'] = 'download_complete' - print(f"Updated YouTube playlist {url_hash} to download_complete phase (no missing tracks)") + logger.warning(f"Updated YouTube playlist {url_hash} to download_complete phase (no missing tracks)") # Update Tidal playlist phase to 'download_complete' if this is a Tidal playlist if playlist_id.startswith('tidal_'): tidal_playlist_id = playlist_id.replace('tidal_', '') if tidal_playlist_id in tidal_discovery_states: tidal_discovery_states[tidal_playlist_id]['phase'] = 'download_complete' - print(f"Updated Tidal playlist {tidal_playlist_id} to download_complete phase (no missing tracks)") + logger.warning(f"Updated Tidal playlist {tidal_playlist_id} to download_complete phase (no missing tracks)") # Update Deezer playlist phase to 'download_complete' if this is a Deezer playlist if playlist_id.startswith('deezer_'): deezer_playlist_id = playlist_id.replace('deezer_', '') if deezer_playlist_id in deezer_discovery_states: deezer_discovery_states[deezer_playlist_id]['phase'] = 'download_complete' - print(f"Updated Deezer playlist {deezer_playlist_id} to download_complete phase (no missing tracks)") + logger.warning(f"Updated Deezer playlist {deezer_playlist_id} to download_complete phase (no missing tracks)") # Update Spotify Public playlist phase to 'download_complete' if this is a Spotify Public playlist if playlist_id.startswith('spotify_public_'): spotify_public_url_hash = playlist_id.replace('spotify_public_', '') if spotify_public_url_hash in spotify_public_discovery_states: spotify_public_discovery_states[spotify_public_url_hash]['phase'] = 'download_complete' - print(f"Updated Spotify Public playlist {spotify_public_url_hash} to download_complete phase (no missing tracks)") + logger.warning(f"Updated Spotify Public playlist {spotify_public_url_hash} to download_complete phase (no missing tracks)") # Handle auto-initiated wishlist completion even when no missing tracks if is_auto_batch and playlist_id == 'wishlist': - print("[Auto-Wishlist] No missing tracks found - calling auto-completion handler to toggle cycle and reschedule") + logger.warning("[Auto-Wishlist] No missing tracks found - calling auto-completion handler to toggle cycle and reschedule") missing_download_executor.submit(_process_failed_tracks_to_wishlist_exact_with_auto_completion, batch_id) return - print(f" transitioning batch {batch_id} to download phase with {len(missing_tracks)} tracks.") + logger.warning(f" transitioning batch {batch_id} to download phase with {len(missing_tracks)} tracks.") # Read batch context (quick lock) before doing any network I/O with tasks_lock: @@ -28790,7 +28713,7 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): try: _sr = source_reuse_logger _sr.info(f"[Album Pre-flight] Searching for '{artist_name} {album_name}'") - print(f"[Album Pre-flight] Searching Soulseek for complete album: '{artist_name} - {album_name}'") + logger.info(f"[Album Pre-flight] Searching Soulseek for complete album: '{artist_name} - {album_name}'") slsk = soulseek_client.soulseek if hasattr(soulseek_client, 'soulseek') else soulseek_client @@ -28829,7 +28752,7 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): _sr.info(f"[Album Pre-flight] Best album result: {best_album.username}:{best_album.album_path} " f"({best_album.track_count} tracks, quality={best_album.dominant_quality})") - print(f"[Album Pre-flight] Found album folder: {best_album.username} ā€” " + logger.info(f"[Album Pre-flight] Found album folder: {best_album.username} ā€” " f"{best_album.track_count} tracks ({best_album.dominant_quality})") # Browse the user's folder to get all tracks (may have more than search returned) @@ -28845,7 +28768,7 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): } preflight_tracks = folder_tracks _sr.info(f"[Album Pre-flight] Browsed folder: {len(folder_tracks)} audio tracks available") - print(f"[Album Pre-flight] Cached {len(folder_tracks)} tracks from {best_album.username} for source reuse") + logger.info(f"[Album Pre-flight] Cached {len(folder_tracks)} tracks from {best_album.username} for source reuse") else: _sr.info(f"[Album Pre-flight] Browse returned files but no audio tracks") else: @@ -28856,16 +28779,16 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): 'folder_path': best_album.album_path } preflight_tracks = best_album.tracks - print(f"[Album Pre-flight] Using {len(best_album.tracks)} tracks from search results (browse unavailable)") + logger.info(f"[Album Pre-flight] Using {len(best_album.tracks)} tracks from search results (browse unavailable)") else: _sr.info(f"[Album Pre-flight] No album results passed quality filter") - print(f"[Album Pre-flight] No album results matched quality preferences") + logger.warning(f"[Album Pre-flight] No album results matched quality preferences") else: _sr.info(f"[Album Pre-flight] Search returned no album results (got {len(track_results)} individual tracks)") - print(f"[Album Pre-flight] No complete album folders found, falling back to track-by-track search") + logger.warning(f"[Album Pre-flight] No complete album folders found, falling back to track-by-track search") except Exception as preflight_err: - print(f"[Album Pre-flight] Search failed (non-fatal, falling back to track-by-track): {preflight_err}") + logger.error(f"[Album Pre-flight] Search failed (non-fatal, falling back to track-by-track): {preflight_err}") source_reuse_logger.info(f"[Album Pre-flight] Exception: {preflight_err}") with tasks_lock: @@ -28878,7 +28801,7 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): download_batches[batch_id]['last_good_source'] = preflight_source download_batches[batch_id]['source_folder_tracks'] = preflight_tracks download_batches[batch_id]['failed_sources'] = set() - print(f"[Album Pre-flight] Pre-loaded source reuse data on batch {batch_id}") + logger.info(f"[Album Pre-flight] Pre-loaded source reuse data on batch {batch_id}") # Compute total_discs for multi-disc album subfolder support # Use ALL tracks (tracks_json), not just missing ones, to correctly detect multi-disc @@ -28887,7 +28810,7 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): total_discs = max((t.get('disc_number', 1) for t in tracks_json), default=1) batch_album_context['total_discs'] = total_discs if total_discs > 1: - print(f"[Multi-Disc] Detected {total_discs} discs for album '{batch_album_context.get('name')}'") + logger.info(f"[Multi-Disc] Detected {total_discs} discs for album '{batch_album_context.get('name')}'") # Pre-compute per-album data for wishlist tracks (grouped by album ID) # Wishlist tracks aren't batch_is_album but each track has disc_number in spotify_data @@ -28948,7 +28871,7 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): else: _fallback_name = t.get('artist', '') wishlist_album_artist_map[album_id] = {'name': _fallback_name or 'Unknown Artist'} - print(f"[Wishlist Album Grouping] Album '{_wl_album.get('name', album_id)}' ā†’ artist: '{wishlist_album_artist_map[album_id].get('name', '?')}'") + logger.info(f"[Wishlist Album Grouping] Album '{_wl_album.get('name', album_id)}' ā†’ artist: '{wishlist_album_artist_map[album_id].get('name', '?')}'") @@ -28961,7 +28884,7 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): track_info['_explicit_album_context'] = batch_album_context track_info['_explicit_artist_context'] = batch_artist_context track_info['_is_explicit_album_download'] = True - print(f"[Task Creation] Added explicit album context for: {track_info.get('name')}") + logger.info(f"[Task Creation] Added explicit album context for: {track_info.get('name')}") # SPECIAL WISHLIST HANDLING: Inject album context if available to force grouping elif playlist_id == 'wishlist': @@ -29020,16 +28943,16 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): track_info['_explicit_album_context'] = album_ctx track_info['_explicit_artist_context'] = artist_ctx track_info['_is_explicit_album_download'] = True - print(f"[Wishlist] Added album context for: '{track_info.get('name')}' -> '{album_ctx['name']}'") + logger.info(f"[Wishlist] Added album context for: '{track_info.get('name')}' -> '{album_ctx['name']}'") # Add playlist folder mode flag for sync page playlists if batch_playlist_folder_mode: track_info['_playlist_folder_mode'] = True track_info['_playlist_name'] = batch_playlist_name - print(f"[Task Creation] Added playlist folder mode for: {track_info.get('name')} ā†’ {batch_playlist_name}") + logger.info(f"[Task Creation] Added playlist folder mode for: {track_info.get('name')} ā†’ {batch_playlist_name}") else: - print(f"[Debug] Task Creation - playlist folder mode NOT enabled for: {track_info.get('name')}") + logger.debug(f"[Debug] Task Creation - playlist folder mode NOT enabled for: {track_info.get('name')}") download_tasks[task_id] = { 'status': 'pending', 'track_info': track_info, @@ -29045,7 +28968,7 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): _start_next_batch_of_downloads(batch_id) except Exception as e: - print(f"Master worker for batch {batch_id} failed: {e}") + logger.error(f"Master worker for batch {batch_id} failed: {e}") import traceback traceback.print_exc() @@ -29061,11 +28984,11 @@ def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): url_hash = playlist_id.replace('youtube_', '') if url_hash in youtube_playlist_states: youtube_playlist_states[url_hash]['phase'] = 'discovered' - print(f"Reset YouTube playlist {url_hash} to discovered phase (error)") + logger.error(f"Reset YouTube playlist {url_hash} to discovered phase (error)") # Handle auto-initiated wishlist errors - reset flag if is_auto_batch and playlist_id == 'wishlist': - print("[Auto-Wishlist] Master worker error - resetting auto-processing flag") + logger.error("[Auto-Wishlist] Master worker error - resetting auto-processing flag") global wishlist_auto_processing, wishlist_auto_processing_timestamp with wishlist_timer_lock: wishlist_auto_processing = False @@ -29077,21 +29000,21 @@ def _run_post_processing_worker(task_id, batch_id): after successful file verification and processing. This matches sync.py's reliability. """ try: - print(f"[Post-Processing] Starting verification for task {task_id}") + logger.info(f"[Post-Processing] Starting verification for task {task_id}") # Retrieve task details from global state with tasks_lock: if task_id not in download_tasks: - print(f"[Post-Processing] Task {task_id} not found in download_tasks") + logger.warning(f"[Post-Processing] Task {task_id} not found in download_tasks") return task = download_tasks[task_id].copy() # Check if task was cancelled or already completed during post-processing if task['status'] == 'cancelled': - print(f"[Post-Processing] Task {task_id} was cancelled, skipping verification") + logger.warning(f"[Post-Processing] Task {task_id} was cancelled, skipping verification") return if task['status'] == 'completed' or task.get('stream_processed'): - print(f"[Post-Processing] Task {task_id} already completed by stream processor, skipping verification") + logger.info(f"[Post-Processing] Task {task_id} already completed by stream processor, skipping verification") return # Extract file information for verification @@ -29100,7 +29023,7 @@ def _run_post_processing_worker(task_id, batch_id): task_username = task.get('username') or track_info.get('username') if not task_filename or not task_username: - print(f"[Post-Processing] Missing filename or username for task {task_id}") + logger.warning(f"[Post-Processing] Missing filename or username for task {task_id}") with tasks_lock: if task_id in download_tasks: download_tasks[task_id]['status'] = 'failed' @@ -29116,39 +29039,39 @@ def _run_post_processing_worker(task_id, batch_id): context_key = _make_context_key(task_username, task_filename) expected_final_filename = None - print(f"[Post-Processing] Looking up context with key: {context_key}") + logger.info(f"[Post-Processing] Looking up context with key: {context_key}") with matched_context_lock: context = matched_downloads_context.get(context_key) # Debug: Show all available context keys available_keys = list(matched_downloads_context.keys()) - print(f"[Post-Processing] Available context keys: {available_keys[:10]}...") # Show first 10 keys + logger.info(f"[Post-Processing] Available context keys: {available_keys[:10]}...") # Show first 10 keys if context: - print(f"[Post-Processing] Found context for key: {context_key}") + logger.info(f"[Post-Processing] Found context for key: {context_key}") try: original_search = context.get("original_search_result", {}) - print(f"[Post-Processing] original_search keys: {list(original_search.keys())}") + logger.info(f"[Post-Processing] original_search keys: {list(original_search.keys())}") spotify_clean_title = original_search.get('spotify_clean_title') track_number = original_search.get('track_number') - print(f"[Post-Processing] spotify_clean_title: '{spotify_clean_title}', track_number: {track_number}") + logger.info(f"[Post-Processing] spotify_clean_title: '{spotify_clean_title}', track_number: {track_number}") if spotify_clean_title and track_number: # Generate expected final filename that stream processor would create # Pattern: f"{track_number:02d} - {clean_title}.flac" sanitized_title = spotify_clean_title.replace('/', '_').replace('\\', '_').replace(':', '_').replace('*', '_').replace('?', '_').replace('"', '_').replace('<', '_').replace('>', '_').replace('|', '_') expected_final_filename = f"{track_number:02d} - {sanitized_title}.flac" - print(f"[Post-Processing] Generated expected final filename: {expected_final_filename}") + logger.info(f"[Post-Processing] Generated expected final filename: {expected_final_filename}") else: - print(f"[Post-Processing] Missing required data - spotify_clean_title: {bool(spotify_clean_title)}, track_number: {bool(track_number)}") + logger.warning(f"[Post-Processing] Missing required data - spotify_clean_title: {bool(spotify_clean_title)}, track_number: {bool(track_number)}") except Exception as e: - print(f"[Post-Processing] Error generating expected filename: {e}") + logger.error(f"[Post-Processing] Error generating expected filename: {e}") import traceback traceback.print_exc() else: - print(f"[Post-Processing] No context found for key: {context_key}") + logger.warning(f"[Post-Processing] No context found for key: {context_key}") # Try fuzzy matching with similar keys containing the filename # SAFETY: Constrain to same Soulseek username to prevent cross-album # metadata contamination during mass downloads (e.g., two albums both @@ -29160,35 +29083,35 @@ def _run_post_processing_worker(task_id, batch_id): # Use the first similar key found fuzzy_key = similar_keys[0] context = matched_downloads_context.get(fuzzy_key) - print(f"[Post-Processing] Found context using fuzzy key matching: {fuzzy_key}") + logger.info(f"[Post-Processing] Found context using fuzzy key matching: {fuzzy_key}") # Generate expected final filename using the found context try: original_search = context.get("original_search_result", {}) - print(f"[Post-Processing] fuzzy context original_search keys: {list(original_search.keys())}") + logger.info(f"[Post-Processing] fuzzy context original_search keys: {list(original_search.keys())}") spotify_clean_title = original_search.get('spotify_clean_title') track_number = original_search.get('track_number') - print(f"[Post-Processing] fuzzy context spotify_clean_title: '{spotify_clean_title}', track_number: {track_number}") + logger.info(f"[Post-Processing] fuzzy context spotify_clean_title: '{spotify_clean_title}', track_number: {track_number}") if spotify_clean_title and track_number: # Generate expected final filename that stream processor would create # Pattern: f"{track_number:02d} - {clean_title}.flac" sanitized_title = spotify_clean_title.replace('/', '_').replace('\\', '_').replace(':', '_').replace('*', '_').replace('?', '_').replace('"', '_').replace('<', '_').replace('>', '_').replace('|', '_') expected_final_filename = f"{track_number:02d} - {sanitized_title}.flac" - print(f"[Post-Processing] Generated expected final filename from fuzzy match: {expected_final_filename}") + logger.info(f"[Post-Processing] Generated expected final filename from fuzzy match: {expected_final_filename}") else: - print(f"[Post-Processing] Missing required data from fuzzy match - spotify_clean_title: {bool(spotify_clean_title)}, track_number: {bool(track_number)}") + logger.warning(f"[Post-Processing] Missing required data from fuzzy match - spotify_clean_title: {bool(spotify_clean_title)}, track_number: {bool(track_number)}") except Exception as e: - print(f"[Post-Processing] Error generating expected filename from fuzzy match: {e}") + logger.error(f"[Post-Processing] Error generating expected filename from fuzzy match: {e}") import traceback traceback.print_exc() else: - print(f"[Post-Processing] No similar keys found containing '{task_basename}'") + logger.warning(f"[Post-Processing] No similar keys found containing '{task_basename}'") # Show a sample of what keys actually exist for debugging sample_keys = list(matched_downloads_context.keys())[:5] - print(f"[Post-Processing] Sample of existing keys: {sample_keys}") + logger.info(f"[Post-Processing] Sample of existing keys: {sample_keys}") # RESILIENT FILE-FINDING LOOP: Try up to 3 times with delays found_file = None @@ -29243,51 +29166,51 @@ def _run_post_processing_worker(task_id, batch_id): for retry_count in range(_file_search_max_retries): # If we already resolved the file (e.g. via YouTube status), skip searching if found_file: - print(f"[Post-Processing] Skipping search loop, file already resolved: {found_file}") + logger.info(f"[Post-Processing] Skipping search loop, file already resolved: {found_file}") break # Check if stream processor already completed this task while we were waiting with tasks_lock: if task_id in download_tasks: if download_tasks[task_id].get('stream_processed') or download_tasks[task_id]['status'] == 'completed': - print(f"[Post-Processing] Task {task_id} was completed by stream processor during file search - done") + logger.info(f"[Post-Processing] Task {task_id} was completed by stream processor during file search - done") return - print(f"[Post-Processing] Attempt {retry_count + 1}/{_file_search_max_retries} to find file") - print(f"[Post-Processing] Original filename: {task_basename}") + logger.warning(f"[Post-Processing] Attempt {retry_count + 1}/{_file_search_max_retries} to find file") + logger.info(f"[Post-Processing] Original filename: {task_basename}") if expected_final_filename: - print(f"[Post-Processing] Expected final filename: {expected_final_filename}") + logger.info(f"[Post-Processing] Expected final filename: {expected_final_filename}") else: - print(f"[Post-Processing] No expected final filename available") + logger.warning(f"[Post-Processing] No expected final filename available") # Strategy 1: Try with original filename in both downloads and transfer - print(f"[Post-Processing] Strategy 1: Searching with original filename...") + logger.info(f"[Post-Processing] Strategy 1: Searching with original filename...") found_file, file_location = _find_completed_file_robust(download_dir, task_filename, transfer_dir) if found_file: - print(f"[Post-Processing] Strategy 1 SUCCESS: Found file with original filename in {file_location}: {found_file}") + logger.info(f"[Post-Processing] Strategy 1 SUCCESS: Found file with original filename in {file_location}: {found_file}") else: - print(f"[Post-Processing] Strategy 1 FAILED: Original filename not found in either location") + logger.error(f"[Post-Processing] Strategy 1 FAILED: Original filename not found in either location") # Strategy 2: If not found and we have an expected final filename, try that in transfer folder if not found_file and expected_final_filename: - print(f"[Post-Processing] Strategy 2: Searching transfer folder with expected final filename...") + logger.info(f"[Post-Processing] Strategy 2: Searching transfer folder with expected final filename...") found_result = _find_completed_file_robust(transfer_dir, expected_final_filename) if found_result and found_result[0]: found_file, file_location = found_result[0], 'transfer' - print(f"[Post-Processing] Strategy 2 SUCCESS: Found file with expected final filename: {found_file}") + logger.info(f"[Post-Processing] Strategy 2 SUCCESS: Found file with expected final filename: {found_file}") else: - print(f"[Post-Processing] Strategy 2 FAILED: Expected final filename not found in transfer folder") + logger.error(f"[Post-Processing] Strategy 2 FAILED: Expected final filename not found in transfer folder") elif not expected_final_filename: - print(f"[Post-Processing] Strategy 2 SKIPPED: No expected final filename available") + logger.warning(f"[Post-Processing] Strategy 2 SKIPPED: No expected final filename available") if found_file: - print(f"[Post-Processing] FILE FOUND after {retry_count + 1} attempts in {file_location}: {found_file}") + logger.warning(f"[Post-Processing] FILE FOUND after {retry_count + 1} attempts in {file_location}: {found_file}") break else: - print(f"[Post-Processing] All search strategies failed on attempt {retry_count + 1}/{_file_search_max_retries}") + logger.error(f"[Post-Processing] All search strategies failed on attempt {retry_count + 1}/{_file_search_max_retries}") if retry_count < _file_search_max_retries - 1: # Don't sleep on final attempt - print(f"[Post-Processing] Waiting 5 seconds before next attempt...") + logger.info(f"[Post-Processing] Waiting 5 seconds before next attempt...") time.sleep(5) if not found_file: @@ -29297,7 +29220,7 @@ def _run_post_processing_worker(task_id, batch_id): with tasks_lock: if task_id in download_tasks: if download_tasks[task_id].get('stream_processed') or download_tasks[task_id]['status'] == 'completed': - print(f"[Post-Processing] Task {task_id} was completed by stream processor - not marking as failed") + logger.error(f"[Post-Processing] Task {task_id} was completed by stream processor - not marking as failed") return download_tasks[task_id]['status'] = 'failed' download_tasks[task_id]['error_message'] = f'File not found on disk after {_file_search_max_retries} search attempts. Expected: {os.path.basename(task_filename)}' @@ -29306,7 +29229,7 @@ def _run_post_processing_worker(task_id, batch_id): # Handle file found in transfer folder - already completed by stream processor if file_location == 'transfer': - print(f"[Post-Processing] File found in transfer folder - already completed by stream processor: {found_file}") + logger.info(f"[Post-Processing] File found in transfer folder - already completed by stream processor: {found_file}") # Check if metadata enhancement was completed metadata_enhanced = False @@ -29315,7 +29238,7 @@ def _run_post_processing_worker(task_id, batch_id): metadata_enhanced = download_tasks[task_id].get('metadata_enhanced', False) if not metadata_enhanced: - print(f"[Post-Processing] File in transfer folder missing metadata enhancement - completing now") + logger.warning(f"[Post-Processing] File in transfer folder missing metadata enhancement - completing now") # Attempt to complete metadata enhancement using context if context and expected_final_filename: try: @@ -29334,13 +29257,16 @@ def _run_post_processing_worker(task_id, batch_id): # If no track number in context, extract from filename if track_number == 1 and found_file: - print(f"[Verification] No track_number in context, extracting from filename: {os.path.basename(found_file)}") track_number = _extract_track_number_from_filename(found_file) - print(f" -> Extracted track number: {track_number}") + logger.warning( + "[Verification] missing track_number; extracted from filename=%r -> %s", + os.path.basename(found_file), + track_number, + ) # Ensure track_number is valid if not isinstance(track_number, int) or track_number < 1: - print(f"[Verification] Invalid track number ({track_number}), defaulting to 1") + logger.error(f"[Verification] Invalid track number ({track_number}), defaulting to 1") track_number = 1 # Get clean track name @@ -29373,42 +29299,42 @@ def _run_post_processing_worker(task_id, batch_id): consistent_album_name = _resolve_album_group(spotify_artist, album_info, original_album_ctx) album_info['album_name'] = consistent_album_name except Exception as group_err: - print(f"[Verification] Album grouping failed, using raw name: {group_err}") + logger.error(f"[Verification] Album grouping failed, using raw name: {group_err}") else: - print(f"[Verification] Explicit album download - preserving Spotify album name: '{album_info['album_name']}'") + logger.info(f"[Verification] Explicit album download - preserving Spotify album name: '{album_info['album_name']}'") - print(f"[Verification] Created proper album_info - track_number: {track_number}, album: {album_info['album_name']}") + logger.info(f"[Verification] Created proper album_info - track_number: {track_number}, album: {album_info['album_name']}") - print(f"[Post-Processing] Attempting metadata enhancement for: {found_file}") - print(f"[Metadata Input] Verification worker - artist: '{spotify_artist.get('name', 'MISSING')}' (id: {spotify_artist.get('id', 'MISSING')})") - print(f"[Metadata Input] Verification worker - album: '{album_info.get('album_name', 'MISSING')}', track#: {album_info.get('track_number', 'MISSING')}, source: {album_info.get('source', 'unknown')}") + logger.info(f"[Post-Processing] Attempting metadata enhancement for: {found_file}") + logger.warning(f"[Metadata Input] Verification worker - artist: '{spotify_artist.get('name', 'MISSING')}' (id: {spotify_artist.get('id', 'MISSING')})") + logger.warning(f"[Metadata Input] Verification worker - album: '{album_info.get('album_name', 'MISSING')}', track#: {album_info.get('track_number', 'MISSING')}, source: {album_info.get('source', 'unknown')}") enhancement_success = _enhance_file_metadata(found_file, context, spotify_artist, album_info) if enhancement_success: with tasks_lock: if task_id in download_tasks: download_tasks[task_id]['metadata_enhanced'] = True - print(f"[Post-Processing] Successfully completed metadata enhancement for: {os.path.basename(found_file)}") + logger.info(f"[Post-Processing] Successfully completed metadata enhancement for: {os.path.basename(found_file)}") else: - print(f"[Post-Processing] Metadata enhancement returned False for: {os.path.basename(found_file)}") + logger.info(f"[Post-Processing] Metadata enhancement returned False for: {os.path.basename(found_file)}") else: - print(f"[Post-Processing] Missing spotify_artist or spotify_album in context") - print(f"[Post-Processing] spotify_artist: {spotify_artist is not None}, spotify_album: {spotify_album is not None}") + logger.warning(f"[Post-Processing] Missing spotify_artist or spotify_album in context") + logger.info(f"[Post-Processing] spotify_artist: {spotify_artist is not None}, spotify_album: {spotify_album is not None}") # Wipe source tags even without full enhancement ā€” prevents # Soulseek uploader's MusicBrainz IDs from causing album splits if found_file and os.path.exists(found_file): _wipe_source_tags(found_file) except Exception as enhancement_error: import traceback - print(f"[Post-Processing] Error during metadata enhancement: {enhancement_error}\n{traceback.format_exc()}") + logger.error(f"[Post-Processing] Error during metadata enhancement: {enhancement_error}\n{traceback.format_exc()}") if found_file and os.path.exists(found_file): _wipe_source_tags(found_file) else: - print(f"[Post-Processing] Cannot complete metadata enhancement - missing context or expected filename") + logger.warning(f"[Post-Processing] Cannot complete metadata enhancement - missing context or expected filename") if found_file and os.path.exists(found_file): _wipe_source_tags(found_file) else: - print(f"[Post-Processing] File already has metadata enhancement completed") + logger.info(f"[Post-Processing] File already has metadata enhancement completed") with tasks_lock: if task_id in download_tasks: @@ -29419,7 +29345,7 @@ def _run_post_processing_worker(task_id, batch_id): with matched_context_lock: if context_key in matched_downloads_context: del matched_downloads_context[context_key] - print(f"[Verification] Cleaned up context after successful verification: {context_key}") + logger.info(f"[Verification] Cleaned up context after successful verification: {context_key}") _on_download_completed(batch_id, task_id, success=True) return @@ -29434,12 +29360,12 @@ def _run_post_processing_worker(task_id, batch_id): context = matched_downloads_context.get(context_key) if context: - print(f"[Post-Processing] Found matched context, running full post-processing for: {context_key}") + logger.info(f"[Post-Processing] Found matched context, running full post-processing for: {context_key}") # Run the existing post-processing logic with verification _post_process_matched_download_with_verification(context_key, context, found_file, task_id, batch_id) else: # No matched context - just mark as completed since file exists - print(f"[Post-Processing] No matched context, marking as completed: {os.path.basename(found_file)}") + logger.warning(f"[Post-Processing] No matched context, marking as completed: {os.path.basename(found_file)}") with tasks_lock: if task_id in download_tasks: track_info = download_tasks[task_id].get('track_info') @@ -29449,13 +29375,13 @@ def _run_post_processing_worker(task_id, batch_id): with matched_context_lock: if context_key in matched_downloads_context: del matched_downloads_context[context_key] - print(f"[Verification] Cleaned up leftover context: {context_key}") + logger.info(f"[Verification] Cleaned up leftover context: {context_key}") # Call completion callback since there's no other post-processing to handle it _on_download_completed(batch_id, task_id, success=True) except Exception as processing_error: - print(f"[Post-Processing] Processing failed for task {task_id}: {processing_error}") + logger.error(f"[Post-Processing] Processing failed for task {task_id}: {processing_error}") with tasks_lock: if task_id in download_tasks: download_tasks[task_id]['status'] = 'failed' @@ -29463,7 +29389,7 @@ def _run_post_processing_worker(task_id, batch_id): _on_download_completed(batch_id, task_id, success=False) except Exception as e: - print(f"[Post-Processing] Critical error in post-processing worker for task {task_id}: {e}") + logger.error(f"[Post-Processing] Critical error in post-processing worker for task {task_id}: {e}") with tasks_lock: if task_id in download_tasks: download_tasks[task_id]['status'] = 'failed' @@ -29480,33 +29406,33 @@ def _download_track_worker(task_id, batch_id=None): # Retrieve task details from global state with tasks_lock: if task_id not in download_tasks: - print(f"[Modal Worker] Task {task_id} not found in download_tasks") + logger.warning(f"[Modal Worker] Task {task_id} not found in download_tasks") return task = download_tasks[task_id].copy() # Cancellation Checkpoint 1: Before doing anything with tasks_lock: if task_id not in download_tasks: - print(f"[Modal Worker] Task {task_id} was deleted before starting") + logger.info(f"[Modal Worker] Task {task_id} was deleted before starting") return if download_tasks[task_id]['status'] == 'cancelled': - print(f"[Modal Worker] Task {task_id} cancelled before starting") + logger.warning(f"[Modal Worker] Task {task_id} cancelled before starting") # V2 FIX: Don't call _on_download_completed for cancelled V2 tasks # V2 system handles worker slot freeing in atomic cancel function task_playlist_id = download_tasks[task_id].get('playlist_id') if task_playlist_id: - print(f"[Modal Worker] V2 task {task_id} cancelled - worker slot already freed by V2 system") + logger.warning(f"[Modal Worker] V2 task {task_id} cancelled - worker slot already freed by V2 system") return # V2 system already handled worker slot management elif batch_id: # Legacy system - use old completion callback - print(f"[Modal Worker] Legacy task {task_id} cancelled - using legacy completion callback") + logger.warning(f"[Modal Worker] Legacy task {task_id} cancelled - using legacy completion callback") _on_download_completed(batch_id, task_id, success=False) return track_data = task['track_info'] track_name = track_data.get('name', 'Unknown Track') - print(f"[Modal Worker] Task {task_id} starting search for track: '{track_name}'") + logger.info(f"[Modal Worker] Task {task_id} starting search for track: '{track_name}'") # Recreate a SpotifyTrack object for the matching engine # Handle both string format and Spotify API format for artists @@ -29537,7 +29463,7 @@ def _download_track_worker(task_id, batch_id=None): duration_ms=track_data.get('duration_ms', 0), popularity=track_data.get('popularity', 0) ) - print(f"[Modal Worker] Starting download task for: {track.name} by {track.artists[0] if track.artists else 'Unknown'}") + logger.info(f"[Modal Worker] Starting download task for: {track.name} by {track.artists[0] if track.artists else 'Unknown'}") # === SOURCE REUSE: Check batch's last good source before searching === if _try_source_reuse(task_id, batch_id, track): @@ -29611,8 +29537,8 @@ def _download_track_worker(task_id, batch_id=None): seen.add(query.lower()) search_queries = unique_queries - print(f"[Modal Worker] Generated {len(search_queries)} smart search queries for '{track.name}': {search_queries}") - print(f"[Modal Worker] About to start search loop for task {task_id} (track: '{track.name}')") + logger.info(f"[Modal Worker] Generated {len(search_queries)} smart search queries for '{track.name}': {search_queries}") + logger.info(f"[Modal Worker] About to start search loop for task {task_id} (track: '{track.name}')") # 2. Sequential Query Search (matches GUI's start_search_worker_parallel logic) search_diagnostics = [] # Track what happened per query for detailed error messages @@ -29621,29 +29547,29 @@ def _download_track_worker(task_id, batch_id=None): # Cancellation check before each query with tasks_lock: if task_id not in download_tasks: - print(f"[Modal Worker] Task {task_id} was deleted during query {query_index + 1}") + logger.debug(f"[Modal Worker] Task {task_id} was deleted during query {query_index + 1}") return if download_tasks[task_id]['status'] == 'cancelled': - print(f"[Modal Worker] Task {task_id} cancelled during query {query_index + 1}") + logger.debug(f"[Modal Worker] Task {task_id} cancelled during query {query_index + 1}") # Don't call _on_download_completed for cancelled tasks as it can stop monitoring return download_tasks[task_id]['current_query_index'] = query_index - print(f"[Modal Worker] Query {query_index + 1}/{len(search_queries)}: '{query}'") - print(f"[DEBUG] About to call soulseek search for task {task_id}") + logger.debug(f"[Modal Worker] Query {query_index + 1}/{len(search_queries)}: '{query}'") + logger.debug(f"About to call soulseek search for task {task_id}") try: # Perform search with timeout tracks_result, _ = run_async(soulseek_client.search(query, timeout=30)) - print(f"[DEBUG] Search completed for task {task_id}, got {len(tracks_result) if tracks_result else 0} results") + logger.debug(f"Search completed for task {task_id}, got {len(tracks_result) if tracks_result else 0} results") # CRITICAL: Check cancellation immediately after search returns with tasks_lock: if task_id not in download_tasks: - print(f"[Modal Worker] Task {task_id} was deleted after search returned") + logger.info(f"[Modal Worker] Task {task_id} was deleted after search returned") return if download_tasks[task_id]['status'] == 'cancelled': - print(f"[Modal Worker] Task {task_id} cancelled after search returned - ignoring results") + logger.warning(f"[Modal Worker] Task {task_id} cancelled after search returned - ignoring results") # Don't call _on_download_completed for cancelled tasks as it can stop monitoring # The cancellation endpoint already handles batch management properly return @@ -29653,15 +29579,15 @@ def _download_track_worker(task_id, batch_id=None): # Validate candidates using GUI's get_valid_candidates logic candidates = get_valid_candidates(tracks_result, track, query) if candidates: - print(f"[Modal Worker] Found {len(candidates)} valid candidates for query '{query}'") + logger.debug(f"[Modal Worker] Found {len(candidates)} valid candidates for query '{query}'") # CRITICAL: Check cancellation before processing candidates with tasks_lock: if task_id not in download_tasks: - print(f"[Modal Worker] Task {task_id} was deleted before processing candidates") + logger.info(f"[Modal Worker] Task {task_id} was deleted before processing candidates") return if download_tasks[task_id]['status'] == 'cancelled': - print(f"[Modal Worker] Task {task_id} cancelled before processing candidates") + logger.warning(f"[Modal Worker] Task {task_id} cancelled before processing candidates") # Don't call _on_download_completed for cancelled tasks as it can stop monitoring return # Store candidates for retry fallback (like GUI) @@ -29672,7 +29598,7 @@ def _download_track_worker(task_id, batch_id=None): if success: # Download initiated successfully - let the download monitoring system handle completion if batch_id: - print(f"[Modal Worker] Download initiated successfully for task {task_id} - monitoring will handle completion") + logger.info(f"[Modal Worker] Download initiated successfully for task {task_id} - monitoring will handle completion") # Store this source for batch reuse with tasks_lock: used_filename = download_tasks.get(task_id, {}).get('filename') @@ -29689,7 +29615,7 @@ def _download_track_worker(task_id, batch_id=None): search_diagnostics.append(f'"{query}": no results found') except Exception as e: - print(f"[Modal Worker] Search failed for query '{query}': {e}") + logger.debug(f"[Modal Worker] Search failed for query '{query}': {e}") search_diagnostics.append(f'"{query}": search error ā€” {e}') continue @@ -29721,7 +29647,7 @@ def _download_track_worker(task_id, batch_id=None): # harmless (streaming sources return fast). remaining_sources = [s for s in hybrid_order[1:] if s in source_clients and source_clients[s]] if remaining_sources: - print(f"[Hybrid Fallback] Primary source had no valid matches. Trying fallback sources: {remaining_sources}") + logger.warning(f"[Hybrid Fallback] Primary source had no valid matches. Trying fallback sources: {remaining_sources}") for fallback_source in remaining_sources: fb_client = source_clients[fallback_source] @@ -29731,27 +29657,27 @@ def _download_track_worker(task_id, batch_id=None): # Use first 2 queries only for speed for fb_query in search_queries[:2]: try: - print(f"[Hybrid Fallback] Trying {fallback_source}: '{fb_query}'") + logger.warning(f"[Hybrid Fallback] Trying {fallback_source}: '{fb_query}'") fb_results, _ = run_async(fb_client.search(fb_query, timeout=20)) if not fb_results: continue fb_candidates = get_valid_candidates(fb_results, track, fb_query) if fb_candidates: - print(f"[Hybrid Fallback] {fallback_source} found {len(fb_candidates)} valid candidates!") + logger.warning(f"[Hybrid Fallback] {fallback_source} found {len(fb_candidates)} valid candidates!") success = _attempt_download_with_candidates(task_id, fb_candidates, track, batch_id) if success: return except Exception as e: - print(f"[Hybrid Fallback] {fallback_source} search failed: {e}") + logger.error(f"[Hybrid Fallback] {fallback_source} search failed: {e}") continue - print(f"[Hybrid Fallback] {fallback_source} returned no valid candidates") + logger.warning(f"[Hybrid Fallback] {fallback_source} returned no valid candidates") except Exception as e: - print(f"[Hybrid Fallback] Error in fallback logic: {e}") + logger.error(f"[Hybrid Fallback] Error in fallback logic: {e}") # If we get here, all search queries and hybrid fallbacks failed - print(f"[Modal Worker] No valid candidates found for '{track.name}' after trying all {len(search_queries)} queries.") + logger.warning(f"[Modal Worker] No valid candidates found for '{track.name}' after trying all {len(search_queries)} queries.") with tasks_lock: if task_id in download_tasks: download_tasks[task_id]['status'] = 'not_found' @@ -29766,12 +29692,12 @@ def _download_track_worker(task_id, batch_id=None): try: _on_download_completed(batch_id, task_id, success=False) except Exception as completion_error: - print(f"Error in batch completion callback for {task_id}: {completion_error}") + logger.error(f"Error in batch completion callback for {task_id}: {completion_error}") except Exception as e: import traceback track_name_safe = locals().get('track_name', 'unknown') # Safe fallback for track_name - print(f"CRITICAL ERROR in download task for '{track_name_safe}' (task_id: {task_id}): {e}") + logger.error(f"CRITICAL ERROR in download task for '{track_name_safe}' (task_id: {task_id}): {e}") traceback.print_exc() # Update task status safely with timeout @@ -29782,27 +29708,27 @@ def _download_track_worker(task_id, batch_id=None): if task_id in download_tasks: download_tasks[task_id]['status'] = 'failed' download_tasks[task_id]['error_message'] = f'Unexpected error during download: {type(e).__name__}: {e}' - print(f"[Exception Recovery] Set task {task_id} status to 'failed'") + logger.error(f"[Exception Recovery] Set task {task_id} status to 'failed'") finally: tasks_lock.release() else: - print(f"[Exception Recovery] Could not acquire lock to update task {task_id} status") + logger.error(f"[Exception Recovery] Could not acquire lock to update task {task_id} status") except Exception as status_error: - print(f"Error updating task status in exception handler: {status_error}") + logger.error(f"Error updating task status in exception handler: {status_error}") # Notify batch manager that this task completed (failed) - THREAD SAFE with RECOVERY if batch_id: try: _on_download_completed(batch_id, task_id, success=False) - print(f"[Exception Recovery] Successfully freed worker slot for task {task_id}") + logger.error(f"[Exception Recovery] Successfully freed worker slot for task {task_id}") except Exception as completion_error: - print(f"[Exception Recovery] Error in batch completion callback for {task_id}: {completion_error}") + logger.error(f"[Exception Recovery] Error in batch completion callback for {task_id}: {completion_error}") # CRITICAL: If batch completion fails, we need to manually recover the worker slot try: - print(f"[Exception Recovery] Attempting manual worker slot recovery for batch {batch_id}") + logger.error(f"[Exception Recovery] Attempting manual worker slot recovery for batch {batch_id}") _recover_worker_slot(batch_id, task_id) except Exception as recovery_error: - print(f"[Exception Recovery] FATAL: Could not recover worker slot: {recovery_error}") + logger.error(f"[Exception Recovery] FATAL: Could not recover worker slot: {recovery_error}") def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None): """ @@ -29823,10 +29749,10 @@ def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None) # Check cancellation before each attempt with tasks_lock: if task_id not in download_tasks: - print(f"[Modal Worker] Task {task_id} was deleted during candidate {candidate_index + 1}") + logger.info(f"[Modal Worker] Task {task_id} was deleted during candidate {candidate_index + 1}") return False if download_tasks[task_id]['status'] == 'cancelled': - print(f"[Modal Worker] Task {task_id} cancelled during candidate {candidate_index + 1}") + logger.warning(f"[Modal Worker] Task {task_id} cancelled during candidate {candidate_index + 1}") # Don't call _on_download_completed for cancelled tasks as it can stop monitoring return False download_tasks[task_id]['current_candidate_index'] = candidate_index @@ -29834,14 +29760,14 @@ def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None) # Create source key to avoid duplicate attempts (like GUI) source_key = f"{candidate.username}_{candidate.filename}" if source_key in used_sources: - print(f"[Modal Worker] Skipping already tried source: {source_key}") + logger.info(f"[Modal Worker] Skipping already tried source: {source_key}") continue # Blacklist check ā€” skip sources the user has flagged as bad matches try: _bl_db = get_database() if _bl_db.is_blacklisted(candidate.username, candidate.filename): - print(f"[Modal Worker] Skipping blacklisted source: {source_key}") + logger.info(f"[Modal Worker] Skipping blacklisted source: {source_key}") continue except Exception: pass @@ -29851,9 +29777,9 @@ def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None) with tasks_lock: if task_id in download_tasks: download_tasks[task_id]['used_sources'].add(source_key) - print(f"[Modal Worker] Marked source as used before download attempt: {source_key}") + logger.info(f"[Modal Worker] Marked source as used before download attempt: {source_key}") - print(f"[Modal Worker] Trying candidate {candidate_index + 1}/{len(candidates)}: {candidate.filename} (Confidence: {candidate.confidence:.2f})") + logger.info(f"[Modal Worker] Trying candidate {candidate_index + 1}/{len(candidates)}: {candidate.filename} (Confidence: {candidate.confidence:.2f})") try: # Update task status to downloading @@ -29901,7 +29827,7 @@ def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None) 'album_type': explicit_album.get('album_type', 'album'), 'artists': explicit_album.get('artists', [{'name': spotify_artist_context.get('name', '')}]) } - print(f"[Explicit Context] Using real album data: '{spotify_album_context['name']}' ({spotify_album_context['album_type']}, {spotify_album_context['total_discs']} disc(s))") + logger.info(f"[Explicit Context] Using real album data: '{spotify_album_context['name']}' ({spotify_album_context['album_type']}, {spotify_album_context['total_discs']} disc(s))") else: # Fallback to generic context for playlists/wishlists # Extract album metadata from track_info if available (discovery enriches tracks with full album objects) @@ -29939,7 +29865,7 @@ def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None) size = download_payload.get('size', 0) if not username or not filename: - print(f"[Modal Worker] Invalid candidate data: missing username or filename") + logger.error(f"[Modal Worker] Invalid candidate data: missing username or filename") continue # PROTECTION: Check if there's already an active download for this task @@ -29949,12 +29875,12 @@ def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None) current_download_id = download_tasks[task_id].get('download_id') if current_download_id: - print(f"[Modal Worker] Task {task_id} already has active download {current_download_id} - skipping new download attempt") - print(f"[Modal Worker] This prevents race condition where multiple retries start overlapping downloads") + logger.info(f"[Modal Worker] Task {task_id} already has active download {current_download_id} - skipping new download attempt") + logger.info(f"[Modal Worker] This prevents race condition where multiple retries start overlapping downloads") continue # Initiate download - print(f"[Modal Worker] Starting download: {username} / {os.path.basename(filename)}") + logger.info(f"[Modal Worker] Starting download: {username} / {os.path.basename(filename)}") download_id = run_async(soulseek_client.download(username, filename, size)) if download_id: @@ -29973,7 +29899,7 @@ def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None) enhanced_payload['spotify_clean_artist'] = track.artists[0] if track.artists else enhanced_payload.get('artist', '') # Preserve all artists for metadata tagging enhanced_payload['artists'] = [{'name': artist} for artist in track.artists] if track.artists else [] - print(f"[Context] Using clean Spotify metadata - Album: '{track.album}', Title: '{track.name}'") + logger.info(f"[Context] Using clean Spotify metadata - Album: '{track.album}', Title: '{track.name}'") # Get track_number and disc_number ā€” prefer track data we already have, # fall back to detailed API call only if needed @@ -29986,14 +29912,14 @@ def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None) enhanced_payload['track_number'] = tn enhanced_payload['disc_number'] = dn got_track_number = True - print(f"[Context] Added track_number from track_info: {tn}, disc_number: {dn}") + logger.info(f"[Context] Added track_number from track_info: {tn}, disc_number: {dn}") # 2. Try the track object itself (from album tracks response) if not got_track_number and hasattr(track, 'track_number') and track.track_number: enhanced_payload['track_number'] = track.track_number enhanced_payload['disc_number'] = getattr(track, 'disc_number', 1) or 1 got_track_number = True - print(f"[Context] Added track_number from track object: {track.track_number}, disc_number: {enhanced_payload['disc_number']}") + logger.info(f"[Context] Added track_number from track object: {track.track_number}, disc_number: {enhanced_payload['disc_number']}") # 3. Last resort ā€” fetch from metadata source API if not got_track_number and hasattr(track, 'id') and track.id: @@ -30003,7 +29929,7 @@ def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None) enhanced_payload['track_number'] = detailed_track['track_number'] enhanced_payload['disc_number'] = detailed_track.get('disc_number', 1) got_track_number = True - print(f"[Context] Added track_number from API: {detailed_track['track_number']}, disc_number: {enhanced_payload['disc_number']}") + logger.info(f"[Context] Added track_number from API: {detailed_track['track_number']}, disc_number: {enhanced_payload['disc_number']}") # Backfill album metadata from detailed track when context # has incomplete data (missing release_date, total_tracks, etc.) @@ -30011,7 +29937,7 @@ def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None) dt_album = detailed_track['album'] if not spotify_album_context.get('release_date') and dt_album.get('release_date'): spotify_album_context['release_date'] = dt_album['release_date'] - print(f"[Context] Backfilled release_date from API: {dt_album['release_date']}") + logger.info(f"[Context] Backfilled release_date from API: {dt_album['release_date']}") if not spotify_album_context.get('album_type') and dt_album.get('album_type'): spotify_album_context['album_type'] = dt_album['album_type'] if not spotify_album_context.get('total_tracks') and dt_album.get('total_tracks'): @@ -30021,18 +29947,18 @@ def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None) if not spotify_album_context.get('image_url') and dt_album.get('images'): spotify_album_context['image_url'] = dt_album['images'][0].get('url', '') except Exception as e: - print(f"[Context] API track details failed: {e}") + logger.error(f"[Context] API track details failed: {e}") if not got_track_number: enhanced_payload.setdefault('track_number', 0) enhanced_payload.setdefault('disc_number', 1) - print(f"[Context] No track_number found from any source") + logger.warning(f"[Context] No track_number found from any source") # Determine if this should be treated as album download # First check if we have explicit album context from artist page if has_explicit_context: is_album_context = True - print(f"[Context] Using explicit album context flag from artist page") + logger.info(f"[Context] Using explicit album context flag from artist page") else: # Fall back to guessing based on clean data is_album_context = ( @@ -30051,7 +29977,7 @@ def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None) enhanced_payload['artists'] = [{'name': enhanced_payload['artist']}] enhanced_payload['track_number'] = track_info.get('track_number', 1) # Fallback when no clean Spotify data is_album_context = False - print(f"[Context] Using fallback data - no clean Spotify metadata available, track_number={enhanced_payload['track_number']}") + logger.warning(f"[Context] Using fallback data - no clean Spotify metadata available, track_number={enhanced_payload['track_number']}") matched_downloads_context[context_key] = { "spotify_artist": spotify_artist_context, @@ -30065,21 +29991,21 @@ def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None) "_download_username": username, # Source username for AcoustID skip logic } - print(f"[Context] Set is_album_download: {is_album_context} (has clean data: {has_clean_spotify_data})") - print(f"[Debug] Context creation - track_info: {track_info is not None}, playlist_folder_mode: {track_info.get('_playlist_folder_mode', False) if track_info else False}") + logger.info(f"[Context] Set is_album_download: {is_album_context} (has clean data: {has_clean_spotify_data})") + logger.debug(f"[Debug] Context creation - track_info: {track_info is not None}, playlist_folder_mode: {track_info.get('_playlist_folder_mode', False) if track_info else False}") # Update task with successful download info with tasks_lock: if task_id in download_tasks: # PHASE 3: Final cancellation check after download started (GUI PARITY) if download_tasks[task_id]['status'] == 'cancelled': - print(f"[Modal Worker] Task {task_id} cancelled after download {download_id} started - attempting to cancel download") + logger.warning(f"[Modal Worker] Task {task_id} cancelled after download {download_id} started - attempting to cancel download") # Try to cancel the download immediately try: run_async(soulseek_client.cancel_download(download_id, username, remove=True)) - print(f"Successfully cancelled active download {download_id}") + logger.warning(f"Successfully cancelled active download {download_id}") except Exception as cancel_error: - print(f"Warning: Failed to cancel active download {download_id}: {cancel_error}") + logger.error(f"Failed to cancel active download {download_id}: {cancel_error}") # Free worker slot if batch_id: @@ -30093,10 +30019,10 @@ def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None) download_tasks[task_id]['username'] = username download_tasks[task_id]['filename'] = filename - print(f"[Modal Worker] Download started successfully for '{filename}'. Download ID: {download_id}") + logger.info(f"[Modal Worker] Download started successfully for '{filename}'. Download ID: {download_id}") return True # Success! else: - print(f"[Modal Worker] Failed to start download for '{filename}'") + logger.error(f"[Modal Worker] Failed to start download for '{filename}'") # Reset status back to searching for next attempt with tasks_lock: if task_id in download_tasks: @@ -30105,7 +30031,7 @@ def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None) except Exception as e: import traceback - print(f"[Modal Worker] Error attempting download for '{candidate.filename}': {e}") + logger.error(f"[Modal Worker] Error attempting download for '{candidate.filename}': {e}") traceback.print_exc() # Reset status back to searching for next attempt with tasks_lock: @@ -30114,7 +30040,7 @@ def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None) continue # All candidates failed - print(f"[Modal Worker] All {len(candidates)} candidates failed for '{track.name}'") + logger.error(f"[Modal Worker] All {len(candidates)} candidates failed for '{track.name}'") return False # ā”€ā”€ Staging folder match cache (per-batch, avoids re-scanning for every track) ā”€ā”€ @@ -30155,7 +30081,7 @@ def _get_staging_file_cache(batch_id): 'extension': ext, }) - print(f"[Staging] Scanned {len(files)} audio files in staging folder") + logger.info(f"[Staging] Scanned {len(files)} audio files in staging folder") with _staging_cache_lock: _staging_cache[batch_id] = files return files @@ -30223,7 +30149,7 @@ def _try_staging_match(task_id, batch_id, track): if not best_match or best_score < 0.75: return False - print(f"[Staging] Match found for '{track_title}' by '{track_artist}': " + logger.info(f"[Staging] Match found for '{track_title}' by '{track_artist}': " f"{os.path.basename(best_match['full_path'])} (score: {best_score:.2f})") # Copy the file to the transfer folder @@ -30240,7 +30166,7 @@ def _try_staging_match(task_id, batch_id, track): import shutil shutil.copy2(best_match['full_path'], dest_path) - print(f"[Staging] Copied to transfer: {dest_path}") + logger.info(f"[Staging] Copied to transfer: {dest_path}") # Mark task as completed with staging context with tasks_lock: @@ -30360,7 +30286,7 @@ def _try_staging_match(task_id, batch_id, track): return True except Exception as e: - print(f"[Staging] Failed to use staging file: {e}") + logger.error(f"[Staging] Failed to use staging file: {e}") return False @@ -30576,7 +30502,7 @@ def start_playlist_missing_downloads(playlist_id): missing_tracks = [t for t in missing_tracks if not _is_explicit_blocked(t.get('track', t))] skipped = before_count - len(missing_tracks) if skipped > 0: - print(f"[Content Filter] Filtered out {skipped} explicit track(s) from playlist download") + logger.warning(f"[Content Filter] Filtered out {skipped} explicit track(s) from playlist download") if not missing_tracks: return jsonify({"success": False, "error": "All tracks were filtered by explicit content setting"}), 400 @@ -30637,7 +30563,7 @@ def start_playlist_missing_downloads(playlist_id): return jsonify({"success": True, "batch_id": batch_id, "message": f"Queued {len(missing_tracks)} downloads for processing."}) except Exception as e: - print(f"Error starting missing downloads: {e}") + logger.error(f"Error starting missing downloads: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/active-processes', methods=['GET']) @@ -30695,7 +30621,7 @@ def get_active_processes(): "download_process_id": state.get('download_process_id') # batch_id for download modal rehydration }) - print(f"Active processes check: {len([p for p in active_processes if p['type'] == 'batch'])} download batches, {len([p for p in active_processes if p['type'] == 'youtube_playlist'])} YouTube playlists") + logger.info(f"Active processes check: {len([p for p in active_processes if p['type'] == 'batch'])} download batches, {len([p for p in active_processes if p['type'] == 'youtube_playlist'])} YouTube playlists") return jsonify({"active_processes": active_processes}) def _build_batch_status_data(batch_id, batch, live_transfers_lookup): @@ -30745,21 +30671,21 @@ def _build_batch_status_data(batch_id, batch, live_transfers_lookup): transfer_dir = docker_resolve_path(config_manager.get('soulseek.transfer_path', './Transfer')) found_file, file_location = _find_completed_file_robust(download_dir, task_filename, transfer_dir) if found_file: - print(f"[Safety Valve] Task {task_id} stuck but file found in {file_location} ā€” routing to post-processing") + logger.info(f"[Safety Valve] Task {task_id} stuck but file found in {file_location} ā€” routing to post-processing") task['status'] = 'post_processing' task['status_change_time'] = current_time missing_download_executor.submit(_run_post_processing_worker, task_id, batch_id) recovered = True except Exception as e: - print(f"[Safety Valve] Error checking for completed file: {e}") + logger.error(f"[Safety Valve] Error checking for completed file: {e}") if not recovered: if stuck_state == 'searching': - print(f"ā° [Safety Valve] Task {task_id} stuck in searching for {task_age:.1f}s - marking not_found") + logger.info(f"ā° [Safety Valve] Task {task_id} stuck in searching for {task_age:.1f}s - marking not_found") task['status'] = 'not_found' task['error_message'] = f'Search stuck for {int(task_age // 60)} minutes with no results ā€” timed out' else: - print(f"ā° [Safety Valve] Task {task_id} stuck for {task_age:.1f}s - forcing failure") + logger.error(f"ā° [Safety Valve] Task {task_id} stuck for {task_age:.1f}s - forcing failure") task['status'] = 'failed' task['error_message'] = f'Task stuck in {stuck_state} state for {int(task_age // 60)} minutes ā€” forcibly stopped' @@ -30797,7 +30723,7 @@ def _build_batch_status_data(batch_id, batch, live_transfers_lookup): elif 'Failed' in state_str or 'Errored' in state_str or 'Rejected' in state_str or 'TimedOut' in state_str: # UNIFIED ERROR HANDLING: Let monitor handle errors for consistency # Monitor will detect errored state and trigger retry within 5 seconds - print(f"Task {task_id} API shows error state: {state_str} - letting monitor handle retry") + logger.error(f"Task {task_id} API shows error state: {state_str} - letting monitor handle retry") # Keep task in current status (downloading/queued) so monitor can detect error # Don't mark as failed here - let the unified retry system handle it @@ -30813,13 +30739,13 @@ def _build_batch_status_data(batch_id, batch, live_transfers_lookup): if expected_size > 0 and transferred < expected_size: # State says complete but bytes don't match ā€” keep current status task_status['status'] = task['status'] - print(f"Task {task_id} state says complete but bytes incomplete ({transferred}/{expected_size})") + logger.info(f"Task {task_id} state says complete but bytes incomplete ({transferred}/{expected_size})") # NEW VERIFICATION WORKFLOW: Use intermediate post_processing status # Only set this status once to prevent multiple worker submissions elif task['status'] != 'post_processing': task_status['status'] = 'post_processing' task['status'] = 'post_processing' - print(f"Task {task_id} API reports 'Succeeded' - starting post-processing verification") + logger.info(f"Task {task_id} API reports 'Succeeded' - starting post-processing verification") # Submit post-processing worker to verify file and complete the task missing_download_executor.submit(_run_post_processing_worker, task_id, batch_id) @@ -30827,7 +30753,7 @@ def _build_batch_status_data(batch_id, batch, live_transfers_lookup): # FIXED: Always require verification workflow - no bypass for stream processed tasks # Stream processing only handles metadata, not file verification task_status['status'] = 'post_processing' - print(f"Task {task_id} waiting for verification worker to complete") + logger.info(f"Task {task_id} waiting for verification worker to complete") elif 'InProgress' in state_str: task_status['status'] = 'downloading' else: @@ -30921,7 +30847,7 @@ def get_batched_download_statuses(): ) except Exception as batch_error: # Don't fail entire request if one batch has issues - print(f"Error processing batch {batch_id}: {batch_error}") + logger.error(f"Error processing batch {batch_id}: {batch_error}") response["batches"][batch_id] = {"error": str(batch_error)} # Add metadata for debugging/monitoring @@ -30950,12 +30876,12 @@ def get_batched_download_statuses(): response["debug_info"] = debug_info - print(f"[Batched Status] Returning status for {len(response['batches'])} batches") + logger.info(f"[Batched Status] Returning status for {len(response['batches'])} batches") # Log worker discrepancies for debugging discrepancies = [bid for bid, info in debug_info.items() if info.get("worker_discrepancy")] if discrepancies: - print(f"[Batched Status] Worker count discrepancies in batches: {discrepancies}") + logger.info(f"[Batched Status] Worker count discrepancies in batches: {discrepancies}") return jsonify(response) @@ -31165,7 +31091,7 @@ def cancel_download_task(): current_status = task.get('status', 'unknown') download_id = task.get('download_id') username = task.get('username') - print(f"[Cancel Debug] Task {task_id} - Current status: '{current_status}', download_id: {download_id}, username: {username}") + logger.info(f"[Cancel Debug] Task {task_id} - Current status: '{current_status}', download_id: {download_id}, username: {username}") # Immediately mark as cancelled to prevent race conditions task['status'] = 'cancelled' @@ -31185,8 +31111,8 @@ def cancel_download_task(): # Free worker slot if there are active workers and task was actively running # This is more reliable than checking task status which can be inconsistent if active_count > 0 and current_status in ['pending', 'searching', 'downloading', 'queued']: - print(f"[Cancel] Task {task_id} (status: {current_status}) - freeing worker slot for batch {batch_id}") - print(f"[Cancel] Active count before: {active_count}") + logger.info(f"[Cancel] Task {task_id} (status: {current_status}) - freeing worker slot for batch {batch_id}") + logger.info(f"[Cancel] Active count before: {active_count}") # Use the completion callback with error handling _on_download_completed(batch_id, task_id, success=False) @@ -31194,35 +31120,35 @@ def cancel_download_task(): # Verify slot was actually freed new_active = download_batches[batch_id]['active_count'] - print(f"[Cancel] Active count after: {new_active}") + logger.info(f"[Cancel] Active count after: {new_active}") elif active_count == 0: - print(f"[Cancel] Task {task_id} - no active workers to free") + logger.warning(f"[Cancel] Task {task_id} - no active workers to free") else: - print(f"[Cancel] Task {task_id} (status: {current_status}) - not actively running, no slot to free") + logger.warning(f"[Cancel] Task {task_id} (status: {current_status}) - not actively running, no slot to free") else: - print(f"[Cancel] Task {task_id} - batch {batch_id} not found") + logger.warning(f"[Cancel] Task {task_id} - batch {batch_id} not found") except Exception as slot_error: - print(f"[Cancel] Error managing worker slot for {task_id}: {slot_error}") + logger.error(f"[Cancel] Error managing worker slot for {task_id}: {slot_error}") # Attempt emergency recovery if normal completion failed if not worker_slot_freed: try: - print(f"[Cancel] Attempting emergency worker slot recovery") + logger.warning(f"[Cancel] Attempting emergency worker slot recovery") _recover_worker_slot(batch_id, task_id) except Exception as recovery_error: - print(f"[Cancel] FATAL: Emergency recovery failed: {recovery_error}") + logger.error(f"[Cancel] FATAL: Emergency recovery failed: {recovery_error}") else: - print(f"[Cancel] Task {task_id} cancelled (no batch_id - likely already completed)") + logger.warning(f"[Cancel] Task {task_id} cancelled (no batch_id - likely already completed)") # Optionally try to cancel the Soulseek download (don't block worker progression) if download_id and username: try: # This is an async call, so we run it and wait run_async(soulseek_client.cancel_download(download_id, username, remove=True)) - print(f"Successfully cancelled Soulseek download {download_id} for task {task_id}") + logger.warning(f"Successfully cancelled Soulseek download {download_id} for task {task_id}") except Exception as e: - print(f"Warning: Failed to cancel download on slskd, but worker already moved on. Error: {e}") + logger.error(f"Failed to cancel download on slskd, but worker already moved on: {e}") ### NEW LOGIC START: Add cancelled track to wishlist ### try: @@ -31293,11 +31219,11 @@ def cancel_download_task(): ) if success: - print(f"Added cancelled track '{track_info.get('name')}' to wishlist.") + logger.warning(f"Added cancelled track '{track_info.get('name')}' to wishlist.") else: - print(f"Failed to add cancelled track '{track_info.get('name')}' to wishlist.") + logger.error(f"Failed to add cancelled track '{track_info.get('name')}' to wishlist.") except Exception as e: - print(f"CRITICAL ERROR adding cancelled track to wishlist: {e}") + logger.error(f"CRITICAL ERROR adding cancelled track to wishlist: {e}") ### NEW LOGIC END ### return jsonify({"success": True, "message": "Task cancelled and added to wishlist for retry."}) @@ -31340,7 +31266,7 @@ def _atomic_cancel_task(playlist_id, track_index): original_status = current_status # Store original status before changing it batch_id = task.get('batch_id') - print(f"[Atomic Cancel] Starting atomic cancel: playlist={playlist_id}, track={track_index}, task={task_id}, status={current_status}") + logger.info(f"[Atomic Cancel] Starting atomic cancel: playlist={playlist_id}, track={track_index}, task={task_id}, status={current_status}") # Mark task as cancelled immediately (within same lock context) task['status'] = 'cancelled' @@ -31361,23 +31287,23 @@ def _atomic_cancel_task(playlist_id, track_index): # Free worker slot if task was consuming one # More precise check: only free if task was actually running if active_count > 0 and current_status in ['pending', 'searching', 'downloading', 'queued']: - print(f"[Atomic Cancel] Freeing worker slot for {task_id} (was {current_status})") + logger.info(f"[Atomic Cancel] Freeing worker slot for {task_id} (was {current_status})") # CRITICAL: Direct worker slot management to prevent _on_download_completed race old_active = batch['active_count'] batch['active_count'] = max(0, old_active - 1) # Prevent negative counts worker_slot_freed = True - print(f"[Atomic Cancel] Worker count: {old_active} ā†’ {batch['active_count']}") + logger.info(f"[Atomic Cancel] Worker count: {old_active} ā†’ {batch['active_count']}") # Try to start next task if available (still within lock) if (batch['queue_index'] < len(batch['queue']) and batch['active_count'] < batch['max_concurrent']): - print(f"[Atomic Cancel] Starting next task in queue") + logger.info(f"[Atomic Cancel] Starting next task in queue") # Call the existing function to start next downloads # Note: This will be called outside the lock to prevent deadlock else: - print(f"[Atomic Cancel] No next task to start (queue_index: {batch['queue_index']}/{len(batch['queue'])}, active: {batch['active_count']}/{batch['max_concurrent']})") + logger.warning(f"[Atomic Cancel] No next task to start (queue_index: {batch['queue_index']}/{len(batch['queue'])}, active: {batch['active_count']}/{batch['max_concurrent']})") # Build result info task_info = { @@ -31390,11 +31316,11 @@ def _atomic_cancel_task(playlist_id, track_index): 'worker_slot_freed': worker_slot_freed } - print(f"[Atomic Cancel] Successfully cancelled task {task_id}") + logger.warning(f"[Atomic Cancel] Successfully cancelled task {task_id}") return True, "Task cancelled successfully", task_info except Exception as e: - print(f"[Atomic Cancel] Error in atomic cancel: {e}") + logger.error(f"[Atomic Cancel] Error in atomic cancel: {e}") import traceback traceback.print_exc() return False, f"Internal error: {str(e)}", None @@ -31437,14 +31363,14 @@ def cancel_task_v2(): try: _start_next_batch_of_downloads(batch_id) except Exception as e: - print(f"[Atomic Cancel] Warning: Could not start next downloads: {e}") + logger.error(f"[Atomic Cancel] Could not start next downloads: {e}") # CRITICAL: Check for batch completion after V2 cancel # V2 system bypasses _on_download_completed, so we need to check completion manually try: _check_batch_completion_v2(batch_id) except Exception as e: - print(f"[Atomic Cancel] Warning: Could not check batch completion: {e}") + logger.error(f"[Atomic Cancel] Could not check batch completion: {e}") # Cancel Soulseek download if active (non-blocking) if task: @@ -31453,27 +31379,27 @@ def cancel_task_v2(): current_status = task.get('status') original_status = task_info.get('original_status', current_status) # Get original status from task_info - print(f"[Atomic Cancel] Task {task_id} state: status='{current_status}', original_status='{original_status}', download_id='{download_id}', username='{username}'") - print(f"[Atomic Cancel] Download ID type: {type(download_id)}, length: {len(str(download_id)) if download_id else 0}") + logger.info(f"[Atomic Cancel] Task {task_id} state: status='{current_status}', original_status='{original_status}', download_id='{download_id}', username='{username}'") + logger.info(f"[Atomic Cancel] Download ID type: {type(download_id)}, length: {len(str(download_id)) if download_id else 0}") backslash = '\\' - print(f"[Atomic Cancel] Download ID looks like filename: {download_id and ('/' in str(download_id) or backslash in str(download_id))}") + logger.info(f"[Atomic Cancel] Download ID looks like filename: {download_id and ('/' in str(download_id) or backslash in str(download_id))}") if download_id and username: # Always try to cancel in slskd - doesn't matter what status it was # If it's not there or already done, the DELETE request will just fail harmlessly try: - print(f"[Atomic Cancel] Attempting to cancel Soulseek download:") - print(f" Username: {username}") - print(f" Download ID: {download_id}") - print(f" Base URL: {soulseek_client.base_url}") - print(f" Expected URL: {soulseek_client.base_url}/transfers/downloads/{username}/{download_id}?remove=true") + logger.info(f"[Atomic Cancel] Attempting to cancel Soulseek download:") + logger.info(f" Username: {username}") + logger.info(f" Download ID: {download_id}") + logger.info(f" Base URL: {soulseek_client.base_url}") + logger.info(f" Expected URL: {soulseek_client.base_url}/transfers/downloads/{username}/{download_id}?remove=true") # CRITICAL: Must use REAL download ID from slskd, not filename success = False real_download_id = None # Step 1: Always search for real download ID first - print(f"[Atomic Cancel] Searching slskd transfers for real download ID") + logger.info(f"[Atomic Cancel] Searching slskd transfers for real download ID") try: all_transfers = run_async(soulseek_client._make_request('GET', 'transfers/downloads')) if all_transfers: @@ -31487,68 +31413,68 @@ def cancel_task_v2(): if (file_filename == download_id or __import__('os').path.basename(file_filename) == __import__('os').path.basename(str(download_id))): real_download_id = file_data.get('id') - print(f"[Atomic Cancel] Found real download ID: {real_download_id} for file: {file_filename}") + logger.info(f"[Atomic Cancel] Found real download ID: {real_download_id} for file: {file_filename}") break if real_download_id: break if real_download_id: break except Exception as search_error: - print(f"[Atomic Cancel] Error searching transfers: {search_error}") + logger.error(f"[Atomic Cancel] Error searching transfers: {search_error}") # Step 2: Try cancellation with real ID if found if real_download_id: - print(f"[Atomic Cancel] Attempting cancel with real ID: {real_download_id}") + logger.info(f"[Atomic Cancel] Attempting cancel with real ID: {real_download_id}") try: # Use EXACT format from slskd web UI: DELETE /api/v0/transfers/downloads/{username}/{download_id}?remove=false endpoint = f'transfers/downloads/{username}/{real_download_id}?remove=true' - print(f"[Atomic Cancel] Using slskd web UI format: {endpoint}") + logger.info(f"[Atomic Cancel] Using slskd web UI format: {endpoint}") response = run_async(soulseek_client._make_request('DELETE', endpoint)) if response is not None: - print(f"[Atomic Cancel] Successfully cancelled with slskd web UI format: {real_download_id}") + logger.warning(f"[Atomic Cancel] Successfully cancelled with slskd web UI format: {real_download_id}") success = True else: - print(f"[Atomic Cancel] Web UI format failed, trying alternative formats") + logger.error(f"[Atomic Cancel] Web UI format failed, trying alternative formats") # Fallback: Try without remove parameter endpoint2 = f'transfers/downloads/{username}/{real_download_id}' response2 = run_async(soulseek_client._make_request('DELETE', endpoint2)) if response2 is not None: - print(f"[Atomic Cancel] Successfully cancelled without remove param: {real_download_id}") + logger.warning(f"[Atomic Cancel] Successfully cancelled without remove param: {real_download_id}") success = True else: # Final fallback: Try simple format (sync.py style) endpoint3 = f'transfers/downloads/{real_download_id}' response3 = run_async(soulseek_client._make_request('DELETE', endpoint3)) if response3 is not None: - print(f"[Atomic Cancel] Successfully cancelled with simple format: {real_download_id}") + logger.warning(f"[Atomic Cancel] Successfully cancelled with simple format: {real_download_id}") success = True else: - print(f"[Atomic Cancel] All DELETE formats failed for real ID: {real_download_id}") + logger.error(f"[Atomic Cancel] All DELETE formats failed for real ID: {real_download_id}") except Exception as cancel_error: - print(f"[Atomic Cancel] Exception cancelling real ID {real_download_id}: {cancel_error}") + logger.error(f"[Atomic Cancel] Exception cancelling real ID {real_download_id}: {cancel_error}") else: - print(f"[Atomic Cancel] Could not find real download ID in slskd transfers") - print(f"[Atomic Cancel] This might be a pending download not yet in slskd - relying on status='cancelled' to prevent it") + logger.error(f"[Atomic Cancel] Could not find real download ID in slskd transfers") + logger.warning(f"[Atomic Cancel] This might be a pending download not yet in slskd - relying on status='cancelled' to prevent it") # For pending downloads, the status='cancelled' will prevent them from starting success = True # Consider this success since pending downloads are prevented if not success: - print(f"[Atomic Cancel] Failed to cancel download in slskd API") + logger.error(f"[Atomic Cancel] Failed to cancel download in slskd API") except Exception as e: - print(f"[Atomic Cancel] Exception cancelling Soulseek download {download_id}: {e}") + logger.error(f"[Atomic Cancel] Exception cancelling Soulseek download {download_id}: {e}") # Print more details about the error import traceback - print(f"[Atomic Cancel] Cancel error traceback: {traceback.format_exc()}") + logger.error(f"[Atomic Cancel] Cancel error traceback: {traceback.format_exc()}") else: - print(f"ā„¹ļø [Atomic Cancel] No download_id or username available - skipping slskd cancel") + logger.warning(f"ā„¹ļø [Atomic Cancel] No download_id or username available - skipping slskd cancel") # Add to wishlist (non-blocking, best effort) try: _add_cancelled_task_to_wishlist(task) except Exception as e: - print(f"[Atomic Cancel] Warning: Could not add to wishlist: {e}") + logger.error(f"[Atomic Cancel] Could not add to wishlist: {e}") return jsonify({ "success": True, @@ -31561,7 +31487,7 @@ def cancel_task_v2(): }) except Exception as e: - print(f"[Cancel V2] Unexpected error: {e}") + logger.error(f"[Cancel V2] Unexpected error: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -31576,7 +31502,7 @@ def _check_batch_completion_v2(batch_id): try: with tasks_lock: if batch_id not in download_batches: - print(f"[Completion Check V2] Batch {batch_id} not found") + logger.warning(f"[Completion Check V2] Batch {batch_id} not found") return batch = download_batches[batch_id] @@ -31598,7 +31524,7 @@ def _check_batch_completion_v2(batch_id): if task_status == 'searching': task_age = current_time - task.get('status_change_time', current_time) if task_age > 600: # 10 minutes - print(f"ā° [Stuck Detection V2] Task {task_id} stuck in searching for {task_age:.0f}s - forcing not_found") + logger.info(f"ā° [Stuck Detection V2] Task {task_id} stuck in searching for {task_age:.0f}s - forcing not_found") task['status'] = 'not_found' task['error_message'] = f'Search stuck for {int(task_age // 60)} minutes with no results ā€” timed out' finished_count += 1 @@ -31607,7 +31533,7 @@ def _check_batch_completion_v2(batch_id): elif task_status == 'post_processing': task_age = current_time - task.get('status_change_time', current_time) if task_age > 300: # 5 minutes (post-processing should be fast) - print(f"ā° [Stuck Detection V2] Task {task_id} stuck in post_processing for {task_age:.0f}s - forcing completion") + logger.info(f"ā° [Stuck Detection V2] Task {task_id} stuck in post_processing for {task_age:.0f}s - forcing completion") task['status'] = 'completed' # Assume it worked if file verification is taking too long finished_count += 1 else: @@ -31616,18 +31542,18 @@ def _check_batch_completion_v2(batch_id): finished_count += 1 else: # Task ID in queue but not in download_tasks - treat as completed to prevent blocking - print(f"[Orphaned Task V2] Task {task_id} in queue but not in download_tasks - counting as finished") + logger.warning(f"[Orphaned Task V2] Task {task_id} in queue but not in download_tasks - counting as finished") finished_count += 1 all_tasks_truly_finished = finished_count >= len(queue) has_retrying_tasks = retrying_count > 0 - print(f"[Completion Check V2] Batch {batch_id}: tasks_started={all_tasks_started}, workers={no_active_workers}, finished={finished_count}/{len(queue)}, retrying={retrying_count}") + logger.warning(f"[Completion Check V2] Batch {batch_id}: tasks_started={all_tasks_started}, workers={no_active_workers}, finished={finished_count}/{len(queue)}, retrying={retrying_count}") if all_tasks_started and no_active_workers and all_tasks_truly_finished and not has_retrying_tasks: # FIXED: Ensure batch is not already marked as complete to prevent duplicate processing if batch.get('phase') != 'complete': - print(f"[Completion Check V2] Batch {batch_id} is complete - marking as finished") + logger.info(f"[Completion Check V2] Batch {batch_id} is complete - marking as finished") # Check if this is an auto-initiated batch is_auto_batch = batch.get('auto_initiated', False) @@ -31655,7 +31581,7 @@ def _check_batch_completion_v2(batch_id): except Exception: pass else: - print(f"[Completion Check V2] Batch {batch_id} already marked complete - skipping duplicate processing") + logger.warning(f"[Completion Check V2] Batch {batch_id} already marked complete - skipping duplicate processing") return True # Already complete # Update YouTube playlist phase to 'download_complete' if this is a YouTube playlist @@ -31664,30 +31590,30 @@ def _check_batch_completion_v2(batch_id): url_hash = playlist_id.replace('youtube_', '') if url_hash in youtube_playlist_states: youtube_playlist_states[url_hash]['phase'] = 'download_complete' - print(f"[Completion Check V2] Updated YouTube playlist {url_hash} to download_complete phase") + logger.info(f"[Completion Check V2] Updated YouTube playlist {url_hash} to download_complete phase") # Update Tidal playlist phase to 'download_complete' if this is a Tidal playlist if playlist_id and playlist_id.startswith('tidal_'): tidal_playlist_id = playlist_id.replace('tidal_', '') if tidal_playlist_id in tidal_discovery_states: tidal_discovery_states[tidal_playlist_id]['phase'] = 'download_complete' - print(f"[Completion Check V2] Updated Tidal playlist {tidal_playlist_id} to download_complete phase") + logger.info(f"[Completion Check V2] Updated Tidal playlist {tidal_playlist_id} to download_complete phase") # Update Deezer playlist phase to 'download_complete' if this is a Deezer playlist if playlist_id and playlist_id.startswith('deezer_'): deezer_playlist_id = playlist_id.replace('deezer_', '') if deezer_playlist_id in deezer_discovery_states: deezer_discovery_states[deezer_playlist_id]['phase'] = 'download_complete' - print(f"[Completion Check V2] Updated Deezer playlist {deezer_playlist_id} to download_complete phase") + logger.info(f"[Completion Check V2] Updated Deezer playlist {deezer_playlist_id} to download_complete phase") # Update Spotify Public playlist phase to 'download_complete' if this is a Spotify Public playlist if playlist_id and playlist_id.startswith('spotify_public_'): spotify_public_url_hash = playlist_id.replace('spotify_public_', '') if spotify_public_url_hash in spotify_public_discovery_states: spotify_public_discovery_states[spotify_public_url_hash]['phase'] = 'download_complete' - print(f"[Completion Check V2] Updated Spotify Public playlist {spotify_public_url_hash} to download_complete phase") + logger.info(f"[Completion Check V2] Updated Spotify Public playlist {spotify_public_url_hash} to download_complete phase") - print(f"[Completion Check V2] Batch {batch_id} complete - stopping monitor") + logger.info(f"[Completion Check V2] Batch {batch_id} complete - stopping monitor") download_monitor.stop_monitoring(batch_id) # REPAIR: Scan all album folders from this batch for track number issues @@ -31715,32 +31641,32 @@ def _check_batch_completion_v2(batch_id): file_lock_fn=_get_file_lock, ) if _cons_result.get('success'): - print(f"[Album Consistency V2] {_cons_result['tags_written']}/{_cons_result['total_files']} files " + logger.info(f"[Album Consistency V2] {_cons_result['tags_written']}/{_cons_result['total_files']} files " f"harmonized to release {_cons_result.get('release_mbid', '')[:8]}...") elif _cons_result.get('error'): - print(f"[Album Consistency V2] Skipped: {_cons_result['error']}") + logger.error(f"[Album Consistency V2] Skipped: {_cons_result['error']}") except Exception as cons_err: - print(f"[Album Consistency V2] Failed (non-fatal): {cons_err}") + logger.error(f"[Album Consistency V2] Failed (non-fatal): {cons_err}") # Process wishlist outside of the lock to prevent threading issues if all_tasks_started and no_active_workers and all_tasks_truly_finished and not has_retrying_tasks: # Call wishlist processing outside the lock if is_auto_batch: - print(f"[Completion Check V2] Processing auto-initiated batch completion") + logger.info(f"[Completion Check V2] Processing auto-initiated batch completion") # Use the existing auto-completion function _process_failed_tracks_to_wishlist_exact_with_auto_completion(batch_id) else: - print(f"[Completion Check V2] Processing regular batch completion") + logger.info(f"[Completion Check V2] Processing regular batch completion") # Use the regular completion function _process_failed_tracks_to_wishlist_exact(batch_id) return True # Batch was completed else: - print(f"[Completion Check V2] Batch {batch_id} not yet complete: finished={finished_count}/{len(queue)}, retrying={retrying_count}, workers={batch['active_count']}") + logger.warning(f"[Completion Check V2] Batch {batch_id} not yet complete: finished={finished_count}/{len(queue)}, retrying={retrying_count}, workers={batch['active_count']}") return False # Batch still in progress except Exception as e: - print(f"[Completion Check V2] Error checking batch completion: {e}") + logger.error(f"[Completion Check V2] Error checking batch completion: {e}") import traceback traceback.print_exc() return False @@ -31816,12 +31742,12 @@ def _add_cancelled_task_to_wishlist(task): ) if success: - print(f"[Atomic Cancel] Added '{track_info.get('name')}' to wishlist") + logger.info(f"[Atomic Cancel] Added '{track_info.get('name')}' to wishlist") else: - print(f"[Atomic Cancel] Failed to add '{track_info.get('name')}' to wishlist") + logger.error(f"[Atomic Cancel] Failed to add '{track_info.get('name')}' to wishlist") except Exception as e: - print(f"[Atomic Cancel] Critical error adding to wishlist: {e}") + logger.error(f"[Atomic Cancel] Critical error adding to wishlist: {e}") @app.route('/api/playlists//cancel_batch', methods=['POST']) def cancel_batch(batch_id): @@ -31849,16 +31775,16 @@ def cancel_batch(batch_id): with wishlist_timer_lock: wishlist_auto_processing = False wishlist_auto_processing_timestamp = 0 - print(f"[Wishlist Cancel] Reset wishlist auto-processing flag for cancelled auto-batch") + logger.warning(f"[Wishlist Cancel] Reset wishlist auto-processing flag for cancelled auto-batch") else: - print(f"ā„¹ļø [Wishlist Cancel] Manual wishlist batch cancelled (no flag reset needed)") + logger.warning(f"ā„¹ļø [Wishlist Cancel] Manual wishlist batch cancelled (no flag reset needed)") # Reset YouTube playlist phase to 'discovered' if this is a YouTube playlist if playlist_id and playlist_id.startswith('youtube_'): url_hash = playlist_id.replace('youtube_', '') if url_hash in youtube_playlist_states: youtube_playlist_states[url_hash]['phase'] = 'discovered' - print(f"Reset YouTube playlist {url_hash} to discovered phase (batch cancelled)") + logger.warning(f"Reset YouTube playlist {url_hash} to discovered phase (batch cancelled)") # Cancel all individual tasks in the batch cancelled_count = 0 @@ -31873,11 +31799,11 @@ def cancel_batch(batch_id): playlist_name = download_batches[batch_id].get('playlist_name', 'Unknown Playlist') add_activity_item("", "Batch Cancelled", f"'{playlist_name}' - {cancelled_count} downloads cancelled", "Now") - print(f"Cancelled batch {batch_id} with {cancelled_count} tasks") + logger.warning(f"Cancelled batch {batch_id} with {cancelled_count} tasks") return jsonify({"success": True, "cancelled_tasks": cancelled_count}) except Exception as e: - print(f"Error cancelling batch {batch_id}: {e}") + logger.error(f"Error cancelling batch {batch_id}: {e}") return jsonify({"success": False, "error": str(e)}), 500 # NEW ENDPOINT: Add this function to web_server.py @@ -31902,7 +31828,7 @@ def cleanup_batch(): # This prevents a race condition where cleanup deletes the batch before # the wishlist processing thread can access it if batch.get('wishlist_processing_started') and not batch.get('wishlist_processing_complete'): - print(f"[Cleanup] Batch {batch_id} cleanup deferred - wishlist processing in progress") + logger.info(f"[Cleanup] Batch {batch_id} cleanup deferred - wishlist processing in progress") return jsonify({ "success": False, "error": "Batch cleanup deferred - wishlist processing in progress", @@ -31920,15 +31846,15 @@ def cleanup_batch(): if task_id in download_tasks: del download_tasks[task_id] - print(f"Cleaned up batch '{batch_id}' and its associated tasks from server state.") + logger.info(f"Cleaned up batch '{batch_id}' and its associated tasks from server state.") return jsonify({"success": True, "message": f"Batch {batch_id} cleaned up."}) else: # It's not an error if the batch is already gone - print(f"Cleanup requested for non-existent batch '{batch_id}'. Already cleaned up?") + logger.info(f"Cleanup requested for non-existent batch '{batch_id}'. Already cleaned up?") return jsonify({"success": True, "message": "Batch already cleaned up."}) except Exception as e: - print(f"Error during batch cleanup for '{batch_id}': {e}") + logger.error(f"Error during batch cleanup for '{batch_id}': {e}") return jsonify({"success": False, "error": str(e)}), 500 # =============================== @@ -32799,12 +32725,12 @@ def start_missing_tracks_process(playlist_id): # Log album context if provided if is_album_download and album_context and artist_context: - print(f"[Artist Album] Received album context: '{album_context.get('name')}' by '{artist_context.get('name')}' ({album_context.get('album_type', 'album')})") - print(f" Release: {album_context.get('release_date', 'Unknown')}, Tracks: {album_context.get('total_tracks', len(tracks))}") + logger.info(f"[Artist Album] Received album context: '{album_context.get('name')}' by '{artist_context.get('name')}' ({album_context.get('album_type', 'album')})") + logger.info(f" Release: {album_context.get('release_date', 'Unknown')}, Tracks: {album_context.get('total_tracks', len(tracks))}") # Log playlist folder mode if enabled if playlist_folder_mode: - print(f"[Playlist Folder] Enabled for playlist: '{playlist_name}'") + logger.info(f"[Playlist Folder] Enabled for playlist: '{playlist_name}'") # Limit concurrent analysis processes to prevent resource exhaustion with tasks_lock: @@ -32864,7 +32790,7 @@ def start_missing_tracks_process(playlist_id): youtube_playlist_states[url_hash]['download_process_id'] = batch_id youtube_playlist_states[url_hash]['phase'] = 'downloading' youtube_playlist_states[url_hash]['converted_spotify_playlist_id'] = playlist_id - print(f"Linked YouTube playlist {url_hash} to download process {batch_id} (converted ID: {playlist_id})") + logger.info(f"Linked YouTube playlist {url_hash} to download process {batch_id} (converted ID: {playlist_id})") # Link Tidal playlist to download process if this is a Tidal playlist if playlist_id.startswith('tidal_'): @@ -32873,7 +32799,7 @@ def start_missing_tracks_process(playlist_id): tidal_discovery_states[tidal_playlist_id]['download_process_id'] = batch_id tidal_discovery_states[tidal_playlist_id]['phase'] = 'downloading' tidal_discovery_states[tidal_playlist_id]['converted_spotify_playlist_id'] = playlist_id - print(f"Linked Tidal playlist {tidal_playlist_id} to download process {batch_id} (converted ID: {playlist_id})") + logger.info(f"Linked Tidal playlist {tidal_playlist_id} to download process {batch_id} (converted ID: {playlist_id})") # Link Spotify Public playlist to download process if this is a Spotify Public playlist if playlist_id.startswith('spotify_public_'): @@ -32882,7 +32808,7 @@ def start_missing_tracks_process(playlist_id): spotify_public_discovery_states[sp_url_hash]['download_process_id'] = batch_id spotify_public_discovery_states[sp_url_hash]['phase'] = 'downloading' spotify_public_discovery_states[sp_url_hash]['converted_spotify_playlist_id'] = playlist_id - print(f"Linked Spotify Public playlist {sp_url_hash} to download process {batch_id} (converted ID: {playlist_id})") + logger.info(f"Linked Spotify Public playlist {sp_url_hash} to download process {batch_id} (converted ID: {playlist_id})") # Link Deezer playlist to download process if this is a Deezer playlist if playlist_id.startswith('deezer_'): @@ -32891,7 +32817,7 @@ def start_missing_tracks_process(playlist_id): deezer_discovery_states[deezer_playlist_id]['download_process_id'] = batch_id deezer_discovery_states[deezer_playlist_id]['phase'] = 'downloading' deezer_discovery_states[deezer_playlist_id]['converted_spotify_playlist_id'] = playlist_id - print(f"Linked Deezer playlist {deezer_playlist_id} to download process {batch_id} (converted ID: {playlist_id})") + logger.info(f"Linked Deezer playlist {deezer_playlist_id} to download process {batch_id} (converted ID: {playlist_id})") # Stamp original index to keep task indices aligned with frontend row order for i, track in enumerate(tracks): @@ -32961,7 +32887,7 @@ def start_missing_downloads(): return jsonify({"success": True, "batch_id": batch_id, "message": f"Queued {len(missing_tracks)} downloads for processing."}) except Exception as e: - print(f"Error starting missing downloads: {e}") + logger.error(f"Error starting missing downloads: {e}") return jsonify({"success": False, "error": str(e)}), 500 # =============================== @@ -32978,7 +32904,7 @@ def _load_sync_status_file(): return data return {} except Exception as e: - print(f"Error loading sync status: {e}") + logger.error(f"Error loading sync status: {e}") return {} def _save_sync_status_file(sync_statuses): @@ -32987,7 +32913,7 @@ def _save_sync_status_file(sync_statuses): database = get_database() database.set_preference('sync_statuses', json.dumps(sync_statuses)) except Exception as e: - print(f"Error saving sync status: {e}") + logger.error(f"Error saving sync status: {e}") def _update_and_save_sync_status(playlist_id, playlist_name, playlist_owner, snapshot_id, **kwargs): """Updates the sync status for a given playlist and saves to file (same logic as GUI).""" @@ -33012,10 +32938,10 @@ def _update_and_save_sync_status(playlist_id, playlist_name, playlist_owner, sna # Save to file _save_sync_status_file(sync_statuses) - print(f"Updated sync status for playlist '{playlist_name}' (ID: {playlist_id})") + logger.info(f"Updated sync status for playlist '{playlist_name}' (ID: {playlist_id})") except Exception as e: - print(f"Error updating sync status for {playlist_id}: {e}") + logger.error(f"Error updating sync status for {playlist_id}: {e}") @app.route('/api/spotify/playlists', methods=['GET']) def get_spotify_playlists(): @@ -33036,24 +32962,37 @@ def get_spotify_playlists(): # Handle snapshot_id safely - may not exist in core Playlist class playlist_snapshot = getattr(p, 'snapshot_id', '') - print(f"Processing playlist: {p.name} (ID: {p.id})") - print(f" - Playlist snapshot: '{playlist_snapshot}'") - print(f" - Status info: {status_info}") - if 'last_synced' in status_info: stored_snapshot = status_info.get('snapshot_id') last_sync_time = datetime.fromisoformat(status_info['last_synced']).strftime('%b %d, %H:%M') - print(f" - Stored snapshot: '{stored_snapshot}'") - print(f" - Snapshots match: {playlist_snapshot == stored_snapshot}") - if playlist_snapshot != stored_snapshot: sync_status = f"Last Sync: {last_sync_time}" - print(f" - Result: Needs Sync (showing: {sync_status})") + logger.info( + "Playlist sync status: name=%s id=%s snapshot=%r stored_snapshot=%r result=Needs Sync display=%s", + p.name, + p.id, + playlist_snapshot, + stored_snapshot, + sync_status, + ) else: sync_status = f"Synced: {last_sync_time}" - print(f" - Result: {sync_status}") + logger.info( + "Playlist sync status: name=%s id=%s snapshot=%r stored_snapshot=%r result=Synced display=%s", + p.name, + p.id, + playlist_snapshot, + stored_snapshot, + sync_status, + ) else: - print(f" - No last_synced found - Never Synced") + logger.warning( + "Playlist sync status: name=%s id=%s snapshot=%r result=Never Synced display=%s", + p.name, + p.id, + playlist_snapshot, + sync_status, + ) playlist_data.append({ "id": p.id, "name": p.name, "owner": p.owner, @@ -33089,9 +33028,9 @@ def get_spotify_playlists(): "sync_status": sync_status, "snapshot_id": "" # Liked Songs doesn't have a snapshot_id }) - print(f"Added virtual 'Liked Songs' playlist with {liked_songs_count} tracks (count only)") + logger.info(f"Added virtual 'Liked Songs' playlist with {liked_songs_count} tracks (count only)") except Exception as liked_error: - print(f"Failed to add Liked Songs playlist: {liked_error}") + logger.error(f"Failed to add Liked Songs playlist: {liked_error}") # Don't fail the entire request if Liked Songs fails return jsonify(playlist_data) @@ -33419,7 +33358,7 @@ def search_spotify(): return jsonify({'tracks': {'items': tracks_items}}) except Exception as e: - print(f"Error searching Spotify: {e}") + logger.error(f"Error searching Spotify: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify/search_tracks', methods=['GET']) @@ -33468,7 +33407,7 @@ def search_spotify_tracks(): return jsonify({'tracks': tracks_dict}) except Exception as e: - print(f"Error searching Spotify tracks: {e}") + logger.error(f"Error searching Spotify tracks: {e}") return jsonify({"error": str(e)}), 500 @@ -33518,7 +33457,7 @@ def search_itunes_tracks(): return jsonify({'tracks': tracks_dict}) except Exception as e: - print(f"Error searching iTunes tracks: {e}") + logger.error(f"Error searching iTunes tracks: {e}") return jsonify({"error": str(e)}), 500 @@ -33560,7 +33499,7 @@ def search_deezer_tracks(): return jsonify({'tracks': tracks_dict}) except Exception as e: - print(f"Error searching Deezer tracks: {e}") + logger.error(f"Error searching Deezer tracks: {e}") return jsonify({"error": str(e)}), 500 @@ -34134,7 +34073,7 @@ def get_tidal_playlists(): playlist_data.append(playlist_dict) - print(f"Loaded {len(playlist_data)} Tidal playlists with track data") + logger.info(f"Loaded {len(playlist_data)} Tidal playlists with track data") return jsonify(playlist_data) except Exception as e: return jsonify({"error": str(e)}), 500 @@ -34145,7 +34084,7 @@ def get_tidal_playlist_tracks(playlist_id): if not tidal_client or not tidal_client.is_authenticated(): return jsonify({"error": "Tidal not authenticated."}), 401 try: - print(f"Getting full Tidal playlist with tracks for: {playlist_id}") + logger.info(f"Getting full Tidal playlist with tracks for: {playlist_id}") # Fetch this single playlist directly ā€” no need to re-fetch all playlists full_playlist = tidal_client.get_playlist(playlist_id) @@ -34155,7 +34094,7 @@ def get_tidal_playlist_tracks(playlist_id): if not full_playlist.tracks: return jsonify({"error": "This playlist appears to have no tracks or they cannot be accessed"}), 403 - print(f"Loaded {len(full_playlist.tracks)} tracks from Tidal playlist: {full_playlist.name}") + logger.info(f"Loaded {len(full_playlist.tracks)} tracks from Tidal playlist: {full_playlist.name}") # Convert playlist to dict (matches sync.py structure) playlist_dict = { @@ -34180,7 +34119,7 @@ def get_tidal_playlist_tracks(playlist_id): return jsonify(playlist_dict) except Exception as e: - print(f"Error getting Tidal playlist tracks: {e}") + logger.error(f"Error getting Tidal playlist tracks: {e}") return jsonify({"error": str(e)}), 500 @@ -34247,11 +34186,11 @@ def start_tidal_discovery(playlist_id): future = tidal_discovery_executor.submit(_run_tidal_discovery_worker, playlist_id) state['discovery_future'] = future - print(f"Started Spotify discovery for Tidal playlist: {target_playlist.name}") + logger.info(f"Started Spotify discovery for Tidal playlist: {target_playlist.name}") return jsonify({"success": True, "message": "Discovery started"}) except Exception as e: - print(f"Error starting Tidal discovery: {e}") + logger.error(f"Error starting Tidal discovery: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/discovery/status/', methods=['GET']) @@ -34277,7 +34216,7 @@ def get_tidal_discovery_status(playlist_id): return jsonify(response) except Exception as e: - print(f"Error getting Tidal discovery status: {e}") + logger.error(f"Error getting Tidal discovery status: {e}") return jsonify({"error": str(e)}), 500 @@ -34338,8 +34277,8 @@ def update_tidal_discovery_match(): if old_status != 'found' and old_status != 'Found': state['spotify_matches'] = state.get('spotify_matches', 0) + 1 - print(f"Manual match updated: tidal - {identifier} - track {track_index}") - print(f" ā†’ {result['spotify_artist']} - {result['spotify_track']}") + logger.info(f"Manual match updated: tidal - {identifier} - track {track_index}") + logger.info(f" ā†’ {result['spotify_artist']} - {result['spotify_track']}") # Save manual fix to discovery cache so it appears in discovery pool try: @@ -34371,14 +34310,14 @@ def update_tidal_discovery_match(): cache_key[0], cache_key[1], 'spotify', 1.0, matched_data, original_name, original_artist ) - print(f"Manual fix saved to discovery cache: {original_name} by {original_artist}") + logger.info(f"Manual fix saved to discovery cache: {original_name} by {original_artist}") except Exception as cache_err: - print(f"Error saving manual fix to discovery cache: {cache_err}") + logger.error(f"Error saving manual fix to discovery cache: {cache_err}") return jsonify({'success': True, 'result': result}) except Exception as e: - print(f"Error updating Tidal discovery match: {e}") + logger.error(f"Error updating Tidal discovery match: {e}") return jsonify({'error': str(e)}), 500 @@ -34408,11 +34347,11 @@ def get_tidal_playlist_states(): } states.append(state_info) - print(f"Returning {len(states)} stored Tidal playlist states for hydration") + logger.info(f"Returning {len(states)} stored Tidal playlist states for hydration") return jsonify({"states": states}) except Exception as e: - print(f"Error getting Tidal playlist states: {e}") + logger.error(f"Error getting Tidal playlist states: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/state/', methods=['GET']) @@ -34445,7 +34384,7 @@ def get_tidal_playlist_state(playlist_id): return jsonify(response) except Exception as e: - print(f"Error getting Tidal playlist state: {e}") + logger.error(f"Error getting Tidal playlist state: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/reset/', methods=['POST']) @@ -34474,11 +34413,11 @@ def reset_tidal_playlist(playlist_id): state['discovery_future'] = None state['last_accessed'] = time.time() - print(f"Reset Tidal playlist to fresh: {playlist_id}") + logger.info(f"Reset Tidal playlist to fresh: {playlist_id}") return jsonify({"success": True, "message": "Playlist reset to fresh phase"}) except Exception as e: - print(f"Error resetting Tidal playlist: {e}") + logger.error(f"Error resetting Tidal playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/delete/', methods=['POST']) @@ -34497,11 +34436,11 @@ def delete_tidal_playlist(playlist_id): # Remove from state dictionary del tidal_discovery_states[playlist_id] - print(f"Deleted Tidal playlist state: {playlist_id}") + logger.info(f"Deleted Tidal playlist state: {playlist_id}") return jsonify({"success": True, "message": "Playlist deleted"}) except Exception as e: - print(f"Error deleting Tidal playlist: {e}") + logger.error(f"Error deleting Tidal playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/update_phase/', methods=['POST']) @@ -34526,11 +34465,11 @@ def update_tidal_playlist_phase(playlist_id): state['phase'] = new_phase state['last_accessed'] = time.time() - print(f"Updated Tidal playlist {playlist_id} phase: {old_phase} ā†’ {new_phase}") + logger.info(f"Updated Tidal playlist {playlist_id} phase: {old_phase} ā†’ {new_phase}") return jsonify({"success": True, "message": f"Phase updated to {new_phase}", "old_phase": old_phase, "new_phase": new_phase}) except Exception as e: - print(f"Error updating Tidal playlist phase: {e}") + logger.error(f"Error updating Tidal playlist phase: {e}") return jsonify({"error": str(e)}), 500 @@ -34551,7 +34490,7 @@ def _pause_enrichment_workers(label='discovery'): if worker and not worker.paused: worker.pause() was_running[name] = True - print(f"Paused {name} enrichment worker during {label}") + logger.warning(f"Paused {name} enrichment worker during {label}") except Exception: pass return was_running @@ -34569,7 +34508,7 @@ def _resume_enrichment_workers(was_running, label='discovery'): try: if was_running.get(name) and worker: worker.resume() - print(f"Resumed {name} enrichment worker after {label}") + logger.info(f"Resumed {name} enrichment worker after {label}") except Exception: pass @@ -34588,10 +34527,10 @@ def _sync_discovery_results_to_mirrored(source_type, source_playlist_id, discove break if not mirrored_pl: - print(f"[Discovery Sync] No mirrored playlist found for {source_type}:{source_playlist_id} (profile {profile_id})") + logger.warning(f"[Discovery Sync] No mirrored playlist found for {source_type}:{source_playlist_id} (profile {profile_id})") return - print(f"[Discovery Sync] Found mirrored playlist '{mirrored_pl.get('name')}' (DB id={mirrored_pl['id']}) for {source_type}:{source_playlist_id}") + logger.info(f"[Discovery Sync] Found mirrored playlist '{mirrored_pl.get('name')}' (DB id={mirrored_pl['id']}) for {source_type}:{source_playlist_id}") mirrored_tracks = db.get_mirrored_playlist_tracks(mirrored_pl['id']) if not mirrored_tracks: return @@ -34649,11 +34588,11 @@ def _sync_discovery_results_to_mirrored(source_type, source_playlist_id, discove updated += 1 if updated > 0: - print(f"Synced {updated} discovery results back to mirrored playlist '{mirrored_pl.get('name', '')}'") + logger.info(f"Synced {updated} discovery results back to mirrored playlist '{mirrored_pl.get('name', '')}'") except Exception as e: import traceback - print(f"Failed to sync discovery results to mirrored playlist: {e}") + logger.error(f"Failed to sync discovery results to mirrored playlist: {e}") traceback.print_exc() @@ -34671,7 +34610,7 @@ def _run_playlist_discovery_worker(playlists, automation_id=None): try: itunes_client_instance = _get_metadata_fallback_client() except Exception: - print(f"Neither Spotify nor {_get_metadata_fallback_source()} available for discovery") + logger.warning(f"Neither Spotify nor {_get_metadata_fallback_source()} available for discovery") _update_automation_progress(automation_id, status='error', progress=100, phase='Error', log_line=f'Neither Spotify nor {_get_metadata_fallback_source()} available', log_type='error') @@ -34703,7 +34642,7 @@ def _run_playlist_discovery_worker(playlists, automation_id=None): if not tracks: continue - print(f"Starting discovery for playlist '{pl_name}' ({len(tracks)} tracks, using {discovery_source.upper()})") + logger.info(f"Starting discovery for playlist '{pl_name}' ({len(tracks)} tracks, using {discovery_source.upper()})") _update_automation_progress(automation_id, phase=f'Discovering: "{pl_name}"', log_line=f'Playlist "{pl_name}" ā€” {len(tracks)} tracks ({discovery_source.upper()})', log_type='info') @@ -34760,7 +34699,7 @@ def _run_playlist_discovery_worker(playlists, automation_id=None): # Check for cancellation if automation_id and automation_id in _playlist_discovery_cancelled: _playlist_discovery_cancelled.discard(automation_id) - print(f"Playlist discovery cancelled (automation {automation_id})") + logger.warning(f"Playlist discovery cancelled (automation {automation_id})") _update_automation_progress(automation_id, status='finished', progress=100, phase='Discovery cancelled', log_line=f'Cancelled: {total_discovered} discovered, {total_failed} failed', @@ -34786,7 +34725,7 @@ def _run_playlist_discovery_worker(playlists, automation_id=None): } db.update_mirrored_track_extra_data(track_id, extra_data) total_discovered += 1 - print(f"CACHE [{i+1}/{len(undiscovered_tracks)}]: {track_name} ā†’ {cached_match.get('name', '?')}") + logger.info(f"CACHE [{i+1}/{len(undiscovered_tracks)}]: {track_name} ā†’ {cached_match.get('name', '?')}") _update_automation_progress(automation_id, progress=((total_skipped + total_discovered + total_failed) / max(1, grand_total)) * 100, current_item=track_name, @@ -34921,7 +34860,7 @@ def _run_playlist_discovery_worker(playlists, automation_id=None): except Exception: pass - print(f"[{i+1}/{len(undiscovered_tracks)}] {track_name} ā†’ {matched_data['name']} ({best_confidence:.2f})") + logger.info(f"[{i+1}/{len(undiscovered_tracks)}] {track_name} ā†’ {matched_data['name']} ({best_confidence:.2f})") _update_automation_progress(automation_id, progress=((total_skipped + total_discovered + total_failed) / max(1, grand_total)) * 100, processed=total_discovered + total_failed, @@ -34939,7 +34878,7 @@ def _run_playlist_discovery_worker(playlists, automation_id=None): } db.update_mirrored_track_extra_data(track_id, extra_data) total_discovered += 1 - print(f"[{i+1}/{len(undiscovered_tracks)}] Wing It: {track_name} by {artist_name}") + logger.info(f"[{i+1}/{len(undiscovered_tracks)}] Wing It: {track_name} by {artist_name}") _update_automation_progress(automation_id, progress=((total_skipped + total_discovered + total_failed) / max(1, grand_total)) * 100, processed=total_discovered + total_failed, @@ -34964,14 +34903,14 @@ def _run_playlist_discovery_worker(playlists, automation_id=None): except Exception: pass - print(f"Playlist discovery complete: {total_discovered} discovered, {total_failed} failed, {total_skipped} skipped") + logger.error(f"Playlist discovery complete: {total_discovered} discovered, {total_failed} failed, {total_skipped} skipped") _update_automation_progress(automation_id, status='finished', progress=100, phase='Discovery complete', log_line=f'Done: {total_discovered} discovered, {total_failed} failed, {total_skipped} skipped', log_type='success') except Exception as e: - print(f"Error in playlist discovery worker: {e}") + logger.error(f"Error in playlist discovery worker: {e}") import traceback traceback.print_exc() _update_automation_progress(automation_id, status='error', progress=100, @@ -35032,7 +34971,7 @@ def _validate_discovery_cache_artist(source_artist, cached_match): best_sim = sim if best_sim < min_artist_similarity: - print(f"Cache artist mismatch: source='{source_artist}' vs cached='{cached_artists[0]}' (sim={best_sim:.2f}), re-searching") + logger.info(f"Cache artist mismatch: source='{source_artist}' vs cached='{cached_artists[0]}' (sim={best_sim:.2f}), re-searching") return False return True @@ -35119,7 +35058,7 @@ def _discovery_score_candidates(source_title, source_artist, source_duration_ms, best_index = idx except Exception as e: - print(f"Error scoring candidate {idx}: {e}") + logger.error(f"Error scoring candidate {idx}: {e}") continue return best_match, best_confidence, best_index @@ -35142,7 +35081,7 @@ def _run_tidal_discovery_worker(playlist_id): if not use_spotify: itunes_client_instance = _get_metadata_fallback_client() - print(f"Starting Tidal discovery for: {playlist.name} (using {discovery_source.upper()})") + logger.info(f"Starting Tidal discovery for: {playlist.name} (using {discovery_source.upper()})") # Store discovery source in state for frontend state['discovery_source'] = discovery_source @@ -35154,7 +35093,7 @@ def _run_tidal_discovery_worker(playlist_id): break try: - print(f"[{i+1}/{len(playlist.tracks)}] Searching {discovery_source.upper()}: {tidal_track.name} by {', '.join(tidal_track.artists)}") + logger.info(f"[{i+1}/{len(playlist.tracks)}] Searching {discovery_source.upper()}: {tidal_track.name} by {', '.join(tidal_track.artists)}") # Check discovery cache first cache_key = _get_discovery_cache_key(tidal_track.name, tidal_track.artists[0] if tidal_track.artists else '') @@ -35162,7 +35101,7 @@ def _run_tidal_discovery_worker(playlist_id): cache_db = get_database() cached_match = cache_db.get_discovery_cache_match(cache_key[0], cache_key[1], discovery_source) if cached_match and _validate_discovery_cache_artist(tidal_track.artists[0] if tidal_track.artists else '', cached_match): - print(f"CACHE HIT [{i+1}/{len(playlist.tracks)}]: {tidal_track.name} by {', '.join(tidal_track.artists)}") + logger.debug(f"CACHE HIT [{i+1}/{len(playlist.tracks)}]: {tidal_track.name} by {', '.join(tidal_track.artists)}") result = { 'tidal_track': { 'id': tidal_track.id, @@ -35182,7 +35121,7 @@ def _run_tidal_discovery_worker(playlist_id): state['discovery_progress'] = int(((i + 1) / len(playlist.tracks)) * 100) continue except Exception as cache_err: - print(f"Cache lookup error: {cache_err}") + logger.error(f"Cache lookup error: {cache_err}") # Use the search function with appropriate provider track_result = _search_spotify_for_tidal_track( @@ -35272,9 +35211,9 @@ def _run_tidal_discovery_worker(playlist_id): result['match_data'], tidal_track.name, tidal_track.artists[0] if tidal_track.artists else '' ) - print(f"CACHE SAVED: {tidal_track.name} (confidence: {match_confidence:.3f})") + logger.info(f"CACHE SAVED: {tidal_track.name} (confidence: {match_confidence:.3f})") except Exception as cache_err: - print(f"Cache save error: {cache_err}") + logger.error(f"Cache save error: {cache_err}") # Auto Wing It fallback for unmatched tracks if result['status'] != 'found': @@ -35301,7 +35240,7 @@ def _run_tidal_discovery_worker(playlist_id): time.sleep(0.1) except Exception as e: - print(f"Error processing track {i+1}: {e}") + logger.error(f"Error processing track {i+1}: {e}") # Add error result result = { 'tidal_track': { @@ -35326,13 +35265,13 @@ def _run_tidal_discovery_worker(playlist_id): source_label = discovery_source.upper() add_activity_item("", f"Tidal Discovery Complete ({source_label})", f"'{playlist.name}' - {successful_discoveries}/{len(playlist.tracks)} tracks found", "Now") - print(f"Tidal discovery complete ({source_label}): {successful_discoveries}/{len(playlist.tracks)} tracks found") + logger.info(f"Tidal discovery complete ({source_label}): {successful_discoveries}/{len(playlist.tracks)} tracks found") # Sync discovery results back to mirrored playlist _sync_discovery_results_to_mirrored('tidal', playlist_id, state.get('discovery_results', []), discovery_source, profile_id=state.get('_profile_id', 1)) except Exception as e: - print(f"Error in Tidal discovery worker: {e}") + logger.error(f"Error in Tidal discovery worker: {e}") state['phase'] = 'error' state['status'] = f'error: {str(e)}' finally: @@ -35370,7 +35309,7 @@ def _search_spotify_for_tidal_track(tidal_track, use_spotify=True, itunes_client source_duration = getattr(tidal_track, 'duration_ms', 0) or 0 source_name = "Spotify" if use_spotify else _get_metadata_fallback_source().capitalize() - print(f"Tidal track: '{artist_name}' - '{track_name}' (searching {source_name})") + logger.info(f"Tidal track: '{artist_name}' - '{track_name}' (searching {source_name})") # Use matching engine to generate search queries (with fallback) try: @@ -35380,9 +35319,9 @@ def _search_spotify_for_tidal_track(tidal_track, use_spotify=True, itunes_client 'album': None })() search_queries = matching_engine.generate_download_queries(temp_track) - print(f"Generated {len(search_queries)} search queries for Tidal track") + logger.info(f"Generated {len(search_queries)} search queries for Tidal track") except Exception as e: - print(f"Matching engine failed for Tidal, falling back to basic queries: {e}") + logger.error(f"Matching engine failed for Tidal, falling back to basic queries: {e}") if use_spotify: search_queries = [ f'track:"{track_name}" artist:"{artist_name}"', @@ -35403,7 +35342,7 @@ def _search_spotify_for_tidal_track(tidal_track, use_spotify=True, itunes_client for query_idx, search_query in enumerate(search_queries): try: - print(f"Tidal query {query_idx + 1}/{len(search_queries)}: {search_query} ({source_name})") + logger.debug(f"Tidal query {query_idx + 1}/{len(search_queries)}: {search_query} ({source_name})") if use_spotify and not _spotify_rate_limited(): results = spotify_client.search_tracks(search_query, limit=10) @@ -35427,19 +35366,19 @@ def _search_spotify_for_tidal_track(tidal_track, use_spotify=True, itunes_client best_match_raw = _cache.get_entity('spotify', 'track', match.id) else: best_match_raw = None - print(f"New best Tidal match: {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") + logger.info(f"New best Tidal match: {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") if best_confidence >= 0.9: - print(f"High confidence Tidal match found ({best_confidence:.3f}), stopping search") + logger.info(f"High confidence Tidal match found ({best_confidence:.3f}), stopping search") break except Exception as e: - print(f"Error in Tidal {source_name} search for query '{search_query}': {e}") + logger.debug(f"Error in Tidal {source_name} search for query '{search_query}': {e}") continue # Strategy 4: Extended search with higher limit (last resort) if not best_match: - print(f"Tidal Strategy 4: Extended search with limit=50") + logger.info(f"Tidal Strategy 4: Extended search with limit=50") query = f"{artist_name} {track_name}" if use_spotify: extended_results = spotify_client.search_tracks(query, limit=50) @@ -35452,17 +35391,17 @@ def _search_spotify_for_tidal_track(tidal_track, use_spotify=True, itunes_client if match and confidence >= min_confidence: best_match = match best_confidence = confidence - print(f"Strategy 4 Tidal match (extended): {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") + logger.info(f"Strategy 4 Tidal match (extended): {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") if best_match: if use_spotify: - print(f"Final Tidal Spotify match: {best_match.artists[0]} - {best_match.name} (confidence: {best_confidence:.3f})") + logger.info(f"Final Tidal Spotify match: {best_match.artists[0]} - {best_match.name} (confidence: {best_confidence:.3f})") return (best_match, best_match_raw, best_confidence) else: result_artists = best_match.artists if hasattr(best_match, 'artists') else [] result_artist = result_artists[0] if result_artists else 'Unknown' result_name = best_match.name if hasattr(best_match, 'name') else 'Unknown' - print(f"Final Tidal {source_name} match: {result_artist} - {result_name} (confidence: {best_confidence:.3f})") + logger.info(f"Final Tidal {source_name} match: {result_artist} - {result_name} (confidence: {best_confidence:.3f})") album_name = best_match.album if hasattr(best_match, 'album') else 'Unknown Album' image_url = best_match.image_url if hasattr(best_match, 'image_url') else '' @@ -35499,11 +35438,11 @@ def _search_spotify_for_tidal_track(tidal_track, use_spotify=True, itunes_client if detailed: track_number = detailed.get('track_number') disc_number = detailed.get('disc_number') - print(f"[Discovery Enrich] {result_name}: track_number={track_number}, disc={disc_number}") + logger.info(f"[Discovery Enrich] {result_name}: track_number={track_number}, disc={disc_number}") else: - print(f"[Discovery Enrich] get_track_details returned None for ID {track_id} ({result_name})") + logger.info(f"[Discovery Enrich] get_track_details returned None for ID {track_id} ({result_name})") except Exception as _enrich_err: - print(f"[Discovery Enrich] Failed for {result_name} (ID {track_id}): {_enrich_err}") + logger.error(f"[Discovery Enrich] Failed for {result_name} (ID {track_id}): {_enrich_err}") result_data = { 'id': track_id, @@ -35520,11 +35459,11 @@ def _search_spotify_for_tidal_track(tidal_track, use_spotify=True, itunes_client result_data['disc_number'] = disc_number return result_data else: - print(f"No suitable Tidal match found (best confidence was {best_confidence:.3f}, required {min_confidence:.3f})") + logger.warning(f"No suitable Tidal match found (best confidence was {best_confidence:.3f}, required {min_confidence:.3f})") return None except Exception as e: - print(f"Error searching Spotify for Tidal track: {e}") + logger.error(f"Error searching Spotify for Tidal track: {e}") return None @@ -35561,7 +35500,7 @@ def convert_tidal_results_to_spotify_tracks(discovery_results): } spotify_tracks.append(track) - print(f"Converted {len(spotify_tracks)} Tidal matches to Spotify tracks for sync") + logger.info(f"Converted {len(spotify_tracks)} Tidal matches to Spotify tracks for sync") return spotify_tracks @@ -35615,11 +35554,11 @@ def start_tidal_sync(playlist_id): future = sync_executor.submit(_run_sync_task, sync_playlist_id, sync_data['playlist_name'], spotify_tracks, None, get_current_profile_id(), playlist_image_url) active_sync_workers[sync_playlist_id] = future - print(f"Started Tidal sync for: {playlist_name} ({len(spotify_tracks)} tracks)") + logger.info(f"Started Tidal sync for: {playlist_name} ({len(spotify_tracks)} tracks)") return jsonify({"success": True, "sync_playlist_id": sync_playlist_id}) except Exception as e: - print(f"Error starting Tidal sync: {e}") + logger.error(f"Error starting Tidal sync: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/sync/status/', methods=['GET']) @@ -35665,7 +35604,7 @@ def get_tidal_sync_status(playlist_id): return jsonify(response) except Exception as e: - print(f"Error getting Tidal sync status: {e}") + logger.error(f"Error getting Tidal sync status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/sync/cancel/', methods=['POST']) @@ -35696,7 +35635,7 @@ def cancel_tidal_sync(playlist_id): return jsonify({"success": True, "message": "Tidal sync cancelled"}) except Exception as e: - print(f"Error cancelling Tidal sync: {e}") + logger.error(f"Error cancelling Tidal sync: {e}") return jsonify({"error": str(e)}), 500 @@ -35797,7 +35736,7 @@ def get_deezer_arl_playlists(): 'sync_status': 'Never Synced', }) - print(f"Loaded {len(playlist_data)} Deezer user playlists via ARL") + logger.info(f"Loaded {len(playlist_data)} Deezer user playlists via ARL") return jsonify(playlist_data) except Exception as e: return jsonify({'error': str(e)}), 500 @@ -35817,7 +35756,7 @@ def get_deezer_arl_playlist_tracks(playlist_id): if not playlist: return jsonify({'error': 'Playlist not found or unable to access.'}), 404 - print(f"Loaded {len(playlist.get('tracks', []))} tracks from Deezer playlist: {playlist.get('name')}") + logger.info(f"Loaded {len(playlist.get('tracks', []))} tracks from Deezer playlist: {playlist.get('name')}") return jsonify(playlist) except Exception as e: return jsonify({'error': str(e)}), 500 @@ -35843,7 +35782,7 @@ def get_deezer_playlist(playlist_id): return jsonify(playlist) except Exception as e: - print(f"Error fetching Deezer playlist: {e}") + logger.error(f"Error fetching Deezer playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/discovery/start/', methods=['POST']) @@ -35916,11 +35855,11 @@ def start_deezer_discovery(playlist_id): future = deezer_discovery_executor.submit(_run_deezer_discovery_worker, playlist_id) state['discovery_future'] = future - print(f"Started Spotify discovery for Deezer playlist: {playlist_name}") + logger.info(f"Started Spotify discovery for Deezer playlist: {playlist_name}") return jsonify({"success": True, "message": "Discovery started"}) except Exception as e: - print(f"Error starting Deezer discovery: {e}") + logger.error(f"Error starting Deezer discovery: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/discovery/status/', methods=['GET']) @@ -35946,7 +35885,7 @@ def get_deezer_discovery_status(playlist_id): return jsonify(response) except Exception as e: - print(f"Error getting Deezer discovery status: {e}") + logger.error(f"Error getting Deezer discovery status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/discovery/update_match', methods=['POST']) @@ -36006,8 +35945,8 @@ def update_deezer_discovery_match(): if old_status != 'found' and old_status != 'Found': state['spotify_matches'] = state.get('spotify_matches', 0) + 1 - print(f"Manual match updated: deezer - {identifier} - track {track_index}") - print(f" ā†’ {result['spotify_artist']} - {result['spotify_track']}") + logger.info(f"Manual match updated: deezer - {identifier} - track {track_index}") + logger.info(f" ā†’ {result['spotify_artist']} - {result['spotify_track']}") # Save manual fix to discovery cache so it appears in discovery pool try: @@ -36037,14 +35976,14 @@ def update_deezer_discovery_match(): cache_key[0], cache_key[1], 'spotify', 1.0, matched_data, original_name, original_artist ) - print(f"Manual fix saved to discovery cache: {original_name} by {original_artist}") + logger.info(f"Manual fix saved to discovery cache: {original_name} by {original_artist}") except Exception as cache_err: - print(f"Error saving manual fix to discovery cache: {cache_err}") + logger.error(f"Error saving manual fix to discovery cache: {cache_err}") return jsonify({'success': True, 'result': result}) except Exception as e: - print(f"Error updating Deezer discovery match: {e}") + logger.error(f"Error updating Deezer discovery match: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/deezer/playlists/states', methods=['GET']) @@ -36071,11 +36010,11 @@ def get_deezer_playlist_states(): } states.append(state_info) - print(f"Returning {len(states)} stored Deezer playlist states for hydration") + logger.info(f"Returning {len(states)} stored Deezer playlist states for hydration") return jsonify({"states": states}) except Exception as e: - print(f"Error getting Deezer playlist states: {e}") + logger.error(f"Error getting Deezer playlist states: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/state/', methods=['GET']) @@ -36108,7 +36047,7 @@ def get_deezer_playlist_state(playlist_id): return jsonify(response) except Exception as e: - print(f"Error getting Deezer playlist state: {e}") + logger.error(f"Error getting Deezer playlist state: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/reset/', methods=['POST']) @@ -36137,11 +36076,11 @@ def reset_deezer_playlist(playlist_id): state['discovery_future'] = None state['last_accessed'] = time.time() - print(f"Reset Deezer playlist to fresh: {playlist_id}") + logger.info(f"Reset Deezer playlist to fresh: {playlist_id}") return jsonify({"success": True, "message": "Playlist reset to fresh phase"}) except Exception as e: - print(f"Error resetting Deezer playlist: {e}") + logger.error(f"Error resetting Deezer playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/delete/', methods=['POST']) @@ -36160,11 +36099,11 @@ def delete_deezer_playlist(playlist_id): # Remove from state dictionary del deezer_discovery_states[playlist_id] - print(f"Deleted Deezer playlist state: {playlist_id}") + logger.info(f"Deleted Deezer playlist state: {playlist_id}") return jsonify({"success": True, "message": "Playlist deleted"}) except Exception as e: - print(f"Error deleting Deezer playlist: {e}") + logger.error(f"Error deleting Deezer playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/update_phase/', methods=['POST']) @@ -36197,11 +36136,11 @@ def update_deezer_playlist_phase(playlist_id): if 'converted_spotify_playlist_id' in data: state['converted_spotify_playlist_id'] = data['converted_spotify_playlist_id'] - print(f"Updated Deezer playlist {playlist_id} phase: {old_phase} ā†’ {new_phase}") + logger.info(f"Updated Deezer playlist {playlist_id} phase: {old_phase} ā†’ {new_phase}") return jsonify({"success": True, "message": f"Phase updated to {new_phase}", "old_phase": old_phase, "new_phase": new_phase}) except Exception as e: - print(f"Error updating Deezer playlist phase: {e}") + logger.error(f"Error updating Deezer playlist phase: {e}") return jsonify({"error": str(e)}), 500 @@ -36222,7 +36161,7 @@ def _run_deezer_discovery_worker(playlist_id): if not use_spotify: itunes_client_instance = _get_metadata_fallback_client() - print(f"Starting Deezer discovery for: {playlist['name']} (using {discovery_source.upper()})") + logger.info(f"Starting Deezer discovery for: {playlist['name']} (using {discovery_source.upper()})") # Store discovery source in state for frontend state['discovery_source'] = discovery_source @@ -36241,7 +36180,7 @@ def _run_deezer_discovery_worker(playlist_id): track_album = deezer_track.get('album', '') track_duration_ms = deezer_track.get('duration_ms', 0) - print(f"[{i+1}/{len(tracks)}] Searching {discovery_source.upper()}: {track_name} by {', '.join(track_artists)}") + logger.info(f"[{i+1}/{len(tracks)}] Searching {discovery_source.upper()}: {track_name} by {', '.join(track_artists)}") # Check discovery cache first cache_key = _get_discovery_cache_key(track_name, track_artists[0] if track_artists else '') @@ -36249,7 +36188,7 @@ def _run_deezer_discovery_worker(playlist_id): cache_db = get_database() cached_match = cache_db.get_discovery_cache_match(cache_key[0], cache_key[1], discovery_source) if cached_match and _validate_discovery_cache_artist(track_artists[0] if track_artists else '', cached_match): - print(f"CACHE HIT [{i+1}/{len(tracks)}]: {track_name} by {', '.join(track_artists)}") + logger.debug(f"CACHE HIT [{i+1}/{len(tracks)}]: {track_name} by {', '.join(track_artists)}") # Extract display-friendly artist string from cached match cached_artists = cached_match.get('artists', []) if cached_artists: @@ -36287,7 +36226,7 @@ def _run_deezer_discovery_worker(playlist_id): state['discovery_progress'] = int(((i + 1) / len(tracks)) * 100) continue except Exception as cache_err: - print(f"Cache lookup error: {cache_err}") + logger.error(f"Cache lookup error: {cache_err}") # Create a SimpleNamespace duck-type object for _search_spotify_for_tidal_track track_ns = types.SimpleNamespace( @@ -36401,9 +36340,9 @@ def _run_deezer_discovery_worker(playlist_id): result['match_data'], track_name, track_artists[0] if track_artists else '' ) - print(f"CACHE SAVED: {track_name} (confidence: {match_confidence:.3f})") + logger.info(f"CACHE SAVED: {track_name} (confidence: {match_confidence:.3f})") except Exception as cache_err: - print(f"Cache save error: {cache_err}") + logger.error(f"Cache save error: {cache_err}") # Auto Wing It fallback for unmatched tracks if result['status_class'] == 'not-found': @@ -36433,7 +36372,7 @@ def _run_deezer_discovery_worker(playlist_id): time.sleep(0.1) except Exception as e: - print(f"Error processing track {i+1}: {e}") + logger.error(f"Error processing track {i+1}: {e}") # Add error result result = { 'deezer_track': { @@ -36463,13 +36402,13 @@ def _run_deezer_discovery_worker(playlist_id): source_label = discovery_source.upper() add_activity_item("", f"Deezer Discovery Complete ({source_label})", f"'{playlist['name']}' - {successful_discoveries}/{len(tracks)} tracks found", "Now") - print(f"Deezer discovery complete ({source_label}): {successful_discoveries}/{len(tracks)} tracks found") + logger.info(f"Deezer discovery complete ({source_label}): {successful_discoveries}/{len(tracks)} tracks found") # Sync discovery results back to mirrored playlist _sync_discovery_results_to_mirrored('deezer', playlist_id, state.get('discovery_results', []), discovery_source, profile_id=state.get('_profile_id', 1)) except Exception as e: - print(f"Error in Deezer discovery worker: {e}") + logger.error(f"Error in Deezer discovery worker: {e}") if playlist_id in deezer_discovery_states: deezer_discovery_states[playlist_id]['phase'] = 'error' deezer_discovery_states[playlist_id]['status'] = f'error: {str(e)}' @@ -36508,7 +36447,7 @@ def convert_deezer_results_to_spotify_tracks(discovery_results): } spotify_tracks.append(track) - print(f"Converted {len(spotify_tracks)} Deezer matches to Spotify tracks for sync") + logger.info(f"Converted {len(spotify_tracks)} Deezer matches to Spotify tracks for sync") return spotify_tracks @@ -36562,11 +36501,11 @@ def start_deezer_sync(playlist_id): future = sync_executor.submit(_run_sync_task, sync_playlist_id, sync_data['playlist_name'], spotify_tracks, None, get_current_profile_id(), playlist_image_url) active_sync_workers[sync_playlist_id] = future - print(f"Started Deezer sync for: {playlist_name} ({len(spotify_tracks)} tracks)") + logger.info(f"Started Deezer sync for: {playlist_name} ({len(spotify_tracks)} tracks)") return jsonify({"success": True, "sync_playlist_id": sync_playlist_id}) except Exception as e: - print(f"Error starting Deezer sync: {e}") + logger.error(f"Error starting Deezer sync: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/sync/status/', methods=['GET']) @@ -36609,7 +36548,7 @@ def get_deezer_sync_status(playlist_id): return jsonify(response) except Exception as e: - print(f"Error getting Deezer sync status: {e}") + logger.error(f"Error getting Deezer sync status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/sync/cancel/', methods=['POST']) @@ -36640,7 +36579,7 @@ def cancel_deezer_sync(playlist_id): return jsonify({"success": True, "message": "Deezer sync cancelled"}) except Exception as e: - print(f"Error cancelling Deezer sync: {e}") + logger.error(f"Error cancelling Deezer sync: {e}") return jsonify({"error": str(e)}), 500 @@ -36668,7 +36607,7 @@ def parse_spotify_public_endpoint(): if not parsed: return jsonify({"error": "Invalid Spotify URL. Please use a playlist or album link from open.spotify.com"}), 400 - print(f"Scraping public Spotify {parsed['type']}: {parsed['id']}") + logger.info(f"Scraping public Spotify {parsed['type']}: {parsed['id']}") result = scrape_spotify_embed(parsed['type'], parsed['id']) @@ -36727,11 +36666,11 @@ def parse_spotify_public_endpoint(): spotify_public_discovery_states[url_hash]['playlist'] = response_data spotify_public_discovery_states[url_hash]['last_accessed'] = time.time() - print(f"Spotify {parsed['type']} scraped: {result['name']} ({len(spotify_tracks)} tracks)") + logger.info(f"Spotify {parsed['type']} scraped: {result['name']} ({len(spotify_tracks)} tracks)") return jsonify(response_data) except Exception as e: - print(f"Error parsing Spotify URL: {e}") + logger.error(f"Error parsing Spotify URL: {e}") import traceback traceback.print_exc() return jsonify({"error": str(e)}), 500 @@ -36766,11 +36705,11 @@ def start_spotify_public_discovery(url_hash): future = spotify_public_discovery_executor.submit(_run_spotify_public_discovery_worker, url_hash) state['discovery_future'] = future - print(f"Started Spotify discovery for Spotify Public playlist: {playlist_name}") + logger.info(f"Started Spotify discovery for Spotify Public playlist: {playlist_name}") return jsonify({"success": True, "message": "Discovery started"}) except Exception as e: - print(f"Error starting Spotify Public discovery: {e}") + logger.error(f"Error starting Spotify Public discovery: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/discovery/status/', methods=['GET']) @@ -36796,7 +36735,7 @@ def get_spotify_public_discovery_status(url_hash): return jsonify(response) except Exception as e: - print(f"Error getting Spotify Public discovery status: {e}") + logger.error(f"Error getting Spotify Public discovery status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/discovery/update_match', methods=['POST']) @@ -36856,8 +36795,8 @@ def update_spotify_public_discovery_match(): if old_status != 'found' and old_status != 'Found': state['spotify_matches'] = state.get('spotify_matches', 0) + 1 - print(f"Manual match updated: spotify_public - {identifier} - track {track_index}") - print(f" ā†’ {result['spotify_artist']} - {result['spotify_track']}") + logger.info(f"Manual match updated: spotify_public - {identifier} - track {track_index}") + logger.info(f" ā†’ {result['spotify_artist']} - {result['spotify_track']}") # Save manual fix to discovery cache so it appears in discovery pool try: @@ -36887,14 +36826,14 @@ def update_spotify_public_discovery_match(): cache_key[0], cache_key[1], 'spotify', 1.0, matched_data, original_name, original_artist ) - print(f"Manual fix saved to discovery cache: {original_name} by {original_artist}") + logger.info(f"Manual fix saved to discovery cache: {original_name} by {original_artist}") except Exception as cache_err: - print(f"Error saving manual fix to discovery cache: {cache_err}") + logger.error(f"Error saving manual fix to discovery cache: {cache_err}") return jsonify({'success': True, 'result': result}) except Exception as e: - print(f"Error updating Spotify Public discovery match: {e}") + logger.error(f"Error updating Spotify Public discovery match: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/spotify-public/playlists/states', methods=['GET']) @@ -36921,11 +36860,11 @@ def get_spotify_public_playlist_states(): } states.append(state_info) - print(f"Returning {len(states)} stored Spotify Public playlist states for hydration") + logger.info(f"Returning {len(states)} stored Spotify Public playlist states for hydration") return jsonify({"states": states}) except Exception as e: - print(f"Error getting Spotify Public playlist states: {e}") + logger.error(f"Error getting Spotify Public playlist states: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/state/', methods=['GET']) @@ -36957,7 +36896,7 @@ def get_spotify_public_playlist_state(url_hash): return jsonify(response) except Exception as e: - print(f"Error getting Spotify Public playlist state: {e}") + logger.error(f"Error getting Spotify Public playlist state: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/reset/', methods=['POST']) @@ -36986,11 +36925,11 @@ def reset_spotify_public_playlist(url_hash): state['discovery_future'] = None state['last_accessed'] = time.time() - print(f"Reset Spotify Public playlist to fresh: {url_hash}") + logger.info(f"Reset Spotify Public playlist to fresh: {url_hash}") return jsonify({"success": True, "message": "Playlist reset to fresh phase"}) except Exception as e: - print(f"Error resetting Spotify Public playlist: {e}") + logger.error(f"Error resetting Spotify Public playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/delete/', methods=['POST']) @@ -37009,11 +36948,11 @@ def delete_spotify_public_playlist(url_hash): # Remove from state dictionary del spotify_public_discovery_states[url_hash] - print(f"Deleted Spotify Public playlist state: {url_hash}") + logger.info(f"Deleted Spotify Public playlist state: {url_hash}") return jsonify({"success": True, "message": "Playlist deleted"}) except Exception as e: - print(f"Error deleting Spotify Public playlist: {e}") + logger.error(f"Error deleting Spotify Public playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/update_phase/', methods=['POST']) @@ -37046,11 +36985,11 @@ def update_spotify_public_playlist_phase(url_hash): if 'converted_spotify_playlist_id' in data: state['converted_spotify_playlist_id'] = data['converted_spotify_playlist_id'] - print(f"Updated Spotify Public playlist {url_hash} phase: {old_phase} ā†’ {new_phase}") + logger.info(f"Updated Spotify Public playlist {url_hash} phase: {old_phase} ā†’ {new_phase}") return jsonify({"success": True, "message": f"Phase updated to {new_phase}", "old_phase": old_phase, "new_phase": new_phase}) except Exception as e: - print(f"Error updating Spotify Public playlist phase: {e}") + logger.error(f"Error updating Spotify Public playlist phase: {e}") return jsonify({"error": str(e)}), 500 @@ -37071,7 +37010,7 @@ def _run_spotify_public_discovery_worker(url_hash): if not use_spotify: itunes_client_instance = _get_metadata_fallback_client() - print(f"Starting Spotify Public discovery for: {playlist['name']} (using {discovery_source.upper()})") + logger.info(f"Starting Spotify Public discovery for: {playlist['name']} (using {discovery_source.upper()})") # Store discovery source in state for frontend state['discovery_source'] = discovery_source @@ -37101,7 +37040,7 @@ def _run_spotify_public_discovery_worker(url_hash): track_album_name = track_album or '' track_duration_ms = sp_track.get('duration_ms', 0) - print(f"[{i+1}/{len(tracks)}] Searching {discovery_source.upper()}: {track_name} by {', '.join(track_artists)}") + logger.info(f"[{i+1}/{len(tracks)}] Searching {discovery_source.upper()}: {track_name} by {', '.join(track_artists)}") # Check discovery cache first cache_key = _get_discovery_cache_key(track_name, track_artists[0] if track_artists else '') @@ -37109,7 +37048,7 @@ def _run_spotify_public_discovery_worker(url_hash): cache_db = get_database() cached_match = cache_db.get_discovery_cache_match(cache_key[0], cache_key[1], discovery_source) if cached_match and _validate_discovery_cache_artist(track_artists[0] if track_artists else '', cached_match): - print(f"CACHE HIT [{i+1}/{len(tracks)}]: {track_name} by {', '.join(track_artists)}") + logger.debug(f"CACHE HIT [{i+1}/{len(tracks)}]: {track_name} by {', '.join(track_artists)}") # Extract display-friendly artist string from cached match cached_artists = cached_match.get('artists', []) if cached_artists: @@ -37147,7 +37086,7 @@ def _run_spotify_public_discovery_worker(url_hash): state['discovery_progress'] = int(((i + 1) / len(tracks)) * 100) continue except Exception as cache_err: - print(f"Cache lookup error: {cache_err}") + logger.error(f"Cache lookup error: {cache_err}") # Create a SimpleNamespace duck-type object for _search_spotify_for_tidal_track track_ns = types.SimpleNamespace( @@ -37261,9 +37200,9 @@ def _run_spotify_public_discovery_worker(url_hash): result['match_data'], track_name, track_artists[0] if track_artists else '' ) - print(f"CACHE SAVED: {track_name} (confidence: {match_confidence:.3f})") + logger.info(f"CACHE SAVED: {track_name} (confidence: {match_confidence:.3f})") except Exception as cache_err: - print(f"Cache save error: {cache_err}") + logger.error(f"Cache save error: {cache_err}") # Auto Wing It fallback for unmatched tracks if result['status_class'] == 'not-found': @@ -37293,7 +37232,7 @@ def _run_spotify_public_discovery_worker(url_hash): time.sleep(0.1) except Exception as e: - print(f"Error processing track {i+1}: {e}") + logger.error(f"Error processing track {i+1}: {e}") # Add error result result = { 'spotify_public_track': { @@ -37323,10 +37262,10 @@ def _run_spotify_public_discovery_worker(url_hash): source_label = discovery_source.upper() add_activity_item("", f"Spotify Link Discovery Complete ({source_label})", f"'{playlist['name']}' - {successful_discoveries}/{len(tracks)} tracks found", "Now") - print(f"Spotify Public discovery complete ({source_label}): {successful_discoveries}/{len(tracks)} tracks found") + logger.info(f"Spotify Public discovery complete ({source_label}): {successful_discoveries}/{len(tracks)} tracks found") except Exception as e: - print(f"Error in Spotify Public discovery worker: {e}") + logger.error(f"Error in Spotify Public discovery worker: {e}") if url_hash in spotify_public_discovery_states: spotify_public_discovery_states[url_hash]['phase'] = 'error' spotify_public_discovery_states[url_hash]['status'] = f'error: {str(e)}' @@ -37366,7 +37305,7 @@ def convert_spotify_public_results_to_spotify_tracks(discovery_results): } spotify_tracks.append(track) - print(f"Converted {len(spotify_tracks)} Spotify Public matches to Spotify tracks for sync") + logger.info(f"Converted {len(spotify_tracks)} Spotify Public matches to Spotify tracks for sync") return spotify_tracks @@ -37420,11 +37359,11 @@ def start_spotify_public_sync(url_hash): future = sync_executor.submit(_run_sync_task, sync_playlist_id, sync_data['playlist_name'], spotify_tracks, None, get_current_profile_id(), playlist_image_url) active_sync_workers[sync_playlist_id] = future - print(f"Started Spotify Public sync for: {playlist_name} ({len(spotify_tracks)} tracks)") + logger.info(f"Started Spotify Public sync for: {playlist_name} ({len(spotify_tracks)} tracks)") return jsonify({"success": True, "sync_playlist_id": sync_playlist_id}) except Exception as e: - print(f"Error starting Spotify Public sync: {e}") + logger.error(f"Error starting Spotify Public sync: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/sync/status/', methods=['GET']) @@ -37467,7 +37406,7 @@ def get_spotify_public_sync_status(url_hash): return jsonify(response) except Exception as e: - print(f"Error getting Spotify Public sync status: {e}") + logger.error(f"Error getting Spotify Public sync status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/sync/cancel/', methods=['POST']) @@ -37498,7 +37437,7 @@ def cancel_spotify_public_sync(url_hash): return jsonify({"success": True, "message": "Spotify Public sync cancelled"}) except Exception as e: - print(f"Error cancelling Spotify Public sync: {e}") + logger.error(f"Error cancelling Spotify Public sync: {e}") return jsonify({"error": str(e)}), 500 @@ -37532,7 +37471,7 @@ def parse_youtube_playlist_endpoint(): if not ('youtube.com/playlist' in url or 'music.youtube.com/playlist' in url): return jsonify({"error": "Invalid YouTube playlist URL"}), 400 - print(f"Parsing YouTube playlist: {url}") + logger.info(f"Parsing YouTube playlist: {url}") # Parse the playlist using our function playlist_data = parse_youtube_playlist(url) @@ -37597,11 +37536,11 @@ def parse_youtube_playlist_endpoint(): playlist_data['url_hash'] = url_hash - print(f"YouTube playlist parsed successfully: {playlist_data['name']} ({len(playlist_data['tracks'])} tracks)") + logger.info(f"YouTube playlist parsed successfully: {playlist_data['name']} ({len(playlist_data['tracks'])} tracks)") return jsonify(playlist_data) except Exception as e: - print(f"Error parsing YouTube playlist: {e}") + logger.error(f"Error parsing YouTube playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/discovery/start/', methods=['POST']) @@ -37637,11 +37576,11 @@ def start_youtube_discovery(url_hash): future = youtube_discovery_executor.submit(_run_youtube_discovery_worker, url_hash) state['discovery_future'] = future - print(f"Started Spotify discovery for YouTube playlist: {state['playlist']['name']}") + logger.info(f"Started Spotify discovery for YouTube playlist: {state['playlist']['name']}") return jsonify({"success": True, "message": "Discovery started"}) except Exception as e: - print(f"Error starting YouTube discovery: {e}") + logger.error(f"Error starting YouTube discovery: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/discovery/status/', methods=['GET']) @@ -37667,7 +37606,7 @@ def get_youtube_discovery_status(url_hash): return jsonify(response) except Exception as e: - print(f"Error getting YouTube discovery status: {e}") + logger.error(f"Error getting YouTube discovery status: {e}") return jsonify({"error": str(e)}), 500 @@ -37739,13 +37678,13 @@ def unmatch_discovery_track(): 'unmatched_by_user': True, }) except Exception as e: - print(f"Error clearing mirrored track match: {e}") + logger.error(f"Error clearing mirrored track match: {e}") - print(f"Unmatched discovery track {track_index}: {result.get('yt_track', result.get('lb_track', ''))}") + logger.info(f"Unmatched discovery track {track_index}: {result.get('yt_track', result.get('lb_track', ''))}") return jsonify({'success': True}) except Exception as e: - print(f"Error unmatching discovery track: {e}") + logger.error(f"Error unmatching discovery track: {e}") return jsonify({'success': False, 'error': str(e)}), 500 @@ -37806,8 +37745,8 @@ def update_youtube_discovery_match(): if old_status != 'found' and old_status != 'Found': state['spotify_matches'] = state.get('spotify_matches', 0) + 1 - print(f"Manual match updated: youtube - {identifier} - track {track_index}") - print(f" ā†’ {result['spotify_artist']} - {result['spotify_track']}") + logger.info(f"Manual match updated: youtube - {identifier} - track {track_index}") + logger.info(f" ā†’ {result['spotify_artist']} - {result['spotify_track']}") # Save manual fix to discovery cache so it appears in discovery pool try: @@ -37841,9 +37780,9 @@ def update_youtube_discovery_match(): cache_key[0], cache_key[1], 'spotify', 1.0, matched_data, original_name, original_artist ) - print(f"Manual fix saved to discovery cache: {original_name} by {original_artist}") + logger.info(f"Manual fix saved to discovery cache: {original_name} by {original_artist}") except Exception as cache_err: - print(f"Error saving manual fix to discovery cache: {cache_err}") + logger.error(f"Error saving manual fix to discovery cache: {cache_err}") # Persist manual fix to DB for mirrored playlists if identifier.startswith('mirrored_'): @@ -37862,14 +37801,14 @@ def update_youtube_discovery_match(): } db.update_mirrored_track_extra_data(db_track_id, extra_data) result['matched_data'] = matched_data - print(f"Persisted manual fix to DB for track {db_track_id}") + logger.info(f"Persisted manual fix to DB for track {db_track_id}") except Exception as wb_err: - print(f"Error persisting manual fix to DB: {wb_err}") + logger.error(f"Error persisting manual fix to DB: {wb_err}") return jsonify({'success': True, 'result': result}) except Exception as e: - print(f"Error updating YouTube discovery match: {e}") + logger.error(f"Error updating YouTube discovery match: {e}") return jsonify({'error': str(e)}), 500 @@ -37903,7 +37842,7 @@ def _run_youtube_discovery_worker(url_hash): # Get fallback client itunes_client = _get_metadata_fallback_client() - print(f"Starting {discovery_source} discovery for {len(tracks)} YouTube tracks...") + logger.info(f"Starting {discovery_source} discovery for {len(tracks)} YouTube tracks...") # Store the discovery source in state state['discovery_source'] = discovery_source @@ -37913,7 +37852,7 @@ def _run_youtube_discovery_worker(url_hash): try: # Check for cancellation (phase changed by reset/delete/close) if state.get('phase') != 'discovering': - print(f"Discovery cancelled for {url_hash} (phase changed to '{state.get('phase')}')") + logger.warning(f"Discovery cancelled for {url_hash} (phase changed to '{state.get('phase')}')") return # Update progress @@ -37927,7 +37866,7 @@ def _run_youtube_discovery_worker(url_hash): cleaned_title = track['name'] cleaned_artist = track['artists'][0] if track['artists'] else 'Unknown Artist' - print(f"Searching {discovery_source} for: '{cleaned_artist}' - '{cleaned_title}'") + logger.info(f"Searching {discovery_source} for: '{cleaned_artist}' - '{cleaned_title}'") # Check discovery cache first cache_key = _get_discovery_cache_key(cleaned_title, cleaned_artist) @@ -37935,7 +37874,7 @@ def _run_youtube_discovery_worker(url_hash): cache_db = get_database() cached_match = cache_db.get_discovery_cache_match(cache_key[0], cache_key[1], discovery_source) if cached_match and _validate_discovery_cache_artist(cleaned_artist, cached_match): - print(f"CACHE HIT [{i+1}/{len(tracks)}]: {cleaned_artist} - {cleaned_title}") + logger.debug(f"CACHE HIT [{i+1}/{len(tracks)}]: {cleaned_artist} - {cleaned_title}") result = { 'index': i, 'yt_track': cleaned_title, @@ -37954,7 +37893,7 @@ def _run_youtube_discovery_worker(url_hash): state['discovery_results'].append(result) continue except Exception as cache_err: - print(f"Cache lookup error: {cache_err}") + logger.error(f"Cache lookup error: {cache_err}") # Try multiple search strategies using matching engine matched_track = None @@ -37971,14 +37910,14 @@ def _run_youtube_discovery_worker(url_hash): 'album': None })() search_queries = matching_engine.generate_download_queries(temp_track) - print(f"Generated {len(search_queries)} search queries for YouTube track") + logger.info(f"Generated {len(search_queries)} search queries for YouTube track") except Exception as e: - print(f"Matching engine failed for YouTube, falling back to basic query: {e}") + logger.error(f"Matching engine failed for YouTube, falling back to basic query: {e}") search_queries = [f"{cleaned_artist} {cleaned_title}", cleaned_title] for query_idx, search_query in enumerate(search_queries): try: - print(f"YouTube query {query_idx + 1}/{len(search_queries)}: {search_query}") + logger.debug(f"YouTube query {query_idx + 1}/{len(search_queries)}: {search_query}") search_results = None @@ -38003,22 +37942,22 @@ def _run_youtube_discovery_worker(url_hash): best_raw_track = _cache.get_entity('spotify', 'track', match.id) else: best_raw_track = None - print(f"New best YouTube match: {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") + logger.info(f"New best YouTube match: {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") if best_confidence >= 0.9: - print(f"High confidence YouTube match found ({best_confidence:.3f}), stopping search") + logger.info(f"High confidence YouTube match found ({best_confidence:.3f}), stopping search") break except Exception as e: - print(f"Error in YouTube search for query '{search_query}': {e}") + logger.debug(f"Error in YouTube search for query '{search_query}': {e}") continue if matched_track: - print(f"Strategy 1 YouTube match: {matched_track.artists[0]} - {matched_track.name} (confidence: {best_confidence:.3f})") + logger.info(f"Strategy 1 YouTube match: {matched_track.artists[0]} - {matched_track.name} (confidence: {best_confidence:.3f})") # Strategy 2: Swapped search (if first failed) - score results properly if not matched_track: - print("YouTube Strategy 2: Trying swapped search (artist/title reversed)") + logger.info("YouTube Strategy 2: Trying swapped search (artist/title reversed)") if use_spotify: query = f"artist:{cleaned_title} track:{cleaned_artist}" fallback_results = spotify_client.search_tracks(query, limit=5) @@ -38032,13 +37971,13 @@ def _run_youtube_discovery_worker(url_hash): if match and confidence >= min_confidence: matched_track = match best_confidence = confidence - print(f"Strategy 2 YouTube match (swapped): {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") + logger.info(f"Strategy 2 YouTube match (swapped): {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") # Strategy 3: Raw data search (if still failed) - score results properly if not matched_track: raw_title = track.get('raw_title', cleaned_title) raw_artist = track.get('raw_artist', cleaned_artist) - print(f"YouTube Strategy 3: Trying raw data search: '{raw_artist} {raw_title}'") + logger.info(f"YouTube Strategy 3: Trying raw data search: '{raw_artist} {raw_title}'") query = f"{raw_artist} {raw_title}" if use_spotify: fallback_results = spotify_client.search_tracks(query, limit=5) @@ -38051,11 +37990,11 @@ def _run_youtube_discovery_worker(url_hash): if match and confidence >= min_confidence: matched_track = match best_confidence = confidence - print(f"Strategy 3 YouTube match (raw): {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") + logger.info(f"Strategy 3 YouTube match (raw): {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") # Strategy 4: Extended search with higher limit (last resort) if not matched_track: - print(f"YouTube Strategy 4: Extended search with limit=50") + logger.info(f"YouTube Strategy 4: Extended search with limit=50") query = f"{cleaned_artist} {cleaned_title}" if use_spotify: extended_results = spotify_client.search_tracks(query, limit=50) @@ -38068,7 +38007,7 @@ def _run_youtube_discovery_worker(url_hash): if match and confidence >= min_confidence: matched_track = match best_confidence = confidence - print(f"Strategy 4 YouTube match (extended): {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") + logger.info(f"Strategy 4 YouTube match (extended): {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") # Create result entry result = { @@ -38122,9 +38061,9 @@ def _run_youtube_discovery_worker(url_hash): cache_key[0], cache_key[1], discovery_source, best_confidence, result['matched_data'], cleaned_title, cleaned_artist ) - print(f"CACHE SAVED: {cleaned_artist} - {cleaned_title} (confidence: {best_confidence:.3f})") + logger.info(f"CACHE SAVED: {cleaned_artist} - {cleaned_title} (confidence: {best_confidence:.3f})") except Exception as cache_err: - print(f"Cache save error: {cache_err}") + logger.error(f"Cache save error: {cache_err}") else: # Auto Wing It fallback ā€” build stub from raw source data @@ -38141,10 +38080,10 @@ def _run_youtube_discovery_worker(url_hash): state['discovery_results'].append(result) - print(f" {'' if matched_track else ''} Track {i+1}/{len(tracks)}: {result['status']}") + logger.info(f" {'' if matched_track else ''} Track {i+1}/{len(tracks)}: {result['status']}") except Exception as e: - print(f"Error processing track {i}: {e}") + logger.error(f"Error processing track {i}: {e}") result = { 'index': i, 'yt_track': track['name'], @@ -38199,9 +38138,9 @@ def _run_youtube_discovery_worker(url_hash): 'provider': discovery_source, } db.update_mirrored_track_extra_data(db_track_id, extra_data) - print(f"Wrote discovery results to DB for {url_hash}") + logger.info(f"Wrote discovery results to DB for {url_hash}") except Exception as wb_err: - print(f"Error writing discovery results to DB: {wb_err}") + logger.error(f"Error writing discovery results to DB: {wb_err}") playlist_name = playlist['name'] source_label = discovery_source.upper() @@ -38211,10 +38150,10 @@ def _run_youtube_discovery_worker(url_hash): activity_msg += f", {wing_it_count} wing it" add_activity_item("", f"YouTube Discovery Complete ({source_label})", activity_msg, "Now") - print(f"YouTube discovery complete ({discovery_source}): {state['spotify_matches']}/{len(tracks)} tracks matched, {wing_it_count} wing it") + logger.info(f"YouTube discovery complete ({discovery_source}): {state['spotify_matches']}/{len(tracks)} tracks matched, {wing_it_count} wing it") except Exception as e: - print(f"Error in YouTube discovery worker: {e}") + logger.error(f"Error in YouTube discovery worker: {e}") state['status'] = 'error' state['phase'] = 'fresh' finally: @@ -38237,7 +38176,7 @@ def _run_listenbrainz_discovery_worker(state_key): # Get fallback client itunes_client = _get_metadata_fallback_client() - print(f"Starting {discovery_source} discovery for {len(tracks)} ListenBrainz tracks...") + logger.info(f"Starting {discovery_source} discovery for {len(tracks)} ListenBrainz tracks...") # Store the discovery source in state state['discovery_source'] = discovery_source @@ -38247,7 +38186,7 @@ def _run_listenbrainz_discovery_worker(state_key): try: # Check for cancellation if state.get('phase') != 'discovering': - print(f"ListenBrainz discovery cancelled (phase changed to '{state.get('phase')}')") + logger.warning(f"ListenBrainz discovery cancelled (phase changed to '{state.get('phase')}')") return # Update progress @@ -38259,7 +38198,7 @@ def _run_listenbrainz_discovery_worker(state_key): album_name = track.get('album_name', '') duration_ms = track.get('duration_ms', 0) - print(f"Searching {discovery_source} for: '{cleaned_artist}' - '{cleaned_title}'") + logger.info(f"Searching {discovery_source} for: '{cleaned_artist}' - '{cleaned_title}'") # Check discovery cache first cache_key = _get_discovery_cache_key(cleaned_title, cleaned_artist) @@ -38267,7 +38206,7 @@ def _run_listenbrainz_discovery_worker(state_key): cache_db = get_database() cached_match = cache_db.get_discovery_cache_match(cache_key[0], cache_key[1], discovery_source) if cached_match and _validate_discovery_cache_artist(cleaned_artist, cached_match): - print(f"CACHE HIT [{i+1}/{len(tracks)}]: {cleaned_artist} - {cleaned_title}") + logger.debug(f"CACHE HIT [{i+1}/{len(tracks)}]: {cleaned_artist} - {cleaned_title}") result = { 'index': i, 'lb_track': cleaned_title, @@ -38286,7 +38225,7 @@ def _run_listenbrainz_discovery_worker(state_key): state['discovery_results'].append(result) continue except Exception as cache_err: - print(f"Cache lookup error: {cache_err}") + logger.error(f"Cache lookup error: {cache_err}") # Try multiple search strategies using matching engine matched_track = None @@ -38303,14 +38242,14 @@ def _run_listenbrainz_discovery_worker(state_key): 'album': album_name if album_name else None })() search_queries = matching_engine.generate_download_queries(temp_track) - print(f"Generated {len(search_queries)} search queries for ListenBrainz track") + logger.info(f"Generated {len(search_queries)} search queries for ListenBrainz track") except Exception as e: - print(f"Matching engine failed for ListenBrainz, falling back to basic query: {e}") + logger.error(f"Matching engine failed for ListenBrainz, falling back to basic query: {e}") search_queries = [f"{cleaned_artist} {cleaned_title}", cleaned_title] for query_idx, search_query in enumerate(search_queries): try: - print(f"ListenBrainz query {query_idx + 1}/{len(search_queries)}: {search_query}") + logger.debug(f"ListenBrainz query {query_idx + 1}/{len(search_queries)}: {search_query}") search_results = None @@ -38335,22 +38274,22 @@ def _run_listenbrainz_discovery_worker(state_key): best_raw_track = _cache.get_entity('spotify', 'track', match.id) else: best_raw_track = None - print(f"New best ListenBrainz match: {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") + logger.info(f"New best ListenBrainz match: {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") if best_confidence >= 0.9: - print(f"High confidence ListenBrainz match found ({best_confidence:.3f}), stopping search") + logger.info(f"High confidence ListenBrainz match found ({best_confidence:.3f}), stopping search") break except Exception as e: - print(f"Error in ListenBrainz search for query '{search_query}': {e}") + logger.debug(f"Error in ListenBrainz search for query '{search_query}': {e}") continue if matched_track: - print(f"Strategy 1 ListenBrainz match: {matched_track.artists[0]} - {matched_track.name} (confidence: {best_confidence:.3f})") + logger.info(f"Strategy 1 ListenBrainz match: {matched_track.artists[0]} - {matched_track.name} (confidence: {best_confidence:.3f})") # Strategy 2: Swapped search (if first failed) - score results properly if not matched_track: - print("ListenBrainz Strategy 2: Trying swapped search (artist/title reversed)") + logger.info("ListenBrainz Strategy 2: Trying swapped search (artist/title reversed)") if use_spotify: query = f"artist:{cleaned_title} track:{cleaned_artist}" fallback_results = spotify_client.search_tracks(query, limit=5) @@ -38364,11 +38303,11 @@ def _run_listenbrainz_discovery_worker(state_key): if match and confidence >= min_confidence: matched_track = match best_confidence = confidence - print(f"Strategy 2 ListenBrainz match (swapped): {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") + logger.info(f"Strategy 2 ListenBrainz match (swapped): {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") # Strategy 3: Album-based search (if still failed and we have album name) - score results properly if not matched_track and album_name: - print(f"ListenBrainz Strategy 3: Trying album-based search: '{cleaned_artist} {album_name} {cleaned_title}'") + logger.info(f"ListenBrainz Strategy 3: Trying album-based search: '{cleaned_artist} {album_name} {cleaned_title}'") if use_spotify: query = f"artist:{cleaned_artist} album:{album_name} track:{cleaned_title}" fallback_results = spotify_client.search_tracks(query, limit=5) @@ -38382,11 +38321,11 @@ def _run_listenbrainz_discovery_worker(state_key): if match and confidence >= min_confidence: matched_track = match best_confidence = confidence - print(f"Strategy 3 ListenBrainz match (album): {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") + logger.info(f"Strategy 3 ListenBrainz match (album): {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") # Strategy 4: Extended search with higher limit (last resort) if not matched_track: - print(f"ListenBrainz Strategy 4: Extended search with limit=50") + logger.info(f"ListenBrainz Strategy 4: Extended search with limit=50") query = f"{cleaned_artist} {cleaned_title}" if use_spotify: extended_results = spotify_client.search_tracks(query, limit=50) @@ -38399,7 +38338,7 @@ def _run_listenbrainz_discovery_worker(state_key): if match and confidence >= min_confidence: matched_track = match best_confidence = confidence - print(f"Strategy 4 ListenBrainz match (extended): {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") + logger.info(f"Strategy 4 ListenBrainz match (extended): {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") # Create result entry result = { @@ -38453,9 +38392,9 @@ def _run_listenbrainz_discovery_worker(state_key): cache_key[0], cache_key[1], discovery_source, best_confidence, result['matched_data'], cleaned_title, cleaned_artist ) - print(f"CACHE SAVED: {cleaned_artist} - {cleaned_title} (confidence: {best_confidence:.3f})") + logger.info(f"CACHE SAVED: {cleaned_artist} - {cleaned_title} (confidence: {best_confidence:.3f})") except Exception as cache_err: - print(f"Cache save error: {cache_err}") + logger.error(f"Cache save error: {cache_err}") else: # Auto Wing It fallback ā€” build stub from raw source data @@ -38472,10 +38411,10 @@ def _run_listenbrainz_discovery_worker(state_key): state['discovery_results'].append(result) - print(f" {'' if matched_track else ''} Track {i+1}/{len(tracks)}: {result['status']}") + logger.info(f" {'' if matched_track else ''} Track {i+1}/{len(tracks)}: {result['status']}") except Exception as e: - print(f"Error processing track {i}: {e}") + logger.error(f"Error processing track {i}: {e}") result = { 'index': i, 'lb_track': track['track_name'], @@ -38498,10 +38437,10 @@ def _run_listenbrainz_discovery_worker(state_key): source_label = discovery_source.upper() add_activity_item("", f"ListenBrainz Discovery Complete ({source_label})", f"'{playlist_name}' - {state['spotify_matches']}/{len(tracks)} tracks found", "Now") - print(f"ListenBrainz discovery complete ({discovery_source}): {state['spotify_matches']}/{len(tracks)} tracks matched") + logger.info(f"ListenBrainz discovery complete ({discovery_source}): {state['spotify_matches']}/{len(tracks)} tracks matched") except Exception as e: - print(f"Error in ListenBrainz discovery worker: {e}") + logger.error(f"Error in ListenBrainz discovery worker: {e}") state['status'] = 'error' state['phase'] = 'fresh' finally: @@ -38577,11 +38516,11 @@ def start_youtube_sync(url_hash): future = sync_executor.submit(_run_sync_task, sync_playlist_id, sync_data['playlist_name'], spotify_tracks, None, get_current_profile_id(), playlist_image_url) active_sync_workers[sync_playlist_id] = future - print(f"Started YouTube sync for: {playlist_name} ({len(spotify_tracks)} tracks)") + logger.info(f"Started YouTube sync for: {playlist_name} ({len(spotify_tracks)} tracks)") return jsonify({"success": True, "sync_playlist_id": sync_playlist_id}) except Exception as e: - print(f"Error starting YouTube sync: {e}") + logger.error(f"Error starting YouTube sync: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/sync/status/', methods=['GET']) @@ -38625,7 +38564,7 @@ def get_youtube_sync_status(url_hash): return jsonify(response) except Exception as e: - print(f"Error getting YouTube sync status: {e}") + logger.error(f"Error getting YouTube sync status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/sync/cancel/', methods=['POST']) @@ -38656,7 +38595,7 @@ def cancel_youtube_sync(url_hash): return jsonify({"success": True, "message": "YouTube sync cancelled"}) except Exception as e: - print(f"Error cancelling YouTube sync: {e}") + logger.error(f"Error cancelling YouTube sync: {e}") return jsonify({"error": str(e)}), 500 # New YouTube Playlist Management Endpoints (for persistent state) @@ -38692,11 +38631,11 @@ def get_all_youtube_playlists(): } playlists.append(playlist_info) - print(f"Returning {len(playlists)} stored YouTube playlists for hydration") + logger.info(f"Returning {len(playlists)} stored YouTube playlists for hydration") return jsonify({"playlists": playlists}) except Exception as e: - print(f"Error getting YouTube playlists: {e}") + logger.error(f"Error getting YouTube playlists: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/state/', methods=['GET']) @@ -38730,7 +38669,7 @@ def get_youtube_playlist_state(url_hash): return jsonify(response) except Exception as e: - print(f"Error getting YouTube playlist state: {e}") + logger.error(f"Error getting YouTube playlist state: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/reset/', methods=['POST']) @@ -38758,11 +38697,11 @@ def reset_youtube_playlist(url_hash): state['discovery_future'] = None state['last_accessed'] = time.time() - print(f"Reset YouTube playlist to fresh phase: {state['playlist']['name']}") + logger.info(f"Reset YouTube playlist to fresh phase: {state['playlist']['name']}") return jsonify({"success": True, "message": "Playlist reset to fresh state"}) except Exception as e: - print(f"Error resetting YouTube playlist: {e}") + logger.error(f"Error resetting YouTube playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/delete/', methods=['DELETE']) @@ -38782,11 +38721,11 @@ def delete_youtube_playlist(url_hash): playlist_name = state['playlist']['name'] del youtube_playlist_states[url_hash] - print(f"Deleted YouTube playlist from backend: {playlist_name}") + logger.info(f"Deleted YouTube playlist from backend: {playlist_name}") return jsonify({"success": True, "message": f"Playlist '{playlist_name}' deleted"}) except Exception as e: - print(f"Error deleting YouTube playlist: {e}") + logger.error(f"Error deleting YouTube playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/update_phase/', methods=['POST']) @@ -38811,11 +38750,11 @@ def update_youtube_playlist_phase(url_hash): state['phase'] = new_phase state['last_accessed'] = time.time() - print(f"Updated YouTube playlist {url_hash} phase: {old_phase} ā†’ {new_phase}") + logger.info(f"Updated YouTube playlist {url_hash} phase: {old_phase} ā†’ {new_phase}") return jsonify({"success": True, "message": f"Phase updated to {new_phase}", "old_phase": old_phase, "new_phase": new_phase}) except Exception as e: - print(f"Error updating YouTube playlist phase: {e}") + logger.error(f"Error updating YouTube playlist phase: {e}") return jsonify({"error": str(e)}), 500 def convert_youtube_results_to_spotify_tracks(discovery_results): @@ -38851,7 +38790,7 @@ def convert_youtube_results_to_spotify_tracks(discovery_results): } spotify_tracks.append(track) - print(f"Converted {len(spotify_tracks)} YouTube matches to Spotify tracks for sync") + logger.info(f"Converted {len(spotify_tracks)} YouTube matches to Spotify tracks for sync") return spotify_tracks @@ -38862,8 +38801,8 @@ def _run_sync_task(playlist_id, playlist_name, tracks_json, automation_id=None, global sync_states, sync_service task_start_time = time.time() - print(f"[TIMING] _run_sync_task STARTED for playlist '{playlist_name}' at {time.strftime('%H:%M:%S')}") - print(f"Received {len(tracks_json)} tracks from frontend") + logger.info(f"[TIMING] _run_sync_task STARTED for playlist '{playlist_name}' at {time.strftime('%H:%M:%S')}") + logger.info(f"Received {len(tracks_json)} tracks from frontend") # Record sync history start (skip for re-syncs triggered from history) _is_resync = playlist_id.startswith('resync_') @@ -38891,7 +38830,7 @@ def _run_sync_task(playlist_id, playlist_name, tracks_json, automation_id=None, try: # Recreate a Playlist object from the JSON data sent by the frontend # This avoids needing to re-fetch it from Spotify - print(f"Converting JSON tracks to SpotifyTrack objects...") + logger.info(f"Converting JSON tracks to SpotifyTrack objects...") # Store original track data with full album objects (for wishlist with cover art) # Normalize formats for wishlist: album must be dict {'name': ...}, artists must be [{'name': ...}] @@ -38957,9 +38896,9 @@ def _run_sync_task(playlist_id, playlist_name, tracks_json, automation_id=None, ) tracks.append(track) if i < 3: # Log first 3 tracks for debugging - print(f" Track {i+1}: '{track.name}' by {track.artists}") + logger.info(f" Track {i+1}: '{track.name}' by {track.artists}") - print(f"Created {len(tracks)} SpotifyTrack objects") + logger.info(f"Created {len(tracks)} SpotifyTrack objects") playlist = SpotifyPlaylist( id=playlist_id, @@ -38971,7 +38910,7 @@ def _run_sync_task(playlist_id, playlist_name, tracks_json, automation_id=None, tracks=tracks, total_tracks=len(tracks) ) - print(f"Created SpotifyPlaylist object: '{playlist.name}' with {playlist.total_tracks} tracks") + logger.info(f"Created SpotifyPlaylist object: '{playlist.name}' with {playlist.total_tracks} tracks") first_callback_time = [None] # Use list to allow modification in nested function @@ -38980,17 +38919,17 @@ def _run_sync_task(playlist_id, playlist_name, tracks_json, automation_id=None, if first_callback_time[0] is None: first_callback_time[0] = time.time() first_callback_duration = (first_callback_time[0] - task_start_time) * 1000 - print(f"ā±ļø [TIMING] FIRST progress callback at {time.strftime('%H:%M:%S')} (took {first_callback_duration:.1f}ms from start)") + logger.info(f"ā±ļø [TIMING] FIRST progress callback at {time.strftime('%H:%M:%S')} (took {first_callback_duration:.1f}ms from start)") - print(f"PROGRESS CALLBACK: {progress.current_step} - {progress.current_track}") - print(f" Progress: {progress.progress}% ({progress.matched_tracks}/{progress.total_tracks} matched, {progress.failed_tracks} failed)") + logger.info(f"PROGRESS CALLBACK: {progress.current_step} - {progress.current_track}") + logger.error(f" Progress: {progress.progress}% ({progress.matched_tracks}/{progress.total_tracks} matched, {progress.failed_tracks} failed)") with sync_lock: sync_states[playlist_id] = { "status": "syncing", "progress": progress.__dict__ # Convert dataclass to dict } - print(f" Updated sync_states for {playlist_id}") + logger.info(f" Updated sync_states for {playlist_id}") # Update automation progress card if automation_id: @@ -39010,7 +38949,7 @@ def _run_sync_task(playlist_id, playlist_name, tracks_json, automation_id=None, log_line=f'{track} ā€” {step}' if track else step, log_type=log_type) except Exception as setup_error: - print(f"SETUP ERROR in _run_sync_task: {setup_error}") + logger.error(f"SETUP ERROR in _run_sync_task: {setup_error}") import traceback traceback.print_exc() with sync_lock: @@ -39024,53 +38963,53 @@ def _run_sync_task(playlist_id, playlist_name, tracks_json, automation_id=None, return try: - print(f"Setting up sync service...") - print(f" sync_service available: {sync_service is not None}") + logger.info(f"Setting up sync service...") + logger.info(f" sync_service available: {sync_service is not None}") if sync_service is None: raise Exception("sync_service is None - not initialized properly") # Check sync service components - print(f" spotify_client: {sync_service.spotify_client is not None}") - print(f" plex_client: {sync_service.plex_client is not None}") - print(f" jellyfin_client: {sync_service.jellyfin_client is not None}") + logger.info(f" spotify_client: {sync_service.spotify_client is not None}") + logger.info(f" plex_client: {sync_service.plex_client is not None}") + logger.info(f" jellyfin_client: {sync_service.jellyfin_client is not None}") # Check media server connection before starting from config.settings import config_manager active_server = config_manager.get_active_media_server() - print(f" Active media server: {active_server}") + logger.info(f" Active media server: {active_server}") media_client, server_type = sync_service._get_active_media_client() - print(f" Media client available: {media_client is not None}") + logger.info(f" Media client available: {media_client is not None}") if media_client: is_connected = media_client.is_connected() - print(f" Media client connected: {is_connected}") + logger.info(f" Media client connected: {is_connected}") # Check database access try: from database.music_database import MusicDatabase db = MusicDatabase() - print(f" Database initialized: {db is not None}") + logger.debug(f" Database initialized: {db is not None}") except Exception as db_error: - print(f" Database initialization failed: {db_error}") + logger.error(f" Database initialization failed: {db_error}") - print(f"Attaching progress callback...") + logger.info(f"Attaching progress callback...") # Attach the progress callback sync_service.set_progress_callback(progress_callback, playlist.name) - print(f"Progress callback attached for playlist: {playlist.name}") + logger.info(f"Progress callback attached for playlist: {playlist.name}") # CRITICAL FIX: Add database-only fallback for web context # If media client is not connected, patch the sync service to use database-only matching if media_client is None or not media_client.is_connected(): - print(f"Media client not connected - patching sync service for database-only matching") + logger.info(f"Media client not connected - patching sync service for database-only matching") # Store original method original_find_track = sync_service._find_track_in_media_server # Create database-only replacement method async def database_only_find_track(spotify_track): - print(f"Database-only search for: '{spotify_track.name}' by {spotify_track.artists}") + logger.info(f"Database-only search for: '{spotify_track.name}' by {spotify_track.artists}") try: from database.music_database import MusicDatabase from config.settings import config_manager @@ -39092,9 +39031,9 @@ def _run_sync_task(playlist_id, playlist_name, tracks_json, automation_id=None, self.ratingKey = db_t.id self.title = db_t.title self.id = db_t.id - print(f"Sync cache hit: '{original_title}' ā†’ server track {cached['server_track_id']}") + logger.debug(f"Sync cache hit: '{original_title}' ā†’ server track {cached['server_track_id']}") return DatabaseTrackCached(db_track_check), cached['confidence'] - print(f"Sync cache stale for '{original_title}' ā€” track gone") + logger.warning(f"Sync cache stale for '{original_title}' ā€” track gone") except Exception: pass # --- End cache fast-path --- @@ -39116,7 +39055,7 @@ def _run_sync_task(playlist_id, playlist_name, tracks_json, automation_id=None, ) if db_track and confidence >= 0.80: - print(f"Database match: '{db_track.title}' (confidence: {confidence:.2f})") + logger.info(f"Database match: '{db_track.title}' (confidence: {confidence:.2f})") # Save to sync match cache if spotify_id: @@ -39139,21 +39078,21 @@ def _run_sync_task(playlist_id, playlist_name, tracks_json, automation_id=None, return DatabaseTrackMock(db_track), confidence - print(f"No database match found for: '{original_title}'") + logger.warning(f"No database match found for: '{original_title}'") return None, 0.0 except Exception as e: - print(f"Database search error: {e}") + logger.error(f"Database search error: {e}") return None, 0.0 # Patch the method sync_service._find_track_in_media_server = database_only_find_track - print(f"Patched sync service to use database-only matching") + logger.info(f"Patched sync service to use database-only matching") sync_start_time = time.time() setup_duration = (sync_start_time - task_start_time) * 1000 - print(f"ā±ļø [TIMING] Setup completed at {time.strftime('%H:%M:%S')} (took {setup_duration:.1f}ms)") - print(f"Starting actual sync process with run_async()...") + logger.info(f"ā±ļø [TIMING] Setup completed at {time.strftime('%H:%M:%S')} (took {setup_duration:.1f}ms)") + logger.info(f"Starting actual sync process with run_async()...") # Attach original tracks map to sync_service for wishlist with album images sync_service._original_tracks_map = original_tracks_map @@ -39173,9 +39112,9 @@ def _run_sync_task(playlist_id, playlist_name, tracks_json, automation_id=None, sync_duration = (time.time() - sync_start_time) * 1000 total_duration = (time.time() - task_start_time) * 1000 - print(f"ā±ļø [TIMING] Sync completed at {time.strftime('%H:%M:%S')} (sync: {sync_duration:.1f}ms, total: {total_duration:.1f}ms)") - print(f"Sync process completed! Result type: {type(result)}") - print(f" Result details: matched={getattr(result, 'matched_tracks', 'N/A')}, total={getattr(result, 'total_tracks', 'N/A')}") + logger.info(f"ā±ļø [TIMING] Sync completed at {time.strftime('%H:%M:%S')} (sync: {sync_duration:.1f}ms, total: {total_duration:.1f}ms)") + logger.info(f"Sync process completed! Result type: {type(result)}") + logger.info(f" Result details: matched={getattr(result, 'matched_tracks', 'N/A')}, total={getattr(result, 'total_tracks', 'N/A')}") # Update final state on completion # Convert result to JSON-serializable dict (datetime/errors can't be emitted via SocketIO) @@ -39200,24 +39139,24 @@ def _run_sync_task(playlist_id, playlist_name, tracks_json, automation_id=None, "progress": result_dict, "result": result_dict } - print(f"Sync finished for {playlist_id} - state updated") + logger.info(f"Sync finished for {playlist_id} - state updated") # Set playlist poster image if available (Plex, Jellyfin, Emby) _synced = getattr(result, 'synced_tracks', 0) - print(f"[PLAYLIST IMAGE] image_url={playlist_image_url!r}, synced_tracks={_synced}") + logger.info(f"[PLAYLIST IMAGE] image_url={playlist_image_url!r}, synced_tracks={_synced}") if playlist_image_url and _synced > 0: try: active_server = config_manager.get_active_media_server() - print(f"[PLAYLIST IMAGE] active_server={active_server}") + logger.info(f"[PLAYLIST IMAGE] active_server={active_server}") if active_server == 'plex' and plex_client: ok = plex_client.set_playlist_image(playlist_name, playlist_image_url) - print(f"[PLAYLIST IMAGE] Plex upload result: {ok}") + logger.info(f"[PLAYLIST IMAGE] Plex upload result: {ok}") elif active_server in ('jellyfin', 'emby') and jellyfin_client: ok = jellyfin_client.set_playlist_image(playlist_name, playlist_image_url) - print(f"[PLAYLIST IMAGE] Jellyfin upload result: {ok}") + logger.info(f"[PLAYLIST IMAGE] Jellyfin upload result: {ok}") # Navidrome doesn't support custom playlist images except Exception as img_err: - print(f"[PLAYLIST IMAGE] Exception: {img_err}") + logger.error(f"[PLAYLIST IMAGE] Exception: {img_err}") # Record sync history completion with per-track data try: @@ -39244,11 +39183,11 @@ def _run_sync_task(playlist_id, playlist_name, tracks_json, automation_id=None, try: track_results_json = json.dumps(match_details, default=str) saved = db.update_sync_history_track_results(target_batch_id, track_results_json) - print(f"[Sync History] Saved {len(match_details)} track results for batch {target_batch_id} (saved={saved})") + logger.info(f"[Sync History] Saved {len(match_details)} track results for batch {target_batch_id} (saved={saved})") except Exception as json_err: - print(f"[Sync History] Failed to serialize track results: {json_err}") + logger.error(f"[Sync History] Failed to serialize track results: {json_err}") else: - print(f"[Sync History] No match_details on SyncResult for batch {target_batch_id}") + logger.warning(f"[Sync History] No match_details on SyncResult for batch {target_batch_id}") except Exception as e: logger.warning(f"Failed to record sync history completion: {e}") @@ -39285,7 +39224,7 @@ def _run_sync_task(playlist_id, playlist_name, tracks_json, automation_id=None, tracks_hash=_tracks_hash) except Exception as e: - print(f"SYNC FAILED for {playlist_id}: {e}") + logger.error(f"SYNC FAILED for {playlist_id}: {e}") import traceback traceback.print_exc() with sync_lock: @@ -39297,21 +39236,21 @@ def _run_sync_task(playlist_id, playlist_name, tracks_json, automation_id=None, _update_automation_progress(automation_id, status='error', progress=100, phase='Error', log_line=f'Sync failed: {str(e)}', log_type='error') finally: - print(f"Cleaning up progress callback for {playlist.name}") + logger.info(f"Cleaning up progress callback for {playlist.name}") # Clean up the callback if sync_service: sync_service.clear_progress_callback(playlist.name) # Clean up original tracks map if hasattr(sync_service, '_original_tracks_map'): del sync_service._original_tracks_map - print(f"Cleanup completed for {playlist_id}") + logger.info(f"Cleanup completed for {playlist_id}") @app.route('/api/sync/start', methods=['POST']) def start_playlist_sync(): """Starts a new sync process for a given playlist.""" request_start_time = time.time() - print(f"ā±ļø [TIMING] Sync request received at {time.strftime('%H:%M:%S')}") + logger.info(f"ā±ļø [TIMING] Sync request received at {time.strftime('%H:%M:%S')}") data = request.get_json() playlist_id = data.get('playlist_id') @@ -39341,10 +39280,10 @@ def start_playlist_sync(): future = sync_executor.submit(_run_sync_task, playlist_id, playlist_name, tracks_json, None, _sync_profile_id, playlist_image_url) active_sync_workers[playlist_id] = future thread_submit_duration = (time.time() - thread_submit_time) * 1000 - print(f"ā±ļø [TIMING] Thread submitted at {time.strftime('%H:%M:%S')} (took {thread_submit_duration:.1f}ms)") + logger.info(f"ā±ļø [TIMING] Thread submitted at {time.strftime('%H:%M:%S')} (took {thread_submit_duration:.1f}ms)") total_request_time = (time.time() - request_start_time) * 1000 - print(f"ā±ļø [TIMING] Request completed at {time.strftime('%H:%M:%S')} (total: {total_request_time:.1f}ms)") + logger.info(f"ā±ļø [TIMING] Request completed at {time.strftime('%H:%M:%S')} (total: {total_request_time:.1f}ms)") return jsonify({"success": True, "message": "Sync started."}) @@ -39398,34 +39337,34 @@ def cancel_playlist_sync(): def test_database_access(): """Test endpoint to verify database connectivity for sync operations""" try: - print(f"Testing database access for sync operations...") + logger.debug(f"Testing database access for sync operations...") # Test database initialization from database.music_database import MusicDatabase db = MusicDatabase() - print(f" Database initialized: {db is not None}") + logger.debug(f" Database initialized: {db is not None}") # Test basic database query stats = db.get_database_info_for_server() - print(f" Database stats retrieved: {stats}") + logger.debug(f" Database stats retrieved: {stats}") # Test track existence check (like sync service does) db_track, confidence = db.check_track_exists("test track", "test artist", confidence_threshold=0.7) - print(f" Track existence check works: found={db_track is not None}, confidence={confidence}") + logger.info(f" Track existence check works: found={db_track is not None}, confidence={confidence}") # Test config manager from config.settings import config_manager active_server = config_manager.get_active_media_server() - print(f" Active media server: {active_server}") + logger.info(f" Active media server: {active_server}") # Test media clients - print(f" Media clients status:") - print(f" plex_client: {plex_client is not None}") + logger.info(f" Media clients status:") + logger.info(f" plex_client: {plex_client is not None}") if plex_client: - print(f" plex_client.is_connected(): {plex_client.is_connected()}") - print(f" jellyfin_client: {jellyfin_client is not None}") + logger.info(f" plex_client.is_connected(): {plex_client.is_connected()}") + logger.info(f" jellyfin_client: {jellyfin_client is not None}") if jellyfin_client: - print(f" jellyfin_client.is_connected(): {jellyfin_client.is_connected()}") + logger.info(f" jellyfin_client.is_connected(): {jellyfin_client.is_connected()}") return jsonify({ "success": True, @@ -39440,7 +39379,7 @@ def test_database_access(): }) except Exception as e: - print(f" Database test failed: {e}") + logger.error(f" Database test failed: {e}") import traceback traceback.print_exc() return jsonify({ @@ -39469,7 +39408,7 @@ def save_discover_download_snapshot(): db.save_bubble_snapshot('discover_downloads', downloads, profile_id=get_current_profile_id()) download_count = len(downloads) - print(f"Saved discover download snapshot: {download_count} downloads") + logger.info(f"Saved discover download snapshot: {download_count} downloads") return jsonify({ 'success': True, @@ -39478,7 +39417,7 @@ def save_discover_download_snapshot(): }) except Exception as e: - print(f"Error saving discover download snapshot: {e}") + logger.error(f"Error saving discover download snapshot: {e}") import traceback traceback.print_exc() return jsonify({ @@ -39514,7 +39453,7 @@ def hydrate_discover_downloads(): snapshot_dt = datetime.fromisoformat(snapshot_time.replace('Z', '+00:00')) cutoff = datetime.now() - timedelta(hours=48) if snapshot_dt < cutoff: - print(f"Cleaning up old discover download snapshot from {snapshot_time}") + logger.info(f"Cleaning up old discover download snapshot from {snapshot_time}") db.delete_bubble_snapshot('discover_downloads', profile_id=get_current_profile_id()) return jsonify({ 'success': True, @@ -39522,7 +39461,7 @@ def hydrate_discover_downloads(): 'message': 'Old snapshot cleaned up' }) except ValueError as e: - print(f"Error checking discover snapshot age: {e}") + logger.error(f"Error checking discover snapshot age: {e}") # Get current active download processes for live status current_processes = {} @@ -39538,11 +39477,11 @@ def hydrate_discover_downloads(): 'phase': batch_data.get('phase') } except Exception as e: - print(f"Error fetching active processes for discover download hydration: {e}") + logger.error(f"Error fetching active processes for discover download hydration: {e}") # If no active processes exist, the app likely restarted - clean up snapshots if not current_processes: - print(f"No active processes found - app likely restarted, cleaning up discover download snapshot") + logger.warning(f"No active processes found - app likely restarted, cleaning up discover download snapshot") db.delete_bubble_snapshot('discover_downloads', profile_id=get_current_profile_id()) return jsonify({ 'success': True, @@ -39557,11 +39496,11 @@ def hydrate_discover_downloads(): if playlist_id in current_processes: process_info = current_processes[playlist_id] live_status = 'in_progress' - print(f"Found active process for discover download {playlist_id}: {process_info['phase']}") + logger.info(f"Found active process for discover download {playlist_id}: {process_info['phase']}") else: # No active process - likely completed live_status = 'completed' - print(f"No active process for discover download {playlist_id} - marking as completed") + logger.warning(f"No active process for discover download {playlist_id} - marking as completed") # Create updated download entry hydrated_downloads[playlist_id] = { @@ -39577,7 +39516,7 @@ def hydrate_discover_downloads(): active_count = sum(1 for d in hydrated_downloads.values() if d['status'] == 'in_progress') completed_count = sum(1 for d in hydrated_downloads.values() if d['status'] == 'completed') - print(f"Hydrated {download_count} discover downloads: {active_count} active, {completed_count} completed") + logger.info(f"Hydrated {download_count} discover downloads: {active_count} active, {completed_count} completed") return jsonify({ 'success': True, @@ -39590,7 +39529,7 @@ def hydrate_discover_downloads(): }) except Exception as e: - print(f"Error hydrating discover downloads: {e}") + logger.error(f"Error hydrating discover downloads: {e}") import traceback traceback.print_exc() return jsonify({ @@ -39618,7 +39557,7 @@ def save_artist_bubble_snapshot(): db.save_bubble_snapshot('artist_bubbles', bubbles, profile_id=get_current_profile_id()) bubble_count = len(bubbles) - print(f"Saved artist bubble snapshot: {bubble_count} artists") + logger.info(f"Saved artist bubble snapshot: {bubble_count} artists") return jsonify({ 'success': True, @@ -39627,7 +39566,7 @@ def save_artist_bubble_snapshot(): }) except Exception as e: - print(f"Error saving artist bubble snapshot: {e}") + logger.error(f"Error saving artist bubble snapshot: {e}") import traceback traceback.print_exc() return jsonify({ @@ -39663,7 +39602,7 @@ def hydrate_artist_bubbles(): snapshot_dt = datetime.fromisoformat(snapshot_time.replace('Z', '+00:00')) cutoff = datetime.now() - timedelta(hours=48) if snapshot_dt < cutoff: - print(f"Cleaning up old snapshot from {snapshot_time}") + logger.info(f"Cleaning up old snapshot from {snapshot_time}") db.delete_bubble_snapshot('artist_bubbles', profile_id=get_current_profile_id()) return jsonify({ 'success': True, @@ -39671,7 +39610,7 @@ def hydrate_artist_bubbles(): 'message': 'Old snapshot cleaned up' }) except ValueError as e: - print(f"Error checking snapshot age: {e}") + logger.error(f"Error checking snapshot age: {e}") # Get current active download processes for live status current_processes = {} @@ -39687,11 +39626,11 @@ def hydrate_artist_bubbles(): 'phase': batch_data.get('phase') } except Exception as e: - print(f"Error fetching active processes for hydration: {e}") + logger.error(f"Error fetching active processes for hydration: {e}") # If no active processes exist, the app likely restarted - clean up snapshots if not current_processes: - print(f"No active processes found - app likely restarted, cleaning up snapshot") + logger.warning(f"No active processes found - app likely restarted, cleaning up snapshot") db.delete_bubble_snapshot('artist_bubbles', profile_id=get_current_profile_id()) return jsonify({ 'success': True, @@ -39715,11 +39654,11 @@ def hydrate_artist_bubbles(): if virtual_playlist_id in current_processes: process_info = current_processes[virtual_playlist_id] live_status = 'in_progress' - print(f"Found active process for {download['album']['name']}: {process_info['phase']}") + logger.info(f"Found active process for {download['album']['name']}: {process_info['phase']}") else: # No active process - likely completed live_status = 'view_results' - print(f"No active process for {download['album']['name']} - marking as completed") + logger.warning(f"No active process for {download['album']['name']} - marking as completed") # Create updated download entry updated_download = { @@ -39748,7 +39687,7 @@ def hydrate_artist_bubbles(): for download in bubble['downloads'] if download['status'] == 'view_results') - print(f"Hydrated {bubble_count} artist bubbles: {active_count} active, {completed_count} completed") + logger.info(f"Hydrated {bubble_count} artist bubbles: {active_count} active, {completed_count} completed") return jsonify({ 'success': True, @@ -39762,7 +39701,7 @@ def hydrate_artist_bubbles(): }) except Exception as e: - print(f"Error hydrating artist bubbles: {e}") + logger.error(f"Error hydrating artist bubbles: {e}") import traceback traceback.print_exc() return jsonify({ @@ -39790,7 +39729,7 @@ def save_search_bubble_snapshot(): db.save_bubble_snapshot('search_bubbles', bubbles, profile_id=get_current_profile_id()) bubble_count = len(bubbles) - print(f"Saved search bubble snapshot: {bubble_count} albums/tracks") + logger.info(f"Saved search bubble snapshot: {bubble_count} albums/tracks") return jsonify({ 'success': True, @@ -39799,7 +39738,7 @@ def save_search_bubble_snapshot(): }) except Exception as e: - print(f"Error saving search bubble snapshot: {e}") + logger.error(f"Error saving search bubble snapshot: {e}") import traceback traceback.print_exc() return jsonify({ @@ -39835,7 +39774,7 @@ def hydrate_search_bubbles(): snapshot_dt = datetime.fromisoformat(snapshot_time.replace('Z', '+00:00')) cutoff = datetime.now() - timedelta(hours=48) if snapshot_dt < cutoff: - print(f"Cleaning up old search snapshot from {snapshot_time}") + logger.info(f"Cleaning up old search snapshot from {snapshot_time}") db.delete_bubble_snapshot('search_bubbles', profile_id=get_current_profile_id()) return jsonify({ 'success': True, @@ -39843,7 +39782,7 @@ def hydrate_search_bubbles(): 'message': 'Old snapshot cleaned up' }) except ValueError as e: - print(f"Error checking snapshot age: {e}") + logger.error(f"Error checking snapshot age: {e}") # Get current active download processes for live status current_processes = {} @@ -39859,11 +39798,11 @@ def hydrate_search_bubbles(): 'phase': batch_data.get('phase') } except Exception as e: - print(f"Error fetching active processes for hydration: {e}") + logger.error(f"Error fetching active processes for hydration: {e}") # If no active processes exist, the app likely restarted - clean up snapshots if not current_processes: - print(f"No active processes found - app likely restarted, cleaning up search snapshot") + logger.warning(f"No active processes found - app likely restarted, cleaning up search snapshot") db.delete_bubble_snapshot('search_bubbles', profile_id=get_current_profile_id()) return jsonify({ 'success': True, @@ -39886,11 +39825,11 @@ def hydrate_search_bubbles(): if virtual_playlist_id in current_processes: process_info = current_processes[virtual_playlist_id] live_status = 'in_progress' - print(f"Found active process for {download['item']['name']}: {process_info['phase']}") + logger.info(f"Found active process for {download['item']['name']}: {process_info['phase']}") else: # No active process - likely completed live_status = 'view_results' - print(f"No active process for {download['item']['name']} - marking as completed") + logger.warning(f"No active process for {download['item']['name']} - marking as completed") # Create updated download entry updated_download = { @@ -39915,7 +39854,7 @@ def hydrate_search_bubbles(): for download in bubble['downloads'] if download['status'] == 'view_results') - print(f"Hydrated {bubble_count} search bubbles (artists): {active_count} active, {completed_count} completed") + logger.info(f"Hydrated {bubble_count} search bubbles (artists): {active_count} active, {completed_count} completed") return jsonify({ 'success': True, @@ -39929,7 +39868,7 @@ def hydrate_search_bubbles(): }) except Exception as e: - print(f"Error hydrating search bubbles: {e}") + logger.error(f"Error hydrating search bubbles: {e}") import traceback traceback.print_exc() return jsonify({ @@ -39953,7 +39892,7 @@ def save_beatport_bubble_snapshot(): db.save_bubble_snapshot('beatport_bubbles', bubbles, profile_id=get_current_profile_id()) bubble_count = len(bubbles) - print(f"Saved Beatport bubble snapshot: {bubble_count} charts") + logger.info(f"Saved Beatport bubble snapshot: {bubble_count} charts") return jsonify({ 'success': True, @@ -39962,7 +39901,7 @@ def save_beatport_bubble_snapshot(): }) except Exception as e: - print(f"Error saving Beatport bubble snapshot: {e}") + logger.error(f"Error saving Beatport bubble snapshot: {e}") import traceback traceback.print_exc() return jsonify({ @@ -39995,7 +39934,7 @@ def hydrate_beatport_bubbles(): snapshot_dt = datetime.fromisoformat(snapshot_time.replace('Z', '+00:00')) cutoff = datetime.now() - timedelta(hours=48) if snapshot_dt < cutoff: - print(f"Cleaning up old Beatport snapshot from {snapshot_time}") + logger.info(f"Cleaning up old Beatport snapshot from {snapshot_time}") db.delete_bubble_snapshot('beatport_bubbles', profile_id=get_current_profile_id()) return jsonify({ 'success': True, @@ -40003,7 +39942,7 @@ def hydrate_beatport_bubbles(): 'message': 'Old snapshot cleaned up' }) except ValueError as e: - print(f"Error checking Beatport snapshot age: {e}") + logger.error(f"Error checking Beatport snapshot age: {e}") # Get current active download processes for live status current_processes = {} @@ -40019,11 +39958,11 @@ def hydrate_beatport_bubbles(): 'phase': batch_data.get('phase') } except Exception as e: - print(f"Error fetching active processes for Beatport hydration: {e}") + logger.error(f"Error fetching active processes for Beatport hydration: {e}") # If no active processes exist, app likely restarted ā€” clean up if not current_processes: - print(f"No active processes found - cleaning up Beatport snapshot") + logger.warning(f"No active processes found - cleaning up Beatport snapshot") db.delete_bubble_snapshot('beatport_bubbles', profile_id=get_current_profile_id()) return jsonify({ 'success': True, @@ -40062,7 +40001,7 @@ def hydrate_beatport_bubbles(): completed_count = sum(1 for b in hydrated_bubbles.values() for d in b['downloads'] if d['status'] == 'view_results') - print(f"Hydrated {bubble_count} Beatport bubbles: {active_count} active, {completed_count} completed") + logger.info(f"Hydrated {bubble_count} Beatport bubbles: {active_count} active, {completed_count} completed") return jsonify({ 'success': True, @@ -40075,7 +40014,7 @@ def hydrate_beatport_bubbles(): }) except Exception as e: - print(f"Error hydrating Beatport bubbles: {e}") + logger.error(f"Error hydrating Beatport bubbles: {e}") import traceback traceback.print_exc() return jsonify({ @@ -40621,7 +40560,7 @@ def get_watchlist_count(): "next_run_in_seconds": next_run_in_seconds }) except Exception as e: - print(f"Error getting watchlist count: {e}") + logger.error(f"Error getting watchlist count: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/artists', methods=['GET']) @@ -40657,7 +40596,7 @@ def get_watchlist_artists(): return jsonify({"success": True, "artists": artists_data}) except Exception as e: - print(f"Error getting watchlist artists: {e}") + logger.error(f"Error getting watchlist artists: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/add', methods=['POST']) @@ -40728,18 +40667,18 @@ def add_to_watchlist(): dc_data = dc.get_artist(artist_id) if dc_data: image_url = dc_data.get('image_url') - print(f"Discogs artist image: {image_url[:60] if image_url else 'None'}") + logger.info(f"Discogs artist image: {image_url[:60] if image_url else 'None'}") elif source == 'deezer' or fallback_source == 'deezer': # Deezer: fetch artist image directly from API dz_resp = requests.get(f'https://api.deezer.com/artist/{artist_id}', timeout=5) if dz_resp.ok: dz_data = dz_resp.json() image_url = dz_data.get('picture_xl') or dz_data.get('picture_big') or dz_data.get('picture_medium') - print(f"Deezer artist image: {image_url[:60] if image_url else 'None'}") + logger.info(f"Deezer artist image: {image_url[:60] if image_url else 'None'}") else: # iTunes: look up album entity for artwork itunes_url = f"https://itunes.apple.com/lookup?id={artist_id}&entity=album&limit=5" - print(f"Fetching iTunes artist image: {itunes_url}") + logger.info(f"Fetching iTunes artist image: {itunes_url}") resp = requests.get(itunes_url, timeout=5) image_url = None @@ -40755,11 +40694,11 @@ def add_to_watchlist(): if image_url: database.update_watchlist_artist_image(artist_id, image_url) - print(f"Cached {fallback_source} artist image for {artist_name}") + logger.warning(f"Cached {fallback_source} artist image for {artist_name}") else: - print(f"No artwork found for {fallback_source} artist {artist_name}") + logger.warning(f"No artwork found for {fallback_source} artist {artist_name}") except Exception as fb_error: - print(f"Error fetching {fallback_source} artwork: {fb_error}") + logger.error(f"Error fetching {fallback_source} artwork: {fb_error}") elif spotify_client and spotify_client.is_authenticated(): # For Spotify artists, fetch from Spotify API artist_data = spotify_client.get_artist(artist_id) @@ -40774,16 +40713,16 @@ def add_to_watchlist(): # Update in database if image_url: database.update_watchlist_artist_image(artist_id, image_url) - print(f"Cached artist image for {artist_name}") + logger.info(f"Cached artist image for {artist_name}") else: - print(f"No image URL found for {artist_name}") + logger.warning(f"No image URL found for {artist_name}") else: - print(f"No images in Spotify data for {artist_name}") + logger.warning(f"No images in Spotify data for {artist_name}") else: - print(f"Spotify client not available for fetching artist image") + logger.info(f"Spotify client not available for fetching artist image") except Exception as img_error: # Don't fail the add operation if image fetch fails - print(f"Could not fetch artist image for {artist_name}: {img_error}") + logger.error(f"Could not fetch artist image for {artist_name}: {img_error}") # Push updated count to this profile's WebSocket room immediately try: @@ -40805,7 +40744,7 @@ def add_to_watchlist(): return jsonify({"success": False, "error": "Failed to add artist to watchlist"}), 500 except Exception as e: - print(f"Error adding to watchlist: {e}") + logger.error(f"Error adding to watchlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/remove', methods=['POST']) @@ -40842,7 +40781,7 @@ def remove_from_watchlist(): return jsonify({"success": False, "error": "Failed to remove artist from watchlist"}), 500 except Exception as e: - print(f"Error removing from watchlist: {e}") + logger.error(f"Error removing from watchlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/add-batch', methods=['POST']) @@ -40905,7 +40844,7 @@ def add_batch_to_watchlist(): if image_url: database.update_watchlist_artist_image(artist_id, image_url) except Exception as img_error: - print(f"Could not fetch artist image for {artist_name}: {img_error}") + logger.error(f"Could not fetch artist image for {artist_name}: {img_error}") return jsonify({ "success": True, @@ -40915,7 +40854,7 @@ def add_batch_to_watchlist(): }) except Exception as e: - print(f"Error batch adding to watchlist: {e}") + logger.error(f"Error batch adding to watchlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/watchlist-all-unwatched', methods=['POST']) @@ -40995,7 +40934,7 @@ def watchlist_all_unwatched_library_artists(): }) except Exception as e: - print(f"Error bulk watchlisting library artists: {e}") + logger.error(f"Error bulk watchlisting library artists: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -41023,7 +40962,7 @@ def remove_batch_from_watchlist(): }) except Exception as e: - print(f"Error batch removing from watchlist: {e}") + logger.error(f"Error batch removing from watchlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/check', methods=['POST']) @@ -41042,7 +40981,7 @@ def check_watchlist_status(): return jsonify({"success": True, "is_watching": is_watching}) except Exception as e: - print(f"Error checking watchlist status: {e}") + logger.error(f"Error checking watchlist status: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/check-batch', methods=['POST']) @@ -41063,7 +41002,7 @@ def check_watchlist_status_batch(): return jsonify({"success": True, "results": results}) except Exception as e: - print(f"Error batch checking watchlist status: {e}") + logger.error(f"Error batch checking watchlist status: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/scan', methods=['POST']) @@ -41106,7 +41045,7 @@ def start_watchlist_scan(): with watchlist_timer_lock: watchlist_auto_scanning = True watchlist_auto_scanning_timestamp = time.time() - print(f"[Manual Watchlist Scan] Flag set at timestamp {watchlist_auto_scanning_timestamp}") + logger.info(f"[Manual Watchlist Scan] Flag set at timestamp {watchlist_auto_scanning_timestamp}") # Get list of artists to scan (for the current profile) database = get_database() @@ -41141,17 +41080,17 @@ def start_watchlist_scan(): pass for _bf_provider in providers_to_backfill: try: - print(f"Checking for missing {_bf_provider} IDs in watchlist...") + logger.debug(f"Checking for missing {_bf_provider} IDs in watchlist...") scanner._backfill_missing_ids(watchlist_artists, _bf_provider) except Exception as backfill_error: - print(f"Error during {_bf_provider} ID backfilling: {backfill_error}") + logger.error(f"Error during {_bf_provider} ID backfilling: {backfill_error}") # Continue with next provider try: filled = scanner.backfill_watchlist_artist_images(scan_profile_id) if filled: - print(f"Backfilled {filled} watchlist artist images") + logger.info(f"Backfilled {filled} watchlist artist images") except Exception as img_err: - print(f"Image backfill error: {img_err}") + logger.error(f"Image backfill error: {img_err}") # Initialize detailed progress tracking watchlist_scan_state.update({ @@ -41201,26 +41140,26 @@ def start_watchlist_scan(): 'tracks_added_to_wishlist': total_added_to_wishlist } - print(f"Watchlist scan completed: {len(successful_scans)}/{len(scan_results)} artists scanned successfully") - print(f"Found {total_new_tracks} new tracks, added {total_added_to_wishlist} to wishlist") + logger.info(f"Watchlist scan completed: {len(successful_scans)}/{len(scan_results)} artists scanned successfully") + logger.info(f"Found {total_new_tracks} new tracks, added {total_added_to_wishlist} to wishlist") else: - print(f"Watchlist scan cancelled ā€” skipping post-scan steps") + logger.warning(f"Watchlist scan cancelled ā€” skipping post-scan steps") # Post-scan steps ā€” skip if cancelled if not was_cancelled: # Populate discovery pool from similar artists - print("Starting discovery pool population...") + logger.info("Starting discovery pool population...") watchlist_scan_state['current_phase'] = 'populating_discovery_pool' try: scanner.populate_discovery_pool(profile_id=scan_profile_id) - print("Discovery pool population complete") + logger.info("Discovery pool population complete") except Exception as discovery_error: - print(f"Error populating discovery pool: {discovery_error}") + logger.error(f"Error populating discovery pool: {discovery_error}") import traceback traceback.print_exc() # Update ListenBrainz playlists cache - print("Starting ListenBrainz playlists update...") + logger.info("Starting ListenBrainz playlists update...") watchlist_scan_state['current_phase'] = 'updating_listenbrainz' try: from core.listenbrainz_manager import ListenBrainzManager @@ -41233,22 +41172,22 @@ def start_watchlist_scan(): lb_manager = ListenBrainzManager(db_path, profile_id=lb_prof['id'], token=lb_prof['token'], base_url=lb_prof['base_url']) lb_result = lb_manager.update_all_playlists() if lb_result.get('success'): - print(f"ListenBrainz update complete for profile {lb_prof['id']}: {lb_result.get('summary', {})}") + logger.info(f"ListenBrainz update complete for profile {lb_prof['id']}: {lb_result.get('summary', {})}") else: # Fallback: use global config token lb_manager = ListenBrainzManager(db_path) lb_result = lb_manager.update_all_playlists() if lb_result.get('success'): - print(f"ListenBrainz update complete (global): {lb_result.get('summary', {})}") + logger.info(f"ListenBrainz update complete (global): {lb_result.get('summary', {})}") elif lb_result.get('error'): - print(f"ListenBrainz update skipped: {lb_result.get('error')}") + logger.error(f"ListenBrainz update skipped: {lb_result.get('error')}") except Exception as lb_error: - print(f"Error updating ListenBrainz: {lb_error}") + logger.error(f"Error updating ListenBrainz: {lb_error}") import traceback traceback.print_exc() # Update current seasonal playlist (weekly refresh) - print("Starting seasonal content update...") + logger.info("Starting seasonal content update...") watchlist_scan_state['current_phase'] = 'updating_seasonal' try: from core.seasonal_discovery import get_seasonal_discovery_service @@ -41258,39 +41197,39 @@ def start_watchlist_scan(): current_season = seasonal_service.get_current_season() if current_season: if seasonal_service.should_populate_seasonal_content(current_season, days_threshold=7): - print(f"Updating {current_season} seasonal content...") + logger.info(f"Updating {current_season} seasonal content...") seasonal_service.populate_seasonal_content(current_season) seasonal_service.curate_seasonal_playlist(current_season) - print(f"{current_season.capitalize()} seasonal content updated") + logger.info(f"{current_season.capitalize()} seasonal content updated") else: - print(f"{current_season.capitalize()} seasonal content recently updated, skipping") + logger.info(f"{current_season.capitalize()} seasonal content recently updated, skipping") else: - print("ā„¹ļø No active season at this time") + logger.warning("ā„¹ļø No active season at this time") except Exception as seasonal_error: - print(f"Error updating seasonal content: {seasonal_error}") + logger.error(f"Error updating seasonal content: {seasonal_error}") import traceback traceback.print_exc() # Generate Last.fm radio playlists (weekly refresh) - print("Starting Last.fm radio generation...") + logger.info("Starting Last.fm radio generation...") watchlist_scan_state['current_phase'] = 'generating_lastfm_radio' try: scanner._generate_lastfm_radio_playlists() - print("Last.fm radio generation complete") + logger.info("Last.fm radio generation complete") except Exception as lastfm_error: - print(f"Error generating Last.fm radio playlists: {lastfm_error}") + logger.error(f"Error generating Last.fm radio playlists: {lastfm_error}") # Sync Spotify library cache - print("Syncing Spotify library cache...") + logger.info("Syncing Spotify library cache...") watchlist_scan_state['current_phase'] = 'syncing_spotify_library' try: scanner.sync_spotify_library_cache(profile_id=scan_profile_id) - print("Spotify library cache sync complete") + logger.info("Spotify library cache sync complete") except Exception as lib_error: - print(f"Error syncing Spotify library: {lib_error}") + logger.error(f"Error syncing Spotify library: {lib_error}") except Exception as e: - print(f"Error during watchlist scan: {e}") + logger.error(f"Error during watchlist scan: {e}") watchlist_scan_state['status'] = 'error' watchlist_scan_state['error'] = str(e) @@ -41308,7 +41247,7 @@ def start_watchlist_scan(): with watchlist_timer_lock: watchlist_auto_scanning = False watchlist_auto_scanning_timestamp = 0 - print("[Manual Watchlist Scan] Flag reset - scan complete") + logger.info("[Manual Watchlist Scan] Flag reset - scan complete") # Initialize scan state global watchlist_scan_state @@ -41329,7 +41268,7 @@ def start_watchlist_scan(): return jsonify({"success": True, "message": "Watchlist scan started"}) except Exception as e: - print(f"Error starting watchlist scan: {e}") + logger.error(f"Error starting watchlist scan: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/scan/status', methods=['GET']) @@ -41359,7 +41298,7 @@ def get_watchlist_scan_status(): return jsonify({"success": True, **state}) except Exception as e: - print(f"Error getting watchlist scan status: {e}") + logger.error(f"Error getting watchlist scan status: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/scan/cancel', methods=['POST']) @@ -41371,11 +41310,11 @@ def cancel_watchlist_scan(): return jsonify({"success": False, "error": "No scan is currently running"}), 400 watchlist_scan_state['cancel_requested'] = True - print("[Watchlist Scan] Cancel requested by user") + logger.info("[Watchlist Scan] Cancel requested by user") return jsonify({"success": True, "message": "Cancel request sent"}) except Exception as e: - print(f"Error cancelling watchlist scan: {e}") + logger.error(f"Error cancelling watchlist scan: {e}") return jsonify({"success": False, "error": str(e)}), 500 # Similar Artists Update State @@ -41415,7 +41354,7 @@ def update_similar_artists_endpoint(): return jsonify({"success": True, "message": "Similar artists update started"}) except Exception as e: - print(f"Error starting similar artists update: {e}") + logger.error(f"Error starting similar artists update: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/similar-artists-status', methods=['GET']) @@ -41425,7 +41364,7 @@ def get_similar_artists_update_status(): global similar_artists_update_state return jsonify({"success": True, **similar_artists_update_state}) except Exception as e: - print(f"Error getting similar artists status: {e}") + logger.error(f"Error getting similar artists status: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/artist//config', methods=['GET', 'POST']) @@ -41479,7 +41418,7 @@ def watchlist_artist_config(artist_id): 'genres': artist_data.get('genres', []) } except Exception as e: - print(f"Warning: Could not fetch artist info from Spotify: {e}") + logger.error(f"Could not fetch artist info from Spotify: {e}") # Fallback to database info if Spotify fetch failed if not artist_info: @@ -41536,7 +41475,7 @@ def watchlist_artist_config(artist_id): ] conn2.close() except Exception as e: - print(f"Warning: Could not enrich artist from library: {e}") + logger.error(f"Could not enrich artist from library: {e}") releases = [] config = { @@ -41627,7 +41566,7 @@ def watchlist_artist_config(artist_id): conn.close() - print(f"Updated watchlist config for artist {artist_id}: albums={include_albums}, eps={include_eps}, singles={include_singles}, live={include_live}, remixes={include_remixes}, acoustic={include_acoustic}, compilations={include_compilations}, instrumentals={include_instrumentals}") + logger.info(f"Updated watchlist config for artist {artist_id}: albums={include_albums}, eps={include_eps}, singles={include_singles}, live={include_live}, remixes={include_remixes}, acoustic={include_acoustic}, compilations={include_compilations}, instrumentals={include_instrumentals}") return jsonify({ "success": True, @@ -41645,7 +41584,7 @@ def watchlist_artist_config(artist_id): }) except Exception as e: - print(f"Error in watchlist artist config: {e}") + logger.error(f"Error in watchlist artist config: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -41710,7 +41649,7 @@ def watchlist_artist_link_provider(artist_id): conn.close() action = 'Cleared' if is_clear else 'Linked' - print(f"{action} watchlist artist '{artist_name}' {provider} ID: {new_provider_id or 'NULL'}") + logger.info(f"{action} watchlist artist '{artist_name}' {provider} ID: {new_provider_id or 'NULL'}") return jsonify({ "success": True, @@ -41719,7 +41658,7 @@ def watchlist_artist_link_provider(artist_id): }) except Exception as e: - print(f"Error linking watchlist artist provider: {e}") + logger.error(f"Error linking watchlist artist provider: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -41774,7 +41713,7 @@ def watchlist_global_config(): config_manager.set('watchlist.global_include_instrumentals', include_instrumentals) config_manager.set('watchlist.exclude_terms', exclude_terms) - print(f"Updated global watchlist config: override={global_override_enabled}, " + logger.info(f"Updated global watchlist config: override={global_override_enabled}, " f"albums={include_albums}, eps={include_eps}, singles={include_singles}, " f"live={include_live}, remixes={include_remixes}, acoustic={include_acoustic}, " f"compilations={include_compilations}, instrumentals={include_instrumentals}, " @@ -41798,7 +41737,7 @@ def watchlist_global_config(): }) except Exception as e: - print(f"Error in watchlist global config: {e}") + logger.error(f"Error in watchlist global config: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -41812,7 +41751,7 @@ def _update_similar_artists_worker(): from database.music_database import get_database import time - print("[Similar Artists] Starting similar artists update...") + logger.info("[Similar Artists] Starting similar artists update...") database = get_database() all_profiles = database.get_all_profiles() @@ -41829,11 +41768,11 @@ def _update_similar_artists_worker(): if not artist_profiles: similar_artists_update_state['status'] = 'completed' - print("[Similar Artists] No watchlist artists to process") + logger.warning("[Similar Artists] No watchlist artists to process") return similar_artists_update_state['total_artists'] = len(artist_profiles) - print(f"[Similar Artists] Processing {len(artist_profiles)} unique watchlist artists across {len(all_profiles)} profiles") + logger.info(f"[Similar Artists] Processing {len(artist_profiles)} unique watchlist artists across {len(all_profiles)} profiles") scanner = get_watchlist_scanner(spotify_client) @@ -41842,7 +41781,7 @@ def _update_similar_artists_worker(): similar_artists_update_state['artists_processed'] = idx similar_artists_update_state['current_artist'] = artist.artist_name - print(f"[{idx}/{len(artist_profiles)}] Updating similar artists for {artist.artist_name} (profiles: {profile_ids})") + logger.info(f"[{idx}/{len(artist_profiles)}] Updating similar artists for {artist.artist_name} (profiles: {profile_ids})") # Update similar artists for each profile that watches this artist for pid in profile_ids: @@ -41853,17 +41792,17 @@ def _update_similar_artists_worker(): time.sleep(2.0) # 2 seconds between artists except Exception as artist_error: - print(f"[Similar Artists] Error processing {artist.artist_name}: {artist_error}") + logger.error(f"[Similar Artists] Error processing {artist.artist_name}: {artist_error}") continue # Update complete similar_artists_update_state['status'] = 'completed' similar_artists_update_state['current_artist'] = None - print(f"[Similar Artists] Update complete! Processed {len(artist_profiles)} artists") + logger.info(f"[Similar Artists] Update complete! Processed {len(artist_profiles)} artists") except Exception as e: - print(f"[Similar Artists] Critical error: {e}") + logger.error(f"[Similar Artists] Critical error: {e}") import traceback traceback.print_exc() @@ -41890,7 +41829,7 @@ def _process_watchlist_scan_automatically(automation_id=None, profile_id=None): global watchlist_auto_scanning, watchlist_auto_scanning_timestamp, watchlist_scan_state scope_label = f"profile {profile_id}" if profile_id else "all profiles" - print(f"[Auto-Watchlist] Timer triggered - starting automatic watchlist scan ({scope_label})...") + logger.info(f"[Auto-Watchlist] Timer triggered - starting automatic watchlist scan ({scope_label})...") _ew_state = {} @@ -41898,20 +41837,20 @@ def _process_watchlist_scan_automatically(automation_id=None, profile_id=None): # CRITICAL FIX: Use smart stuck detection BEFORE acquiring lock # This prevents deadlock and handles stuck flags (2-hour timeout) if is_watchlist_actually_scanning(): - print("[Auto-Watchlist] Already scanning (verified with stuck detection), skipping.") + logger.info("[Auto-Watchlist] Already scanning (verified with stuck detection), skipping.") return with watchlist_timer_lock: # Re-check inside lock to handle race conditions if watchlist_auto_scanning: - print("[Auto-Watchlist] Already scanning (race condition check), skipping.") + logger.info("[Auto-Watchlist] Already scanning (race condition check), skipping.") return # Set flag and timestamp import time watchlist_auto_scanning = True watchlist_auto_scanning_timestamp = time.time() - print(f"[Auto-Watchlist] Flag set at timestamp {watchlist_auto_scanning_timestamp}") + logger.info(f"[Auto-Watchlist] Flag set at timestamp {watchlist_auto_scanning_timestamp}") # Use app context for database operations with app.app_context(): @@ -41930,23 +41869,23 @@ def _process_watchlist_scan_automatically(automation_id=None, profile_id=None): watchlist_count = sum(database.get_watchlist_count(profile_id=p['id']) for p in scan_profiles) profile_label = f"profile {profile_id}" if profile_id else f"{len(scan_profiles)} profiles" - print(f"[Auto-Watchlist] Watchlist count check: {watchlist_count} artists found ({profile_label})") + logger.info(f"[Auto-Watchlist] Watchlist count check: {watchlist_count} artists found ({profile_label})") if watchlist_count == 0: - print("ā„¹ļø [Auto-Watchlist] No artists in watchlist for auto-scanning.") + logger.warning("ā„¹ļø [Auto-Watchlist] No artists in watchlist for auto-scanning.") with watchlist_timer_lock: watchlist_auto_scanning = False watchlist_auto_scanning_timestamp = 0 return if not spotify_client or not spotify_client.is_authenticated(): - print("ā„¹ļø [Auto-Watchlist] Spotify client not available or not authenticated.") + logger.info("ā„¹ļø [Auto-Watchlist] Spotify client not available or not authenticated.") with watchlist_timer_lock: watchlist_auto_scanning = False watchlist_auto_scanning_timestamp = 0 return - print(f"[Auto-Watchlist] Found {watchlist_count} artists in watchlist, starting automatic scan...") + logger.info(f"[Auto-Watchlist] Found {watchlist_count} artists in watchlist, starting automatic scan...") _update_automation_progress(automation_id, progress=5, phase='Loading watchlist', log_line=f'{watchlist_count} artists ({profile_label})', log_type='info') @@ -41961,9 +41900,9 @@ def _process_watchlist_scan_automatically(automation_id=None, profile_id=None): try: filled = scanner.backfill_watchlist_artist_images(p['id']) if filled: - print(f"Backfilled {filled} watchlist artist images for profile {p['id']}") + logger.info(f"Backfilled {filled} watchlist artist images for profile {p['id']}") except Exception as img_err: - print(f"Image backfill error for profile {p['id']}: {img_err}") + logger.error(f"Image backfill error for profile {p['id']}: {img_err}") # Initialize detailed progress tracking (same as manual scan) watchlist_scan_state = { @@ -42084,20 +42023,20 @@ def _process_watchlist_scan_automatically(automation_id=None, profile_id=None): 'tracks_added_to_wishlist': total_added_to_wishlist } - print(f"Automatic watchlist scan completed: {len(successful_scans)}/{len(scan_results)} artists scanned successfully") - print(f"Found {total_new_tracks} new tracks, added {total_added_to_wishlist} to wishlist") + logger.info(f"Automatic watchlist scan completed: {len(successful_scans)}/{len(scan_results)} artists scanned successfully") + logger.info(f"Found {total_new_tracks} new tracks, added {total_added_to_wishlist} to wishlist") _update_automation_progress(automation_id, progress=95, phase='Scan complete', log_line=f'Scanned {len(successful_scans)} artists ā€” {total_new_tracks} new tracks, {total_added_to_wishlist} added to wishlist', log_type='success' if total_new_tracks > 0 else 'info') else: total_new_tracks = watchlist_scan_state.get('summary', {}).get('new_tracks_found', 0) total_added_to_wishlist = watchlist_scan_state.get('summary', {}).get('tracks_added_to_wishlist', 0) - print(f"Automatic watchlist scan cancelled ā€” skipping post-scan steps") + logger.warning(f"Automatic watchlist scan cancelled ā€” skipping post-scan steps") # Post-scan steps ā€” skip if cancelled if not was_cancelled: # Populate discovery pool from similar artists (per-profile) - print("Starting discovery pool population...") + logger.info("Starting discovery pool population...") watchlist_scan_state['current_phase'] = 'populating_discovery_pool' _update_automation_progress(automation_id, progress=96, phase='Populating discovery pool', log_line='Building discovery pool from similar artists...', log_type='info') @@ -42119,16 +42058,16 @@ def _process_watchlist_scan_automatically(automation_id=None, profile_id=None): for p in all_profiles: scanner.populate_discovery_pool(profile_id=p['id'], progress_callback=_discovery_progress) - print("Discovery pool population complete") + logger.info("Discovery pool population complete") except Exception as discovery_error: - print(f"Error populating discovery pool: {discovery_error}") + logger.error(f"Error populating discovery pool: {discovery_error}") import traceback traceback.print_exc() _update_automation_progress(automation_id, log_line=f'Discovery pool error: {discovery_error}', log_type='error') # Update ListenBrainz playlists cache - print("Starting ListenBrainz playlists update...") + logger.info("Starting ListenBrainz playlists update...") watchlist_scan_state['current_phase'] = 'updating_listenbrainz' _update_automation_progress(automation_id, progress=97, phase='Updating ListenBrainz', log_line='Fetching ListenBrainz playlists...', log_type='info') @@ -42143,7 +42082,7 @@ def _process_watchlist_scan_automatically(automation_id=None, profile_id=None): lb_result = lb_manager.update_all_playlists() if lb_result.get('success'): summary = lb_result.get('summary', {}) - print(f"ListenBrainz update complete for profile {lb_prof['id']}: {summary}") + logger.info(f"ListenBrainz update complete for profile {lb_prof['id']}: {summary}") _update_automation_progress(automation_id, log_line=f'ListenBrainz (profile {lb_prof["id"]}): playlists updated', log_type='success') else: @@ -42151,22 +42090,22 @@ def _process_watchlist_scan_automatically(automation_id=None, profile_id=None): lb_result = lb_manager.update_all_playlists() if lb_result.get('success'): summary = lb_result.get('summary', {}) - print(f"ListenBrainz update complete (global): {summary}") + logger.info(f"ListenBrainz update complete (global): {summary}") _update_automation_progress(automation_id, log_line=f'ListenBrainz: playlists updated', log_type='success') else: - print(f"ListenBrainz update had issues: {lb_result.get('error', 'Unknown error')}") + logger.error(f"ListenBrainz update had issues: {lb_result.get('error', 'Unknown error')}") _update_automation_progress(automation_id, log_line=f'ListenBrainz: {lb_result.get("error", "Unknown error")}', log_type='error') except Exception as lb_error: - print(f"Error updating ListenBrainz: {lb_error}") + logger.error(f"Error updating ListenBrainz: {lb_error}") import traceback traceback.print_exc() _update_automation_progress(automation_id, log_line=f'ListenBrainz error: {lb_error}', log_type='error') # Update current seasonal playlist (weekly refresh) - print("Starting seasonal content update...") + logger.info("Starting seasonal content update...") watchlist_scan_state['current_phase'] = 'updating_seasonal' _update_automation_progress(automation_id, progress=98, phase='Updating seasonal content', log_line='Checking seasonal playlists...', log_type='info') @@ -42178,54 +42117,54 @@ def _process_watchlist_scan_automatically(automation_id=None, profile_id=None): current_season = seasonal_service.get_current_season() if current_season: if seasonal_service.should_populate_seasonal_content(current_season, days_threshold=7): - print(f"Updating {current_season} seasonal content...") + logger.info(f"Updating {current_season} seasonal content...") _update_automation_progress(automation_id, log_line=f'Updating {current_season} seasonal content...', log_type='info') seasonal_service.populate_seasonal_content(current_season) seasonal_service.curate_seasonal_playlist(current_season) - print(f"{current_season.capitalize()} seasonal content updated") + logger.info(f"{current_season.capitalize()} seasonal content updated") _update_automation_progress(automation_id, log_line=f'{current_season.capitalize()} seasonal content updated', log_type='success') else: - print(f"{current_season.capitalize()} seasonal content recently updated, skipping") + logger.info(f"{current_season.capitalize()} seasonal content recently updated, skipping") _update_automation_progress(automation_id, log_line=f'{current_season.capitalize()} seasonal content up to date', log_type='info') else: - print("ā„¹ļø No active season at this time") + logger.warning("ā„¹ļø No active season at this time") _update_automation_progress(automation_id, log_line='No active season', log_type='info') except Exception as seasonal_error: - print(f"Error updating seasonal content: {seasonal_error}") + logger.error(f"Error updating seasonal content: {seasonal_error}") import traceback traceback.print_exc() _update_automation_progress(automation_id, log_line=f'Seasonal error: {seasonal_error}', log_type='error') # Generate Last.fm radio playlists (weekly refresh) - print("Starting Last.fm radio generation...") + logger.info("Starting Last.fm radio generation...") watchlist_scan_state['current_phase'] = 'generating_lastfm_radio' _update_automation_progress(automation_id, progress=99, phase='Generating Last.fm radio', log_line='Building Last.fm radio playlists...', log_type='info') try: scanner._generate_lastfm_radio_playlists() - print("Last.fm radio generation complete") + logger.info("Last.fm radio generation complete") _update_automation_progress(automation_id, log_line='Last.fm radio playlists updated', log_type='success') except Exception as lastfm_error: - print(f"Error generating Last.fm radio playlists: {lastfm_error}") + logger.error(f"Error generating Last.fm radio playlists: {lastfm_error}") _update_automation_progress(automation_id, log_line=f'Last.fm radio error: {lastfm_error}', log_type='error') # Sync Spotify library cache - print("Syncing Spotify library cache...") + logger.info("Syncing Spotify library cache...") try: for p in all_profiles: scanner.sync_spotify_library_cache(profile_id=p['id']) - print("Spotify library cache sync complete") + logger.info("Spotify library cache sync complete") _update_automation_progress(automation_id, log_line='Spotify library cache synced', log_type='info') except Exception as lib_error: - print(f"Error syncing Spotify library: {lib_error}") + logger.error(f"Error syncing Spotify library: {lib_error}") _update_automation_progress(automation_id, log_line=f'Library cache error: {lib_error}', log_type='error') @@ -42244,7 +42183,7 @@ def _process_watchlist_scan_automatically(automation_id=None, profile_id=None): pass except Exception as e: - print(f"Error in automatic watchlist scan: {e}") + logger.error(f"Error in automatic watchlist scan: {e}") import traceback traceback.print_exc() _update_automation_progress(automation_id, log_line=f'Error: {str(e)}', log_type='error') @@ -42268,7 +42207,7 @@ def _process_watchlist_scan_automatically(automation_id=None, profile_id=None): watchlist_auto_scanning = False watchlist_auto_scanning_timestamp = 0 - print("Automatic watchlist scanning complete") + logger.info("Automatic watchlist scanning complete") # --- Metadata Updater System --- @@ -42317,7 +42256,7 @@ def get_discover_hero(): # Determine active source active_source = _get_active_discovery_source() - print(f"Discover hero using source: {active_source}") + logger.info(f"Discover hero using source: {active_source}") # Import fallback client for non-Spotify lookups itunes_client = _get_metadata_fallback_client() @@ -42325,12 +42264,12 @@ def get_discover_hero(): # Get top similar artists (excluding watchlist, cycled by last_featured) # Fetch more than needed since strict source filtering may drop many pid = get_current_profile_id() - print(f"[Discover Hero] Profile ID: {pid}, Active source: {active_source}") + logger.info(f"[Discover Hero] Profile ID: {pid}, Active source: {active_source}") similar_artists = database.get_top_similar_artists(limit=200, profile_id=pid, require_source=active_source) # FALLBACK: If no similar artists exist, use watchlist artists for Hero section if not similar_artists: - print("[Discover Hero] No similar artists found, falling back to watchlist artists") + logger.warning("[Discover Hero] No similar artists found, falling back to watchlist artists") watchlist_artists = database.get_watchlist_artists(profile_id=pid) if not watchlist_artists: @@ -42369,7 +42308,7 @@ def get_discover_hero(): hero_artists.append(artist_data) - print(f"[Discover Hero] Returning {len(hero_artists)} watchlist artists as fallback") + logger.warning(f"[Discover Hero] Returning {len(hero_artists)} watchlist artists as fallback") return jsonify({"success": True, "artists": hero_artists, "source": active_source, "fallback": "watchlist"}) # Artists are already filtered by source in SQL ā€” no post-filter needed @@ -42377,7 +42316,7 @@ def get_discover_hero(): # FALLBACK: If no valid artists for fallback source, try to resolve IDs on-the-fly if active_source in ('itunes', 'deezer') and not valid_artists: - print(f"[{active_source} Fallback] No artists with {active_source} IDs found, attempting on-the-fly resolution for {len(similar_artists)} artists") + logger.warning(f"[{active_source} Fallback] No artists with {active_source} IDs found, attempting on-the-fly resolution for {len(similar_artists)} artists") resolved_count = 0 for artist in similar_artists: existing_id = getattr(artist, f'similar_artist_{active_source}_id', None) or (artist.similar_artist_itunes_id if active_source == 'itunes' else None) @@ -42398,15 +42337,15 @@ def get_discover_hero(): artist.similar_artist_itunes_id = resolved_id valid_artists.append(artist) resolved_count += 1 - print(f" [Resolved] {artist.similar_artist_name} -> {active_source} ID: {resolved_id}") + logger.info(f" [Resolved] {artist.similar_artist_name} -> {active_source} ID: {resolved_id}") except Exception as resolve_err: - print(f" [Failed] Could not resolve {active_source} ID for {artist.similar_artist_name}: {resolve_err}") + logger.error(f" [Failed] Could not resolve {active_source} ID for {artist.similar_artist_name}: {resolve_err}") # Stop after 10 successful resolutions to avoid rate limiting if len(valid_artists) >= 10: break - print(f"[{active_source} Fallback] Resolved {resolved_count} artists with IDs") + logger.warning(f"[{active_source} Fallback] Resolved {resolved_count} artists with IDs") - print(f"[Discover Hero] Found {len(valid_artists)} valid artists for source: {active_source}") + logger.info(f"[Discover Hero] Found {len(valid_artists)} valid artists for source: {active_source}") # Filter out blacklisted artists blacklisted = database.get_discovery_blacklist_names() @@ -42474,7 +42413,7 @@ def get_discover_hero(): artist_data.get('genres'), artist_data.get('popularity') ) except Exception as img_err: - print(f"Could not fetch artist image: {img_err}") + logger.error(f"Could not fetch artist image: {img_err}") hero_artists.append(artist_data) @@ -42485,7 +42424,7 @@ def get_discover_hero(): return jsonify({"success": True, "artists": hero_artists, "source": active_source}) except Exception as e: - print(f"Error getting discover hero: {e}") + logger.error(f"Error getting discover hero: {e}") return jsonify({"success": False, "error": str(e)}), 500 @@ -42530,7 +42469,7 @@ def get_discover_similar_artists(): artist_data["popularity"] = artist.popularity result_artists.append(artist_data) - print(f"[Similar Artists] {len(similar_artists)} from DB, {len(result_artists)} valid for {active_source}") + logger.info(f"[Similar Artists] {len(similar_artists)} from DB, {len(result_artists)} valid for {active_source}") return jsonify({ "success": True, @@ -42540,7 +42479,7 @@ def get_discover_similar_artists(): }) except Exception as e: - print(f"Error getting similar artists: {e}") + logger.error(f"Error getting similar artists: {e}") return jsonify({"success": False, "error": str(e)}), 500 @@ -42614,7 +42553,7 @@ def enrich_similar_artists(): except Exception as e: from core.spotify_client import _detect_and_set_rate_limit _detect_and_set_rate_limit(e, 'enrich_similar_artists') - print(f"Error enriching Spotify batch: {e}") + logger.error(f"Error enriching Spotify batch: {e}") else: fallback_client = _get_metadata_fallback_client() fallback_source = _get_metadata_fallback_source() @@ -42641,12 +42580,12 @@ def enrich_similar_artists(): cached_count = len(enriched) - len([aid for aid in uncached_ids if aid in enriched]) api_count = len([aid for aid in uncached_ids if aid in enriched]) if uncached_ids: - print(f"[Enrich] {cached_count} from cache, {api_count} from API ({len(uncached_ids) - api_count} missed)") + logger.warning(f"[Enrich] {cached_count} from cache, {api_count} from API ({len(uncached_ids) - api_count} missed)") return jsonify({"success": True, "artists": enriched}) except Exception as e: - print(f"Error enriching similar artists: {e}") + logger.error(f"Error enriching similar artists: {e}") return jsonify({"success": False, "error": str(e)}), 500 @@ -42729,7 +42668,7 @@ def get_spotify_library(): }) except Exception as e: - print(f"Error getting Spotify library: {e}") + logger.error(f"Error getting Spotify library: {e}") return jsonify({"success": False, "error": str(e)}), 500 @@ -42747,9 +42686,9 @@ def refresh_spotify_library(): database.set_metadata('spotify_library_last_sync', '') database.set_metadata('spotify_library_last_full_sync', '') scanner.sync_spotify_library_cache(profile_id=get_current_profile_id()) - print("Manual Spotify library refresh complete") + logger.info("Manual Spotify library refresh complete") except Exception as e: - print(f"Error in manual Spotify library refresh: {e}") + logger.error(f"Error in manual Spotify library refresh: {e}") import threading thread = threading.Thread(target=_run_sync, daemon=True) @@ -42758,7 +42697,7 @@ def refresh_spotify_library(): return jsonify({"success": True, "message": "Spotify library refresh started"}) except Exception as e: - print(f"Error starting Spotify library refresh: {e}") + logger.error(f"Error starting Spotify library refresh: {e}") return jsonify({"success": False, "error": str(e)}), 500 @@ -42816,7 +42755,7 @@ def get_discover_recent_releases(): return jsonify({"success": True, "albums": albums, "source": active_source}) except Exception as e: - print(f"Error getting recent releases: {e}") + logger.error(f"Error getting recent releases: {e}") return jsonify({"success": False, "error": str(e)}), 500 @@ -42882,7 +42821,7 @@ def get_discover_release_radar(): return jsonify({"success": True, "tracks": [], "source": active_source}) except Exception as e: - print(f"Error getting release radar: {e}") + logger.error(f"Error getting release radar: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -43195,7 +43134,7 @@ def get_discover_weekly(): return jsonify({"success": True, "tracks": [], "source": active_source}) except Exception as e: - print(f"Error getting discovery weekly: {e}") + logger.error(f"Error getting discovery weekly: {e}") return jsonify({"success": False, "error": str(e)}), 500 @@ -43211,16 +43150,16 @@ def refresh_discover_data(): database = get_database() scanner = WatchlistScanner(spotify_client, database) - print("[Discover Refresh] Starting forced refresh of discover data...") + logger.info("[Discover Refresh] Starting forced refresh of discover data...") refresh_pid = get_current_profile_id() # Cache recent albums from watchlist and similar artists - print("[Discover Refresh] Caching recent albums...") + logger.info("[Discover Refresh] Caching recent albums...") scanner.cache_discovery_recent_albums(profile_id=refresh_pid) # Curate playlists - print("[Discover Refresh] Curating discovery playlists...") + logger.info("[Discover Refresh] Curating discovery playlists...") scanner.curate_discovery_playlists(profile_id=refresh_pid) # Get counts for response @@ -43230,7 +43169,7 @@ def refresh_discover_data(): release_radar = database.get_curated_playlist(f'release_radar_{active_source}', profile_id=pid) or [] discovery_weekly = database.get_curated_playlist(f'discovery_weekly_{active_source}', profile_id=pid) or [] - print(f"[Discover Refresh] Complete! Recent albums: {len(recent_albums)}, Release Radar: {len(release_radar)} tracks, Discovery Weekly: {len(discovery_weekly)} tracks") + logger.info(f"[Discover Refresh] Complete! Recent albums: {len(recent_albums)}, Release Radar: {len(release_radar)} tracks, Discovery Weekly: {len(discovery_weekly)} tracks") return jsonify({ "success": True, @@ -43242,7 +43181,7 @@ def refresh_discover_data(): }) except Exception as e: - print(f"Error refreshing discover data: {e}") + logger.error(f"Error refreshing discover data: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -43313,7 +43252,7 @@ def diagnose_discover_data(): }) except Exception as e: - print(f"Error diagnosing discover data: {e}") + logger.error(f"Error diagnosing discover data: {e}") return jsonify({"success": False, "error": str(e)}), 500 @@ -43358,7 +43297,7 @@ def get_current_seasonal_content(): }) except Exception as e: - print(f"Error getting current seasonal content: {e}") + logger.error(f"Error getting current seasonal content: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/seasonal//albums', methods=['GET']) @@ -43387,7 +43326,7 @@ def get_seasonal_albums(season_key): }) except Exception as e: - print(f"Error getting seasonal albums: {e}") + logger.error(f"Error getting seasonal albums: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/seasonal//playlist', methods=['GET']) @@ -43485,7 +43424,7 @@ def get_seasonal_playlist(season_key): }) except Exception as e: - print(f"Error getting seasonal playlist: {e}") + logger.error(f"Error getting seasonal playlist: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -43505,14 +43444,14 @@ def refresh_seasonal_content(): try: current_season = seasonal_service.get_current_season() if current_season: - print(f"Force-refreshing seasonal content for: {current_season}") + logger.info(f"Force-refreshing seasonal content for: {current_season}") seasonal_service.populate_seasonal_content(current_season) seasonal_service.curate_seasonal_playlist(current_season) - print(f"Seasonal content refreshed for: {current_season}") + logger.info(f"Seasonal content refreshed for: {current_season}") else: - print("ā„¹ļø No active season to refresh") + logger.warning("ā„¹ļø No active season to refresh") except Exception as e: - print(f"Error in background seasonal population: {e}") + logger.error(f"Error in background seasonal population: {e}") thread = threading.Thread(target=populate_all, daemon=True) thread.start() @@ -43520,7 +43459,7 @@ def refresh_seasonal_content(): return jsonify({"success": True, "message": "Seasonal content refresh started"}) except Exception as e: - print(f"Error refreshing seasonal content: {e}") + logger.error(f"Error refreshing seasonal content: {e}") return jsonify({"success": False, "error": str(e)}), 500 # ======================================== @@ -43544,7 +43483,7 @@ def get_recently_added_playlist(): }) except Exception as e: - print(f"Error getting recently added playlist: {e}") + logger.error(f"Error getting recently added playlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/personalized/top-tracks', methods=['GET']) @@ -43564,7 +43503,7 @@ def get_top_tracks_playlist(): }) except Exception as e: - print(f"Error getting top tracks playlist: {e}") + logger.error(f"Error getting top tracks playlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/personalized/forgotten-favorites', methods=['GET']) @@ -43584,7 +43523,7 @@ def get_forgotten_favorites_playlist(): }) except Exception as e: - print(f"Error getting forgotten favorites playlist: {e}") + logger.error(f"Error getting forgotten favorites playlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/personalized/decade/', methods=['GET']) @@ -43605,7 +43544,7 @@ def get_decade_playlist(decade): }) except Exception as e: - print(f"Error getting decade playlist: {e}") + logger.error(f"Error getting decade playlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/personalized/popular-picks', methods=['GET']) @@ -43625,7 +43564,7 @@ def get_popular_picks_playlist(): }) except Exception as e: - print(f"Error getting popular picks playlist: {e}") + logger.error(f"Error getting popular picks playlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/personalized/hidden-gems', methods=['GET']) @@ -43645,7 +43584,7 @@ def get_hidden_gems_playlist(): }) except Exception as e: - print(f"Error getting hidden gems playlist: {e}") + logger.error(f"Error getting hidden gems playlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/personalized/daily-mixes', methods=['GET']) @@ -43665,7 +43604,7 @@ def get_daily_mixes(): }) except Exception as e: - print(f"Error getting daily mixes: {e}") + logger.error(f"Error getting daily mixes: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -43688,7 +43627,7 @@ def get_discovery_shuffle(): }) except Exception as e: - print(f"Error getting discovery shuffle playlist: {e}") + logger.error(f"Error getting discovery shuffle playlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/personalized/familiar-favorites', methods=['GET']) @@ -43709,7 +43648,7 @@ def get_familiar_favorites(): }) except Exception as e: - print(f"Error getting familiar favorites playlist: {e}") + logger.error(f"Error getting familiar favorites playlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/artist-blacklist', methods=['GET']) @@ -43853,7 +43792,7 @@ def refresh_your_artists(): if request.args.get('clear', '').lower() == 'true': database = get_database() cleared = database.clear_liked_artists(profile_id) - print(f"[Your Artists] Cleared {cleared} entries before refresh") + logger.info(f"[Your Artists] Cleared {cleared} entries before refresh") _trigger_your_artists_refresh(profile_id) return jsonify({"success": True, "message": "Refresh started"}) except Exception as e: @@ -43934,9 +43873,9 @@ def _fetch_and_match_liked_artists(profile_id: int): # 1. Fetch from Spotify (followed artists) try: if 'spotify' not in enabled_sources: - print("[Your Artists] Spotify skipped (disabled in sources config)") + logger.warning("[Your Artists] Spotify skipped (disabled in sources config)") elif spotify_client and spotify_client.is_spotify_authenticated(): - print("[Your Artists] Fetching followed artists from Spotify...") + logger.info("[Your Artists] Fetching followed artists from Spotify...") artists = spotify_client.get_followed_artists() for a in artists: database.upsert_liked_artist( @@ -43946,18 +43885,18 @@ def _fetch_and_match_liked_artists(profile_id: int): profile_id=profile_id ) fetched += len(artists) - print(f"[Your Artists] Fetched {len(artists)} from Spotify") + logger.info(f"[Your Artists] Fetched {len(artists)} from Spotify") except Exception as e: logger.error(f"[Your Artists] Spotify fetch error: {e}") # 2. Fetch from Tidal (favorite artists) try: if 'tidal' not in enabled_sources: - print("[Your Artists] Tidal skipped (disabled in sources config)") + logger.warning("[Your Artists] Tidal skipped (disabled in sources config)") elif tidal_client and hasattr(tidal_client, 'get_favorite_artists'): tidal_auth = tidal_client._ensure_valid_token() if hasattr(tidal_client, '_ensure_valid_token') else False if tidal_auth: - print("[Your Artists] Fetching favorite artists from Tidal...") + logger.info("[Your Artists] Fetching favorite artists from Tidal...") artists = tidal_client.get_favorite_artists(limit=200) for a in artists: database.upsert_liked_artist( @@ -43965,26 +43904,26 @@ def _fetch_and_match_liked_artists(profile_id: int): image_url=a.get('image_url'), profile_id=profile_id ) fetched += len(artists) - print(f"[Your Artists] Fetched {len(artists)} from Tidal") + logger.info(f"[Your Artists] Fetched {len(artists)} from Tidal") except Exception as e: logger.error(f"[Your Artists] Tidal fetch error: {e}") # 3. Fetch from Last.fm (top artists) try: if 'lastfm' not in enabled_sources: - print("[Your Artists] Last.fm skipped (disabled in sources config)") + logger.warning("[Your Artists] Last.fm skipped (disabled in sources config)") else: lastfm_key = config_manager.get('lastfm.api_key', '') lastfm_secret = config_manager.get('lastfm.api_secret', '') lastfm_session = config_manager.get('lastfm.session_key', '') - print(f"[Your Artists] Last.fm credentials: key={'yes' if lastfm_key else 'NO'}, secret={'yes' if lastfm_secret else 'NO'}, session={'yes' if lastfm_session else 'NO'}") + logger.info(f"[Your Artists] Last.fm credentials: key={'yes' if lastfm_key else 'NO'}, secret={'yes' if lastfm_secret else 'NO'}, session={'yes' if lastfm_session else 'NO'}") if lastfm_key and lastfm_secret and lastfm_session: from core.lastfm_client import LastFMClient lfm = LastFMClient(api_key=lastfm_key, api_secret=lastfm_secret, session_key=lastfm_session) username = lfm.get_authenticated_username() - print(f"[Your Artists] Last.fm username resolved: {username or 'NONE'}") + logger.info(f"[Your Artists] Last.fm username resolved: {username or 'NONE'}") if username: - print(f"[Your Artists] Fetching top artists from Last.fm ({username})...") + logger.info(f"[Your Artists] Fetching top artists from Last.fm ({username})...") artists = lfm.get_user_top_artists(username, period='overall', limit=200) for a in artists: database.upsert_liked_artist( @@ -43992,23 +43931,23 @@ def _fetch_and_match_liked_artists(profile_id: int): image_url=a.get('image_url'), profile_id=profile_id ) fetched += len(artists) - print(f"[Your Artists] Fetched {len(artists)} from Last.fm") + logger.info(f"[Your Artists] Fetched {len(artists)} from Last.fm") except Exception as e: logger.error(f"[Your Artists] Last.fm fetch error: {e}") # 4. Fetch from Deezer (favorite artists ā€” OAuth or ARL) try: if 'deezer' not in enabled_sources: - print("[Your Artists] Deezer skipped (disabled in sources config)") + logger.warning("[Your Artists] Deezer skipped (disabled in sources config)") else: deezer_cl = _get_deezer_client() artists = [] if deezer_cl and hasattr(deezer_cl, 'is_user_authenticated') and deezer_cl.is_user_authenticated(): - print("[Your Artists] Fetching favorite artists from Deezer (OAuth)...") + logger.info("[Your Artists] Fetching favorite artists from Deezer (OAuth)...") artists = deezer_cl.get_user_favorite_artists(limit=200) elif (hasattr(soulseek_client, 'deezer_dl') and soulseek_client.deezer_dl and soulseek_client.deezer_dl.is_authenticated()): - print("[Your Artists] Fetching favorite artists from Deezer (ARL)...") + logger.info("[Your Artists] Fetching favorite artists from Deezer (ARL)...") artists = soulseek_client.deezer_dl.get_user_favorite_artists(limit=200) for a in artists: database.upsert_liked_artist( @@ -44018,11 +43957,11 @@ def _fetch_and_match_liked_artists(profile_id: int): ) fetched += len(artists) if artists: - print(f"[Your Artists] Fetched {len(artists)} from Deezer") + logger.info(f"[Your Artists] Fetched {len(artists)} from Deezer") except Exception as e: logger.error(f"[Your Artists] Deezer fetch error: {e}") - print(f"[Your Artists] Total fetched: {fetched}") + logger.info(f"[Your Artists] Total fetched: {fetched}") # 5. Match pending artists to active source _match_liked_artists_to_all_sources(database, profile_id) @@ -44225,7 +44164,7 @@ def _match_liked_artists_to_all_sources(database, profile_id: int): matched += 1 database.sync_liked_artists_watchlist_flags(profile_id) - print(f"[Your Artists] Matched {matched}/{len(pending)} artists to {len(search_clients)} sources ({api_calls} API calls)") + logger.info(f"[Your Artists] Matched {matched}/{len(pending)} artists to {len(search_clients)} sources ({api_calls} API calls)") # Image backfill: fetch images for matched artists that have IDs but no image _backfill_liked_artist_images(database, profile_id, search_clients) @@ -44249,7 +44188,7 @@ def _backfill_liked_artist_images(database, profile_id: int, search_clients: dic if not rows: return - print(f"[Your Artists] Backfilling images for {len(rows)} artists...") + logger.info(f"[Your Artists] Backfilling images for {len(rows)} artists...") filled = 0 for row in rows: @@ -44285,7 +44224,7 @@ def _backfill_liked_artist_images(database, profile_id: int, search_clients: dic conn.commit() if filled: - print(f"[Your Artists] Backfilled {filled}/{len(rows)} artist images") + logger.info(f"[Your Artists] Backfilled {filled}/{len(rows)} artist images") except Exception as e: logger.debug(f"[Your Artists] Image backfill error: {e}") @@ -44387,7 +44326,7 @@ def refresh_your_albums(): if request.args.get('clear', '').lower() == 'true': database = get_database() cleared = database.clear_liked_albums(profile_id) - print(f"[Your Albums] Cleared {cleared} entries before refresh") + logger.info(f"[Your Albums] Cleared {cleared} entries before refresh") _trigger_your_albums_refresh(profile_id) return jsonify({"success": True, "message": "Refresh started"}) except Exception as e: @@ -44462,9 +44401,9 @@ def _fetch_liked_albums(profile_id: int): # 1. Fetch from Spotify (saved albums) try: if 'spotify' not in enabled_sources: - print("[Your Albums] Spotify skipped (disabled in sources config)") + logger.warning("[Your Albums] Spotify skipped (disabled in sources config)") elif spotify_client and spotify_client.is_spotify_authenticated(): - print("[Your Albums] Fetching saved albums from Spotify...") + logger.info("[Your Albums] Fetching saved albums from Spotify...") albums = spotify_client.get_saved_albums() for a in albums: database.upsert_liked_album( @@ -44475,18 +44414,18 @@ def _fetch_liked_albums(profile_id: int): total_tracks=a.get('total_tracks', 0), profile_id=profile_id ) fetched += len(albums) - print(f"[Your Albums] Fetched {len(albums)} from Spotify") + logger.info(f"[Your Albums] Fetched {len(albums)} from Spotify") except Exception as e: logger.error(f"[Your Albums] Spotify fetch error: {e}") # 2. Fetch from Tidal (favorite albums) try: if 'tidal' not in enabled_sources: - print("[Your Albums] Tidal skipped (disabled in sources config)") + logger.warning("[Your Albums] Tidal skipped (disabled in sources config)") elif tidal_client and hasattr(tidal_client, 'get_favorite_albums'): tidal_auth = tidal_client._ensure_valid_token() if hasattr(tidal_client, '_ensure_valid_token') else False if tidal_auth: - print("[Your Albums] Fetching favorite albums from Tidal...") + logger.info("[Your Albums] Fetching favorite albums from Tidal...") albums = tidal_client.get_favorite_albums(limit=500) for a in albums: database.upsert_liked_album( @@ -44497,23 +44436,23 @@ def _fetch_liked_albums(profile_id: int): total_tracks=a.get('total_tracks', 0), profile_id=profile_id ) fetched += len(albums) - print(f"[Your Albums] Fetched {len(albums)} from Tidal") + logger.info(f"[Your Albums] Fetched {len(albums)} from Tidal") except Exception as e: logger.error(f"[Your Albums] Tidal fetch error: {e}") # 3. Fetch from Deezer (favorite albums ā€” OAuth or ARL) try: if 'deezer' not in enabled_sources: - print("[Your Albums] Deezer skipped (disabled in sources config)") + logger.warning("[Your Albums] Deezer skipped (disabled in sources config)") else: deezer_cl = _get_deezer_client() albums = [] if deezer_cl and hasattr(deezer_cl, 'is_user_authenticated') and deezer_cl.is_user_authenticated(): - print("[Your Albums] Fetching favorite albums from Deezer (OAuth)...") + logger.info("[Your Albums] Fetching favorite albums from Deezer (OAuth)...") albums = deezer_cl.get_user_favorite_albums(limit=500) elif (hasattr(soulseek_client, 'deezer_dl') and soulseek_client.deezer_dl and soulseek_client.deezer_dl.is_authenticated()): - print("[Your Albums] Fetching favorite albums from Deezer (ARL)...") + logger.info("[Your Albums] Fetching favorite albums from Deezer (ARL)...") albums = soulseek_client.deezer_dl.get_user_favorite_albums(limit=500) for a in albums: database.upsert_liked_album( @@ -44525,11 +44464,11 @@ def _fetch_liked_albums(profile_id: int): ) fetched += len(albums) if albums: - print(f"[Your Albums] Fetched {len(albums)} from Deezer") + logger.info(f"[Your Albums] Fetched {len(albums)} from Deezer") except Exception as e: logger.error(f"[Your Albums] Deezer fetch error: {e}") - print(f"[Your Albums] Total fetched: {fetched}") + logger.info(f"[Your Albums] Total fetched: {fetched}") @app.route('/api/discover/your-artists/info/', methods=['GET']) @@ -45214,11 +45153,11 @@ def get_artist_map_genres(): _img_count = sum(1 for n in nodes if n.get('image_url')) _deezer_count = sum(1 for n in nodes if n.get('image_url', '').startswith('https://api.deezer')) _none_count = sum(1 for n in nodes if not n.get('image_url')) - print(f"[Genre Map] {len(nodes)} artists, {len(sorted_genres)} genres") - print(f"[Genre Map] Images: {_img_count} have URLs, {_deezer_count} Deezer fallback, {_none_count} missing") + logger.info(f"[Genre Map] {len(nodes)} artists, {len(sorted_genres)} genres") + logger.warning(f"[Genre Map] Images: {_img_count} have URLs, {_deezer_count} Deezer fallback, {_none_count} missing") if _none_count > 0: samples = [n['name'] for n in nodes if not n.get('image_url')][:5] - print(f"[Genre Map] Missing image samples: {samples}") + logger.warning(f"[Genre Map] Missing image samples: {samples}") result = { 'success': True, @@ -45341,7 +45280,7 @@ def get_artist_map_explore(): center_image = ia.image_url if hasattr(ia, 'image_url') else '' artist_found = True except Exception as e: - print(f"[Artist Explorer] API validation failed for '{artist_name}': {e}") + logger.debug(f"[Artist Explorer] API validation failed for '{artist_name}': {e}") if not artist_found: return jsonify({"success": False, "error": f"Artist '{artist_name}' not found"}), 404 @@ -45404,7 +45343,7 @@ def get_artist_map_explore(): # If no similar artists in DB, fetch from MusicMap on-the-fly if not ring1_artists: try: - print(f"[Artist Explorer] No stored similar artists for '{center_name}', fetching from MusicMap...") + logger.debug(f"[Artist Explorer] No stored similar artists for '{center_name}', fetching from MusicMap...") from core.watchlist_scanner import WatchlistScanner scanner = WatchlistScanner(spotify_client=spotify_client) if spotify_client else None if scanner: @@ -45451,10 +45390,10 @@ def get_artist_map_explore(): ORDER BY similarity_rank ASC """, (source_artist_id, profile_id)) ring1_artists = cursor.fetchall() - print(f"[Artist Explorer] Fetched {len(ring1_artists)} similar artists from MusicMap for '{center_name}'") + logger.debug(f"[Artist Explorer] Fetched {len(ring1_artists)} similar artists from MusicMap for '{center_name}'") _artmap_cache_invalidate(profile_id) # New similar artists added except Exception as e: - print(f"[Artist Explorer] MusicMap fetch failed for '{center_name}': {e}") + logger.debug(f"[Artist Explorer] MusicMap fetch failed for '{center_name}': {e}") # Deduplicate ring 1 for r in ring1_artists: @@ -45604,7 +45543,7 @@ def get_artist_map_explore(): if alb: n['image_url'] = alb['image_url'] - print(f"[Artist Explorer] Center: {center_name}, Ring 1: {sum(1 for n in nodes if n.get('ring')==1)}, Ring 2: {sum(1 for n in nodes if n.get('ring')==2)}, Edges: {len(edges)}") + logger.info(f"[Artist Explorer] Center: {center_name}, Ring 1: {sum(1 for n in nodes if n.get('ring')==1)}, Ring 2: {sum(1 for n in nodes if n.get('ring')==2)}, Edges: {len(edges)}") return jsonify({ 'success': True, @@ -45678,7 +45617,7 @@ def search_artists_for_playlist(): }) except Exception as e: - print(f"Error searching for artists: {e}") + logger.error(f"Error searching for artists: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/build-playlist/generate', methods=['POST']) @@ -45711,7 +45650,7 @@ def generate_custom_playlist(): }) except Exception as e: - print(f"Error generating custom playlist: {e}") + logger.error(f"Error generating custom playlist: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -45753,7 +45692,7 @@ def get_available_decades(): }) except Exception as e: - print(f"Error getting available decades: {e}") + logger.error(f"Error getting available decades: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/decade/', methods=['GET']) @@ -45796,7 +45735,7 @@ def get_discover_decade_playlist(decade): }) except Exception as e: - print(f"Error getting decade playlist: {e}") + logger.error(f"Error getting decade playlist: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -45818,7 +45757,7 @@ def get_available_genres(): }) except Exception as e: - print(f"Error getting available genres: {e}") + logger.error(f"Error getting available genres: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -45863,7 +45802,7 @@ def get_discover_genre_playlist(genre_name): }) except Exception as e: - print(f"Error getting genre playlist: {e}") + logger.error(f"Error getting genre playlist: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -45894,7 +45833,7 @@ def _get_lb_discover_playlists(playlist_type): "count": 0, "username": None }) - print(f"Cache empty for profile {lb_manager.profile_id}, populating ListenBrainz playlists...") + logger.warning(f"Cache empty for profile {lb_manager.profile_id}, populating ListenBrainz playlists...") lb_manager.update_all_playlists() playlists = lb_manager.get_cached_playlists(playlist_type) @@ -45925,7 +45864,7 @@ def get_listenbrainz_created_for(): try: return _get_lb_discover_playlists('created_for') except Exception as e: - print(f"Error getting cached ListenBrainz created-for playlists: {e}") + logger.error(f"Error getting cached ListenBrainz created-for playlists: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -45936,7 +45875,7 @@ def get_listenbrainz_user_playlists(): try: return _get_lb_discover_playlists('user') except Exception as e: - print(f"Error getting cached ListenBrainz user playlists: {e}") + logger.error(f"Error getting cached ListenBrainz user playlists: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -45947,7 +45886,7 @@ def get_listenbrainz_collaborative(): try: return _get_lb_discover_playlists('collaborative') except Exception as e: - print(f"Error getting cached ListenBrainz collaborative playlists: {e}") + logger.error(f"Error getting cached ListenBrainz collaborative playlists: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -45962,7 +45901,7 @@ def get_listenbrainz_playlist_tracks(playlist_mbid): if not tracks: # Cache miss or stale entry with no tracks ā€” try fetching from LB API if lb_manager.client.is_authenticated(): - print(f"Cache miss for playlist {playlist_mbid}, fetching from ListenBrainz...") + logger.debug(f"Cache miss for playlist {playlist_mbid}, fetching from ListenBrainz...") # Remove stale playlist row (if any) so _update_playlist doesn't # skip due to matching track_count with 0 actual tracks existing_type = lb_manager.get_playlist_type(playlist_mbid) or 'created_for' @@ -45985,7 +45924,7 @@ def get_listenbrainz_playlist_tracks(playlist_mbid): }) except Exception as e: - print(f"Error getting cached ListenBrainz playlist tracks: {e}") + logger.error(f"Error getting cached ListenBrainz playlist tracks: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -46002,7 +45941,7 @@ def refresh_listenbrainz(): return jsonify(result) except Exception as e: - print(f"Error refreshing ListenBrainz: {e}") + logger.error(f"Error refreshing ListenBrainz: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -46060,7 +45999,7 @@ def lastfm_search_tracks(): return jsonify({"success": True, "results": results}) except Exception as e: - print(f"Error searching Last.fm tracks: {e}") + logger.error(f"Error searching Last.fm tracks: {e}") return jsonify({"success": False, "error": str(e), "results": []}), 500 @@ -46140,7 +46079,7 @@ def lastfm_radio_generate(): state['spotify_total'] = len(similar) state['last_accessed'] = time.time() - print(f"Last.fm Radio generated: '{title}' ({len(similar)} tracks) ā†’ {playlist_mbid}") + logger.info(f"Last.fm Radio generated: '{title}' ({len(similar)} tracks) ā†’ {playlist_mbid}") return jsonify({ "success": True, "playlist_mbid": playlist_mbid, @@ -46149,7 +46088,7 @@ def lastfm_radio_generate(): }) except Exception as e: - print(f"Error generating Last.fm radio: {e}") + logger.error(f"Error generating Last.fm radio: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -46180,7 +46119,7 @@ def get_listenbrainz_lastfm_radio(): ] return jsonify({"success": True, "playlists": formatted, "count": len(formatted), "username": username, "source": source}) except Exception as e: - print(f"Error getting Last.fm radio playlists: {e}") + logger.error(f"Error getting Last.fm radio playlists: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -46228,11 +46167,11 @@ def get_all_listenbrainz_playlists(): } playlists.append(playlist_info) - print(f"Returning {len(playlists)} stored ListenBrainz playlists for profile {profile_id}") + logger.info(f"Returning {len(playlists)} stored ListenBrainz playlists for profile {profile_id}") return jsonify({"playlists": playlists}) except Exception as e: - print(f"Error getting ListenBrainz playlists: {e}") + logger.error(f"Error getting ListenBrainz playlists: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/state/', methods=['GET']) @@ -46267,7 +46206,7 @@ def get_listenbrainz_playlist_state(playlist_mbid): return jsonify(response) except Exception as e: - print(f"Error getting ListenBrainz playlist state: {e}") + logger.error(f"Error getting ListenBrainz playlist state: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/reset/', methods=['POST']) @@ -46296,11 +46235,11 @@ def reset_listenbrainz_playlist(playlist_mbid): state['discovery_future'] = None state['last_accessed'] = time.time() - print(f"Reset ListenBrainz playlist to fresh: {state['playlist']['title']}") + logger.info(f"Reset ListenBrainz playlist to fresh: {state['playlist']['title']}") return jsonify({"success": True, "phase": "fresh"}) except Exception as e: - print(f"Error resetting ListenBrainz playlist: {e}") + logger.error(f"Error resetting ListenBrainz playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/remove/', methods=['POST']) @@ -46320,11 +46259,11 @@ def remove_listenbrainz_playlist(playlist_mbid): # Remove from state del listenbrainz_playlist_states[state_key] - print(f"Removed ListenBrainz playlist from state: {playlist_mbid}") + logger.info(f"Removed ListenBrainz playlist from state: {playlist_mbid}") return jsonify({"success": True}) except Exception as e: - print(f"Error removing ListenBrainz playlist: {e}") + logger.error(f"Error removing ListenBrainz playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/discovery/start/', methods=['POST']) @@ -46353,7 +46292,7 @@ def start_listenbrainz_discovery(playlist_mbid): 'created_at': time.time(), 'last_accessed': time.time() } - print(f"Created new ListenBrainz playlist state: {playlist_data.get('name', 'Unknown')}") + logger.info(f"Created new ListenBrainz playlist state: {playlist_data.get('name', 'Unknown')}") else: # State already exists, update it state = listenbrainz_playlist_states[state_key] @@ -46379,11 +46318,11 @@ def start_listenbrainz_discovery(playlist_mbid): future = listenbrainz_discovery_executor.submit(_run_listenbrainz_discovery_worker, state_key) state['discovery_future'] = future - print(f"Started Spotify discovery for ListenBrainz playlist: {playlist_name}") + logger.info(f"Started Spotify discovery for ListenBrainz playlist: {playlist_name}") return jsonify({"success": True, "message": "Discovery started"}) except Exception as e: - print(f"Error starting ListenBrainz discovery: {e}") + logger.error(f"Error starting ListenBrainz discovery: {e}") import traceback traceback.print_exc() return jsonify({"error": str(e)}), 500 @@ -46412,7 +46351,7 @@ def get_listenbrainz_discovery_status(playlist_mbid): return jsonify(response) except Exception as e: - print(f"Error getting ListenBrainz discovery status: {e}") + logger.error(f"Error getting ListenBrainz discovery status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/update-phase/', methods=['POST']) @@ -46451,7 +46390,7 @@ def update_listenbrainz_phase(playlist_mbid): }) except Exception as e: - print(f"Error updating ListenBrainz playlist phase: {e}") + logger.error(f"Error updating ListenBrainz playlist phase: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/discovery/update_match', methods=['POST']) @@ -46509,13 +46448,13 @@ def update_listenbrainz_discovery_match(): result['manual_match'] = True - print(f"Updated ListenBrainz match for track {track_index}: {result['status']}") + logger.info(f"Updated ListenBrainz match for track {track_index}: {result['status']}") return jsonify({'success': True}) else: return jsonify({'error': 'Invalid track index'}), 400 except Exception as e: - print(f"Error updating ListenBrainz discovery match: {e}") + logger.error(f"Error updating ListenBrainz discovery match: {e}") import traceback traceback.print_exc() return jsonify({'error': str(e)}), 500 @@ -46553,7 +46492,7 @@ def convert_listenbrainz_results_to_spotify_tracks(discovery_results): } spotify_tracks.append(track) - print(f"Converted {len(spotify_tracks)} ListenBrainz matches to Spotify tracks for sync") + logger.info(f"Converted {len(spotify_tracks)} ListenBrainz matches to Spotify tracks for sync") return spotify_tracks @app.route('/api/wing-it/sync', methods=['POST']) @@ -46664,11 +46603,11 @@ def start_listenbrainz_sync(playlist_mbid): future = sync_executor.submit(_run_sync_task, sync_playlist_id, sync_data['playlist_name'], spotify_tracks, None, get_current_profile_id()) active_sync_workers[sync_playlist_id] = future - print(f"Started ListenBrainz sync for: {playlist_name} ({len(spotify_tracks)} tracks)") + logger.info(f"Started ListenBrainz sync for: {playlist_name} ({len(spotify_tracks)} tracks)") return jsonify({"success": True, "sync_playlist_id": sync_playlist_id}) except Exception as e: - print(f"Error starting ListenBrainz sync: {e}") + logger.error(f"Error starting ListenBrainz sync: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/sync/status/', methods=['GET']) @@ -46713,7 +46652,7 @@ def get_listenbrainz_sync_status(playlist_mbid): return jsonify(response) except Exception as e: - print(f"Error getting ListenBrainz sync status: {e}") + logger.error(f"Error getting ListenBrainz sync status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/sync/cancel/', methods=['POST']) @@ -46745,7 +46684,7 @@ def cancel_listenbrainz_sync(playlist_mbid): return jsonify({"success": True, "message": "ListenBrainz sync cancelled"}) except Exception as e: - print(f"Error cancelling ListenBrainz sync: {e}") + logger.error(f"Error cancelling ListenBrainz sync: {e}") return jsonify({"error": str(e)}), 500 @@ -46770,7 +46709,7 @@ def _old_get_listenbrainz_playlist_tracks_DEPRECATED(playlist_mbid): # Convert to our standard format - prepare tracks first without cover art tracks = [] - print(f"Processing {len(jspf_tracks)} tracks from playlist") + logger.info(f"Processing {len(jspf_tracks)} tracks from playlist") # First pass: extract all track data without cover art track_data_list = [] @@ -46788,8 +46727,8 @@ def _old_get_listenbrainz_playlist_tracks_DEPRECATED(playlist_mbid): mb_data = extension.get('https://musicbrainz.org/doc/jspf#track', {}) if idx == 0: - print(f"Sample track extension data: {extension}") - print(f"Sample mb_data keys: {mb_data.keys() if mb_data else 'None'}") + logger.debug(f"Sample track extension data: {extension}") + logger.debug(f"Sample mb_data keys: {mb_data.keys() if mb_data else 'None'}") # Extract release MBID for cover art release_mbid = None @@ -46803,7 +46742,7 @@ def _old_get_listenbrainz_playlist_tracks_DEPRECATED(playlist_mbid): release_mbid = mb_data['release_mbid'] if idx == 0: - print(f"šŸ†” First track release_mbid: {release_mbid}") + logger.debug(f"šŸ†” First track release_mbid: {release_mbid}") track_data = { 'track_name': track.get('title', 'Unknown Track'), @@ -46849,7 +46788,7 @@ def _old_get_listenbrainz_playlist_tracks_DEPRECATED(playlist_mbid): return None - print(f"Fetching cover art for {len(track_data_list)} tracks in parallel...") + logger.info(f"Fetching cover art for {len(track_data_list)} tracks in parallel...") start_time = time.time() # Fetch up to 10 covers at a time @@ -46868,7 +46807,7 @@ def _old_get_listenbrainz_playlist_tracks_DEPRECATED(playlist_mbid): elapsed = time.time() - start_time covers_found = sum(1 for t in track_data_list if t.get('album_cover_url')) - print(f"Fetched {covers_found}/{len(track_data_list)} covers in {elapsed:.2f}s") + logger.info(f"Fetched {covers_found}/{len(track_data_list)} covers in {elapsed:.2f}s") tracks = track_data_list @@ -46879,7 +46818,7 @@ def _old_get_listenbrainz_playlist_tracks_DEPRECATED(playlist_mbid): }) except Exception as e: - print(f"Error getting ListenBrainz playlist tracks: {e}") + logger.error(f"Error getting ListenBrainz playlist tracks: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @@ -46918,20 +46857,21 @@ def start_metadata_update(): add_activity_item("", "Metadata Update", "Plex client not available", "Now") return jsonify({"success": False, "error": "Plex client not available"}), 400 - # DEBUG: Check Plex connection details - print(f"[DEBUG] Active server: {active_server}") - print(f"[DEBUG] Plex client: {media_client}") + logger.debug("Plex connection details: active_server=%s client=%s", active_server, media_client) if hasattr(media_client, 'server') and media_client.server: - print(f"[DEBUG] Plex server URL: {getattr(media_client.server, '_baseurl', 'NO_URL')}") - print(f"[DEBUG] Plex server name: {getattr(media_client.server, 'friendlyName', 'NO_NAME')}") + logger.debug( + "Plex server details: url=%s name=%s", + getattr(media_client.server, '_baseurl', 'NO_URL'), + getattr(media_client.server, 'friendlyName', 'NO_NAME'), + ) # Check available libraries try: sections = media_client.server.library.sections() - print(f"[DEBUG] Available Plex libraries: {[(s.title, s.type) for s in sections]}") + logger.debug("Available Plex libraries: %s", [(s.title, s.type) for s in sections]) except Exception as e: - print(f"[DEBUG] Error getting Plex libraries: {e}") + logger.debug("Error getting Plex libraries: %s", e) else: - print(f"[DEBUG] Plex server is NOT connected!") + logger.debug("Plex server is NOT connected!") # Check Spotify client - EXACTLY like dashboard.py if not spotify_client: @@ -46967,7 +46907,7 @@ def start_metadata_update(): metadata_update_runtime_worker = metadata_worker metadata_worker.run() except Exception as e: - print(f"Error in metadata update worker: {e}") + logger.error(f"Error in metadata update worker: {e}") metadata_update_state['status'] = 'error' metadata_update_state['error'] = str(e) add_activity_item("", "Metadata Error", str(e), "Now") @@ -46981,7 +46921,7 @@ def start_metadata_update(): return jsonify({"success": True}) except Exception as e: - print(f"Error starting metadata update: {e}") + logger.error(f"Error starting metadata update: {e}") metadata_update_state['status'] = 'error' metadata_update_state['error'] = str(e) return jsonify({"success": False, "error": str(e)}), 500 @@ -47000,7 +46940,7 @@ def stop_metadata_update(): return jsonify({"success": True}) except Exception as e: - print(f"Error stopping metadata update: {e}") + logger.error(f"Error stopping metadata update: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/metadata/status', methods=['GET']) @@ -47019,7 +46959,7 @@ def get_metadata_update_status(): return jsonify({"success": True, "status": state_copy}) except Exception as e: - print(f"Error getting metadata update status: {e}") + logger.error(f"Error getting metadata update status: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/active-media-server', methods=['GET']) @@ -47029,7 +46969,7 @@ def get_active_media_server(): active_server = config_manager.get_active_media_server() return jsonify({"success": True, "active_server": active_server}) except Exception as e: - print(f"Error getting active media server: {e}") + logger.error(f"Error getting active media server: {e}") return jsonify({"success": False, "error": str(e)}), 500 # ================================= # @@ -48579,21 +48519,21 @@ def start_beatport_discovery(url_hash): # Get chart data from request body data = request.get_json() or {} - print(f"Raw request data: {data}") + logger.debug(f"Raw request data: {data}") chart_data = data.get('chart_data') - print(f"Chart data extracted: {chart_data is not None}") + logger.debug(f"Chart data extracted: {chart_data is not None}") # Debug logging if chart_data: - print(f"Chart data keys: {list(chart_data.keys()) if isinstance(chart_data, dict) else 'Not a dict'}") - print(f"Chart name: {chart_data.get('name') if isinstance(chart_data, dict) else 'N/A'}") + logger.debug(f"Chart data keys: {list(chart_data.keys()) if isinstance(chart_data, dict) else 'Not a dict'}") + logger.debug(f"Chart name: {chart_data.get('name') if isinstance(chart_data, dict) else 'N/A'}") if isinstance(chart_data, dict) and 'tracks' in chart_data: - print(f"Number of tracks: {len(chart_data['tracks'])}") + logger.debug(f"Number of tracks: {len(chart_data['tracks'])}") if chart_data['tracks']: - print(f"First track: {chart_data['tracks'][0]}") + logger.debug(f"First track: {chart_data['tracks'][0]}") else: - print("No chart data received") + logger.warning("No chart data received") if not chart_data or not chart_data.get('tracks'): return jsonify({"error": "Chart data with tracks is required"}), 400 @@ -48633,7 +48573,7 @@ def start_beatport_discovery(url_hash): future = beatport_discovery_executor.submit(_run_beatport_discovery_worker, url_hash) state['discovery_future'] = future - print(f"Started Spotify discovery for Beatport chart: {chart_name}") + logger.info(f"Started Spotify discovery for Beatport chart: {chart_name}") return jsonify({"success": True, "message": "Discovery started", "status": "discovering"}) except Exception as e: @@ -48767,7 +48707,7 @@ def _run_beatport_discovery_worker(url_hash): if not use_spotify: itunes_client_instance = _get_metadata_fallback_client() - print(f"Starting {discovery_source.upper()} discovery for {len(tracks)} Beatport tracks...") + logger.info(f"Starting {discovery_source.upper()} discovery for {len(tracks)} Beatport tracks...") # Store discovery source in state for frontend state['discovery_source'] = discovery_source @@ -48777,7 +48717,7 @@ def _run_beatport_discovery_worker(url_hash): try: # Check for cancellation if state.get('phase') != 'discovering': - print(f"Beatport discovery cancelled (phase changed to '{state.get('phase')}')") + logger.warning(f"Beatport discovery cancelled (phase changed to '{state.get('phase')}')") return # Update progress @@ -48796,7 +48736,7 @@ def _run_beatport_discovery_worker(url_hash): else: track_artist = clean_beatport_text(str(track_artists)) - print(f"Searching {discovery_source.upper()} for: '{track_artist}' - '{track_title}'") + logger.debug(f"Searching {discovery_source.upper()} for: '{track_artist}' - '{track_title}'") # Check discovery cache first cache_key = _get_discovery_cache_key(track_title, track_artist) @@ -48804,7 +48744,7 @@ def _run_beatport_discovery_worker(url_hash): cache_db = get_database() cached_match = cache_db.get_discovery_cache_match(cache_key[0], cache_key[1], discovery_source) if cached_match and _validate_discovery_cache_artist(track_artist, cached_match): - print(f"CACHE HIT [{i+1}/{len(tracks)}]: {track_artist} - {track_title}") + logger.debug(f"CACHE HIT [{i+1}/{len(tracks)}]: {track_artist} - {track_title}") # Convert artists from ['str'] to [{'name': 'str'}] for Beatport frontend format beatport_artists = cached_match.get('artists', []) if beatport_artists and isinstance(beatport_artists[0], str): @@ -48824,7 +48764,7 @@ def _run_beatport_discovery_worker(url_hash): state['discovery_results'].append(result_entry) continue except Exception as cache_err: - print(f"Cache lookup error: {cache_err}") + logger.error(f"Cache lookup error: {cache_err}") # Use matching engine for track matching found_track = None @@ -48840,9 +48780,9 @@ def _run_beatport_discovery_worker(url_hash): 'album': None })() search_queries = matching_engine.generate_download_queries(temp_track) - print(f"Generated {len(search_queries)} search queries using matching engine") + logger.debug(f"Generated {len(search_queries)} search queries using matching engine") except Exception as e: - print(f"Matching engine failed for Beatport, falling back to basic queries: {e}") + logger.error(f"Matching engine failed for Beatport, falling back to basic queries: {e}") if use_spotify: search_queries = [ f"{track_artist} {track_title}", @@ -48858,7 +48798,7 @@ def _run_beatport_discovery_worker(url_hash): for query_idx, search_query in enumerate(search_queries): try: - print(f"Query {query_idx + 1}/{len(search_queries)}: {search_query} ({discovery_source.upper()})") + logger.debug(f"Query {query_idx + 1}/{len(search_queries)}: {search_query} ({discovery_source.upper()})") search_results = None @@ -48883,19 +48823,19 @@ def _run_beatport_discovery_worker(url_hash): best_raw_track = _cache.get_entity('spotify', 'track', match.id) else: best_raw_track = None - print(f"New best Beatport match: {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") + logger.debug(f"New best Beatport match: {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") if best_confidence >= 0.9: - print(f"High confidence match found ({best_confidence:.3f}), stopping search") + logger.debug(f"High confidence match found ({best_confidence:.3f}), stopping search") break except Exception as e: - print(f"Error in {discovery_source.upper()} search for query '{search_query}': {e}") + logger.debug(f"Error in {discovery_source.upper()} search for query '{search_query}': {e}") continue # Strategy 4: Extended search with higher limit (last resort) if not found_track: - print(f"Beatport Strategy 4: Extended search with limit=50") + logger.debug(f"Beatport Strategy 4: Extended search with limit=50") query = f"{track_artist} {track_title}" if use_spotify: extended_results = spotify_client.search_tracks(query, limit=50) @@ -48908,12 +48848,12 @@ def _run_beatport_discovery_worker(url_hash): if match and confidence >= min_confidence: found_track = match best_confidence = confidence - print(f"Strategy 4 Beatport match (extended): {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") + logger.debug(f"Strategy 4 Beatport match (extended): {match.artists[0]} - {match.name} (confidence: {confidence:.3f})") if found_track: - print(f"Final Beatport match: {found_track.artists[0]} - {found_track.name} (confidence: {best_confidence:.3f})") + logger.info(f"Final Beatport match: {found_track.artists[0]} - {found_track.name} (confidence: {best_confidence:.3f})") else: - print(f"No suitable match found (best confidence was {best_confidence:.3f}, required {min_confidence:.3f})") + logger.warning(f"No suitable match found (best confidence was {best_confidence:.3f}, required {min_confidence:.3f})") # Create result entry result_entry = { @@ -48932,7 +48872,7 @@ def _run_beatport_discovery_worker(url_hash): if use_spotify: # SPOTIFY result formatting # Debug: show available attributes - print(f"Spotify track attributes: {dir(found_track)}") + logger.debug(f"Spotify track attributes: {dir(found_track)}") # Format artists correctly for frontend compatibility formatted_artists = [] @@ -49009,9 +48949,9 @@ def _run_beatport_discovery_worker(url_hash): cache_key[0], cache_key[1], discovery_source, best_confidence, cache_data, track_title, track_artist ) - print(f"CACHE SAVED: {track_artist} - {track_title} (confidence: {best_confidence:.3f})") + logger.debug(f"CACHE SAVED: {track_artist} - {track_title} (confidence: {best_confidence:.3f})") except Exception as cache_err: - print(f"Cache save error: {cache_err}") + logger.error(f"Cache save error: {cache_err}") # Auto Wing It fallback for unmatched tracks if result_entry.get('status_class') == 'not-found': @@ -49036,7 +48976,7 @@ def _run_beatport_discovery_worker(url_hash): time.sleep(0.1) except Exception as e: - print(f"Error processing Beatport track {i}: {e}") + logger.error(f"Error processing Beatport track {i}: {e}") # Add error result state['discovery_results'].append({ 'index': i, # Add index for frontend table row identification @@ -49061,13 +49001,13 @@ def _run_beatport_discovery_worker(url_hash): add_activity_item("", f"Beatport Discovery Complete ({source_label})", f"'{chart_name}' - {state['spotify_matches']}/{len(tracks)} tracks found", "Now") - print(f"Beatport discovery complete ({source_label}): {state['spotify_matches']}/{len(tracks)} tracks found") + logger.info(f"Beatport discovery complete ({source_label}): {state['spotify_matches']}/{len(tracks)} tracks found") # Sync discovery results back to mirrored playlist _sync_discovery_results_to_mirrored('beatport', url_hash, state.get('discovery_results', []), discovery_source, profile_id=state.get('_profile_id', 1)) except Exception as e: - print(f"Error in Beatport discovery worker: {e}") + logger.error(f"Error in Beatport discovery worker: {e}") if url_hash in beatport_chart_states: beatport_chart_states[url_hash]['status'] = 'error' beatport_chart_states[url_hash]['phase'] = 'fresh' @@ -49078,19 +49018,19 @@ def _run_beatport_discovery_worker(url_hash): def start_beatport_sync(url_hash): """Start sync process for a Beatport chart using discovered Spotify tracks""" try: - print(f"Beatport sync start requested for: {url_hash}") + logger.info(f"Beatport sync start requested for: {url_hash}") if url_hash not in beatport_chart_states: - print(f"Beatport chart not found: {url_hash}") + logger.warning(f"Beatport chart not found: {url_hash}") return jsonify({"error": "Beatport chart not found"}), 404 state = beatport_chart_states[url_hash] state['last_accessed'] = time.time() # Update access time - print(f"Beatport chart state: phase={state.get('phase')}, has_discovery_results={len(state.get('discovery_results', []))}") + logger.info(f"Beatport chart state: phase={state.get('phase')}, has_discovery_results={len(state.get('discovery_results', []))}") if state['phase'] not in ['discovered', 'sync_complete', 'download_complete']: - print(f"Beatport chart not ready for sync: {state['phase']}") + logger.info(f"Beatport chart not ready for sync: {state['phase']}") return jsonify({"error": "Beatport chart not ready for sync"}), 400 # Convert discovery results to Spotify tracks format @@ -49124,11 +49064,11 @@ def start_beatport_sync(url_hash): future = sync_executor.submit(_run_sync_task, sync_playlist_id, sync_data['name'], spotify_tracks, None, get_current_profile_id()) state['sync_future'] = future - print(f"Started Beatport sync for chart: {state['chart']['name']}") + logger.info(f"Started Beatport sync for chart: {state['chart']['name']}") return jsonify({"success": True, "sync_id": sync_playlist_id}) except Exception as e: - print(f"Error starting Beatport sync: {e}") + logger.error(f"Error starting Beatport sync: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/beatport/sync/status/', methods=['GET']) @@ -49172,7 +49112,7 @@ def get_beatport_sync_status(url_hash): return jsonify(response) except Exception as e: - print(f"Error getting Beatport sync status: {e}") + logger.error(f"Error getting Beatport sync status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/beatport/sync/cancel/', methods=['POST']) @@ -49200,11 +49140,11 @@ def cancel_beatport_sync(url_hash): state['sync_playlist_id'] = None state['sync_progress'] = {} - print(f"Cancelled Beatport sync for: {url_hash}") + logger.warning(f"Cancelled Beatport sync for: {url_hash}") return jsonify({"success": True}) except Exception as e: - print(f"Error cancelling Beatport sync: {e}") + logger.error(f"Error cancelling Beatport sync: {e}") return jsonify({"error": str(e)}), 500 # =================================================================== @@ -49865,13 +49805,13 @@ def retry_failed_mirrored_discovery(playlist_id): 'discovery_attempted': False, }) except Exception as db_err: - print(f"Error clearing discovery_attempted in DB: {db_err}") + logger.error(f"Error clearing discovery_attempted in DB: {db_err}") # Submit worker future = youtube_discovery_executor.submit(_run_youtube_discovery_worker, url_hash) state['discovery_future'] = future - print(f"Retrying failed discovery for {url_hash}: {retry_count} tracks to retry, {already_found} already found") + logger.error(f"Retrying failed discovery for {url_hash}: {retry_count} tracks to retry, {already_found} already found") return jsonify({ "success": True, "retry_count": retry_count, @@ -50363,7 +50303,7 @@ class WebMetadataUpdateWorker: pass all_artists = self.media_client.get_all_artists() - print(f"[DEBUG] Raw artists returned: {[getattr(a, 'title', 'NO_TITLE') for a in (all_artists or [])]}") + logger.debug(f"Raw artists returned: {[getattr(a, 'title', 'NO_TITLE') for a in (all_artists or [])]}") if not all_artists: metadata_update_state['status'] = 'error' metadata_update_state['error'] = f"No artists found in {self.server_type.title()} library" @@ -50450,7 +50390,7 @@ class WebMetadataUpdateWorker: add_activity_item("", "Metadata Complete", summary, "Now") except Exception as e: - print(f"Metadata update failed: {e}") + logger.error(f"Metadata update failed: {e}") metadata_update_state['status'] = 'error' metadata_update_state['error'] = str(e) add_activity_item("", "Metadata Error", str(e), "Now") @@ -50466,7 +50406,7 @@ class WebMetadataUpdateWorker: return self.media_client.needs_update_by_age(artist, self.refresh_interval_days) except Exception as e: - print(f"Error checking artist {getattr(artist, 'title', 'Unknown')}: {e}") + logger.error(f"Error checking artist {getattr(artist, 'title', 'Unknown')}: {e}") return True # Process if we can't determine status def _check_db_artist(self, artist_name): @@ -50553,9 +50493,9 @@ class WebMetadataUpdateWorker: if raw and 'name' in raw: spotify_artist = SpotifyArtistDC.from_spotify_artist(raw) highest_score = 1.0 - print(f"Metadata updater: direct Spotify lookup for '{artist_name}' via cached ID {db_spotify_id}") + logger.debug(f"Metadata updater: direct Spotify lookup for '{artist_name}' via cached ID {db_spotify_id}") except Exception as e: - print(f"Direct Spotify lookup failed for {db_spotify_id}: {e}") + logger.debug(f"Direct Spotify lookup failed for {db_spotify_id}: {e}") spotify_artist = None # Fall back to search if direct lookup didn't work @@ -50626,7 +50566,7 @@ class WebMetadataUpdateWorker: if albums_updated > 0: changes_made.append(f"{albums_updated} album art") elif self.server_type != "plex": - print(f"Skipping album artwork updates for Jellyfin artist: {artist.title}") + logger.info(f"Skipping album artwork updates for Jellyfin artist: {artist.title}") if changes_made: biography_updated = self.media_client.update_artist_biography(artist) @@ -50662,15 +50602,15 @@ class WebMetadataUpdateWorker: try: # Check if artist already has a good photo (skip check for Jellyfin) if self.server_type != "jellyfin" and self.artist_has_valid_photo(artist): - print(f"Skipping {artist.title}: already has valid photo ({getattr(artist, 'thumb', 'None')})") + logger.info(f"Skipping {artist.title}: already has valid photo ({getattr(artist, 'thumb', 'None')})") return False # Get the image URL from Spotify if not spotify_artist.image_url: - print(f"Skipping {artist.title}: no Spotify image URL available") + logger.warning(f"Skipping {artist.title}: no Spotify image URL available") return False - print(f"Processing {artist.title}: downloading from Spotify...") + logger.info(f"Processing {artist.title}: downloading from Spotify...") image_url = spotify_artist.image_url @@ -50682,7 +50622,7 @@ class WebMetadataUpdateWorker: if self.server_type == "jellyfin": # For Jellyfin, use raw image data to preserve original format image_data = response.content - print(f"Using raw image data for Jellyfin ({len(image_data)} bytes)") + logger.info(f"Using raw image data for Jellyfin ({len(image_data)} bytes)") else: # For other servers, validate and convert image_data = self.validate_and_convert_image(response.content) @@ -50693,7 +50633,7 @@ class WebMetadataUpdateWorker: return self.media_client.update_artist_poster(artist, image_data) except Exception as e: - print(f"Error updating photo for {getattr(artist, 'title', 'Unknown')}: {e}") + logger.error(f"Error updating photo for {getattr(artist, 'title', 'Unknown')}: {e}") return False def update_artist_genres(self, artist, spotify_artist): @@ -50737,7 +50677,7 @@ class WebMetadataUpdateWorker: return False except Exception as e: - print(f"Error updating genres for {getattr(artist, 'title', 'Unknown')}: {e}") + logger.error(f"Error updating genres for {getattr(artist, 'title', 'Unknown')}: {e}") return False def update_album_artwork(self, artist, spotify_artist): @@ -50751,11 +50691,11 @@ class WebMetadataUpdateWorker: try: albums = list(artist.albums()) except Exception: - print(f"Could not access albums for artist '{artist.title}'") + logger.error(f"Could not access albums for artist '{artist.title}'") return 0 if not albums: - print(f"No albums found for artist '{artist.title}'") + logger.warning(f"No albums found for artist '{artist.title}'") return 0 import time @@ -50798,13 +50738,13 @@ class WebMetadataUpdateWorker: updated_count += 1 except Exception as e: - print(f"Error processing album '{getattr(album, 'title', 'Unknown')}': {e}") + logger.error(f"Error processing album '{getattr(album, 'title', 'Unknown')}': {e}") continue return updated_count except Exception as e: - print(f"Error updating album artwork for artist '{getattr(artist, 'title', 'Unknown')}': {e}") + logger.error(f"Error updating album artwork for artist '{getattr(artist, 'title', 'Unknown')}': {e}") return 0 def album_has_valid_artwork(self, album): @@ -50852,7 +50792,7 @@ class WebMetadataUpdateWorker: return success except Exception as e: - print(f"Error downloading/uploading artwork for album '{getattr(album, 'title', 'Unknown')}': {e}") + logger.error(f"Error downloading/uploading artwork for album '{getattr(album, 'title', 'Unknown')}': {e}") return False def artist_has_valid_photo(self, artist): @@ -50927,7 +50867,7 @@ class WebMetadataUpdateWorker: jellyfin_token = jellyfin_config.get('api_key', '') if not jellyfin_base_url or not jellyfin_token: - print("Jellyfin configuration missing for image upload") + logger.warning("Jellyfin configuration missing for image upload") return False upload_url = f"{jellyfin_base_url.rstrip('/')}/Items/{artist.ratingKey}/Images/Primary" @@ -50942,7 +50882,7 @@ class WebMetadataUpdateWorker: # Navidrome: Currently not supported (Subsonic API doesn't support image uploads) elif self.server_type == "navidrome": - print("ā„¹ļø Navidrome does not support artist image uploads via Subsonic API") + logger.info("ā„¹ļø Navidrome does not support artist image uploads via Subsonic API") return False else: @@ -50950,7 +50890,7 @@ class WebMetadataUpdateWorker: return False except Exception as e: - print(f"Error uploading poster: {e}") + logger.error(f"Error uploading poster: {e}") return False # --- Docker Helper Functions --- @@ -51104,33 +51044,33 @@ def start_oauth_callback_servers(): _env_val = os.environ.get('SOULSYNC_SPOTIFY_CALLBACK_PORT') spotify_port = int(_env_val) if _env_val else 8888 if _env_val: - print(f"[OAuth] SOULSYNC_SPOTIFY_CALLBACK_PORT={_env_val!r} ā€” binding Spotify callback server on port {spotify_port}") + logger.info(f"[OAuth] SOULSYNC_SPOTIFY_CALLBACK_PORT={_env_val!r} ā€” binding Spotify callback server on port {spotify_port}") else: - print(f"[OAuth] SOULSYNC_SPOTIFY_CALLBACK_PORT not set ā€” using default port {spotify_port}") + logger.info(f"[OAuth] SOULSYNC_SPOTIFY_CALLBACK_PORT not set ā€” using default port {spotify_port}") try: bind_addr = ('0.0.0.0', spotify_port) spotify_server = HTTPServer(bind_addr, SpotifyCallbackHandler) _oauth_logger.info(f"Spotify OAuth callback server listening on {bind_addr[0]}:{bind_addr[1]}") - print(f"Started Spotify OAuth callback server on {bind_addr[0]}:{bind_addr[1]}") + logger.info(f"Started Spotify OAuth callback server on {bind_addr[0]}:{bind_addr[1]}") spotify_server.serve_forever() except OSError as e: _oauth_logger.error(f"Failed to start Spotify callback server on port {spotify_port}: {e} ā€” port may already be in use") - print(f"Failed to start Spotify callback server on port {spotify_port}: {e}") + logger.error(f"Failed to start Spotify callback server on port {spotify_port}: {e}") except Exception as e: _oauth_logger.error(f"Failed to start Spotify callback server: {e}") - print(f"Failed to start Spotify callback server: {e}") + logger.error(f"Failed to start Spotify callback server: {e}") # Tidal callback server class TidalCallbackHandler(BaseHTTPRequestHandler): def do_GET(self): - print("TIDAL CALLBACK SERVER RECEIVED REQUEST ") + logger.info("TIDAL CALLBACK SERVER RECEIVED REQUEST ") parsed_url = urllib.parse.urlparse(self.path) query_params = urllib.parse.parse_qs(parsed_url.query) - print(f"Callback path: {self.path}") + logger.info(f"Callback path: {self.path}") if 'code' in query_params: auth_code = query_params['code'][0] - print(f"Received Tidal authorization code: {auth_code[:10]}...") + logger.info(f"Received Tidal authorization code: {auth_code[:10]}...") # Exchange the authorization code for tokens try: @@ -51145,7 +51085,7 @@ def start_oauth_callback_servers(): temp_client.code_verifier = tidal_oauth_state["code_verifier"] temp_client.code_challenge = tidal_oauth_state["code_challenge"] - print(f"Restored PKCE - verifier: {temp_client.code_verifier[:20] if temp_client.code_verifier else 'None'}... challenge: {temp_client.code_challenge[:20] if temp_client.code_challenge else 'None'}...") + logger.info(f"Restored PKCE - verifier: {temp_client.code_verifier[:20] if temp_client.code_verifier else 'None'}... challenge: {temp_client.code_challenge[:20] if temp_client.code_challenge else 'None'}...") success = temp_client.fetch_token_from_code(auth_code) @@ -51165,7 +51105,7 @@ def start_oauth_callback_servers(): raise Exception("Failed to exchange authorization code for tokens") except Exception as e: - print(f"Tidal token processing error: {e}") + logger.error(f"Tidal token processing error: {e}") add_activity_item("", "Tidal Auth Failed", f"Token processing failed: {str(e)}", "Now") self.send_response(400) self.send_header('Content-type', 'text/html') @@ -51173,7 +51113,7 @@ def start_oauth_callback_servers(): self.wfile.write(f'

    Tidal Authentication Failed

    {str(e)}

    '.encode()) else: error = query_params.get('error', ['Unknown error'])[0] - print(f"Tidal OAuth error: {error}") + logger.error(f"Tidal OAuth error: {error}") add_activity_item("", "Tidal Auth Failed", f"OAuth error: {error}", "Now") self.send_response(400) self.send_header('Content-type', 'text/html') @@ -51187,18 +51127,18 @@ def start_oauth_callback_servers(): _env_val = os.environ.get('SOULSYNC_TIDAL_CALLBACK_PORT') tidal_port = int(_env_val) if _env_val else 8889 if _env_val: - print(f"[OAuth] SOULSYNC_TIDAL_CALLBACK_PORT={_env_val!r} ā€” binding Tidal callback server on port {tidal_port}") + logger.info(f"[OAuth] SOULSYNC_TIDAL_CALLBACK_PORT={_env_val!r} ā€” binding Tidal callback server on port {tidal_port}") else: - print(f"[OAuth] SOULSYNC_TIDAL_CALLBACK_PORT not set ā€” using default port {tidal_port}") + logger.info(f"[OAuth] SOULSYNC_TIDAL_CALLBACK_PORT not set ā€” using default port {tidal_port}") try: tidal_server = HTTPServer(('0.0.0.0', tidal_port), TidalCallbackHandler) - print(f"Started Tidal OAuth callback server on port {tidal_port}") - print(f"Tidal server listening on all interfaces, port {tidal_port}") + logger.info(f"Started Tidal OAuth callback server on port {tidal_port}") + logger.info(f"Tidal server listening on all interfaces, port {tidal_port}") tidal_server.serve_forever() except Exception as e: - print(f"Failed to start Tidal callback server: {e}") + logger.error(f"Failed to start Tidal callback server: {e}") import traceback - print(f"Full error: {traceback.format_exc()}") + logger.error(f"Full error: {traceback.format_exc()}") # Start both servers in background threads spotify_thread = threading.Thread(target=run_spotify_server, daemon=True) @@ -51207,7 +51147,7 @@ def start_oauth_callback_servers(): spotify_thread.start() tidal_thread.start() - print("OAuth callback servers started") + logger.info("OAuth callback servers started") # ================================================================================================ # MUSICBRAINZ ENRICHMENT - PHASE 5 WEB UI INTEGRATION @@ -51228,11 +51168,11 @@ try: mb_worker.start() if config_manager.get('musicbrainz_enrichment_paused', False): mb_worker.pause() - print("MusicBrainz enrichment worker initialized (paused ā€” restored from config)") + logger.info("MusicBrainz enrichment worker initialized (paused ā€” restored from config)") else: - print("MusicBrainz enrichment worker initialized and started") + logger.info("MusicBrainz enrichment worker initialized and started") except Exception as e: - print(f"MusicBrainz worker initialization failed: {e}") + logger.error(f"MusicBrainz worker initialization failed: {e}") mb_worker = None # --- MusicBrainz API Endpoints --- @@ -51305,11 +51245,11 @@ try: audiodb_worker.start() if config_manager.get('audiodb_enrichment_paused', False): audiodb_worker.pause() - print("AudioDB enrichment worker initialized (paused ā€” restored from config)") + logger.info("AudioDB enrichment worker initialized (paused ā€” restored from config)") else: - print("AudioDB enrichment worker initialized and started") + logger.info("AudioDB enrichment worker initialized and started") except Exception as e: - print(f"AudioDB worker initialization failed: {e}") + logger.error(f"AudioDB worker initialization failed: {e}") audiodb_worker = None # --- AudioDB API Endpoints --- @@ -51378,11 +51318,11 @@ try: discogs_worker.start() if config_manager.get('discogs_enrichment_paused', False): discogs_worker.pause() - print("Discogs enrichment worker initialized (paused ā€” restored from config)") + logger.info("Discogs enrichment worker initialized (paused ā€” restored from config)") else: - print("Discogs enrichment worker initialized and started") + logger.info("Discogs enrichment worker initialized and started") except Exception as e: - print(f"Discogs worker initialization failed: {e}") + logger.error(f"Discogs worker initialization failed: {e}") discogs_worker = None # --- Discogs API Endpoints --- @@ -51440,11 +51380,11 @@ try: deezer_worker.start() if config_manager.get('deezer_enrichment_paused', False): deezer_worker.pause() - print("Deezer enrichment worker initialized (paused ā€” restored from config)") + logger.info("Deezer enrichment worker initialized (paused ā€” restored from config)") else: - print("Deezer enrichment worker initialized and started") + logger.info("Deezer enrichment worker initialized and started") except Exception as e: - print(f"Deezer worker initialization failed: {e}") + logger.error(f"Deezer worker initialization failed: {e}") deezer_worker = None # --- Deezer API Endpoints --- @@ -51518,11 +51458,11 @@ try: spotify_enrichment_worker.paused = True # Set BEFORE start() to prevent race condition spotify_enrichment_worker.start() if spotify_enrichment_worker.paused: - print("Spotify enrichment worker initialized (paused ā€” restored from config)") + logger.info("Spotify enrichment worker initialized (paused ā€” restored from config)") else: - print("Spotify enrichment worker initialized and started") + logger.info("Spotify enrichment worker initialized and started") except Exception as e: - print(f"Spotify enrichment worker initialization failed: {e}") + logger.error(f"Spotify enrichment worker initialization failed: {e}") spotify_enrichment_worker = None # --- API Rate Monitor Endpoints --- @@ -51617,11 +51557,11 @@ try: itunes_enrichment_worker.start() if config_manager.get('itunes_enrichment_paused', False): itunes_enrichment_worker.pause() - print("iTunes enrichment worker initialized (paused ā€” restored from config)") + logger.info("iTunes enrichment worker initialized (paused ā€” restored from config)") else: - print("iTunes enrichment worker initialized and started") + logger.info("iTunes enrichment worker initialized and started") except Exception as e: - print(f"iTunes enrichment worker initialization failed: {e}") + logger.error(f"iTunes enrichment worker initialization failed: {e}") itunes_enrichment_worker = None # --- iTunes API Endpoints --- @@ -51693,11 +51633,11 @@ try: lastfm_worker.start() if config_manager.get('lastfm_enrichment_paused', False): lastfm_worker.pause() - print("Last.fm enrichment worker initialized (paused ā€” restored from config)") + logger.info("Last.fm enrichment worker initialized (paused ā€” restored from config)") else: - print("Last.fm enrichment worker initialized and started") + logger.info("Last.fm enrichment worker initialized and started") except Exception as e: - print(f"Last.fm worker initialization failed: {e}") + logger.error(f"Last.fm worker initialization failed: {e}") lastfm_worker = None # --- Last.fm API Endpoints --- @@ -51836,11 +51776,11 @@ try: genius_worker.paused = True genius_worker.start() if genius_worker.paused: - print("Genius enrichment worker initialized (paused ā€” restored from config)") + logger.info("Genius enrichment worker initialized (paused ā€” restored from config)") else: - print("Genius enrichment worker initialized and started") + logger.info("Genius enrichment worker initialized and started") except Exception as e: - print(f"Genius worker initialization failed: {e}") + logger.error(f"Genius worker initialization failed: {e}") genius_worker = None # --- Genius API Endpoints --- @@ -51913,11 +51853,11 @@ try: tidal_enrichment_worker.start() if config_manager.get('tidal_enrichment_paused', False): tidal_enrichment_worker.pause() - print("Tidal enrichment worker initialized (paused ā€” restored from config)") + logger.info("Tidal enrichment worker initialized (paused ā€” restored from config)") else: - print("Tidal enrichment worker initialized and started") + logger.info("Tidal enrichment worker initialized and started") except Exception as e: - print(f"Tidal worker initialization failed: {e}") + logger.error(f"Tidal worker initialization failed: {e}") tidal_enrichment_worker = None # --- Tidal Enrichment API Endpoints --- @@ -51987,11 +51927,11 @@ try: qobuz_enrichment_worker.start() if config_manager.get('qobuz_enrichment_paused', False): qobuz_enrichment_worker.pause() - print("Qobuz enrichment worker initialized (paused ā€” restored from config)") + logger.info("Qobuz enrichment worker initialized (paused ā€” restored from config)") else: - print("Qobuz enrichment worker initialized and started") + logger.info("Qobuz enrichment worker initialized and started") except Exception as e: - print(f"Qobuz worker initialization failed: {e}") + logger.error(f"Qobuz worker initialization failed: {e}") qobuz_enrichment_worker = None # --- Qobuz Enrichment API Endpoints --- @@ -52065,13 +52005,13 @@ try: hydrabase_worker = HydrabaseWorker(get_ws_and_lock=_get_hydrabase_ws_and_lock) hydrabase_worker.start() hydrabase_client = HydrabaseClient(get_ws_and_lock=_get_hydrabase_ws_and_lock) - print("Hydrabase P2P mirror worker and metadata client initialized") + logger.info("Hydrabase P2P mirror worker and metadata client initialized") # Update API blueprint references if hasattr(app, 'soulsync'): app.soulsync['hydrabase_client'] = hydrabase_client app.soulsync['hydrabase_worker'] = hydrabase_worker except Exception as e: - print(f"Hydrabase initialization failed: {e}") + logger.error(f"Hydrabase initialization failed: {e}") hydrabase_worker = None hydrabase_client = None @@ -52088,9 +52028,9 @@ try: _hydrabase_ws = _auto_ws # Don't auto-enable dev mode ā€” user must explicitly activate dev mode # Auto-connect just establishes the WebSocket for fallback/search tab use - print(f"Hydrabase auto-connected to {_hydra_cfg['url']}") + logger.info(f"Hydrabase auto-connected to {_hydra_cfg['url']}") except Exception as e: - print(f"Hydrabase auto-reconnect failed: {e}") + logger.error(f"Hydrabase auto-reconnect failed: {e}") # --- Hydrabase Worker API Endpoints --- @@ -52162,9 +52102,9 @@ try: soulid_db = MusicDatabase() soulid_worker = SoulIDWorker(database=soulid_db) soulid_worker.start() - print("SoulID worker initialized and started") + logger.info("SoulID worker initialized and started") except Exception as e: - print(f"SoulID worker initialization failed: {e}") + logger.error(f"SoulID worker initialization failed: {e}") soulid_worker = None @app.route('/api/soulid/status', methods=['GET']) @@ -52196,9 +52136,9 @@ try: navidrome_client=navidrome_client, ) listening_stats_worker.start() - print("Listening stats worker initialized and started") + logger.info("Listening stats worker initialized and started") except Exception as e: - print(f"Listening stats worker initialization failed: {e}") + logger.error(f"Listening stats worker initialization failed: {e}") listening_stats_worker = None # --- Stats API Endpoints --- @@ -52489,13 +52429,13 @@ def listening_stats_sync(): import threading def _do_sync(): try: - print("[Stats Sync] Starting manual poll...") + logger.info("[Stats Sync] Starting manual poll...") listening_stats_worker._poll() listening_stats_worker.stats['polls_completed'] += 1 listening_stats_worker.stats['last_poll'] = time.strftime('%Y-%m-%d %H:%M:%S') - print("[Stats Sync] Manual poll completed") + logger.info("[Stats Sync] Manual poll completed") except Exception as e: - print(f"[Stats Sync] Manual poll failed: {e}") + logger.error(f"[Stats Sync] Manual poll failed: {e}") import traceback traceback.print_exc() logger.error(f"Manual stats sync failed: {e}") @@ -52585,9 +52525,9 @@ try: repair_worker._progress_lock_ref = repair_job_progress_lock repair_worker._progress_states_ref = repair_job_progress_states repair_worker.start() - print("Repair worker initialized and started") + logger.info("Repair worker initialized and started") except Exception as e: - print(f"Repair worker initialization failed: {e}") + logger.error(f"Repair worker initialization failed: {e}") repair_worker = None # --- Repair Worker API Endpoints --- @@ -53888,11 +53828,11 @@ try: ) if config_manager.get('auto_import.enabled', False): auto_import_worker.start() - print("Auto-import worker started") + logger.info("Auto-import worker started") else: - print("Auto-import worker initialized (disabled)") + logger.info("Auto-import worker initialized (disabled)") except Exception as _ai_err: - print(f"Auto-import worker init failed: {_ai_err}") + logger.error(f"Auto-import worker init failed: {_ai_err}") @app.route('/api/auto-import/status', methods=['GET']) @@ -54119,13 +54059,13 @@ def _hydrabase_reconnect_loop(): ) _hydrabase_ws = ws _consecutive_failures = 0 - print(f"[Hydrabase] Auto-reconnected to {hydra_cfg['url']}") + logger.info(f"[Hydrabase] Auto-reconnected to {hydra_cfg['url']}") except Exception as e: _consecutive_failures += 1 if _consecutive_failures <= 3: - print(f"[Hydrabase] Reconnect attempt failed ({_consecutive_failures}): {e}") + logger.error(f"[Hydrabase] Reconnect attempt failed ({_consecutive_failures}): {e}") elif _consecutive_failures == 4: - print(f"[Hydrabase] Reconnect failing repeatedly ā€” suppressing further logs until success") + logger.error(f"[Hydrabase] Reconnect failing repeatedly ā€” suppressing further logs until success") except Exception: pass # Don't crash the monitor loop @@ -54470,10 +54410,10 @@ def _emit_live_log_loop(): _last_pos = {} # {source: file_position} _active_source = 'app' log_map = { - 'app': os.path.join('logs', 'app.log'), - 'post_processing': os.path.join('logs', 'post_processing.log'), - 'acoustid': os.path.join('logs', 'acoustid.log'), - 'source_reuse': os.path.join('logs', 'source_reuse.log'), + 'app': Path(_log_path), + 'acoustid': _log_dir / 'acoustid.log', + 'post_processing': _log_dir / 'post_processing.log', + 'source_reuse': _log_dir / 'source_reuse.log', } while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(0.5) @@ -54734,36 +54674,36 @@ def start_runtime_services(): if _runtime_started: return - print("Starting SoulSync runtime services...") + logger.info("Starting SoulSync runtime services...") # Dump SOULSYNC_* env vars for diagnostics (helps debug Docker/Unraid env issues) _soulsync_env = {k: v for k, v in os.environ.items() if k.startswith('SOULSYNC_')} if _soulsync_env: - print(f"[Startup] SOULSYNC environment variables: {_soulsync_env}") + logger.info(f"[Startup] SOULSYNC environment variables: {_soulsync_env}") else: - print("[Startup] No SOULSYNC_* environment variables detected") + logger.warning("[Startup] No SOULSYNC_* environment variables detected") # Start OAuth callback servers - print("Starting OAuth callback servers...") + logger.info("Starting OAuth callback servers...") start_oauth_callback_servers() # Startup diagnostics: Check and recover stuck flags - print("Running startup diagnostics...") + logger.info("Running startup diagnostics...") stuck_flags_recovered = check_and_recover_stuck_flags() if stuck_flags_recovered: - print("Recovered stuck flags from previous session") + logger.warning("Recovered stuck flags from previous session") else: - print("No stuck flags detected - system healthy") + logger.warning("No stuck flags detected - system healthy") # Start simple background monitor when server starts - print("Starting simple background monitor...") + logger.info("Starting simple background monitor...") start_simple_background_monitor() - print("Simple background monitor started (includes automatic search cleanup)") + logger.info("Simple background monitor started (includes automatic search cleanup)") # Wishlist/watchlist timers are now managed by AutomationEngine system automations # Pre-build import suggestions cache in background - print("Pre-building import suggestions cache...") + logger.info("Pre-building import suggestions cache...") start_import_suggestions_cache() # Initialize app start time for uptime tracking @@ -54773,26 +54713,26 @@ def start_runtime_services(): _register_automation_handlers() if automation_engine: try: - print("Starting automation engine...") + logger.info("Starting automation engine...") automation_engine.start() - print("Automation engine started") + logger.info("Automation engine started") try: automation_engine.emit('app_started', {}) except Exception: pass except AttributeError as e: - print(f"Automation engine failed to start: {e}") - print(" If using Docker, check that your volume mount is /app/data (not /app/database)") + logger.error(f"Automation engine failed to start: {e}") + logger.info(" If using Docker, check that your volume mount is /app/data (not /app/database)") logger.error(f"Automation engine start error (possible stale Docker volume): {e}") except Exception as e: - print(f"Automation engine failed to start: {e}") + logger.error(f"Automation engine failed to start: {e}") logger.error(f"Automation engine start error: {e}") # Add startup activity add_activity_item("", "System Started", "SoulSync Web UI Server initialized", "Now") # Start WebSocket background emitters - print("Starting WebSocket background emitters...") + logger.info("Starting WebSocket background emitters...") # Phase 1: Global pollers socketio.start_background_task(_emit_service_status_loop) socketio.start_background_task(_emit_watchlist_count_loop) @@ -54820,7 +54760,7 @@ def start_runtime_services(): socketio.start_background_task(_emit_rate_monitor_loop) # Live log tail ā€” streams new log lines to the log viewer socketio.start_background_task(_emit_live_log_loop) - print("WebSocket emitters started (Phase 1-7: global/dashboard/enrichment/tools/sync/automations/repair + rate monitor + live logs)") + logger.info("WebSocket emitters started (Phase 1-7: global/dashboard/enrichment/tools/sync/automations/repair + rate monitor + live logs)") _runtime_started = True @@ -54828,8 +54768,8 @@ def start_runtime_services(): # Direct execution: python web_server.py (dev/Windows fallback) # Production should use: gunicorn -c gunicorn.conf.py wsgi:application if _DIRECT_RUN: - print("Starting SoulSync Web UI Server...") - print("Open your browser and navigate to http://127.0.0.1:8008") - print("Tip: For production, use gunicorn -c gunicorn.conf.py wsgi:application") + logger.info("Starting SoulSync Web UI Server...") + logger.info("Open your browser and navigate to http://127.0.0.1:8008") + logger.info("Tip: For production, use gunicorn -c gunicorn.conf.py wsgi:application") start_runtime_services() socketio.run(app, host='0.0.0.0', port=8008, debug=False, allow_unsafe_werkzeug=True) diff --git a/webui/index.html b/webui/index.html index e8d14fc7..6961bf86 100644 --- a/webui/index.html +++ b/webui/index.html @@ -5098,28 +5098,28 @@ Variables: $albumartist, $artist, $artistletter, $album, $albumtype, - $title, $track, $disc (01), $discnum (1), $year, $quality (filename only) + $title, $track, $disc (01), $discnum (1), $year, $quality (filename only). Use ${var} to append text: ${albumtype}s ā†’ Albums
    - Variables: $albumartist, $artist, $artistletter, $title, $track (01), $album, $albumtype, $year, $quality (filename only) + Variables: $albumartist, $artist, $artistletter, $title, $track (01), $album, $albumtype, $year, $quality (filename only). Use ${var} to append text: ${albumtype}s ā†’ Singles
    - Variables: $playlist, $albumartist, $artist, $artistletter, $title, $year, $quality (filename only) + Variables: $playlist, $albumartist, $artist, $artistletter, $title, $year, $quality (filename only). Use ${var} to append text
    - Variables: $artist, $artistletter, $title, $year. Default: $artist/$title-video ā†’ Artist/Title-video.mp4 + Variables: $artist, $artistletter, $title, $year. Use ${var} to append text. Default: $artist/$title-video
    @@ -5142,6 +5142,30 @@ Full artist list is always preserved in file metadata tags.
    +
    + + + Separator between multiple artists in the ARTIST tag +
    +
    + + Write each artist as a separate tag value for Navidrome/Jellyfin multi-artist support +
    +
    + + Keep only primary artist in ARTIST tag, append others as (feat. ...) in title +
    +