Compare commits

...

53 commits

Author SHA1 Message Date
Abdulmohsen
c68646e266
Merge pull request #621 from arabcoders/dev
Some checks failed
native-build / build (amd64, ubuntu-latest) (push) Has been cancelled
native-build / build (amd64, windows-latest) (push) Has been cancelled
native-build / build (arm64, macos-latest) (push) Has been cancelled
native-build / build (arm64, ubuntu-latest) (push) Has been cancelled
native-build / build (arm64, windows-latest) (push) Has been cancelled
fix: setting simple_mode cookie was crashing http layer
2026-06-19 19:59:35 +03:00
arabcoders
3c571429e7 fix: seeting simple_mode cookie was crashing http layer 2026-06-19 19:43:44 +03:00
Abdulmohsen
0ba52fa38e
Merge pull request #620 from arabcoders/dev
Refactor: re-design simple mode
2026-06-19 18:50:15 +03:00
arabcoders
19f0b7819e refactor: improve logs view 2026-06-19 18:39:35 +03:00
arabcoders
3381ca3805 refactor: re-design simple mode toggle. 2026-06-19 17:41:04 +03:00
arabcoders
72f2373c42 refactor: update the history item in UI automaticly whenever a item_update received via sockets 2026-06-17 22:44:37 +03:00
Abdulmohsen
44f5f2eee0
Merge pull request #618 from arabcoders/dev
chore: use ty as type checker.
2026-06-14 19:35:40 +03:00
arabcoders
13424d1bcf ci: bump node version to 22 for eslint compatibility 2026-06-14 18:41:03 +03:00
arabcoders
3631947234 chore: use ty as type checker. 2026-06-14 18:35:03 +03:00
Abdulmohsen
aedeaf9a0a
Merge pull request #617 from arabcoders/dev
Feat: paginate queue
2026-06-14 18:29:27 +03:00
arabcoders
18f54a28c6 feat: paginate queue 2026-06-12 20:18:58 +03:00
arabcoders
db8d8663eb refactor: update some logging messages. 2026-06-11 23:54:15 +03:00
Abdulmohsen
a614a48108
Merge pull request #615 from arabcoders/dev
Some checks failed
native-build / build (amd64, ubuntu-latest) (push) Has been cancelled
native-build / build (amd64, windows-latest) (push) Has been cancelled
native-build / build (arm64, macos-latest) (push) Has been cancelled
native-build / build (arm64, ubuntu-latest) (push) Has been cancelled
native-build / build (arm64, windows-latest) (push) Has been cancelled
fix: breaking change between yt-dlp 2026.03.17 -> 2026.06.09
2026-06-11 18:03:12 +03:00
arabcoders
4f5ac8d8a0 fix: breaking change between yt-dlp 2026.03.17 -> 2026.06.09 due to CVE related to exec 2026-06-11 17:51:30 +03:00
arabcoders
c7fbe6b484 refactor: add item_progress event for queue status update 2026-06-11 08:18:08 +03:00
arabcoders
8c54ed6c0a refactor: remove folders from configuration endpoint 2026-06-10 21:46:41 +03:00
Abdulmohsen
9ada8b5a91
Merge pull request #613 from arabcoders/dev
Some checks failed
native-build / build (amd64, ubuntu-latest) (push) Has been cancelled
native-build / build (amd64, windows-latest) (push) Has been cancelled
native-build / build (arm64, macos-latest) (push) Has been cancelled
native-build / build (arm64, ubuntu-latest) (push) Has been cancelled
native-build / build (arm64, windows-latest) (push) Has been cancelled
fix: video progress bar on iOS would fail
2026-06-10 16:53:16 +03:00
arabcoders
a346ed69d9 chore: external packages update 2026-06-10 16:26:00 +03:00
arabcoders
3e663bd483 fix: video progress bar on iOS would fail 2026-06-09 18:54:13 +03:00
arabcoders
4b7230843e docs: update screenshots 2026-06-09 18:35:44 +03:00
arabcoders
196d2d4e32 feat: add share button 2026-06-09 18:30:39 +03:00
Abdulmohsen
a194b9bf28
Merge pull request #610 from arabcoders/dev
Some checks failed
native-build / build (amd64, ubuntu-latest) (push) Has been cancelled
native-build / build (amd64, windows-latest) (push) Has been cancelled
native-build / build (arm64, macos-latest) (push) Has been cancelled
native-build / build (arm64, ubuntu-latest) (push) Has been cancelled
native-build / build (arm64, windows-latest) (push) Has been cancelled
Refactor: minor improvements to the WebUI
2026-06-08 10:08:19 +03:00
arabcoders
d6318fca0f refactor: fix loading older logs 2026-06-08 09:56:21 +03:00
arabcoders
4881fabb15 feat: add YTP_DISABLE_EXEC to strip dangerous yt-dlp options 2026-06-08 09:29:31 +03:00
arabcoders
7a3c41b6bc refactor: update other uselect to use uselectmenu 2026-06-08 09:00:56 +03:00
arabcoders
473e45c55b refactor: use list with filtering for preset menus 2026-06-08 08:55:08 +03:00
arabcoders
4319be36f6 fix: disable file logging during tests 2026-06-08 08:44:25 +03:00
arabcoders
2efc09d587 refactor: improve log details view 2026-06-08 08:38:12 +03:00
arabcoders
acca33a7dc rerfactor: add page transition toggle 2026-06-08 07:53:05 +03:00
arabcoders
e61df14ec0 refactor: improve how cards look 2026-06-08 07:11:31 +03:00
arabcoders
0482df2fec chore: update external packages 2026-06-04 09:31:43 +03:00
arabcoders
50dd2d336c docs: screenshots updates 2026-06-01 07:44:41 +03:00
Abdulmohsen
6df1250a43
Merge pull request #609 from arabcoders/dev
feat: make log level runtime configurable
2026-05-31 21:07:00 +03:00
arabcoders
c70b3a46bd chore: update dependancies 2026-05-31 16:15:31 +03:00
arabcoders
10c18ff5b9 refactor: minor UI update for diagnostics page 2026-05-31 16:08:45 +03:00
arabcoders
9259119227 docs: document security recommendations 2026-05-29 17:39:29 +03:00
arabcoders
ab56a7d8c9 fix: startup crash if access long was turned off 2026-05-28 22:21:56 +03:00
arabcoders
fa8ba1af34 feat: make log level runtime managable. 2026-05-28 21:26:23 +03:00
arabcoders
1267dbaf6b refactor: use single logger namespace 2026-05-28 19:07:11 +03:00
arabcoders
39ed3d0361 refactor: add more context to the actual log message. 2026-05-28 17:56:28 +03:00
arabcoders
cf90db3b4c refactor: update log mesages to take advantage of JSONL 2026-05-27 23:53:42 +03:00
Abdulmohsen
ef8642ace7
Merge pull request #608 from arabcoders/dev
feat: add system diagnostics endpoint.
2026-05-26 19:49:47 +03:00
arabcoders
434d3e981d feat: add system diagnostics endpoint. 2026-05-26 19:22:36 +03:00
arabcoders
376e439115 docs: add info about youtube rss feeds 2026-05-26 16:15:29 +03:00
arabcoders
64fdcac0f7 refactor: implement re-extraction logic and process-safe handling for non-picklable objects. 2026-05-25 20:06:34 +03:00
Abdulmohsen
8e14258c7a
Merge pull request #607 from arabcoders/dev
Some checks failed
native-build / build (amd64, ubuntu-latest) (push) Has been cancelled
native-build / build (amd64, windows-latest) (push) Has been cancelled
native-build / build (arm64, macos-latest) (push) Has been cancelled
native-build / build (arm64, ubuntu-latest) (push) Has been cancelled
native-build / build (arm64, windows-latest) (push) Has been cancelled
Fix: recent change made fetch_info unpicklable
2026-05-24 22:07:41 +03:00
arabcoders
2e9684de5d refactor: standardize JSONL structure. 2026-05-24 21:19:25 +03:00
arabcoders
ca7227ffc5 refactor: adjust width and shrink behavior of filter input 2026-05-18 22:20:31 +03:00
arabcoders
3b3c8120b8 fix: recent change made fetch_info unpicklable 2026-05-18 22:12:13 +03:00
arabcoders
88db357b7f refactor: removed thumbnail proxying 2026-05-18 12:28:06 +03:00
arabcoders
854f5f4b42 refactor: use jsonl for loggng for better log view experience 2026-05-18 09:44:29 +03:00
arabcoders
d18145f1c5 refactor: make clear message more clear 2026-05-18 07:44:37 +03:00
arabcoders
3bd2a7bee7 refactor: minor ui cleanup 2026-05-17 20:21:58 +03:00
207 changed files with 14311 additions and 6085 deletions

View file

@ -15,7 +15,7 @@ on:
env:
BUN_VERSION: latest
NODE_VERSION: 20
NODE_VERSION: 22
PYTHON_VERSION: "3.13"
jobs:

View file

@ -29,7 +29,7 @@ env:
DOCKERHUB_SLUG: arabcoders/ytptube
GHCR_SLUG: ghcr.io/arabcoders/ytptube
BUN_VERSION: latest
NODE_VERSION: 20
NODE_VERSION: 22
PYTHON_VERSION: "3.13"
jobs:

View file

@ -39,7 +39,7 @@ jobs:
env:
PYTHON_VERSION: "3.13"
BUN_VERSION: latest
NODE_VERSION: 20
NODE_VERSION: 22
TAG_NAME: ${{ github.event.inputs.tag || github.ref_name }}
steps:

249
API.md
View file

@ -59,7 +59,6 @@ This document describes the available endpoints and their usage. All endpoints r
- [GET /api/player/subtitle/{file:.\*}.vtt](#get-apiplayersubtitlefilevtt)
- [GET /api/player/subtitles/manifest/{file:.\*}](#get-apiplayersubtitlesmanifestfile)
- [GET /api/player/subtitles/{source\_format}/{file:.\*}](#get-apiplayersubtitlessource_formatfile)
- [GET /api/thumbnail](#get-apithumbnail)
- [GET /api/file/ffprobe/{file:.\*}](#get-apifileffprobefile)
- [GET /api/file/info/{file:.\*}](#get-apifileinfofile)
- [GET /api/file/browser/{path:.\*}](#get-apifilebrowserpath)
@ -89,6 +88,8 @@ This document describes the available endpoints and their usage. All endpoints r
- [DELETE /api/conditions/{id}](#delete-apiconditionsid)
- [GET /api/logs](#get-apilogs)
- [GET /api/logs/stream](#get-apilogsstream)
- [GET /api/logs/level](#get-apilogslevel)
- [POST /api/logs/level/{level}](#post-apilogslevellevel)
- [GET /api/notifications/](#get-apinotifications)
- [GET /api/notifications/events/](#get-apinotificationsevents)
- [POST /api/notifications/](#post-apinotifications)
@ -100,6 +101,8 @@ This document describes the available endpoints and their usage. All endpoints r
- [POST /api/notifications/test](#post-apinotificationstest)
- [GET /api/yt-dlp/options](#get-apiyt-dlpoptions)
- [GET /api/system/configuration](#get-apisystemconfiguration)
- [GET /api/system/folders](#get-apisystemfolders)
- [GET /api/system/diagnostics](#get-apisystemdiagnostics)
- [GET /api/system/limits](#get-apisystemlimits)
- [POST /api/system/terminal](#post-apisystemterminal)
- [GET /api/system/terminal](#get-apisystemterminal)
@ -697,10 +700,16 @@ GET /api/history?type=queue&status=pending&order=ASC
This endpoint returns the current state of active downloads from memory.
**Query Parameters**:
- `limit` (optional): Override the configured queue display limit for this request. `0` means unlimited.
**Response**:
```json
{
"history_count": 0, // total number of completed items in history
"queue_count": 250, // total number of queued items
"queue_loaded": 100, // number of queued items included in this response
"queue_limit": 100, // effective display limit, 0 means unlimited
"queue":{
"id": "abc123",
"url": "https://example.com/video",
@ -1655,17 +1664,6 @@ Binary TS data (`Content-Type: video/mpegts`).
---
### GET /api/thumbnail
**Purpose**: Proxy/fetch a remote thumbnail image.
**Query Parameter**:
- `?url=<remote-thumbnail-url>`
**Response**:
Binary image data with the appropriate `Content-Type`.
---
### GET /api/file/ffprobe/{file:.*}
**Purpose**: Return the `ffprobe` data for a local file.
@ -2325,12 +2323,46 @@ Binary image data with appropriate headers
{
"logs": [
{
"timestamp": "2023-01-01T12:00:00Z",
"level": "INFO",
"message": "...",
...
},
...
"id": "<uuid>",
"datetime": "2026-05-18T12:00:00.000+00:00",
"level": "error",
"levelno": 40,
"logger": "ytptube",
"message": "Failed to download 'Example Video'.",
"exception": {
"type": "ValueError",
"message": "bad",
"file": "/app/library/downloads/queue_manager.py",
"line": 123,
"stack": [
{
"path": "/app/library/downloads/queue_manager.py",
"file": "queue_manager.py",
"module": "queue_manager",
"function": "start",
"line": 123
}
]
},
"source": {
"path": "/app/library/downloads/queue_manager.py",
"file": "queue_manager.py",
"module": "queue_manager",
"function": "start",
"line": 123
},
"fields": {
"download": {
"download_id": "abc123",
"media_id": "video-id",
"title": "Example Video",
"url": "https://example.test/video",
"preset": "default",
"status": "error",
"has_cookies": false
}
}
}
],
"offset": 0,
"limit": 100,
@ -2352,9 +2384,45 @@ Binary image data with appropriate headers
**Event Payload**:
```json
{
"id": "<sha256>",
"line": "<log line>",
"datetime": "2024-01-01T12:00:00.000000+00:00"
"id": "<uuid>",
"datetime": "2026-05-18T12:00:00.000+00:00",
"level": "error",
"levelno": 40,
"logger": "ytptube",
"message": "Failed to download 'Example Video'.",
"exception": {
"type": "ValueError",
"message": "bad",
"file": "/app/library/downloads/queue_manager.py",
"line": 123,
"stack": [
{
"path": "/app/library/downloads/queue_manager.py",
"file": "queue_manager.py",
"module": "queue_manager",
"function": "start",
"line": 123
}
]
},
"source": {
"path": "/app/library/downloads/queue_manager.py",
"file": "queue_manager.py",
"module": "queue_manager",
"function": "start",
"line": 123
},
"fields": {
"download": {
"download_id": "abc123",
"media_id": "video-id",
"title": "Example Video",
"url": "https://example.test/video",
"preset": "default",
"status": "error",
"has_cookies": false
}
}
}
```
@ -2362,6 +2430,31 @@ Binary image data with appropriate headers
---
### GET /api/logs/level
**Purpose**: Read the active runtime log level.
**Response**:
```json
{
"conf": "info",
"active": "info",
"levels": ["debug", "info", "warning", "error"]
}
```
---
### POST /api/logs/level/{level}
**Purpose**: Change the active runtime log level.
**Path Parameter**:
- `level`: One of `debug`, `info`, `warning`, `error`.
**Response**:
- `204 No Content` on success.
---
### GET /api/notifications/
**Purpose**: Retrieve notification targets with pagination.
@ -2542,55 +2635,86 @@ or an error:
---
### GET /api/system/configuration
**Purpose**: Retrieve comprehensive system configuration including app settings, presets, download fields, queue status, and folder structure.
**Purpose**: Retrieve system configuration.
**Response**:
```json
{
"app": {
"version": "...",
"download_path": "/path/to/downloads",
"base_path": "/",
...
},
"presets": [
{
"id": 1,
"name": "default",
"description": "...",
...
}
],
"dl_fields": [
{
"id": 1,
"name": "Title",
"field": "title",
"kind": "text",
...
}
],
"app": {...},
"presets": [...],
"dl_fields": [...],
"paused": false,
"folders": [
{"name": "folder1", "path": "folder1"},
{"name": "folder2", "path": "folder2"}
],
"history_count": 150,
"queue": [
{
"id": "abc123",
"url": "https://example.com/video",
"status": "pending",
...
}
]
"history_count": 150
}
```
---
### GET /api/system/folders
**Purpose**: List child directories for a given relative path within the download directory.
**Query Parameters**:
- `path=<relative-path>` (optional, default: root) - Relative path within the download directory.
**Response**:
```json
{
"path": "videos",
"folders": ["archive", "shorts", "2024"]
}
```
**Notes**:
- This endpoint combines multiple data sources into a single response for efficient initialization
- The `folders` array includes available download folders up to the configured depth limit
- The `queue` array contains active download items
- Results are cached server-side for a short time.
- Non-existent paths return an empty folder list.
---
### GET /api/system/diagnostics
**Purpose**: View system information.
**Response**:
```json
{
"status": "error",
"generated_at": 1713000000,
"summary": {
"total": 10,
"pass": 5,
"fail": 2,
"warn": 1,
"skip": 2,
"required_failed": 2
},
"runtime": {
"app_version": "1.0.0",
"app_branch": "main",
"app_commit_sha": "abcdef12",
"app_build_date": "20260526",
"started": 1712999900,
"uptime_seconds": 100,
"platform": "linux",
"platform_release": "6.8.0",
"platform_machine": "x86_64",
"python_version": "3.13.1",
"python_minimum": "3.13",
"is_native": false,
"console_enabled": false
},
"requirements": {
"python": {
"current": "3.13.1",
"required": "3.13",
"supported": true,
"note": ""
}
},
"checks": []
}
```
**Notes**:
- Unexpected collection errors are returned as an `error`.
---
@ -2602,7 +2726,6 @@ or an error:
{
"downloads": {
"paused": false,
"live_bypasses_limits": true,
"global": {
"limit": 20,
"active": 3,
@ -3345,7 +3468,7 @@ Emitted when a download item is moved between queue and history.
"data": {
"id": "abc123",
"from": "queue",
"to": "done"
"to": "history"
}
}
```

57
FAQ.md
View file

@ -3,6 +3,9 @@
Certain configuration values can be set via environment variables, using the `-e` parameter on the docker command line,
or the `environment:` section in `compose.yaml` file.
<details>
<summary>Click to expand</summary>
| Environment Variable | Description | Default |
| ------------------------------- | ------------------------------------------------------------------- | --------------------- |
| TZ | The timezone to use for the application | `(not_set)` |
@ -44,10 +47,10 @@ or the `environment:` section in `compose.yaml` file.
| YTP_FLARESOLVERR_CACHE_TTL | The cache TTL (in seconds) for FlareSolverr solutions | `600` |
| YTP_BASE_PATH | Set this if you are serving YTPTube from sub-folder | `/` |
| YTP_PREVENT_LIVE_PREMIERE | Prevents the initial youtube premiere stream from being downloaded | `false` |
| YTP_QUEUE_DISPLAY_LIMIT | Max queued downloads returned to the UI. `0` = unlimited | `100` |
| YTP_LIVE_PREMIERE_BUFFER | buffer time in minutes to add to video duration | `5` |
| YTP_TASKS_HANDLER_TIMER | The cron expression for the tasks handler timer | `15 */1 * * *` |
| YTP_TEMP_DISABLED | Disable temp files handling. | `false` |
| YTP_DOWNLOAD_PATH_DEPTH | How many subdirectories to show in auto complete. | `1` |
| YTP_ALLOW_INTERNAL_URLS | Allow requests to internal URLs | `false` |
| YTP_SIMPLE_MODE | Switch default interface to Simple mode. | `false` |
| YTP_STATIC_UI_PATH | Path to custom static UI files. | `(not_set)` |
@ -60,19 +63,20 @@ or the `environment:` section in `compose.yaml` file.
| YTP_THUMB_CONCURRENCY | The number of concurrent ffmpeg thumbnail generations allowed. | `2` |
| YTP_THUMB_GENERATE | Enable ffmpeg thumbnail generation when no local thumbnail exists. | `true` |
| YTP_THUMB_SIDECAR | Save generated thumbnails next to media instead of temp cache. | `false` |
| YTP_DISABLE_EXEC | Strip some dangerous yt-dlp options. | `false` |
</details>
> [!NOTE]
> To raise the maximum workers for specific extractor, you need to add a ENV variable that follows the pattern `YTP_MAX_WORKERS_FOR_<EXTRACTOR_NAME>`.
> The extractor name must be in uppercase, to know the extractor name, check the log for the specific extractor used for the download.
> The limit should not exceed the `YTP_MAX_WORKERS` value as it will be ignored.
> [!IMPORTANT]
> The env variable `YTP_SIMPLE_MODE` only control what being displayed for first time visitor, the users can still switch between the two modes via the WebUI settings page.
## Notes about YTP_AUTO_CLEAR_HISTORY_DAYS
- `0` days means no automatic clearing of the download history. lowest value that will trigger the clearing is `1` day.
- This setting will **NOT** delete the downloaded files, it will only clear the history from the database.
> To raise the worker limit for a specific extractor, set an env variable using this format: `YTP_MAX_WORKERS_FOR_<EXTRACTOR_NAME>`
> The extractor name must be uppercase. You can find the extractor name in the download logs. This value cannot be
> higher than `YTP_MAX_WORKERS`; higher values are ignored.
>
> `YTP_SIMPLE_MODE=true` only applies when the browser has no saved layout choice yet. Users can still choose a layout in
> WebUI Settings. `/?simple=1` forces and saves Simple for that browser.
>
> `YTP_AUTO_CLEAR_HISTORY_DAYS` `0` days means no automatic clearing of the download history. lowest value that will
> trigger the clearing is `1` day. This setting will **NOT** delete the downloaded files, it will only clear the
> history from the database.
# Browser extensions & bookmarklets
@ -119,6 +123,35 @@ As this is a simple basic authentication, if your browser doesn't show the promp
`http://username:password@your_ytptube_url:port`
# Security recommendations
YTPTube is designed for LAN and home-lab use behind a firewall or reverse proxy. The web interface and API are
unauthenticated by default because in a trusted network, auth adds friction without meaningful benefit. However,
if you expose YTPTube to the internet directly or via port forwarding **YOU MUST enable authentication**.
### Without auth, anyone who can reach the API can:
- Download arbitrary content through your IP and server.
- Delete or modify your downloaded files and database.
- Run arbitrary `yt-dlp` options, including `--exec`, which executes shell commands inside the container.
This is not a vulnerability, it's the intended design. The `cli` field passes options directly to `yt-dlp`,
a tool that by design can execute commands. Auth is the mechanism that controls who gets to use that power.
**If you expose YTPTube to untrusted networks**, do one of the following:
1. **Enable authentication** — set both `YTP_AUTH_USERNAME` and `YTP_AUTH_PASSWORD`.
2. **Put it behind a reverse proxy** with its own authentication layer (see [Run behind reverse proxy](#run-behind-reverse-proxy)).
3. **Keep it on a private network** with no public exposure.
YTPTube already gates other powerful features behind explicit opt-in: the built-in terminal, file browser actions and internal
URL requests for example. The `cli` field is no different, its power is by design, and access control is your responsibility.
> [!NOTE]
> If you choose to run without authentication but still want to reduce at least some impact, you can set
> `YTP_DISABLE_EXEC=true`. This strips some dangerous options at run time. However, understand that this is not a
> substitute for auth an unauthenticated API is still fully open for all other operations.
# I cant download anything
If you are receiving errors like:

View file

@ -44,20 +44,28 @@ Please read the [FAQ](FAQ.md) for more information.
# Installation
> [!IMPORTANT]
> By default YTPTube runs without authentication. If you expose it to the internet, **enable auth**. See [security recommendations](FAQ.md#security-recommendations).
## Run using docker command
```bash
mkdir -p ./{config,downloads/files,downloads/tmp} && docker run -itd --rm --user "${UID}:${UID}" --name ytptube \
mkdir -p ./{config,downloads/{files,tmp}} && docker run -itd --rm --user "${UID}:${UID}" --name ytptube \
-e YTP_TEMP_PATH=/downloads/tmp -e YTP_DOWNLOAD_PATH=/downloads/files \
-p 8081:8081 -v ./config:/config:rw -v ./downloads:/downloads:rw \
ghcr.io/arabcoders/ytptube:latest
```
Then you can access the WebUI at `http://localhost:8081`.
## Run using podman
> [!NOTE]
> If you are using `podman` instead of `docker`, you can use the same command, but you need to change the user to `0:0`
> it will appears to be running as root, but it will run as the user who started the container.
```bash
mkdir -p ./{config,downloads/{files,tmp}} && podman run -itd --rm --userns=keep-id --name ytptube \
-e YTP_TEMP_PATH=/downloads/tmp -e YTP_DOWNLOAD_PATH=/downloads/files \
-p 8081:8081 -v ./config:/config:rw -v ./downloads:/downloads:rw \
arabcoders/ytptube:latest
```
Then you can access the WebUI at `http://localhost:8081`.
## Using compose file
@ -67,6 +75,8 @@ The following is an example of a `compose.yaml` file that can be used to run YTP
services:
ytptube:
user: "${UID:-1000}:${UID:-1000}" # change this to your user id and group id.
# comment out the above line and uncomment the below line if you are using podman-compose.
#userns_mode: keep-id
image: ghcr.io/arabcoders/ytptube:latest
container_name: ytptube
restart: unless-stopped
@ -81,18 +91,14 @@ services:
```
> [!IMPORTANT]
> Make sure to change the `user` line to match your user id and group id.
> Make sure to change the `user` line to match your user id and group id in docker setups, or use `userns_mode: keep-id` in podman setups.
```bash
mkdir -p ./{config,downloads/files,downloads/tmp} && docker compose -f compose.yaml up -d
mkdir -p ./{config,downloads/{files,tmp}} && docker compose -f compose.yaml up -d
```
Then you can access the WebUI at `http://localhost:8081`.
> [!NOTE]
> you can use podman-compose instead of docker-compose, as it supports the same syntax. However, you should change the
> user to `0:0` it will appears to be running as root, but it will run as the user who started the container.
## Unraid
For `Unraid` users You can install the `Community Applications` plugin, and search for **ytptube** it comes
@ -106,17 +112,14 @@ For simple API documentation, you can refer to the [API documentation](API.md).
This project is not affiliated with yt-dlp or any other service.
Its a personal project designed to make downloading videos from the internet more convenient. Its not intended for
piracy or any unlawful use.
This is a personal project designed to make downloading videos from the internet more convenient for me. It is not
intended for piracy or any unlawful use. This project was built primarily for my own use and preferences.
AI-based tools may have been used to assist with parts of this project. Regardless of how a change is produced, every
change is reviewed and approved by the human maintainer before it is included.
AI-assisted tools are used in this project. If you are uncomfortable with this, you should not use this project.
This project was built primarily for my own needs and preferences. The UI might not be the most polished or visually
refined, but Im happy with it as it is. You can, however, create and load your own UI for complete customization.
Contributions are welcome, but I may decline changes that dont align with my vision for the project. Unsolicited pull
requests may be ignored. For suggestions or feature requests, please open a discussion or join the Discord server.
Contributions are welcome, but I may decline changes that do not interest me or do not align with my vision for this
project. Unsolicited pull requests will be closed. For suggestions or feature requests, please open a discussion or
join the Discord server.
# Social contact

View file

@ -16,7 +16,10 @@ def pytest_configure(config) -> None:
if getattr(config.option, "basetemp", None) is None:
config.option.basetemp = str(get_test_run_root() / "pytest")
os.environ["YTP_FILE_LOGGING"] = "false"
def pytest_unconfigure(config) -> None:
del config
os.environ.pop("YTP_FILE_LOGGING", None)
cleanup_test_run_root()

View file

@ -1,18 +1,18 @@
from __future__ import annotations
import json
import logging
from pathlib import Path
from typing import TYPE_CHECKING, Any, cast
from app.features.conditions.models import ConditionModel
from app.features.core.migration import Migration as FeatureMigration
from app.library.config import Config
from app.library.log import get_logger
if TYPE_CHECKING:
from app.features.conditions.repository import ConditionsRepository
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
class Migration(FeatureMigration):
@ -36,7 +36,11 @@ class Migration(FeatureMigration):
try:
items: list[dict] | None = json.loads(self._source_file.read_text())
except Exception as exc:
LOG.exception("Failed to read %s: %s. Ignoring", self._source_file, exc)
LOG.exception(
"Failed to read conditions migration file '%s'. Ignoring.",
self._source_file,
extra={"file_path": str(self._source_file), "exception_type": type(exc).__name__},
)
await self._move_file(self._source_file)
return
@ -54,7 +58,11 @@ class Migration(FeatureMigration):
await self._repo.create(normalized)
inserted += 1
except Exception as exc:
LOG.exception("Failed to insert condition '%s': %s", normalized.name, exc)
LOG.exception(
"Failed to insert condition '%s'.",
normalized.name,
extra={"condition_name": normalized.name, "exception_type": type(exc).__name__},
)
LOG.info("Migrated %s condition(s) from %s.", inserted, self._source_file)
await self._move_file(self._source_file)

View file

@ -1,31 +1,50 @@
from __future__ import annotations
import logging
from typing import TYPE_CHECKING, Any
from app.features.conditions.migration import Migration
from app.library.Singleton import Singleton
if TYPE_CHECKING:
from collections.abc import AsyncGenerator, Iterable
from collections.abc import Callable, Iterable
from contextlib import AbstractAsyncContextManager
from sqlalchemy.engine.result import Result
from sqlalchemy.ext.asyncio import AsyncSession
from sqlalchemy.sql.elements import ColumnElement
from sqlalchemy.sql.selectable import Select
SessionFactory = Callable[[], AbstractAsyncContextManager[AsyncSession]]
from sqlalchemy import delete, func, or_, select
from app.features.conditions.models import ConditionModel
from app.features.core.deps import get_session
from app.library.log import get_logger
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
def _model_from_payload(payload: dict[str, Any]) -> ConditionModel:
model = ConditionModel()
for key, value in payload.items():
if not hasattr(model, key):
msg = f"'{key}' is an invalid keyword argument for ConditionModel"
raise TypeError(msg)
setattr(model, key, value)
return model
def _coerce_model(payload: ConditionModel | dict[str, Any]) -> ConditionModel:
if isinstance(payload, ConditionModel):
return payload
return _model_from_payload(payload)
class ConditionsRepository(metaclass=Singleton):
def __init__(self, session: AsyncGenerator[AsyncSession] | None = None) -> None:
def __init__(self, session: SessionFactory | None = None) -> None:
self._migrated = False
self.session: AsyncGenerator[AsyncSession] = session or get_session
self.session: SessionFactory = session or get_session
async def run_migrations(self) -> None:
if self._migrated:
@ -38,7 +57,7 @@ class ConditionsRepository(metaclass=Singleton):
def get_instance() -> ConditionsRepository:
return ConditionsRepository()
async def list(self) -> list[ConditionModel]:
async def all(self) -> list[ConditionModel]:
async with self.session() as session:
result: Result[tuple[ConditionModel]] = await session.execute(
select(ConditionModel).order_by(ConditionModel.priority.desc(), ConditionModel.name.asc())
@ -93,11 +112,11 @@ class ConditionsRepository(metaclass=Singleton):
result: Result[tuple[ConditionModel]] = await session.execute(query.limit(1))
return result.scalar_one_or_none()
async def create(self, payload: ConditionModel | dict) -> ConditionModel:
async def create(self, payload: ConditionModel | dict[str, Any]) -> ConditionModel:
async with self.session() as session:
model: ConditionModel = ConditionModel(**payload) if isinstance(payload, dict) else payload
model = _coerce_model(payload)
if model.id is not None:
model.id = None
model.id = None # ty: ignore
if await self.get_by_name(name=model.name) is not None:
msg: str = f"Condition with name '{model.name}' already exists."
@ -160,13 +179,11 @@ class ConditionsRepository(metaclass=Singleton):
await session.commit()
return model
async def replace_all(self, items: Iterable[dict | ConditionModel]) -> list[ConditionModel]:
async def replace_all(self, items: Iterable[dict[str, Any] | ConditionModel]) -> list[ConditionModel]:
async with self.session() as session:
try:
await session.execute(delete(ConditionModel))
models: list[ConditionModel] = [
ConditionModel(**item) if isinstance(item, dict) else item for item in items
]
models: list[ConditionModel] = [_coerce_model(item) for item in items]
session.add_all(models)
await session.commit()
except Exception:

View file

@ -1,5 +1,4 @@
import asyncio
import logging
from collections import OrderedDict
from typing import Any
@ -15,10 +14,11 @@ from app.library.cache import Cache
from app.library.config import Config
from app.library.encoder import Encoder
from app.library.Events import EventBus, Events
from app.library.log import get_logger
from app.library.router import route
from app.library.Utils import validate_url
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
def _model(model: Any) -> Condition:
@ -115,18 +115,44 @@ async def conditions_test(request: Request, encoder: Encoder, cache: Cache, conf
else:
data = cache.get(key)
except Exception as e:
LOG.exception(e)
LOG.exception(
"Failed to extract video info for condition check '%s'.",
cond,
extra={
"route": "conditions.match",
"condition": cond,
"url": url,
"preset": preset,
"exception_type": type(e).__name__,
},
)
return web.json_response(
data={"error": f"Failed to extract video info. '{e!s}'"},
status=web.HTTPInternalServerError.status_code,
)
if not isinstance(data, dict):
return web.json_response(
data={"error": "Failed to extract video info."},
status=web.HTTPInternalServerError.status_code,
)
try:
from app.features.ytdlp.mini_filter import match_str
status: bool = match_str(cond, data)
except Exception as e:
LOG.exception(e)
LOG.exception(
"Failed to evaluate condition '%s'.",
cond,
extra={
"route": "conditions.match",
"condition": cond,
"url": url,
"preset": preset,
"exception_type": type(e).__name__,
},
)
return web.json_response(
data={"error": str(e)},
status=web.HTTPBadRequest.status_code,

View file

@ -1,19 +1,19 @@
import logging
from collections.abc import Iterable
from numbers import Number
from aiohttp import web
from app.features.conditions.models import ConditionModel
from app.features.conditions.repository import ConditionsRepository
from app.features.conditions.schemas import Condition
from app.features.ytdlp.mini_filter import match_str
from app.library.Events import EventBus, Events
from app.library.log import get_logger
from app.library.Singleton import Singleton
LOG: logging.Logger = logging.getLogger("feature.conditions")
LOG = get_logger()
def _ignored_identifiers(ignore_conditions: Iterable[str | Number] | None) -> tuple[set[str], bool]:
def _ignored_identifiers(ignore_conditions: Iterable[str | int | float] | None) -> tuple[set[str], bool]:
ignored: set[str] = set()
ignore_all = False
@ -21,7 +21,7 @@ def _ignored_identifiers(ignore_conditions: Iterable[str | Number] | None) -> tu
return ignored, ignore_all
for value in ignore_conditions:
if isinstance(value, bool) or not isinstance(value, (str, Number)):
if isinstance(value, bool) or not isinstance(value, (str, int, float)):
continue
identifier = str(value).strip()
@ -55,7 +55,7 @@ class Conditions(metaclass=Singleton):
EventBus.get_instance().subscribe(Events.STARTED, handle_event, "ConditionsRepository.run_migrations")
async def get_all(self) -> list[ConditionModel]:
return await self._repo.list()
return await self._repo.all()
async def save(self, item: ConditionModel | dict) -> ConditionModel:
"""
@ -80,7 +80,7 @@ class Conditions(metaclass=Singleton):
if item.id is None or 0 == item.id:
model = await repo.create(item)
else:
model = await repo.update(item.id, item.serialize())
model = await repo.update(item.id, Condition.model_validate(item).model_dump())
except KeyError as exc:
raise ValueError(str(exc)) from exc
@ -113,13 +113,15 @@ class Conditions(metaclass=Singleton):
repo = self._repo
return await repo.get(identifier)
async def match(self, info: dict, ignore_conditions: Iterable[str | Number] | None = None) -> ConditionModel | None:
async def match(
self, info: dict, ignore_conditions: Iterable[str | int | float] | None = None
) -> ConditionModel | None:
"""
Check if any condition matches the info dict.
Args:
info (dict): The info dict to check.
ignore_conditions (Iterable[str | Number] | None): Condition ids or names to skip for this match.
ignore_conditions (Iterable[str | int | float] | None): Condition ids or names to skip for this match.
Returns:
Condition|None: The condition if found, None otherwise.
@ -133,7 +135,7 @@ class Conditions(metaclass=Singleton):
return None
repo = self._repo
items: list[ConditionModel] = await repo.list()
items: list[ConditionModel] = await repo.all()
if len(items) < 1:
return None
@ -145,17 +147,29 @@ class Conditions(metaclass=Singleton):
continue
if not item.filter:
LOG.error(f"Filter is empty for '{item.name}'.")
LOG.error(
"Filter is empty for '%s'.", item.name, extra={"condition_id": item.id, "condition_name": item.name}
)
continue
try:
if not match_str(item.filter, info):
continue
LOG.debug(f"Matched '{item.id}: {item.name}' with filter '{item.filter}'.")
LOG.debug(
"Matched '%s: %s' with filter '%s'.",
item.id,
item.name,
item.filter,
extra={"condition_id": item.id, "condition_name": item.name, "filter": item.filter},
)
return item
except Exception as e:
LOG.error(f"Failed to evaluate '{item.id}: {item.name}'. '{e!s}'.")
LOG.exception(
"Failed to evaluate condition '%s'.",
item.name,
extra={"condition_id": item.id, "condition_name": item.name, "exception_type": type(e).__name__},
)
continue
return None
@ -175,7 +189,7 @@ class Conditions(metaclass=Singleton):
if not info or not isinstance(info, dict) or len(info) < 1:
return None
if not (item := await self.get(identifier)) or not item.enabled or not item.filter:
if not (item := await self.get(str(identifier))) or not item.enabled or not item.filter:
return None
return item if match_str(item.filter, info) else None

View file

@ -6,6 +6,7 @@ import pytest
import pytest_asyncio
from types import SimpleNamespace
import pytest
from typing import Any
from aiohttp import web
from aiohttp.test_utils import make_mocked_request
@ -39,13 +40,13 @@ async def repo():
def _json_request(path: str, payload: object) -> web.Request:
request = make_mocked_request("POST", path)
mock_request: Any = make_mocked_request("POST", path)
async def _json() -> object:
return payload
request.json = _json # type: ignore[attr-defined]
return request
mock_request.json = _json
return mock_request
class TestAllowInternalUrlsScope:
@ -208,7 +209,7 @@ class TestConditionsRepository:
await repo.create({"name": "A", "filter": "test", "priority": 1})
await repo.create({"name": "C", "filter": "test", "priority": 2})
items = await repo.list()
items = await repo.all()
assert items[0].name == "C", "Highest priority should be first"
assert items[1].name == "A", "Same priority sorted alphabetically"
@ -240,6 +241,6 @@ class TestConditionsRepository:
assert len(result) == 2, "Should create 2 new conditions"
all_items = await repo.list()
all_items = await repo.all()
assert len(all_items) == 2, "Should only have new conditions"
assert all_items[0].name in ["New 1", "New 2"], "Should only have new items"

View file

@ -1,15 +1,16 @@
from __future__ import annotations
import abc
import logging
import time
from pathlib import Path
from typing import TYPE_CHECKING
from app.library.log import get_logger
if TYPE_CHECKING:
from app.library.config import Config
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
class Migration(abc.ABC):
@ -26,7 +27,11 @@ class Migration(abc.ABC):
try:
await self.migrate()
except Exception as exc:
LOG.exception("Feature migration '%s' failed: %s", self.name, exc)
LOG.exception(
"Feature migration '%s' failed.",
self.name,
extra={"feature": self.name, "exception_type": type(exc).__name__},
)
return False
return True

View file

@ -3,7 +3,7 @@ from __future__ import annotations
from datetime import UTC, datetime
from sqlalchemy import DateTime as SQLADateTime
from sqlalchemy import TypeDecorator
from sqlalchemy import Dialect, TypeDecorator
from sqlalchemy.orm import DeclarativeBase
@ -20,16 +20,18 @@ class UTCDateTime(TypeDecorator):
impl = SQLADateTime
cache_ok = True
def process_bind_param(self, value: datetime | None, _dialect) -> datetime | None:
def process_bind_param(self, value: datetime | None, dialect: Dialect) -> datetime | None:
"""Convert datetime to UTC before storing."""
_ = dialect
if value is not None:
if value.tzinfo is None:
return value.replace(tzinfo=UTC)
return value.astimezone(UTC).replace(tzinfo=None)
return value
def process_result_value(self, value: datetime | None, _dialect) -> datetime | None:
def process_result_value(self, value: datetime | None, dialect: Dialect) -> datetime | None:
"""Ensure datetime is timezone-aware (UTC) when loading."""
_ = dialect
if value is not None and value.tzinfo is None:
return value.replace(tzinfo=UTC)
return value

View file

@ -1,18 +1,18 @@
from __future__ import annotations
import json
import logging
from pathlib import Path
from typing import TYPE_CHECKING, Any, cast
from app.features.core.migration import Migration as FeatureMigration
from app.features.dl_fields.schemas import DLField
from app.library.config import Config
from app.library.log import get_logger
if TYPE_CHECKING:
from app.features.dl_fields.repository import DLFieldsRepository
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
class Migration(FeatureMigration):
@ -36,7 +36,11 @@ class Migration(FeatureMigration):
try:
items: list[dict[str, Any]] | None = json.loads(self._source_file.read_text())
except Exception as exc:
LOG.exception("Failed to read %s: %s. Ignoring", self._source_file, exc)
LOG.exception(
"Failed to read download fields migration file '%s'. Ignoring.",
self._source_file,
extra={"file_path": str(self._source_file), "exception_type": type(exc).__name__},
)
await self._move_file(self._source_file)
return
@ -54,7 +58,11 @@ class Migration(FeatureMigration):
await self._repo.create(normalized)
inserted += 1
except Exception as exc:
LOG.exception("Failed to insert dl field '%s': %s", normalized["name"], exc)
LOG.exception(
"Failed to insert download field '%s'.",
normalized["name"],
extra={"field_name": normalized["name"], "exception_type": type(exc).__name__},
)
LOG.info("Migrated %s dl field(s) from %s.", inserted, self._source_file)
await self._move_file(self._source_file)

View file

@ -1,30 +1,49 @@
from __future__ import annotations
import logging
from typing import TYPE_CHECKING, Any
from typing import TYPE_CHECKING, Any, cast
from sqlalchemy import delete, func, or_, select
from app.features.core.deps import get_session
from app.features.dl_fields.migration import Migration
from app.features.dl_fields.models import DLFieldModel
from app.library.log import get_logger
from app.library.Singleton import Singleton
if TYPE_CHECKING:
from collections.abc import AsyncGenerator, Iterable
from collections.abc import Callable, Iterable
from contextlib import AbstractAsyncContextManager
from sqlalchemy.engine.result import Result
from sqlalchemy.ext.asyncio import AsyncSession
from sqlalchemy.sql.elements import ColumnElement
from sqlalchemy.sql.selectable import Select
LOG: logging.Logger = logging.getLogger(__name__)
SessionFactory = Callable[[], AbstractAsyncContextManager[AsyncSession]]
LOG = get_logger()
def _model_from_payload(payload: dict[str, Any]) -> DLFieldModel:
model = DLFieldModel()
for key, value in payload.items():
if not hasattr(model, key):
msg = f"'{key}' is an invalid keyword argument for DLFieldModel"
raise TypeError(msg)
setattr(model, key, value)
return model
def _coerce_model(payload: DLFieldModel | dict[str, Any]) -> DLFieldModel:
if isinstance(payload, DLFieldModel):
return payload
return _model_from_payload(payload)
class DLFieldsRepository(metaclass=Singleton):
def __init__(self, session: AsyncGenerator[AsyncSession] | None = None) -> None:
def __init__(self, session: SessionFactory | None = None) -> None:
self._migrated = False
self.session: AsyncGenerator[AsyncSession] = session or get_session
self.session: SessionFactory = session or get_session
async def run_migrations(self) -> None:
if self._migrated:
@ -37,7 +56,7 @@ class DLFieldsRepository(metaclass=Singleton):
def get_instance() -> DLFieldsRepository:
return DLFieldsRepository()
async def list(self) -> list[DLFieldModel]:
async def all(self) -> list[DLFieldModel]:
async with self.session() as session:
result: Result[tuple[DLFieldModel]] = await session.execute(
select(DLFieldModel).order_by(DLFieldModel.order.asc(), DLFieldModel.name.asc())
@ -90,9 +109,9 @@ class DLFieldsRepository(metaclass=Singleton):
result: Result[tuple[DLFieldModel]] = await session.execute(query.limit(1))
return result.scalar_one_or_none()
async def create(self, payload: DLFieldModel | dict) -> DLFieldModel:
async def create(self, payload: DLFieldModel | dict[str, Any]) -> DLFieldModel:
async with self.session() as session:
model: DLFieldModel = DLFieldModel(**payload) if isinstance(payload, dict) else payload
model = _coerce_model(payload)
if await self.get_by_name(name=model.name) is not None:
msg: str = f"DL field with name '{model.name}' already exists."
@ -153,13 +172,16 @@ class DLFieldsRepository(metaclass=Singleton):
await session.commit()
return model
async def replace_all(self, items: Iterable[dict | DLFieldModel]) -> list[DLFieldModel]:
async def replace_all(self, items: Iterable[dict[str, Any] | DLFieldModel]) -> list[DLFieldModel]:
async with self.session() as session:
try:
await session.execute(delete(DLFieldModel))
models: list[DLFieldModel] = [
DLFieldModel(**item) if isinstance(item, dict) else item for item in items
]
models: list[DLFieldModel] = []
for item in items:
if isinstance(item, dict):
models.append(DLFieldModel(**cast("dict[str, Any]", item)))
else:
models.append(item)
session.add_all(models)
await session.commit()
except Exception:

View file

@ -1,4 +1,3 @@
import logging
from typing import Any
from aiohttp import web
@ -11,9 +10,10 @@ from app.features.dl_fields.schemas import DLField, DLFieldList, DLFieldPatch
from app.features.dl_fields.service import DLFields
from app.library.encoder import Encoder
from app.library.Events import EventBus, Events
from app.library.log import get_logger
from app.library.router import route
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
def _model(model: Any) -> DLField:

View file

@ -1,18 +1,18 @@
from __future__ import annotations
import logging
from typing import TYPE_CHECKING, Any
from app.features.dl_fields.models import DLFieldModel
from app.features.dl_fields.repository import DLFieldsRepository
from app.features.dl_fields.schemas import DLField
from app.library.Events import EventBus, Events
from app.library.log import get_logger
from app.library.Singleton import Singleton
if TYPE_CHECKING:
from aiohttp import web
LOG: logging.Logger = logging.getLogger("feature.dl_fields")
LOG = get_logger()
class DLFields(metaclass=Singleton):
@ -33,10 +33,10 @@ class DLFields(metaclass=Singleton):
EventBus.get_instance().subscribe(Events.STARTED, handle_event, "DLFieldsRepository.run_migrations")
async def get_all(self) -> list[DLFieldModel]:
return await self._repo.list()
return await self._repo.all()
async def get_all_serialized(self) -> list[dict[str, Any]]:
items = await self._repo.list()
items = await self._repo.all()
return [DLField.model_validate(item).model_dump() for item in items]
async def save(self, item: DLField | dict) -> DLFieldModel:

View file

@ -204,7 +204,7 @@ class TestDLFieldsRepository:
await repo.create({"name": "a", "description": "a", "field": "--a", "kind": "text", "order": 1})
await repo.create({"name": "c", "description": "c", "field": "--c", "kind": "text", "order": 0})
items = await repo.list()
items = await repo.all()
assert items[0].name == "c", "Lowest order should be first"
assert items[1].name == "a", "Same order sorted alphabetically"
@ -243,6 +243,6 @@ class TestDLFieldsRepository:
assert len(result) == 2, "Should create 2 new fields"
all_items = await repo.list()
all_items = await repo.all()
assert len(all_items) == 2, "Should only have new fields"
assert {item.name for item in all_items} == {"new_1", "new_2"}, "Should only have new items"

View file

@ -1,7 +1,6 @@
from __future__ import annotations
import json
import logging
from pathlib import Path
from typing import TYPE_CHECKING, Any, cast
@ -9,11 +8,12 @@ from app.features.core.migration import Migration as FeatureMigration
from app.features.notifications.schemas import NotificationEvents
from app.features.presets.service import Presets
from app.library.config import Config
from app.library.log import get_logger
if TYPE_CHECKING:
from app.features.notifications.repository import NotificationsRepository
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
class Migration(FeatureMigration):
@ -37,7 +37,11 @@ class Migration(FeatureMigration):
try:
items: list[dict] | None = json.loads(self._source_file.read_text())
except Exception as exc:
LOG.exception("Failed to read %s: %s. Ignoring", self._source_file, exc)
LOG.exception(
"Failed to read notifications migration file '%s'. Ignoring.",
self._source_file,
extra={"file_path": str(self._source_file), "exception_type": type(exc).__name__},
)
await self._move_file(self._source_file)
return
@ -56,7 +60,11 @@ class Migration(FeatureMigration):
await self._repo.create(normalized)
inserted += 1
except Exception as exc:
LOG.exception("Failed to insert notification '%s': %s", normalized.get("name"), exc)
LOG.exception(
"Failed to insert notification target '%s'.",
normalized.get("name"),
extra={"target_name": normalized.get("name"), "exception_type": type(exc).__name__},
)
LOG.info("Migrated %s notification target(s) from %s.", inserted, self._source_file)
await self._move_file(self._source_file)

View file

@ -1,6 +1,5 @@
from __future__ import annotations
import logging
from typing import TYPE_CHECKING, Any
from sqlalchemy import func, or_, select
@ -8,23 +7,43 @@ from sqlalchemy import func, or_, select
from app.features.core.deps import get_session
from app.features.notifications.migration import Migration
from app.features.notifications.models import NotificationModel
from app.library.log import get_logger
from app.library.Singleton import Singleton
if TYPE_CHECKING:
from collections.abc import AsyncGenerator
from collections.abc import Callable
from contextlib import AbstractAsyncContextManager
from sqlalchemy.engine.result import Result
from sqlalchemy.ext.asyncio import AsyncSession
from sqlalchemy.sql.elements import ColumnElement
from sqlalchemy.sql.selectable import Select
LOG: logging.Logger = logging.getLogger(__name__)
SessionFactory = Callable[[], AbstractAsyncContextManager[AsyncSession]]
LOG = get_logger()
def _model_from_payload(payload: dict[str, Any]) -> NotificationModel:
model = NotificationModel()
for key, value in payload.items():
if not hasattr(model, key):
msg = f"'{key}' is an invalid keyword argument for NotificationModel"
raise TypeError(msg)
setattr(model, key, value)
return model
def _coerce_model(payload: NotificationModel | dict[str, Any]) -> NotificationModel:
if isinstance(payload, NotificationModel):
return payload
return _model_from_payload(payload)
class NotificationsRepository(metaclass=Singleton):
def __init__(self, session: AsyncGenerator[AsyncSession] | None = None) -> None:
def __init__(self, session: SessionFactory | None = None) -> None:
self._migrated = False
self.session: AsyncGenerator[AsyncSession] = session or get_session
self.session: SessionFactory = session or get_session
async def run_migrations(self) -> None:
if self._migrated:
@ -37,7 +56,7 @@ class NotificationsRepository(metaclass=Singleton):
def get_instance() -> NotificationsRepository:
return NotificationsRepository()
async def list(self) -> list[NotificationModel]:
async def all(self) -> list[NotificationModel]:
async with self.session() as session:
result: Result[tuple[NotificationModel]] = await session.execute(
select(NotificationModel).order_by(NotificationModel.name.asc())
@ -92,11 +111,11 @@ class NotificationsRepository(metaclass=Singleton):
result: Result[tuple[NotificationModel]] = await session.execute(query.limit(1))
return result.scalar_one_or_none()
async def create(self, payload: NotificationModel | dict) -> NotificationModel:
async def create(self, payload: NotificationModel | dict[str, Any]) -> NotificationModel:
async with self.session() as session:
model: NotificationModel = NotificationModel(**payload) if isinstance(payload, dict) else payload
model = _coerce_model(payload)
if model.id is not None:
model.id = None
model.id = None # ty: ignore
if await self.get_by_name(name=model.name) is not None:
msg: str = f"Notification target with name '{model.name}' already exists."

View file

@ -1,4 +1,3 @@
import logging
from typing import Any
from aiohttp import web
@ -11,9 +10,10 @@ from app.features.notifications.schemas import Notification, NotificationEvents,
from app.features.notifications.service import Notifications
from app.library.encoder import Encoder
from app.library.Events import EventBus, Events
from app.library.log import get_logger
from app.library.router import route
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
def _model(model: Any) -> Notification:

View file

@ -1,10 +1,8 @@
from __future__ import annotations
import asyncio
import logging
import traceback
from pathlib import Path
from typing import TYPE_CHECKING, Any
from typing import TYPE_CHECKING, Any, cast
from app.features.notifications.models import NotificationModel
from app.features.notifications.repository import NotificationsRepository
@ -23,6 +21,7 @@ from app.library.encoder import Encoder
from app.library.Events import Event, EventBus, Events
from app.library.httpx_client import async_client
from app.library.ItemDTO import Item, ItemDTO
from app.library.log import get_logger
from app.library.Singleton import Singleton
if TYPE_CHECKING:
@ -31,7 +30,7 @@ if TYPE_CHECKING:
import httpx
from aiohttp import web
LOG: logging.Logger = logging.getLogger("feature.notifications")
LOG = get_logger()
class Notifications(metaclass=Singleton):
@ -65,10 +64,10 @@ class Notifications(metaclass=Singleton):
await self._repo.run_migrations()
EventBus.get_instance().subscribe(Events.STARTED, handle_event, "NotificationsRepository.run_migrations")
EventBus.get_instance().subscribe(NotificationEvents.events(), self.emit, f"{__class__.__name__}.emit")
EventBus.get_instance().subscribe(NotificationEvents.events(), self.emit, f"{type(self).__name__}.emit")
async def list(self) -> list[NotificationModel]:
return await self._repo.list()
async def all(self) -> list[NotificationModel]:
return await self._repo.all()
async def list_paginated(self, page: int, per_page: int) -> tuple[list[NotificationModel], int, int, int]:
return await self._repo.list_paginated(page, per_page)
@ -93,8 +92,8 @@ class Notifications(metaclass=Singleton):
async def delete(self, identifier: int | str) -> NotificationModel:
return await self._repo.delete(identifier)
async def send(self, ev: Event, wait: bool = True) -> list[dict] | list[Awaitable[dict]]:
targets = await self._repo.list()
async def send(self, ev: Event, wait: bool = True) -> list[dict | Awaitable[dict]]:
targets = await self._repo.all()
if len(targets) < 1:
return []
@ -127,7 +126,7 @@ class Notifications(metaclass=Singleton):
if wait:
return await asyncio.gather(*tasks)
return tasks
return cast("list[dict | Awaitable[dict]]", tasks)
def emit(self, e: Event, _, **__) -> None:
if not NotificationEvents.is_valid(e.event):
@ -272,14 +271,27 @@ class Notifications(metaclass=Singleton):
if not status:
msg = "Apprise failed to send notification."
raise RuntimeError(msg) # noqa: TRY301
self._raise_apprise_error(msg)
except Exception as exc:
LOG.exception(exc)
LOG.error("Error sending Apprise notification: %s", exc)
LOG.exception(
"Failed to send Apprise notification for event '%s'.",
ev.event,
extra={
"event_id": ev.id,
"event": ev.event,
"target_count": len(targets),
"targets": [t.name for t in targets],
"exception_type": type(exc).__name__,
},
)
return {"error": str(exc), "event": ev.event, "id": ev.id, "targets": [t.name for t in targets]}
return {}
@staticmethod
def _raise_apprise_error(msg: str) -> None:
raise RuntimeError(msg)
async def _send(self, target: Notification, ev: Event) -> dict:
try:
LOG.info("Sending notification event '%s: %s' to '%s'.", ev.event, ev.id, target.name)
@ -335,14 +347,17 @@ class Notifications(metaclass=Singleton):
return resp_data
except Exception as exc:
err_msg = str(exc) or type(exc).__name__
tb = "".join(traceback.format_exception(type(exc), exc, exc.__traceback__))
LOG.error(
"Error sending notification event '%s: %s' to '%s'. '%s'. %s",
LOG.exception(
"Failed to send notification event '%s: %s' to '%s'.",
ev.event,
ev.id,
target.name,
err_msg,
tb,
extra={
"event_id": ev.id,
"event": ev.event,
"target_name": target.name,
"url": target.request.url,
"exception_type": type(exc).__name__,
},
)
return {"url": target.request.url, "status": 500, "text": str(ev)}

View file

@ -35,7 +35,7 @@ class TestNotificationsRepository:
@pytest.mark.asyncio
async def test_list_empty(self, repo):
"""List returns empty when no notifications exist."""
notifications = await repo.list()
notifications = await repo.all()
assert notifications == [], "Should return empty list when no notifications exist"
@pytest.mark.asyncio

View file

@ -1,7 +1,6 @@
from __future__ import annotations
import json
import logging
from pathlib import Path
from typing import TYPE_CHECKING, Any
@ -9,11 +8,12 @@ from app.features.core.migration import Migration as FeatureMigration
from app.features.presets.schemas import Preset
from app.features.presets.utils import preset_name
from app.library.config import Config
from app.library.log import get_logger
if TYPE_CHECKING:
from app.features.presets.repository import PresetsRepository
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
class Migration(FeatureMigration):
@ -32,7 +32,11 @@ class Migration(FeatureMigration):
try:
items: list[dict[str, Any]] | None = json.loads(self._source_file.read_text())
except Exception as exc:
LOG.exception("Failed to read %s: %s. Ignoring", self._source_file, exc)
LOG.exception(
"Failed to read presets migration file '%s'. Ignoring.",
self._source_file,
extra={"file_path": str(self._source_file), "exception_type": type(exc).__name__},
)
await self._move_file(self._source_file)
return
@ -42,7 +46,7 @@ class Migration(FeatureMigration):
return
inserted = 0
seen_names: dict[str, int] = {preset_name(preset.name): 1 for preset in await self._repo.list()}
seen_names: dict[str, int] = {preset_name(preset.name): 1 for preset in await self._repo.all()}
for index, item in enumerate(items):
if not (normalized := self._normalize(item, index, seen_names)):
@ -51,7 +55,11 @@ class Migration(FeatureMigration):
await self._repo.create(normalized)
inserted += 1
except Exception as exc:
LOG.exception("Failed to insert preset '%s': %s", normalized["name"], exc)
LOG.exception(
"Failed to insert preset '%s'.",
normalized["name"],
extra={"preset": normalized["name"], "exception_type": type(exc).__name__},
)
LOG.info("Migrated %s preset(s) from %s.", inserted, self._source_file)
await self._move_file(self._source_file)

View file

@ -1,6 +1,5 @@
from __future__ import annotations
import logging
from typing import TYPE_CHECKING, Any
from sqlalchemy import func, or_, select
@ -12,6 +11,7 @@ from app.features.presets.models import PresetModel
from app.features.presets.utils import preset_name, seed_defaults
from app.library.config import Config
from app.library.Events import Event, EventBus, Events
from app.library.log import get_logger
from app.library.Services import Services
from app.library.Singleton import Singleton
@ -27,7 +27,31 @@ if TYPE_CHECKING:
SessionFactory = Callable[[], AbstractAsyncContextManager[AsyncSession]]
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
def _payload_data(payload: PresetModel | dict[str, Any]) -> dict[str, Any]:
if isinstance(payload, dict):
data: dict[str, Any] = {}
for key, value in payload.items():
if not isinstance(key, str):
msg = "Preset payload keys must be strings."
raise TypeError(msg)
data[key] = value
return data
return {
"name": payload.name,
"description": payload.description,
"folder": payload.folder,
"template": payload.template,
"cookies": payload.cookies,
"cli": payload.cli,
"default": payload.default,
"priority": payload.priority,
"created_at": payload.created_at,
"updated_at": payload.updated_at,
}
class PresetsRepository(metaclass=Singleton):
@ -73,15 +97,15 @@ class PresetsRepository(metaclass=Singleton):
LOG.debug("Refreshing presets cache due to configuration update.")
await self._update_cache()
Services.get_instance().add(__class__.__name__, self)
Services.get_instance().add(PresetsRepository.__name__, self)
EventBus.get_instance().subscribe(
Events.STARTED, handle_event, f"{__class__.__name__}.run_migrations"
Events.STARTED, handle_event, f"{PresetsRepository.__name__}.run_migrations"
).subscribe(Events.CONFIG_UPDATE, handler, "Presets.refresh_cache")
async def _update_cache(self) -> None:
from app.features.presets.service import Presets
await Presets.get_instance().refresh_cache(await self.list())
await Presets.get_instance().refresh_cache(await self.all())
@staticmethod
def get_instance() -> PresetsRepository:
@ -97,7 +121,7 @@ class PresetsRepository(metaclass=Singleton):
LOG.error("Default preset '%s' not found, using 'default' preset.", default_name)
config.default_preset = "default"
async def list(self) -> list[PresetModel]:
async def all(self) -> list[PresetModel]:
async with self.session() as session:
result: Result[tuple[PresetModel]] = await session.execute(
select(PresetModel).order_by(PresetModel.priority.desc(), PresetModel.name.asc())
@ -238,24 +262,9 @@ class PresetsRepository(metaclass=Singleton):
result: Result[tuple[PresetModel]] = await session.execute(query.limit(1))
return result.scalar_one_or_none()
async def create(self, payload: PresetModel | dict) -> PresetModel:
async def create(self, payload: PresetModel | dict[str, Any]) -> PresetModel:
async with self.session() as session:
data: dict[str, Any]
if isinstance(payload, dict):
data = dict(payload)
else:
data = {
"name": payload.name,
"description": payload.description,
"folder": payload.folder,
"template": payload.template,
"cookies": payload.cookies,
"cli": payload.cli,
"default": payload.default,
"priority": payload.priority,
"created_at": payload.created_at,
"updated_at": payload.updated_at,
}
data = _payload_data(payload)
data.pop("id", None)
model = PresetModel(**data)

View file

@ -12,7 +12,7 @@ class Presets(metaclass=Singleton):
def __init__(self, repo: PresetsRepository | None = None) -> None:
self._repo: PresetsRepository = repo or PresetsRepository.get_instance()
self._cache: list[tuple[int, str, Preset]] = []
Services.get_instance().add(__class__.__name__, self)
Services.get_instance().add(type(self).__name__, self)
@staticmethod
def get_instance() -> Presets:

View file

@ -57,7 +57,7 @@ class TestPresetsRepository:
await repo.create({"name": "A", "priority": 1})
await repo.create({"name": "C", "priority": 2})
items = await repo.list()
items = await repo.all()
assert items[0].name == "c", "Highest priority should be first"
assert items[1].name == "a", "Same priority should sort by name"

View file

@ -1,10 +1,11 @@
import logging
import re
from datetime import UTC, datetime
from app.library.log import get_logger
NAME_WHITESPACE_PATTERN = re.compile(r"\s+")
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
async def seed_defaults(repo) -> None:
@ -48,7 +49,11 @@ async def seed_defaults(repo) -> None:
await repo.update(existing.id, payload)
except Exception as exc:
LOG.exception("Failed to seed default preset '%s': %s", preset.get("name"), exc)
LOG.exception(
"Failed to seed default preset '%s'.",
preset.get("name"),
extra={"preset": preset.get("name"), "exception_type": type(exc).__name__},
)
def preset_name(value: str) -> str:

View file

@ -5,18 +5,16 @@ Python wrapper for ffprobe command line tool. ffprobe must exist in the path.
import asyncio
import functools
import json
import logging
import operator
import os
import subprocess # qa: ignore
from pathlib import Path
import anyio
from app.features.streaming.types import FFProbeError
from app.library.log import get_logger
from app.library.Utils import timed_lru_cache
LOG: logging.Logger = logging.getLogger("streaming.ffprobe")
LOG = get_logger()
class FFStream:
@ -39,21 +37,26 @@ class FFStream:
def __repr__(self):
if "codec_long_name" not in self.__dict__:
self.codec_long_name = self.__dict__.get("codec_name", "")
self.__dict__["codec_long_name"] = self.__dict__.get("codec_name", "")
index = self.__dict__.get("index", "?")
codec_type = self.__dict__.get("codec_type", "unknown")
codec_long_name = self.__dict__.get("codec_long_name", "")
if self.is_video():
return f"<Stream: #{self.index} [{self.codec_type}] {self.codec_long_name}, {self.framerate}, ({self.width}x{self.height})>"
return f"<Stream: #{index} [{codec_type}] {codec_long_name}, {self.__dict__.get('framerate')}, ({self.__dict__.get('width')}x{self.__dict__.get('height')})>"
if self.is_audio():
return (
f"<Stream: #{self.index} [{self.codec_type}] {self.codec_long_name}, channels: {self.channels} ({self.channel_layout}), "
"{sample_rate}Hz> "
f"<Stream: #{index} [{codec_type}] {codec_long_name}, "
f"channels: {self.__dict__.get('channels')} ({self.__dict__.get('channel_layout')}), "
f"{self.__dict__.get('sample_rate')}Hz> "
)
if self.is_subtitle() or self.is_attachment():
return f"<Stream: #{self.index} [{self.codec_type}] {self.codec_long_name}>"
return f"<Stream: #{index} [{codec_type}] {codec_long_name}>"
return f"<Stream: #{self.index} [{self.codec_type}]>"
return f"<Stream: #{index} [{codec_type}]>"
def is_audio(self):
"""
@ -252,14 +255,14 @@ async def ffprobe(file: Path | str) -> FFProbeResult:
raise OSError(msg)
try:
async with await anyio.open_file(os.devnull, "w") as tempf:
await asyncio.create_subprocess_exec(
"ffprobe",
"-h",
stdout=tempf,
stderr=tempf,
creationflags=subprocess.CREATE_NO_WINDOW if os.name == "nt" else 0,
)
proc = await asyncio.create_subprocess_exec(
"ffprobe",
"-h",
stdout=asyncio.subprocess.DEVNULL,
stderr=asyncio.subprocess.DEVNULL,
creationflags=subprocess.CREATE_NO_WINDOW if os.name == "nt" else 0,
)
await proc.wait()
except FileNotFoundError as e:
msg = "ffprobe not found."
raise OSError(msg) from e

View file

@ -39,7 +39,7 @@ class M3u8:
m3u8.append("#EXT-X-MEDIA-SEQUENCE:0")
m3u8.append("#EXT-X-PLAYLIST-TYPE:VOD")
segmentSize: float = f"{self.duration:.6f}"
segmentSize: str = f"{self.duration:.6f}"
splits: int = math.ceil(duration / self.duration)
segmentParams: dict = {}

View file

@ -14,7 +14,7 @@ class Playlist:
"The path where files are downloaded."
async def make(self, file: Path) -> str:
ref: str = Path(str(file.relative_to(self.download_path)).strip("/"))
ref: Path = Path(str(file.relative_to(self.download_path)).strip("/"))
try:
ff = await ffprobe(file)

View file

@ -1,7 +1,7 @@
# flake8: noqa: ARG002
from __future__ import annotations
import os
import shutil
import subprocess
import sys
from functools import lru_cache
@ -16,9 +16,13 @@ def detect_qsv_capabilities() -> dict[str, dict[str, bool]]:
Returns a dict where keys are codec names (e.g. "h264", "hevc", "vp9") and
values are dicts with keys "full" and "lp" booleans.
"""
vainfo = shutil.which("vainfo")
if not vainfo:
return {}
try:
result: subprocess.CompletedProcess[str] = subprocess.run(
["vainfo"], # noqa: S607
[vainfo],
capture_output=True,
text=True,
check=False,
@ -87,9 +91,13 @@ def ffmpeg_encoders() -> set[str]:
"""
from app.library.config import SUPPORTED_CODECS
ffmpeg = shutil.which("ffmpeg")
if not ffmpeg:
return set()
try:
result: subprocess.CompletedProcess[str] = subprocess.run(
["ffmpeg", "-hide_banner", "-loglevel", "error", "-encoders"], # noqa: S607
[ffmpeg, "-hide_banner", "-loglevel", "error", "-encoders"],
capture_output=True,
text=True,
check=False,
@ -149,9 +157,11 @@ class _BaseBuilder:
codec_name: str
def input_args(self, ctx: dict[str, Any] | None = None) -> list[str]:
_ = ctx
return []
def add_video_args(self, args: list[str], ctx: dict[str, Any] | None = None) -> list[str]:
_ = ctx
return [*args, "-codec:v", self.codec_name]
@ -312,4 +322,4 @@ def encoder_fallback_chain(codec: str) -> tuple[str, ...]:
"libx264": [],
}
return chains.get(codec, chains["libx264"])
return tuple(chains.get(codec, chains["libx264"]))

View file

@ -1,7 +1,6 @@
import asyncio
import logging
import os
import subprocess # type: ignore
import subprocess
import sys
import tempfile
from pathlib import Path
@ -19,6 +18,7 @@ from app.features.streaming.library.segment_encoders import (
select_encoder,
)
from app.library.config import SUPPORTED_CODECS, Config
from app.library.log import get_logger
if TYPE_CHECKING:
from asyncio.subprocess import Process
@ -26,7 +26,7 @@ if TYPE_CHECKING:
from .ffprobe import FFProbeResult
from .segment_encoders import EncoderBuilder
LOG: logging.Logger = logging.getLogger("player.segments")
LOG = get_logger()
class Segments:
@ -170,9 +170,15 @@ class Segments:
stderr_task: asyncio.Task[None] = asyncio.create_task(_drain_stderr())
LOG.debug(f"Streaming '{file}' segment '{self.index}'. ffmpeg: {' '.join(args)}")
LOG.debug(
"Streaming segment %s for '%s'.",
self.index,
file,
extra={"file": str(file), "segment_index": self.index, "ffmpeg_args": args},
)
try:
assert proc.stdout is not None
while True:
chunk: bytes = await proc.stdout.read(1024 * 64)
if not chunk:
@ -191,7 +197,10 @@ class Segments:
try:
await asyncio.wait_for(proc.wait(), timeout=5)
except TimeoutError:
LOG.error("ffmpeg process did not terminate in time. Killing it.")
LOG.warning(
"Segment stream for '%s' did not stop ffmpeg in time after the client disconnected; killing it.",
file,
)
proc.kill()
raise
except ConnectionResetError:
@ -204,7 +213,10 @@ class Segments:
try:
rc: int = await asyncio.wait_for(proc.wait(), timeout=5)
except TimeoutError:
LOG.error("ffmpeg process did not terminate in time after disconnect. Killing it.")
LOG.warning(
"Segment stream for '%s' did not stop ffmpeg in time after the client disconnected; killing it.",
file,
)
proc.kill()
try:
rc = await asyncio.wait_for(proc.wait(), timeout=5)
@ -215,7 +227,7 @@ class Segments:
try:
rc = await asyncio.wait_for(proc.wait(), timeout=30)
except TimeoutError:
LOG.error("ffmpeg process wait timed out. Killing it.")
LOG.warning("Segment stream for '%s' did not stop ffmpeg in time; killing the process.", file)
proc.kill()
try:
rc = await asyncio.wait_for(proc.wait(), timeout=5)
@ -229,11 +241,13 @@ class Segments:
return (wrote_any, rc, client_disconnected_local, stderr_buf.decode("utf-8", errors="ignore").strip())
async def stream(self, file: Path, resp: web.StreamResponse) -> None:
codec: str = Segments._cached_vcodec if Segments._cache_initialized else self.vcodec
codec: str = self.vcodec
if Segments._cache_initialized and Segments._cached_vcodec:
codec = Segments._cached_vcodec
if not codec or codec not in SUPPORTED_CODECS:
codec: str = select_encoder(self.vcodec or "")
LOG.debug(f"Selected video codec '{codec}' for segment streaming.")
LOG.debug("Selected video codec '%s' for segment streaming.", codec, extra={"codec": codec})
if Segments._cached_vcodec and Segments._cache_initialized:
codecs: list[str] = [Segments._cached_vcodec]
@ -259,7 +273,14 @@ class Segments:
if 0 != rc:
err: str = stderr_text[:500] if stderr_text else "no error output"
LOG.warning(f"transcoding has failed (cmd={ffmpeg_args}) (rc={rc}): {err}. Trying fallbacks.")
LOG.warning(
"Retrying segment %s for '%s' because hardware encoder '%s' failed: %s.",
self.index,
file,
s_codec,
err,
extra={"ffmpeg_args": ffmpeg_args, "returncode": rc, "stderr": err, "codec": s_codec},
)
self.attempted.add(s_codec)
finally:
if stream_input.is_symlink():

View file

@ -1,17 +1,18 @@
from __future__ import annotations
import logging
from dataclasses import dataclass
from pathlib import Path
from typing import Any
import anyio
import pysubs2
from pysubs2.formats.substation import SubstationFormat
from pysubs2.time import ms_to_times
from app.library.log import get_logger
from app.library.Utils import ALLOWED_SUBS_EXTENSIONS, get_file_sidecar
LOG: logging.Logger = logging.getLogger("player.subtitle")
LOG = get_logger()
SOURCE_FORMATS: tuple[str, ...] = ("vtt", "srt", "ass")
DELIVERY_FORMATS: dict[str, str] = {
@ -48,7 +49,8 @@ def ms_to_timestamp(ms: int) -> str:
return f"{h:01d}:{m:02d}:{s:02d}.{cs:02d}"
SubstationFormat.ms_to_timestamp = ms_to_timestamp
_substation_format: Any = SubstationFormat
_substation_format.ms_to_timestamp = ms_to_timestamp
class Subtitle:

View file

@ -1,7 +1,6 @@
from __future__ import annotations
import asyncio
import logging
import os
import subprocess
from pathlib import Path
@ -9,9 +8,10 @@ from pathlib import Path
from app.features.streaming.library.ffprobe import ffprobe
from app.library.cache import Cache
from app.library.config import Config
from app.library.log import get_logger
from app.library.Utils import FILES_TYPE, get_file_sidecar
LOG: logging.Logger = logging.getLogger("player.thumbnail")
LOG = get_logger()
IMAGE_TYPES: tuple[str, ...] = (".jpg", ".jpeg", ".png", ".webp")
FOLDER_IMAGE_ORDER: tuple[str, ...] = ("thumbnail", "poster", "artwork", "cover", "fanart")
@ -24,6 +24,8 @@ THUMBNAIL_MISS_TTL = 3600.0
_LOCK = asyncio.Lock()
_IN_PROCESS: dict[str, asyncio.Task[Path | None]] = {}
_SEM: asyncio.Semaphore | None = None
_SEM_LIMIT: int | None = None
@ -35,7 +37,7 @@ def _get_semaphore() -> asyncio.Semaphore:
if _SEM is None or _SEM_LIMIT != limit:
_SEM = asyncio.Semaphore(limit)
_SEM_LIMIT = limit
LOG.info(f"Configured thumbnail generation concurrency limit: {limit}")
LOG.info("Configured thumbnail generation to run %s job(s) at a time.", limit, extra={"limit": limit})
return _SEM
@ -129,7 +131,11 @@ def _build_ffmpeg_args(media_file: Path, output_file: Path, *, seek_seconds: flo
async def _run_ffmpeg(media_file: Path, output_file: Path) -> Path | None:
ff_info = await ffprobe(media_file)
if not ff_info.has_video():
LOG.debug(f"Skipping thumbnail generation for '{media_file}' because no video stream exists.")
LOG.debug(
"Skipping thumbnail generation for '%s' because no video stream exists.",
media_file,
extra={"media_file": str(media_file)},
)
return None
output_file.parent.mkdir(parents=True, exist_ok=True)
@ -146,7 +152,12 @@ async def _run_ffmpeg(media_file: Path, output_file: Path) -> Path | None:
sem = _get_semaphore()
if sem.locked():
limit = _SEM_LIMIT or 1
LOG.debug(f"Waiting for thumbnail generation slot for '{media_file}'. limit={limit}")
LOG.debug(
"Waiting for a thumbnail generation slot for '%s' (limit=%s).",
media_file,
limit,
extra={"media_file": str(media_file), "limit": limit},
)
async with sem:
last_error: str = "ffmpeg produced an empty thumbnail file"
@ -154,7 +165,17 @@ async def _run_ffmpeg(media_file: Path, output_file: Path) -> Path | None:
temp_file.unlink(missing_ok=True)
args: list[str] = _build_ffmpeg_args(media_file, temp_file, seek_seconds=attempt_seek)
LOG.debug(
f"Generating thumbnail for '{media_file}'. attempt={idx}/{len(attempts)} seek={'none' if attempt_seek is None else f'{attempt_seek:.3f}s'}"
"Generating thumbnail for '%s'. attempt=%s/%s seek=%s",
media_file,
idx,
len(attempts),
"none" if attempt_seek is None else f"{attempt_seek:.3f}s",
extra={
"media_file": str(media_file),
"attempt": idx,
"attempt_count": len(attempts),
"seek": "none" if attempt_seek is None else f"{attempt_seek:.3f}s",
},
)
try:
@ -171,7 +192,12 @@ async def _run_ffmpeg(media_file: Path, output_file: Path) -> Path | None:
stdout, stderr = await proc.communicate()
if 0 == proc.returncode and temp_file.exists() and temp_file.stat().st_size > 0:
temp_file.replace(output_file)
LOG.info(f"Generated thumbnail '{output_file}' for '{media_file}'.")
LOG.info(
"Generated thumbnail '%s' for '%s'.",
output_file,
media_file,
extra={"media_file": str(media_file), "output_file": str(output_file)},
)
return output_file
if 0 != proc.returncode:
@ -184,7 +210,13 @@ async def _run_ffmpeg(media_file: Path, output_file: Path) -> Path | None:
last_error: str = "ffmpeg produced an empty thumbnail file"
LOG.debug(
f"Thumbnail generation attempt failed for '{media_file}'. seek={'none' if attempt_seek is None else f'{attempt_seek:.3f}s'}"
"Thumbnail generation attempt failed for '%s'. seek=%s",
media_file,
"none" if attempt_seek is None else f"{attempt_seek:.3f}s",
extra={
"media_file": str(media_file),
"seek": "none" if attempt_seek is None else f"{attempt_seek:.3f}s",
},
)
temp_file.unlink(missing_ok=True)
@ -224,11 +256,16 @@ async def ensure_thumb(media_file: Path, cache_root: Path, item_id: str | None =
task = _IN_PROCESS.get(thumb_id)
if task is not None and not task.done():
LOG.debug(f"Waiting for thumbnail generation for '{media_file}'.")
LOG.debug("Waiting for thumbnail generation for '%s'.", media_file, extra={"media_file": str(media_file)})
else:
task = asyncio.create_task(_run_ffmpeg(media_file, cache_file), name=f"thumb-{item_id or media_file.stem}")
_IN_PROCESS[thumb_id] = task
LOG.debug(f"Starting thumbnail generation task for '{media_file}' -> '{cache_file}'.")
LOG.debug(
"Starting thumbnail generation for '%s' -> '%s'.",
media_file,
cache_file,
extra={"media_file": str(media_file), "cache_file": str(cache_file)},
)
try:
result: Path | None = await task

View file

@ -1,10 +1,10 @@
import logging
import time
from datetime import UTC, datetime
from pathlib import Path
from aiohttp import web
from aiohttp.web import Request, Response
from aiohttp.web_response import StreamResponse
from app.features.streaming.library.m3u8 import M3u8
from app.features.streaming.library.playlist import Playlist
@ -12,10 +12,11 @@ from app.features.streaming.library.segments import Segments
from app.features.streaming.library.subtitle import Subtitle, get_subtitle_tracks
from app.features.streaming.types import StreamingError
from app.library.config import Config
from app.library.log import get_logger
from app.library.router import route
from app.library.Utils import get_file
LOG: logging.Logger = logging.getLogger("streaming")
LOG = get_logger()
@route("GET", "api/player/playlist/{file:.*}.m3u8", "playlist_create")
@ -32,7 +33,7 @@ async def playlist_create(request: Request, config: Config, app: web.Application
Response: The response object.
"""
file: str = request.match_info.get("file")
file: str | None = request.match_info.get("file")
if not file:
return web.json_response(data={"error": "file is required"}, status=web.HTTPBadRequest.status_code)
@ -83,8 +84,8 @@ async def m3u8_create(request: Request, config: Config, app: web.Application) ->
Response: The response object.
"""
file: str = request.match_info.get("file")
mode: str = request.match_info.get("mode")
file: str | None = request.match_info.get("file")
mode: str | None = request.match_info.get("mode")
if mode not in ["video", "subtitle"]:
return web.json_response(
@ -94,13 +95,14 @@ async def m3u8_create(request: Request, config: Config, app: web.Application) ->
if not file:
return web.json_response(data={"error": "file is required"}, status=web.HTTPBadRequest.status_code)
duration = request.query.get("duration", None)
duration: float | None = None
duration_arg = request.query.get("duration", None)
if "subtitle" in mode:
if not duration:
if not duration_arg:
return web.json_response(data={"error": "duration is required."}, status=web.HTTPBadRequest.status_code)
duration = float(duration)
duration = float(duration_arg)
base_path: str = config.base_path.rstrip("/")
@ -124,11 +126,19 @@ async def m3u8_create(request: Request, config: Config, app: web.Application) ->
return web.json_response(data={"error": f"File '{file}' does not exist."}, status=status)
if "subtitle" in mode:
if duration is None:
return web.json_response(data={"error": "duration is required."}, status=web.HTTPBadRequest.status_code)
text = await cls.make_subtitle(file=realFile, duration=duration)
else:
text = await cls.make_stream(file=realFile)
except StreamingError as e:
LOG.exception(e)
LOG.exception(
"Failed to create %s streaming playlist for '%s': %s.",
mode,
file,
e,
extra={"route": "streaming.playlist", "file_path": file, "mode": mode, "exception_type": type(e).__name__},
)
return web.json_response(data={"error": str(e)}, status=web.HTTPNotFound.status_code)
return web.Response(
@ -143,7 +153,7 @@ async def m3u8_create(request: Request, config: Config, app: web.Application) ->
@route("GET", r"api/player/segments/{segment:\d+}/{file:.*}.ts", "segments_stream")
async def segments_stream(request: Request, config: Config, app: web.Application) -> Response:
async def segments_stream(request: Request, config: Config, app: web.Application) -> StreamResponse:
"""
Get the segments.
@ -156,9 +166,9 @@ async def segments_stream(request: Request, config: Config, app: web.Application
Response: The response object.
"""
file: str = request.match_info.get("file")
segment: int = request.match_info.get("segment")
sd: int = request.query.get("sd")
file: str | None = request.match_info.get("file")
segment: str | None = request.match_info.get("segment")
sd: str | None = request.query.get("sd")
vc: int = int(request.query.get("vc", 0))
ac: int = int(request.query.get("ac", 0))
@ -235,7 +245,7 @@ async def subtitles_get(request: Request, config: Config, app: web.Application)
Response: The response object.
"""
file: str = request.match_info.get("file")
file: str | None = request.match_info.get("file")
if not file:
return web.json_response(data={"error": "file is required"}, status=web.HTTPBadRequest.status_code)
@ -293,7 +303,7 @@ async def subtitles_manifest_get(request: Request, config: Config, app: web.Appl
Response: The response object.
"""
file: str = request.match_info.get("file")
file: str | None = request.match_info.get("file")
if not file:
return web.json_response(data={"error": "file is required"}, status=web.HTTPBadRequest.status_code)
@ -348,7 +358,7 @@ async def subtitles_track_get(request: Request, config: Config, app: web.Applica
Response: The response object.
"""
file: str = request.match_info.get("file")
file: str | None = request.match_info.get("file")
source_format: str | None = request.match_info.get("source_format")
if not file:

View file

@ -4,6 +4,7 @@ from pathlib import Path
from typing import Any
import pytest
from aiohttp import web
from app.features.streaming.library.segments import Segments
from app.tests.helpers import get_test_system_temp_root
@ -148,18 +149,18 @@ class _FakeProc:
self.killed = True
class _FakeResp:
def __init__(self, fail_with: Exception | None = None) -> None:
class _FakeResp(web.StreamResponse):
def __init__(self, fail_with: BaseException | None = None) -> None:
self.data: bytearray = bytearray()
self.eof = False
self._exc = fail_with
async def write(self, data: bytes) -> None:
async def write(self, data: bytes | bytearray | memoryview, *_args: Any, **_kwargs: Any) -> None:
if self._exc:
raise self._exc
self.data.extend(data)
async def write_eof(self) -> None:
async def write_eof(self, *_args: Any, **_kwargs: Any) -> None:
self.eof = True
@ -255,14 +256,14 @@ async def test_stream_gpu_fallback(
# Encourage GPU preference
seg.vcodec = "" # empty -> try GPUs first
resp = _FakeResp()
with caplog.at_level(logging.WARNING, logger="player.segments"):
with caplog.at_level(logging.WARNING, logger="ytptube"):
await seg.stream(tmp_path / "file.mp4", resp)
# Ensure fallback path streamed data
assert len(resp.data) > 0
# Ensure we logged the reason for GPU failure (message text may vary)
assert any(
("Hardware encoder failed" in r.message) or ("transcoding has failed" in r.message) for r in caplog.records
("hardware encoder" in r.message.lower()) or ("transcoding has failed" in r.message) for r in caplog.records
)
assert any("nvenc failure" in r.message for r in caplog.records)
# Verify second invocation switched codec to a safe fallback (software)

View file

@ -2,6 +2,7 @@ from __future__ import annotations
import asyncio
from pathlib import Path
from typing import Any
from unittest.mock import AsyncMock
import pytest
@ -260,7 +261,7 @@ async def test_retry_no_seek(monkeypatch: pytest.MonkeyPatch) -> None:
output = temp_dir / ".jpg"
media.write_text("video")
ff_info = FFProbeResult()
ff_info: Any = FFProbeResult()
ff_info.metadata = {"duration": "120.0"}
ff_info.video = [type("Video", (), {"codec_type": "video", "codec_name": "h264"})()]
@ -321,7 +322,7 @@ async def test_limit_wait(monkeypatch: pytest.MonkeyPatch) -> None:
media1.write_text("video")
media2.write_text("video")
ff_info = FFProbeResult()
ff_info: Any = FFProbeResult()
ff_info.metadata = {"duration": "60.0"}
ff_info.video = [type("Video", (), {"codec_type": "video", "codec_name": "h264"})()]
monkeypatch.setattr(thumbnail, "ffprobe", AsyncMock(return_value=ff_info))

View file

@ -1,4 +1,3 @@
# flake8: noqa: ARG004
from typing import TYPE_CHECKING, Any
from app.features.tasks.definitions.results import HandleTask, TaskFailure, TaskResult
@ -12,6 +11,7 @@ if TYPE_CHECKING:
class BaseHandler:
@staticmethod
async def can_handle(task: HandleTask) -> bool:
_ = task
return False
@staticmethod
@ -24,6 +24,7 @@ class BaseHandler:
@staticmethod
def parse(url: str) -> Any | None:
_ = url
return None
@staticmethod

View file

@ -6,7 +6,6 @@ import asyncio
import fnmatch
import hashlib
import json
import logging
import re
from collections.abc import Mapping
from typing import TYPE_CHECKING, Any
@ -26,6 +25,7 @@ from app.features.ytdlp.utils import get_archive_id
from app.library.cache import Cache
from app.library.config import Config
from app.library.httpx_client import Globals, build_request_headers, get_async_client, resolve_curl_transport
from app.library.log import get_logger
from ._base_handler import BaseHandler
@ -34,7 +34,7 @@ if TYPE_CHECKING:
from parsel.selector import SelectorList
LOG: logging.Logger = logging.getLogger("handlers.generic")
LOG = get_logger()
CACHE: Cache = Cache()
@ -64,12 +64,15 @@ class GenericTaskHandler(BaseHandler):
from app.features.tasks.definitions.utils import model_to_schema
repo = TaskDefinitionsRepository.get_instance()
models = await repo.list()
models = await repo.all()
cls._definitions = [model_to_schema(model) for model in models]
return cls._definitions
except Exception as exc:
LOG.error(f"Failed to load task definitions from database: {exc}")
LOG.exception(
"Failed to load generic task definitions.",
extra={"error": str(exc), "exception_type": type(exc).__name__},
)
return []
@classmethod
@ -102,7 +105,15 @@ class GenericTaskHandler(BaseHandler):
if pattern_str and re.match(pattern_str, url):
return definition
except Exception as exc:
LOG.error(f"Error while matching definition '{definition.name}': {exc}")
LOG.exception(
"Failed to match a generic task definition.",
extra={
"definition": definition.name,
"url": url,
"error": str(exc),
"exception_type": type(exc).__name__,
},
)
return None
@ -120,13 +131,18 @@ class GenericTaskHandler(BaseHandler):
"""
definition: TaskDefinition | None = await GenericTaskHandler._find_definition(task.url)
if definition:
LOG.debug(f"'{task.name}': Matched generic task definition '{definition.name}'.")
LOG.debug(
"Task '%s' matched a generic task definition.",
task.name,
extra={"task_name": task.name, "url": task.url, "definition": definition.name},
)
return True
return False
@staticmethod
async def extract(task: HandleTask, config: Config | None = None) -> TaskResult | TaskFailure: # noqa: ARG004
async def extract(task: HandleTask, config: Config | None = None) -> TaskResult | TaskFailure:
_ = config
definition: TaskDefinition | None = await GenericTaskHandler._find_definition(task.url)
if not definition:
return TaskFailure(message="No generic task definition matched the provided URL.")
@ -134,7 +150,16 @@ class GenericTaskHandler(BaseHandler):
ytdlp_opts: dict[str, Any] = task.get_ytdlp_opts().get_all()
target_url: str = definition.definition.request.url or task.url
LOG.debug(f"{task.name!r}: Fetching '{target_url}' using engine '{definition.definition.engine.type}'.")
LOG.debug(
"Fetching content for task '%s'.",
task.name,
extra={
"task_name": task.name,
"definition": definition.name,
"url": target_url,
"engine": definition.definition.engine.type,
},
)
try:
body_text, json_data = await GenericTaskHandler._fetch_content(
@ -143,7 +168,16 @@ class GenericTaskHandler(BaseHandler):
except httpx.HTTPError as exc:
return TaskFailure(message="Failed to fetch target URL.", error=str(exc))
except Exception as exc:
LOG.exception(exc)
LOG.exception(
"Failed to fetch content for task '%s'.",
task.name,
extra={
"task_name": task.name,
"definition": definition.name,
"url": target_url,
"exception_type": type(exc).__name__,
},
)
return TaskFailure(message="Failed to fetch target URL.", error=str(exc))
if "json" == definition.definition.response.type and json_data is None:
@ -181,7 +215,9 @@ class GenericTaskHandler(BaseHandler):
continue
else:
LOG.warning(
f"[{definition.name}]: '{task.name}': Unable to generate static archive id for '{url}' in feed. Doing real request to fetch yt-dlp archive id."
"Task '%s' could not generate a static archive ID. Fetching it with yt-dlp.",
task.name,
extra={"definition": definition.name, "task_name": task.name, "url": url},
)
(info, _) = await fetch_info(
@ -194,14 +230,18 @@ class GenericTaskHandler(BaseHandler):
if not info:
LOG.error(
f"[{definition.name}]: '{task.name}': Failed to extract info for URL '{url}' to generate archive ID. Skipping."
"Task '%s' failed to extract info to generate an archive ID. Skipping item.",
task.name,
extra={"definition": definition.name, "task_name": task.name, "url": url},
)
CACHE.set(cache_key, None)
continue
if not info.get("id") or not info.get("extractor_key"):
LOG.error(
f"[{definition.name}]: '{task.name}': Incomplete info extracted for URL '{url}' to generate archive ID. Skipping."
"Task '%s' returned incomplete info while generating an archive ID. Skipping item.",
task.name,
extra={"definition": definition.name, "task_name": task.name, "url": url},
)
CACHE.set(cache_key, None)
continue
@ -297,7 +337,17 @@ class GenericTaskHandler(BaseHandler):
try:
json_data: dict[str, Any] = response.json()
except Exception as exc:
LOG.error(f"Failed to decode JSON response from '{url}': {exc}")
LOG.exception(
"Task definition '%s' returned invalid JSON for '%s'.",
definition.name,
url,
extra={
"definition": definition.name,
"url": url,
"error": str(exc),
"exception_type": type(exc).__name__,
},
)
return response.text, None
return response.text, json_data
@ -327,7 +377,11 @@ class GenericTaskHandler(BaseHandler):
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
except ImportError as exc:
LOG.error(f"Selenium engine requested but selenium is not installed: {exc!s}.")
LOG.exception(
"Task definition '%s' requested Selenium, but Selenium is not installed.",
definition.name,
extra={"definition": definition.name, "error": str(exc), "exception_type": type(exc).__name__},
)
return (None, None)
options_map: dict[str, Any] = definition.definition.engine.options
@ -340,7 +394,12 @@ class GenericTaskHandler(BaseHandler):
browser: str = str(options_map.get("browser", "chrome")).lower()
if "chrome" != browser:
LOG.error(f"Unsupported selenium browser '{browser}'. Only 'chrome' is supported.")
LOG.error(
"Task definition '%s' requested unsupported Selenium browser '%s'.",
definition.name,
browser,
extra={"definition": definition.name, "browser": browser},
)
return (None, None)
arguments: list[str] | str = options_map.get("arguments", ["--headless", "--disable-gpu"])
@ -422,7 +481,9 @@ class GenericTaskHandler(BaseHandler):
link_values: list[str] = extracted.get("link", [])
if not link_values:
LOG.debug(f"Definition '{definition.name}' produced no link values.")
LOG.debug(
"Definition '%s' produced no link values.", definition.name, extra={"definition": definition.name}
)
return []
total_items: int = len(link_values)
@ -457,7 +518,11 @@ class GenericTaskHandler(BaseHandler):
base_url: str,
) -> list[dict[str, str]]:
if json_data is None:
LOG.debug(f"Definition '{definition.name}' expects JSON but no data was parsed.")
LOG.debug(
"Definition '%s' expects JSON but no data was parsed.",
definition.name,
extra={"definition": definition.name},
)
return []
if definition.definition.parse.get("items"):
@ -496,7 +561,11 @@ class GenericTaskHandler(BaseHandler):
container_type = container.get("type", "css")
container_selector = container.get("selector") or container.get("expression") or ""
if not container_selector:
LOG.error(f"Container missing selector/expression. Definition '{definition.name}'.")
LOG.error(
"Task definition '%s' is missing an item container selector.",
definition.name,
extra={"definition": definition.name},
)
return []
container_fields = container.get("fields", {})
@ -550,7 +619,11 @@ class GenericTaskHandler(BaseHandler):
container_fields = container.get("fields", {})
if "jsonpath" != container_type:
LOG.error(f"JSON response requires container selector type 'jsonpath'. Definition '{definition.name}'.")
LOG.error(
"JSON response requires container selector type 'jsonpath'. Definition '%s'.",
definition.name,
extra={"definition": definition.name, "container_type": container_type},
)
return []
nodes: Any = GenericTaskHandler._json_search(json_data, container_selector)
@ -606,7 +679,16 @@ class GenericTaskHandler(BaseHandler):
try:
pattern: re.Pattern[str] = re.compile(rule.expression, re.MULTILINE | re.DOTALL)
except re.error as exc:
LOG.error(f"Invalid regex expression '{rule.expression}': {exc}")
LOG.exception(
"Invalid regex expression '%s'.",
rule.expression,
extra={
"field": field,
"expression": rule.expression,
"error": str(exc),
"exception_type": type(exc).__name__,
},
)
return values
for match in pattern.finditer(target):
@ -617,7 +699,12 @@ class GenericTaskHandler(BaseHandler):
return values
LOG.error(f"Unsupported extraction type '{rule.type}' for JSON data in field '{field}'.")
LOG.error(
"Unsupported extraction type '%s' for JSON data in field '%s'.",
rule.type,
field,
extra={"field": field, "rule_type": rule.type},
)
return values
@staticmethod
@ -625,7 +712,11 @@ class GenericTaskHandler(BaseHandler):
try:
return jmespath.search(expression, data)
except Exception as exc:
LOG.error(f"JSONPath search failed for expression '{expression}': {exc}")
LOG.exception(
"JSONPath search failed for expression '%s'.",
expression,
extra={"expression": expression, "error": str(exc), "exception_type": type(exc).__name__},
)
return None
@staticmethod
@ -660,7 +751,16 @@ class GenericTaskHandler(BaseHandler):
try:
pattern: re.Pattern[str] = re.compile(rule.expression, re.MULTILINE | re.DOTALL)
except re.error as exc:
LOG.error(f"Invalid regex expression '{rule.expression}': {exc}")
LOG.exception(
"Invalid regex expression '%s'.",
rule.expression,
extra={
"field": field,
"expression": rule.expression,
"error": str(exc),
"exception_type": type(exc).__name__,
},
)
return values
for match in pattern.finditer(html):
@ -672,7 +772,7 @@ class GenericTaskHandler(BaseHandler):
return values
if "jsonpath" == rule.type:
LOG.error("Extraction type 'jsonpath' is only valid for JSON responses.")
LOG.error("Field '%s' uses 'jsonpath' on a non-JSON response.", field, extra={"field": field})
return values
selection: SelectorList[Selector] = (
@ -704,7 +804,12 @@ class GenericTaskHandler(BaseHandler):
try:
return match.group(attribute)
except (IndexError, KeyError):
LOG.debug(f"Regex group '{attribute}' not found in pattern '{match.re.pattern}'.")
LOG.debug(
"Regex group '%s' not found in pattern '%s'.",
attribute,
match.re.pattern,
extra={"attribute": attribute, "pattern": match.re.pattern},
)
return None
if match.groupdict():

View file

@ -1,5 +1,4 @@
import hashlib
import logging
import re
from typing import TYPE_CHECKING, Any
from xml.etree.ElementTree import Element
@ -10,13 +9,15 @@ from app.features.tasks.definitions.results import HandleTask, TaskFailure, Task
from app.features.ytdlp.extractor import fetch_info
from app.features.ytdlp.utils import get_archive_id
from app.library.cache import Cache
from app.library.config import Config
from app.library.log import get_logger
from ._base_handler import BaseHandler
if TYPE_CHECKING:
from xml.etree.ElementTree import Element
LOG: logging.Logger = logging.getLogger("handlers.rss")
LOG = get_logger()
CACHE: Cache = Cache()
@ -28,7 +29,11 @@ class RssGenericHandler(BaseHandler):
@staticmethod
async def can_handle(task: HandleTask) -> bool:
LOG.debug(f"'{task.name}': Checking if task URL is parsable RSS feed: {task.url}")
LOG.debug(
"Checking if task '%s' uses a parsable RSS feed.",
task.name,
extra={"task_name": task.name, "url": task.url},
)
return RssGenericHandler.parse(task.url) is not None
@staticmethod
@ -52,7 +57,11 @@ class RssGenericHandler(BaseHandler):
from defusedxml.ElementTree import fromstring
feed_url: str = parsed["url"]
LOG.debug(f"'{task.name}': Fetching RSS/Atom feed from {feed_url}")
LOG.debug(
"Fetching RSS/Atom feed for task '%s'.",
task.name,
extra={"task_name": task.name, "feed_url": feed_url},
)
response = await RssGenericHandler.request(url=feed_url, ytdlp_opts=params)
response.raise_for_status()
@ -73,7 +82,12 @@ class RssGenericHandler(BaseHandler):
# Try to parse as Atom feed first
entries = root.findall("atom:entry", ns)
if entries:
LOG.debug(f"'{task.name}': Detected Atom feed format with {len(entries)} entries")
LOG.debug(
"'%s': Detected Atom feed format with %s entries",
task.name,
len(entries),
extra={"task_name": task.name, "feed_url": feed_url, "entry_count": len(entries)},
)
for entry in entries:
link_elem: Element | None = entry.find("atom:link[@rel='alternate']", ns)
if link_elem is None:
@ -84,7 +98,11 @@ class RssGenericHandler(BaseHandler):
url = link_elem.get("href", "")
if not url:
LOG.warning(f"'{task.name}': Atom entry missing URL. Skipping.")
LOG.warning(
"'%s': Atom entry missing URL. Skipping.",
task.name,
extra={"task_name": task.name, "feed_url": feed_url},
)
continue
title_elem: Element | None = entry.find("atom:title", ns)
@ -98,7 +116,12 @@ class RssGenericHandler(BaseHandler):
else:
# Try to parse as RSS feed
rss_items = root.findall(".//item")
LOG.debug(f"'{task.name}': Detected RSS feed format with {len(rss_items)} items")
LOG.debug(
"'%s': Detected RSS feed format with %s items",
task.name,
len(rss_items),
extra={"task_name": task.name, "feed_url": feed_url, "entry_count": len(rss_items)},
)
for item in rss_items:
# Try different link element names (link, url, media:content)
@ -119,7 +142,11 @@ class RssGenericHandler(BaseHandler):
url = enclosure_elem.get("url", "")
if not url:
LOG.warning(f"'{task.name}': RSS item missing URL. Skipping.")
LOG.warning(
"'%s': RSS item missing URL. Skipping.",
task.name,
extra={"task_name": task.name, "feed_url": feed_url},
)
continue
title_elem = item.find("title")
@ -134,12 +161,14 @@ class RssGenericHandler(BaseHandler):
return feed_url, items, real_count
@staticmethod
async def extract(task: HandleTask) -> TaskResult | TaskFailure:
async def extract(task: HandleTask, config: Config | None = None) -> TaskResult | TaskFailure:
_ = config
"""
Extract items from an RSS/Atom feed.
Args:
task (Task): The task containing the feed URL.
config (Config | None): Optional handler configuration.
Returns:
TaskResult | TaskFailure: Extraction result with parsed items or failure information.
@ -156,7 +185,16 @@ class RssGenericHandler(BaseHandler):
except httpx.HTTPError as exc:
return TaskFailure(message="Failed to fetch RSS/Atom feed.", error=str(exc))
except Exception as exc:
LOG.exception(exc)
LOG.exception(
"Failed to fetch RSS/Atom feed for task '%s'.",
task.name,
extra={
"task_id": task.id,
"task_name": task.name,
"url": task.url,
"exception_type": type(exc).__name__,
},
)
return TaskFailure(message="Failed to fetch RSS/Atom feed.", error=str(exc))
task_items: list[TaskItem] = []
@ -176,12 +214,17 @@ class RssGenericHandler(BaseHandler):
if CACHE.has(cache_key):
archive_id = CACHE.get(cache_key)
if not archive_id:
LOG.debug(f"'{task.name}': Cached failure for URL '{url}'. Skipping.")
LOG.debug(
"Task '%s' has a cached archive ID lookup failure. Skipping item.",
task.name,
extra={"task_name": task.name, "url": url},
)
continue
else:
LOG.warning(
f"'{task.name}': Unable to generate static archive ID for '{url}' in feed. "
"Doing real request to fetch yt-dlp archive ID."
"Task '%s' could not generate a static archive ID. Fetching it with yt-dlp.",
task.name,
extra={"task_name": task.name, "url": url},
)
(info, _) = await fetch_info(
@ -194,14 +237,18 @@ class RssGenericHandler(BaseHandler):
if not info:
LOG.error(
f"'{task.name}': Failed to extract info for URL '{url}' to generate archive ID. Skipping."
"Task '%s' failed to extract info to generate an archive ID. Skipping item.",
task.name,
extra={"task_name": task.name, "url": url},
)
CACHE.set(cache_key, None)
continue
if not info.get("id") or not info.get("extractor_key"):
LOG.error(
f"'{task.name}': Incomplete info extracted for URL '{url}' to generate archive ID. Skipping."
"Task '%s' returned incomplete info while generating an archive ID. Skipping item.",
task.name,
extra={"task_name": task.name, "url": url},
)
CACHE.set(cache_key, None)
continue

View file

@ -1,14 +1,15 @@
import logging
import re
import httpx
from app.features.tasks.definitions.results import HandleTask, TaskFailure, TaskItem, TaskResult
from app.features.ytdlp.utils import get_archive_id
from app.library.config import Config
from app.library.log import get_logger
from ._base_handler import BaseHandler
LOG: logging.Logger = logging.getLogger("handlers.tver")
LOG = get_logger()
class TverHandler(BaseHandler):
@ -24,7 +25,11 @@ class TverHandler(BaseHandler):
@staticmethod
async def can_handle(task: HandleTask) -> bool:
LOG.debug(f"Checking if task '{task.name}' is using parsable Tver series URL: {task.url}")
LOG.debug(
"Checking if task '%s' uses a parsable Tver series URL.",
task.name,
extra={"task_name": task.name, "url": task.url},
)
return TverHandler.parse(task.url) is not None
@staticmethod
@ -55,7 +60,11 @@ class TverHandler(BaseHandler):
return {"platform_uid": platform_uid, "platform_token": platform_token}
except Exception as exc:
LOG.warning(f"Failed to create tver session: {exc}")
LOG.warning(
"Failed to create Tver session.",
extra={"error": str(exc), "exception_type": type(exc).__name__},
exc_info=True,
)
return None
@staticmethod
@ -83,7 +92,11 @@ class TverHandler(BaseHandler):
feed_url = TverHandler.SERIES_API.format(id=series_id)
LOG.debug(f"Fetching '{task.name}' episodes from tver series {series_id}.")
LOG.debug(
"Fetching Tver episodes for task '%s'.",
task.name,
extra={"task_name": task.name, "series_id": series_id, "feed_url": feed_url},
)
response = await TverHandler.request(
url=feed_url,
@ -105,7 +118,11 @@ class TverHandler(BaseHandler):
try:
contents = data.get("result", {}).get("contents", [])
if not contents:
LOG.warning(f"No contents found in tver series response for '{task.name}'.")
LOG.warning(
"No contents found in Tver series response for '%s'.",
task.name,
extra={"task_name": task.name, "series_id": series_id, "feed_url": feed_url},
)
return feed_url, items, has_items
season_block = contents[0] if contents else {}
@ -116,9 +133,13 @@ class TverHandler(BaseHandler):
continue
content = episode_data.get("content", {})
episode_id = content.pop("id")
episode_id = content.pop("id", None)
if not episode_id:
LOG.warning(f"Episode missing ID in '{task.name}' feed. Skipping.")
LOG.warning(
"Episode missing ID in '%s' feed. Skipping.",
task.name,
extra={"task_name": task.name, "series_id": series_id, "feed_url": feed_url},
)
continue
url = f"https://tver.jp/episodes/{episode_id}"
@ -129,7 +150,9 @@ class TverHandler(BaseHandler):
archive_id = id_dict.get("archive_id")
if not archive_id:
LOG.warning(
f"Could not compute archive ID for episode '{episode_id}' in '{task.name}' feed. Skipping."
"Task '%s' could not compute an archive ID for an episode. Skipping item.",
task.name,
extra={"task_name": task.name, "series_id": series_id, "episode_id": episode_id, "url": url},
)
continue
@ -139,12 +162,24 @@ class TverHandler(BaseHandler):
)
except Exception as exc:
LOG.warning(f"Error parsing tver episodes for '{task.name}': {exc}")
LOG.warning(
"Failed to parse Tver episodes for task '%s'.",
task.name,
extra={
"task_id": task.id,
"task_name": task.name,
"series_id": series_id,
"error": str(exc),
"exception_type": type(exc).__name__,
},
exc_info=True,
)
return feed_url, items, has_items
@staticmethod
async def extract(task: HandleTask) -> TaskResult | TaskFailure:
async def extract(task: HandleTask, config: Config | None = None) -> TaskResult | TaskFailure:
_ = config
series_id: str | None = TverHandler.parse(task.url)
if not series_id:
return TaskFailure(message="Unrecognized Tver series URL.")
@ -156,7 +191,17 @@ class TverHandler(BaseHandler):
except httpx.HTTPError as exc:
return TaskFailure(message="Failed to fetch Tver feed.", error=str(exc))
except Exception as exc:
LOG.exception(exc)
LOG.exception(
"Failed to fetch Tver feed for task '%s'.",
task.name,
extra={
"task_id": task.id,
"task_name": task.name,
"url": task.url,
"series_id": series_id,
"exception_type": type(exc).__name__,
},
)
return TaskFailure(message="Failed to fetch Tver feed.", error=str(exc))
task_items: list[TaskItem] = []
@ -165,10 +210,11 @@ class TverHandler(BaseHandler):
if not (url := entry.get("url")):
continue
archive_id: str = entry.get("archive_id")
task_items.append(
TaskItem(url=url, title=entry.get("title"), archive_id=archive_id, metadata=entry.get("metadata", {}))
)
archive_id: str | None = entry.get("archive_id")
metadata = entry.get("metadata", {})
if not isinstance(metadata, dict):
metadata = {}
task_items.append(TaskItem(url=url, title=entry.get("title"), archive_id=archive_id, metadata=metadata))
return TaskResult(items=task_items, metadata={"feed_url": feed_url, "has_entries": has_items})

View file

@ -1,4 +1,3 @@
import logging
import re
from typing import TYPE_CHECKING
from xml.etree.ElementTree import Element
@ -7,13 +6,15 @@ import httpx
from app.features.tasks.definitions.results import HandleTask, TaskFailure, TaskItem, TaskResult
from app.features.ytdlp.utils import get_archive_id
from app.library.config import Config
from app.library.log import get_logger
from ._base_handler import BaseHandler
if TYPE_CHECKING:
from xml.etree.ElementTree import Element
LOG: logging.Logger = logging.getLogger("handlers.twitch")
LOG = get_logger()
class TwitchHandler(BaseHandler):
@ -23,7 +24,11 @@ class TwitchHandler(BaseHandler):
@staticmethod
async def can_handle(task: HandleTask) -> bool:
LOG.debug(f"Checking if task '{task.name}' is using parsable Twitch URL: {task.url}")
LOG.debug(
"Checking if task '%s' uses a parsable Twitch URL.",
task.name,
extra={"task_name": task.name, "url": task.url},
)
return TwitchHandler.parse(task.url) is not None
@staticmethod
@ -36,7 +41,7 @@ class TwitchHandler(BaseHandler):
feed_url: str = TwitchHandler.FEED.format(handle=handle_name)
LOG.debug(f"Fetching '{task.name}' feed.")
LOG.debug("Fetching '%s' feed.", task.name, extra={"task_name": task.name, "feed_url": feed_url})
response = await TwitchHandler.request(url=feed_url, ytdlp_opts=params)
response.raise_for_status()
@ -48,14 +53,22 @@ class TwitchHandler(BaseHandler):
link_elem: Element[str] | None = entry.find("link")
url: str = link_elem.text.strip() if link_elem is not None and link_elem.text else ""
if not url:
LOG.warning(f"Entry in '{task.name}' feed is missing URL. Skipping entry.")
LOG.warning(
"Entry in '%s' feed is missing URL. Skipping entry.",
task.name,
extra={"task_name": task.name, "feed_url": feed_url},
)
continue
match: re.Match[str] | None = re.search(
r"^https?://(?:www\.)?twitch\.tv/videos/(?P<id>\d+)(?:[/?].*)?$", url
)
if not match:
LOG.warning(f"URL in '{task.name}' feed does not look like a VOD link: {url}")
LOG.warning(
"Task '%s' produced a feed entry that does not look like a Twitch VOD link. Skipping entry.",
task.name,
extra={"task_name": task.name, "url": url},
)
continue
vid: str = match.group("id")
@ -68,7 +81,11 @@ class TwitchHandler(BaseHandler):
id_dict = get_archive_id(url)
archive_id: str | None = id_dict.get("archive_id")
if not archive_id:
LOG.warning(f"Could not compute archive ID for video '{vid}' in '{task.name}' feed. Skipping entry.")
LOG.warning(
"Task '%s' could not compute an archive ID for a Twitch video. Skipping entry.",
task.name,
extra={"task_name": task.name, "video_id": vid, "url": url},
)
continue
items.append({"id": vid, "url": url, "title": title, "archive_id": archive_id})
@ -76,7 +93,8 @@ class TwitchHandler(BaseHandler):
return feed_url, items, has_items
@staticmethod
async def extract(task: HandleTask) -> TaskResult | TaskFailure:
async def extract(task: HandleTask, config: Config | None = None) -> TaskResult | TaskFailure:
_ = config
handle_name: str | None = TwitchHandler.parse(task.url)
if not handle_name:
return TaskFailure(message="Unrecognized Twitch channel URL.")
@ -88,7 +106,16 @@ class TwitchHandler(BaseHandler):
except httpx.HTTPError as exc:
return TaskFailure(message="Failed to fetch Twitch feed.", error=str(exc))
except Exception as exc:
LOG.exception(exc)
LOG.exception(
"Failed to fetch Twitch feed for task '%s'.",
task.name,
extra={
"task_id": task.id,
"task_name": task.name,
"url": task.url,
"exception_type": type(exc).__name__,
},
)
return TaskFailure(message="Failed to fetch Twitch feed.", error=str(exc))
task_items: list[TaskItem] = []
@ -97,7 +124,7 @@ class TwitchHandler(BaseHandler):
if not (url := entry.get("url")):
continue
archive_id: str = entry.get("archive_id")
archive_id: str | None = entry.get("archive_id")
task_items.append(TaskItem(url=url, title=entry.get("title"), archive_id=archive_id))
return TaskResult(items=task_items, metadata={"feed_url": feed_url, "has_entries": has_items})

View file

@ -1,4 +1,3 @@
import logging
import re
from typing import TYPE_CHECKING, Any
from xml.etree.ElementTree import Element
@ -7,13 +6,15 @@ import httpx
from app.features.tasks.definitions.results import HandleTask, TaskFailure, TaskItem, TaskResult
from app.features.ytdlp.utils import get_archive_id
from app.library.config import Config
from app.library.log import get_logger
from ._base_handler import BaseHandler
if TYPE_CHECKING:
from xml.etree.ElementTree import Element
LOG: logging.Logger = logging.getLogger("handlers.youtube")
LOG = get_logger()
class YoutubeHandler(BaseHandler):
@ -29,7 +30,11 @@ class YoutubeHandler(BaseHandler):
@staticmethod
async def can_handle(task: HandleTask) -> bool:
LOG.debug(f"'{task.name}': Checking if task URL is parsable YouTube URL: {task.url}")
LOG.debug(
"Checking if task '%s' uses a parsable YouTube URL.",
task.name,
extra={"task_name": task.name, "url": task.url},
)
return YoutubeHandler.parse(task.url) is not None
@staticmethod
@ -49,7 +54,7 @@ class YoutubeHandler(BaseHandler):
from defusedxml.ElementTree import fromstring
feed_url: str = YoutubeHandler.FEED.format(type=parsed["type"], id=parsed["id"])
LOG.debug(f"'{task.name}': Fetching feed.")
LOG.debug("'%s': Fetching feed.", task.name, extra={"task_name": task.name, "feed_url": feed_url})
response = await YoutubeHandler.request(url=feed_url, ytdlp_opts=params)
response.raise_for_status()
@ -67,7 +72,11 @@ class YoutubeHandler(BaseHandler):
vid_elem: Element[str] | None = entry.find("yt:videoId", ns)
vid: str = vid_elem.text if vid_elem is not None and vid_elem.text else ""
if not vid:
LOG.warning(f"'{task.name}': Entry in the feed is missing a video ID. Skipping.")
LOG.warning(
"'%s': Entry in the feed is missing a video ID. Skipping.",
task.name,
extra={"task_name": task.name, "feed_url": feed_url},
)
continue
url: str = f"https://www.youtube.com/watch?v={vid}"
@ -75,7 +84,11 @@ class YoutubeHandler(BaseHandler):
id_dict: dict[str, str | None] = get_archive_id(url)
archive_id: str | None = id_dict.get("archive_id")
if not archive_id:
LOG.warning(f"'{task.name}': Could not compute archive ID for video '{vid}' in feed. Skipping.")
LOG.warning(
"Task '%s' could not compute an archive ID for a YouTube video. Skipping item.",
task.name,
extra={"task_name": task.name, "video_id": vid, "url": url},
)
continue
title_elem: Element[str] | None = entry.find("atom:title", ns)
@ -91,7 +104,8 @@ class YoutubeHandler(BaseHandler):
return feed_url, items, real_count
@staticmethod
async def extract(task: HandleTask) -> TaskResult | TaskFailure:
async def extract(task: HandleTask, config: Config | None = None) -> TaskResult | TaskFailure:
_ = config
parsed: dict[str, str] | None = YoutubeHandler.parse(task.url)
if not parsed:
return TaskFailure(message="Unrecognized YouTube channel or playlist URL.")
@ -103,7 +117,16 @@ class YoutubeHandler(BaseHandler):
except httpx.HTTPError as exc:
return TaskFailure(message="Failed to fetch YouTube feed.", error=str(exc))
except Exception as exc:
LOG.exception(exc)
LOG.exception(
"Failed to fetch YouTube feed for task '%s'.",
task.name,
extra={
"task_id": task.id,
"task_name": task.name,
"url": task.url,
"exception_type": type(exc).__name__,
},
)
return TaskFailure(message="Failed to fetch YouTube feed.", error=str(exc))
task_items: list[TaskItem] = []
@ -112,7 +135,7 @@ class YoutubeHandler(BaseHandler):
if not (url := entry.get("url")):
continue
archive_id: str = entry.get("archive_id")
archive_id: str | None = entry.get("archive_id")
metadata: dict[str, Any] = {"published": entry.get("published")}
task_items.append(TaskItem(url=url, title=entry.get("title"), archive_id=archive_id, metadata=metadata))

View file

@ -1,17 +1,17 @@
from __future__ import annotations
import json
import logging
from pathlib import Path
from typing import TYPE_CHECKING, Any
from app.features.core.migration import Migration as FeatureMigration
from app.library.config import Config
from app.library.log import get_logger
if TYPE_CHECKING:
from app.features.tasks.definitions.repository import TaskDefinitionsRepository
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
class Migration(FeatureMigration):
@ -48,7 +48,11 @@ class Migration(FeatureMigration):
await self._repo.create(normalized)
inserted += 1
except Exception as exc:
LOG.exception("Failed to insert task definition '%s': %s", normalized.get("name"), exc)
LOG.exception(
"Failed to insert task definition '%s'.",
normalized.get("name"),
extra={"definition": normalized.get("name"), "exception_type": type(exc).__name__},
)
finally:
await self._move_file(path)
@ -62,13 +66,21 @@ class Migration(FeatureMigration):
try:
content = path.read_text(encoding="utf-8")
except Exception as exc:
LOG.error("Failed to read task definition '%s': %s", path, exc)
LOG.exception(
"Failed to read task definition '%s'.",
path,
extra={"path": str(path), "exception_type": type(exc).__name__},
)
return None
try:
payload = json.loads(content)
except Exception as exc:
LOG.error("Failed to parse JSON for '%s': %s", path, exc)
LOG.exception(
"Failed to parse JSON for task definition '%s'.",
path,
extra={"path": str(path), "exception_type": type(exc).__name__},
)
return None
if not isinstance(payload, dict):

View file

@ -1,6 +1,5 @@
from __future__ import annotations
import logging
from typing import TYPE_CHECKING, Any
from sqlalchemy import func, or_, select
@ -10,24 +9,28 @@ from app.features.core.schemas import CEFeature, ConfigEvent
from app.features.tasks.definitions.migration import Migration
from app.features.tasks.definitions.models import TaskDefinitionModel
from app.library.Events import Event, EventBus, Events
from app.library.log import get_logger
from app.library.Services import Services
from app.library.Singleton import Singleton
if TYPE_CHECKING:
from collections.abc import AsyncGenerator
from collections.abc import Callable
from contextlib import AbstractAsyncContextManager
from sqlalchemy.engine.result import Result
from sqlalchemy.ext.asyncio import AsyncSession
from sqlalchemy.sql.elements import ColumnElement
from sqlalchemy.sql.selectable import Select
LOG: logging.Logger = logging.getLogger(__name__)
SessionFactory = Callable[[], AbstractAsyncContextManager[AsyncSession]]
LOG = get_logger()
class TaskDefinitionsRepository(metaclass=Singleton):
def __init__(self, session: AsyncGenerator[AsyncSession] | None = None) -> None:
def __init__(self, session: SessionFactory | None = None) -> None:
self._migrated = False
self.session: AsyncGenerator[AsyncSession] = session or get_session
self.session: SessionFactory = session or get_session
async def run_migrations(self) -> None:
if self._migrated:
@ -51,12 +54,12 @@ class TaskDefinitionsRepository(metaclass=Singleton):
LOG.debug("Refreshing task definitions due to configuration update.")
await GenericTaskHandler.refresh_definitions(force=True)
Services.get_instance().add(__class__.__name__, self)
Services.get_instance().add(TaskDefinitionsRepository.__name__, self)
EventBus.get_instance().subscribe(
Events.STARTED, handle_event, f"{__class__.__name__}.run_migrations"
Events.STARTED, handle_event, f"{TaskDefinitionsRepository.__name__}.run_migrations"
).subscribe(Events.CONFIG_UPDATE, handler, "GenericTaskHandler.refresh_definitions")
async def list(self) -> list[TaskDefinitionModel]:
async def all(self) -> list[TaskDefinitionModel]:
async with self.session() as session:
result: Result[tuple[TaskDefinitionModel]] = await session.execute(
select(TaskDefinitionModel).order_by(TaskDefinitionModel.priority.asc(), TaskDefinitionModel.name.asc())
@ -115,9 +118,9 @@ class TaskDefinitionsRepository(metaclass=Singleton):
async def create(self, payload: dict[str, Any]) -> TaskDefinitionModel:
async with self.session() as session:
model: TaskDefinitionModel = TaskDefinitionModel(**payload) if isinstance(payload, dict) else payload
model: TaskDefinitionModel = TaskDefinitionModel(**payload)
if model.id is not None:
model.id = None
model.id = None # ty: ignore
if await self.get_by_name(name=model.name) is not None:
msg: str = f"Task definition with name '{model.name}' already exists."

View file

@ -48,10 +48,13 @@ class HandleTask(TaskSchema):
if isinstance(ret, tuple):
return ret
archive_file: Path = ret.get("file")
items: set[str] = ret.get("items", set())
archive_file = ret.get("file")
items = ret.get("items", set())
if not isinstance(archive_file, Path) or not isinstance(items, set):
return (False, "Failed to get archive information.")
archive_items = [item for item in items if isinstance(item, str)]
if len(items) < 1 or not archive_add(archive_file, list(items)):
if len(archive_items) < 1 or not archive_add(archive_file, archive_items):
return (True, "No new items to mark as downloaded.")
return (True, f"Task '{self.name}' items marked as downloaded.")
@ -70,10 +73,13 @@ class HandleTask(TaskSchema):
if isinstance(ret, tuple):
return ret
archive_file: Path = ret.get("file")
items: set[str] = ret.get("items", set())
archive_file = ret.get("file")
items = ret.get("items", set())
if not isinstance(archive_file, Path) or not isinstance(items, set):
return (False, "Failed to get archive information.")
archive_items = [item for item in items if isinstance(item, str)]
if len(items) < 1 or not archive_delete(archive_file, list(items)):
if len(archive_items) < 1 or not archive_delete(archive_file, archive_items):
return (True, "No items to remove from archive file.")
return (True, f"Removed '{self.name}' items from archive file.")

View file

@ -1,4 +1,3 @@
import logging
from typing import Any
from aiohttp import web
@ -16,9 +15,10 @@ from app.features.tasks.definitions.schemas import (
from app.features.tasks.definitions.utils import model_to_schema, schema_to_payload
from app.library.encoder import Encoder
from app.library.Events import EventBus, Events
from app.library.log import get_logger
from app.library.router import route
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
@route("GET", "api/tasks/definitions/", "task_definitions")
@ -95,7 +95,11 @@ async def task_definitions_create(request: Request, encoder: Encoder, notify: Ev
except ValueError as exc:
return web.json_response(data={"error": str(exc)}, status=web.HTTPBadRequest.status_code)
except Exception as exc:
LOG.exception(exc)
LOG.exception(
"Failed to create task definition '%s'.",
getattr(definition_input, "name", None),
extra={"definition": getattr(definition_input, "name", None), "exception_type": type(exc).__name__},
)
return web.json_response(
data={"error": "Failed to create task definition."},
status=web.HTTPInternalServerError.status_code,
@ -144,7 +148,15 @@ async def task_definitions_update(request: Request, encoder: Encoder, notify: Ev
except ValueError as exc:
return web.json_response(data={"error": str(exc)}, status=web.HTTPBadRequest.status_code)
except Exception as exc:
LOG.exception(exc)
LOG.exception(
"Failed to update task definition '%s'.",
definition_input.name,
extra={
"definition_id": identifier,
"definition": definition_input.name,
"exception_type": type(exc).__name__,
},
)
return web.json_response(
data={"error": "Failed to update task definition."},
status=web.HTTPInternalServerError.status_code,
@ -202,7 +214,11 @@ async def task_definitions_patch(request: Request, encoder: Encoder, notify: Eve
except ValueError as exc:
return web.json_response(data={"error": str(exc)}, status=web.HTTPBadRequest.status_code)
except Exception as exc:
LOG.exception(exc)
LOG.exception(
"Failed to patch task definition '%s'.",
identifier,
extra={"definition_id": identifier, "exception_type": type(exc).__name__},
)
return web.json_response(
data={"error": "Failed to patch task definition."},
status=web.HTTPInternalServerError.status_code,
@ -228,7 +244,11 @@ async def task_definitions_delete(request: Request, encoder: Encoder, notify: Ev
except KeyError as exc:
return web.json_response(data={"error": str(exc)}, status=web.HTTPNotFound.status_code)
except Exception as exc:
LOG.exception(exc)
LOG.exception(
"Failed to delete task definition '%s'.",
identifier,
extra={"definition_id": identifier, "exception_type": type(exc).__name__},
)
return web.json_response(
data={"error": "Failed to delete task definition."},
status=web.HTTPInternalServerError.status_code,

View file

@ -3,18 +3,19 @@ from __future__ import annotations
import asyncio
import importlib
import inspect
import logging
import pkgutil
import random
from datetime import UTC, datetime
from typing import TYPE_CHECKING, Any
from app.features.tasks.definitions.handlers._base_handler import BaseHandler
from app.features.tasks.definitions.results import HandleTask, TaskFailure, TaskItem, TaskResult
from app.features.tasks.models import TaskModel
from app.features.ytdlp.utils import archive_read
from app.library.downloads.queue_manager import DownloadQueue
from app.library.Events import EventBus, Events
from app.library.ItemDTO import Item, ItemDTO
from app.library.log import get_logger
from app.library.Services import Services
if TYPE_CHECKING:
@ -22,12 +23,12 @@ if TYPE_CHECKING:
from app.library.config import Config
from app.library.Scheduler import Scheduler
LOG: logging.Logger = logging.getLogger("definitions.service")
LOG = get_logger()
class TaskHandle:
def __init__(self, scheduler: Scheduler, tasks: TasksRepository, config: Config) -> None:
self._handlers: list[type] = []
self._handlers: list[type[BaseHandler]] = []
"The available handlers."
self._repo: TasksRepository = tasks
"The tasks manager."
@ -35,7 +36,7 @@ class TaskHandle:
"The scheduler."
self._config: Config = config
"The configuration."
self._task_name: str = f"{__class__.__name__}._dispatcher"
self._task_name: str = f"{TaskHandle.__name__}._dispatcher"
"The task name for the scheduler."
self._queued: dict[str, set[str]] = {}
"Queued archive IDs per handler."
@ -45,11 +46,11 @@ class TaskHandle:
EventBus.get_instance().subscribe(
Events.ITEM_ERROR,
self._handle_item_error,
f"{__class__.__name__}.item_error",
f"{TaskHandle.__name__}.item_error",
)
def load(self) -> None:
self._handlers: list[type] = self._discover()
self._handlers: list[type[BaseHandler]] = self._discover()
timer: str = self._config.tasks_handler_timer
try:
@ -58,21 +59,30 @@ class TaskHandle:
CronSim(timer, datetime.now(UTC))
except Exception as e:
timer = "15 */1 * * *"
LOG.error(f"Invalid timer format. '{e!s}'. Defaulting to '{timer}'.")
LOG.error(
"Invalid task handler timer '%s'; using default '%s'.",
self._config.tasks_handler_timer,
timer,
extra={
"timer": self._config.tasks_handler_timer,
"default_timer": timer,
"exception_type": type(e).__name__,
},
)
self._scheduler.add(
timer=timer,
func=lambda: asyncio.create_task(self._dispatcher(), name="task-handler-dispatcher"),
id=f"{__class__.__name__}._dispatcher",
id=f"{TaskHandle.__name__}._dispatcher",
)
async def _dispatcher(self):
s: dict[str, list[str]] = {"h": [], "d": [], "u": [], "f": []}
handler_groups: dict[str, list[tuple[HandleTask, type]]] = {}
dispatches: list[tuple[HandleTask, type, asyncio.Task[TaskResult | TaskFailure | None]]] = []
handler_groups: dict[str, list[tuple[HandleTask, type[BaseHandler]]]] = {}
dispatches: list[tuple[HandleTask, type[BaseHandler], asyncio.Task[TaskResult | TaskFailure | None]]] = []
tasks: list[TaskModel] = await self._repo.list()
tasks: list[TaskModel] = await self._repo.all()
for task_model in tasks:
task: HandleTask = HandleTask.model_validate(task_model)
@ -82,12 +92,16 @@ class TaskHandle:
continue
if not task.get_ytdlp_opts().get_all().get("download_archive"):
LOG.debug(f"Task '{task.name}' does not have an archive file configured.")
LOG.debug(
"Task '%s' does not have an archive file configured.",
task.name,
extra={"task_id": task.id, "task_name": task.name},
)
s["f"].append(task.name)
continue
try:
handler: type | None = await self._find_handler(task)
handler: type[BaseHandler] | None = await self._find_handler(task)
if handler is None:
s["u"].append(task.name)
continue
@ -97,7 +111,11 @@ class TaskHandle:
handler_groups[handler_name] = []
handler_groups[handler_name].append((task, handler))
except Exception as e:
LOG.error(f"Failed to handle task '{task.name}'. '{e!s}'.")
LOG.exception(
"Failed to find handler for task '%s'.",
task.name,
extra={"task_id": task.id, "task_name": task.name, "exception_type": type(e).__name__},
)
s["f"].append(task.name)
for tasks_with_handlers in handler_groups.values():
@ -114,7 +132,17 @@ class TaskHandle:
t.add_done_callback(lambda fut, t=task: self._handle_exception(fut, t))
dispatches.append((task, handler, t))
except Exception as e:
LOG.error(f"Failed to dispatch task '{task.name}'. '{e!s}'.")
LOG.exception(
"Failed to schedule handler '%s' for task '%s'.",
handler.__name__,
task.name,
extra={
"task_id": task.id,
"task_name": task.name,
"handler_name": handler.__name__,
"exception_type": type(e).__name__,
},
)
s["f"].append(task.name)
if dispatches:
@ -130,16 +158,33 @@ class TaskHandle:
continue
if result is None:
LOG.error(f"Handler '{handler.__name__}' returned no result for task '{task.name}'.")
LOG.error(
"Handler '%s' returned no result for task '%s'.",
handler.__name__,
task.name,
extra={"task_id": task.id, "task_name": task.name, "handler_name": handler.__name__},
)
s["f"].append(task.name)
if len(tasks) > 0:
LOG.info(
f"Tasks handler summary: Handled: {len(s['h'])}, Unhandled: {len(s['u'])}, Disabled: {len(s['d'])}, Failed: {len(s['f'])}."
"Task dispatch finished: %s handled, %s unhandled, %s disabled, %s failed.",
len(s["h"]),
len(s["u"]),
len(s["d"]),
len(s["f"]),
extra={
"handled_count": len(s["h"]),
"unhandled_count": len(s["u"]),
"disabled_count": len(s["d"]),
"failed_count": len(s["f"]),
},
)
async def _dispatch(self, task: HandleTask, handler: type, delay: float) -> TaskResult | TaskFailure | None:
async def _dispatch(
self, task: HandleTask, handler: type[BaseHandler], delay: float
) -> TaskResult | TaskFailure | None:
"""
Dispatch a task after a random delay to avoid rate limiting.
@ -153,7 +198,12 @@ class TaskHandle:
"""
if delay > 0:
LOG.debug(f"Delaying dispatch of task '{task.name}' by {delay:.1f} seconds.")
LOG.debug(
"Delaying dispatch of task '%s' by %.1f seconds.",
task.name,
delay,
extra={"task_id": task.id, "task_name": task.name, "delay_s": round(delay, 1)},
)
await asyncio.sleep(delay)
return await self.dispatch(task, handler=handler)
@ -162,15 +212,29 @@ class TaskHandle:
return
if exc := fut.exception():
LOG.error(f"Exception while handling task '{task.name}': {exc}")
LOG.exception(
"Task handler raised after dispatch.",
extra={"task_id": task.id, "task_name": task.name, "exception_type": type(exc).__name__},
exc_info=(type(exc), exc, exc.__traceback__),
)
async def _find_handler(self, task: HandleTask) -> type | None:
async def _find_handler(self, task: HandleTask) -> type[BaseHandler] | None:
for cls in self._handlers:
try:
if await Services.get_instance().handle_async(handler=cls.can_handle, task=task):
return cls
except Exception as e:
LOG.exception(e)
LOG.exception(
"Handler '%s' capability check failed for task '%s'.",
cls.__name__,
task.name,
extra={
"task_id": task.id,
"task_name": task.name,
"handler_name": cls.__name__,
"exception_type": type(e).__name__,
},
)
continue
return None
@ -178,9 +242,10 @@ class TaskHandle:
async def dispatch(
self,
task: HandleTask,
handler: type | None = None,
**kwargs, # noqa: ARG002
handler: type[BaseHandler] | None = None,
**kwargs,
) -> TaskResult | TaskFailure | None:
_ = kwargs
"""
Dispatch a task to the appropriate handler.
@ -204,11 +269,31 @@ class TaskHandle:
extraction: TaskResult | TaskFailure = await services.handle_async(
handler=handler.extract, task=task, config=self._config
)
except NotImplementedError:
LOG.error(f"Handler '{handler.__name__}' does not implement extract().")
except NotImplementedError as exc:
LOG.exception(
"Task handler '%s' does not implement extraction for task '%s'.",
handler.__name__,
task.name,
extra={
"task_id": task.id,
"task_name": task.name,
"handler_name": handler.__name__,
"exception_type": type(exc).__name__,
},
)
return TaskFailure(message="Handler does not support extraction.")
except Exception as exc:
LOG.exception(exc)
LOG.exception(
"Handler '%s' extraction failed for task '%s'.",
handler.__name__,
task.name,
extra={
"task_id": task.id,
"task_name": task.name,
"handler_name": handler.__name__,
"exception_type": type(exc).__name__,
},
)
raise
if isinstance(extraction, TaskFailure):
@ -216,12 +301,27 @@ class TaskHandle:
if extraction.error and extraction.error != extraction.message:
msg = f"{msg} {extraction.error}"
LOG.error(f"Handler '{handler.__name__}' failed to extract items for task '{task.name}': {msg}")
LOG.error(
"Handler '%s' failed to extract items for task '%s' because %s.",
handler.__name__,
task.name,
msg,
extra={"task_id": task.id, "task_name": task.name, "handler_name": handler.__name__, "error": msg},
)
return extraction
if not isinstance(extraction, TaskResult):
LOG.error(
f"Handler '{handler.__name__}' returned unexpected result type '{type(extraction).__name__}'.",
"Handler '%s' returned unexpected result type '%s' for task '%s'.",
handler.__name__,
type(extraction).__name__,
task.name,
extra={
"task_id": task.id,
"task_name": task.name,
"handler_name": handler.__name__,
"result_type": type(extraction).__name__,
},
)
return TaskFailure(
message="Handler returned invalid result type.", metadata={"type": type(extraction).__name__}
@ -249,7 +349,18 @@ class TaskHandle:
for item in raw_items:
if not isinstance(item, TaskItem):
LOG.warning(f"Handler '{handler.__name__}' returned unexpected result: {item!r}")
LOG.warning(
"Handler '%s' returned unexpected item type '%s' for task '%s'.",
handler.__name__,
type(item).__name__,
task.name,
extra={
"task_id": task.id,
"task_name": task.name,
"handler_name": handler.__name__,
"item_type": type(item).__name__,
},
)
continue
url: str = item.url
@ -258,7 +369,13 @@ class TaskHandle:
archive_id: str | None = item.archive_id
if not archive_id:
LOG.warning(f"'{task.name}': Item with URL '{url}' is missing an archive ID. Skipping.")
LOG.warning(
"Handler '%s' skipped '%s' for task '%s' because it has no archive ID.",
handler.__name__,
url,
task.name,
extra={"task_id": task.id, "task_name": task.name, "handler_name": handler.__name__, "url": url},
)
continue
if archive_id in queued:
@ -287,12 +404,31 @@ class TaskHandle:
if not filtered:
if raw_items:
LOG.debug(
f"Handler '{handler.__name__}' produced '{len(raw_items)}' for '{task.name}' items, none queued after filtering."
"Handler '%s' found %s item(s) for task '%s', but none were queued.",
handler.__name__,
len(raw_items),
task.name,
extra={
"task_id": task.id,
"task_name": task.name,
"handler_name": handler.__name__,
"raw_count": len(raw_items),
},
)
return TaskResult(items=[], metadata=metadata)
LOG.info(
f"Handler '{handler.__name__}' Found '{len(filtered)}' new items for '{task.name}' (raw={len(raw_items)})."
"Handler '%s' found %s new item(s) for task '%s'.",
handler.__name__,
len(filtered),
task.name,
extra={
"task_id": task.id,
"task_name": task.name,
"handler_name": handler.__name__,
"item_count": len(filtered),
"raw_count": len(raw_items),
},
)
base_item = Item.format(
@ -367,7 +503,12 @@ class TaskHandle:
try:
matched = await services.handle_async(handler=handler_cls.can_handle, task=task)
except Exception as exc: # pragma: no cover - defensive
LOG.exception(exc)
LOG.exception(
"Handler '%s' inspection capability check failed for '%s'.",
handler_cls.__name__,
url,
extra={"handler_name": handler_cls.__name__, "url": url, "exception_type": type(exc).__name__},
)
message = str(exc)
return TaskFailure(
message=message,
@ -405,7 +546,12 @@ class TaskHandle:
metadata={**base_metadata, "supported": False},
)
except Exception as exc:
LOG.exception(exc)
LOG.exception(
"Handler '%s' manual inspection failed for '%s'.",
handler_cls.__name__,
url,
extra={"handler_name": handler_cls.__name__, "url": url, "exception_type": type(exc).__name__},
)
message = str(exc)
return TaskFailure(
message=message,
@ -426,7 +572,11 @@ class TaskHandle:
if not isinstance(extraction, TaskResult):
LOG.error(
f"Handler '{handler_cls.__name__}' returned unexpected result type '{type(extraction).__name__}' during inspection.",
"Handler '%s' returned unexpected result type '%s' while inspecting '%s'.",
handler_cls.__name__,
type(extraction).__name__,
url,
extra={"handler_name": handler_cls.__name__, "url": url, "result_type": type(extraction).__name__},
)
extraction = TaskResult()
@ -436,11 +586,11 @@ class TaskHandle:
return TaskResult(items=list(extraction.items), metadata=combined_metadata)
def _discover(self) -> list[type]:
def _discover(self) -> list[type[BaseHandler]]:
"""Discover all available task handlers."""
import app.features.tasks.definitions.handlers as handlers_pkg
handlers: list[type] = []
handlers: list[type[BaseHandler]] = []
for _, module_name, _ in pkgutil.iter_modules(handlers_pkg.__path__):
if module_name.startswith("_"):

View file

@ -8,6 +8,7 @@ from app.features.tasks.definitions.results import TaskFailure, TaskResult
from app.features.tasks.definitions.schemas import (
Definition,
EngineConfig,
Parse,
RequestConfig,
ResponseConfig,
TaskDefinition,
@ -30,10 +31,12 @@ def test_build_def_payload():
created_at=datetime.now(),
updated_at=datetime.now(),
definition=Definition(
parse={
"link": {"type": "css", "expression": ".article a.link::attr(href)"},
"title": {"type": "css", "expression": ".article .title", "attribute": "text"},
},
parse=Parse.model_validate(
{
"link": {"type": "css", "expression": ".article a.link::attr(href)"},
"title": {"type": "css", "expression": ".article .title", "attribute": "text"},
}
),
engine=EngineConfig(),
request=RequestConfig(),
response=ResponseConfig(),
@ -54,15 +57,17 @@ def test_build_def_container():
created_at=datetime.now(),
updated_at=datetime.now(),
definition=Definition(
parse={
"items": {
"selector": ".cards .card",
"fields": {
"link": {"type": "css", "expression": ".card-header a", "attribute": "href"},
"title": {"type": "css", "expression": ".card-header a", "attribute": "text"},
},
parse=Parse.model_validate(
{
"items": {
"selector": ".cards .card",
"fields": {
"link": {"type": "css", "expression": ".card-header a", "attribute": "href"},
"title": {"type": "css", "expression": ".card-header a", "attribute": "text"},
},
}
}
},
),
engine=EngineConfig(),
request=RequestConfig(),
response=ResponseConfig(),
@ -82,16 +87,18 @@ def test_build_def_json():
created_at=datetime.now(),
updated_at=datetime.now(),
definition=Definition(
parse={
"items": {
"type": "jsonpath",
"selector": "items",
"fields": {
"link": {"type": "jsonpath", "expression": "url"},
"title": {"type": "jsonpath", "expression": "title"},
},
parse=Parse.model_validate(
{
"items": {
"type": "jsonpath",
"selector": "items",
"fields": {
"link": {"type": "jsonpath", "expression": "url"},
"title": {"type": "jsonpath", "expression": "title"},
},
}
}
},
),
engine=EngineConfig(),
request=RequestConfig(),
response=ResponseConfig(type="json"),
@ -112,11 +119,13 @@ def test_parse_items_basic():
created_at=datetime.now(),
updated_at=datetime.now(),
definition=Definition(
parse={
"link": {"type": "css", "expression": ".article a.link::attr(href)", "attribute": None},
"title": {"type": "css", "expression": ".article .title", "attribute": "text"},
"id": {"type": "css", "expression": ".article", "attribute": "data-id"},
},
parse=Parse.model_validate(
{
"link": {"type": "css", "expression": ".article a.link::attr(href)", "attribute": None},
"title": {"type": "css", "expression": ".article .title", "attribute": "text"},
"id": {"type": "css", "expression": ".article", "attribute": "data-id"},
}
),
engine=EngineConfig(),
request=RequestConfig(),
response=ResponseConfig(),
@ -154,34 +163,36 @@ def test_parse_items_cards():
created_at=datetime.now(),
updated_at=datetime.now(),
definition=Definition(
parse={
"items": {
"type": "css",
"selector": ".columns .card",
"fields": {
"link": {
"type": "css",
"expression": ".card-header a[href]",
"attribute": "href",
parse=Parse.model_validate(
{
"items": {
"type": "css",
"selector": ".columns .card",
"fields": {
"link": {
"type": "css",
"expression": ".card-header a[href]",
"attribute": "href",
},
"title": {
"type": "css",
"expression": ".card-header a[href]",
"attribute": "text",
},
"poet": {
"type": "css",
"expression": "footer .card-footer-item:first-child a",
"attribute": "text",
},
"category": {
"type": "css",
"expression": "footer .card-footer-item:nth-child(2) a",
"attribute": "text",
},
},
"title": {
"type": "css",
"expression": ".card-header a[href]",
"attribute": "text",
},
"poet": {
"type": "css",
"expression": "footer .card-footer-item:first-child a",
"attribute": "text",
},
"category": {
"type": "css",
"expression": "footer .card-footer-item:nth-child(2) a",
"attribute": "text",
},
},
}
}
},
),
engine=EngineConfig(),
request=RequestConfig(),
response=ResponseConfig(),
@ -249,17 +260,19 @@ def test_parse_items_json():
created_at=datetime.now(),
updated_at=datetime.now(),
definition=Definition(
parse={
"items": {
"type": "jsonpath",
"selector": "entries",
"fields": {
"link": {"type": "jsonpath", "expression": "url"},
"title": {"type": "jsonpath", "expression": "title"},
"id": {"type": "jsonpath", "expression": "id"},
},
parse=Parse.model_validate(
{
"items": {
"type": "jsonpath",
"selector": "entries",
"fields": {
"link": {"type": "jsonpath", "expression": "url"},
"title": {"type": "jsonpath", "expression": "title"},
"id": {"type": "jsonpath", "expression": "id"},
},
}
}
},
),
engine=EngineConfig(),
request=RequestConfig(),
response=ResponseConfig(type="json"),
@ -297,16 +310,18 @@ async def test_generic_task_handler_inspect(monkeypatch):
created_at=datetime.now(),
updated_at=datetime.now(),
definition=Definition(
parse={
"items": {
"type": "jsonpath",
"selector": "items",
"fields": {
"link": {"type": "jsonpath", "expression": "url"},
"title": {"type": "jsonpath", "expression": "title"},
},
parse=Parse.model_validate(
{
"items": {
"type": "jsonpath",
"selector": "items",
"fields": {
"link": {"type": "jsonpath", "expression": "url"},
"title": {"type": "jsonpath", "expression": "title"},
},
}
}
},
),
engine=EngineConfig(),
request=RequestConfig(),
response=ResponseConfig(type="json"),
@ -351,16 +366,18 @@ def test_parse_items_json_list():
created_at=datetime.now(),
updated_at=datetime.now(),
definition=Definition(
parse={
"items": {
"type": "jsonpath",
"selector": "[]",
"fields": {
"link": {"type": "jsonpath", "expression": "url"},
"title": {"type": "jsonpath", "expression": "title"},
},
parse=Parse.model_validate(
{
"items": {
"type": "jsonpath",
"selector": "[]",
"fields": {
"link": {"type": "jsonpath", "expression": "url"},
"title": {"type": "jsonpath", "expression": "title"},
},
}
}
},
),
engine=EngineConfig(),
request=RequestConfig(),
response=ResponseConfig(type="json"),

View file

@ -69,7 +69,7 @@ class TestTaskDefinitionsRepository:
await repo.create(_sample_definition("Alpha", priority=2))
await repo.create(_sample_definition("Beta", priority=1))
items = await repo.list()
items = await repo.all()
assert len(items) == 2, "Should return two task definitions"
assert [item.name for item in items] == ["Beta", "Alpha"], "Should sort by priority then name"

View file

@ -1,9 +1,17 @@
from typing import Any
from typing import Any, Literal, overload
from app.features.tasks.definitions.models import TaskDefinitionModel
from app.features.tasks.definitions.schemas import Definition, TaskDefinition, TaskDefinitionSummary
@overload
def model_to_schema(model: TaskDefinitionModel, summary: Literal[False] = False) -> TaskDefinition: ...
@overload
def model_to_schema(model: TaskDefinitionModel, summary: Literal[True]) -> TaskDefinitionSummary: ...
def model_to_schema(model: TaskDefinitionModel, summary: bool = False) -> TaskDefinition | TaskDefinitionSummary:
"""
Convert a TaskDefinitionModel to a TaskDefinition or TaskDefinitionSummary schema.

View file

@ -1,18 +1,18 @@
from __future__ import annotations
import json
import logging
from pathlib import Path
from typing import TYPE_CHECKING, Any
from app.features.core.migration import Migration as FeatureMigration
from app.features.tasks.schemas import Task
from app.library.config import Config
from app.library.log import get_logger
if TYPE_CHECKING:
from app.features.tasks.repository import TasksRepository
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
class Migration(FeatureMigration):
@ -36,7 +36,11 @@ class Migration(FeatureMigration):
try:
items: list[dict[str, Any]] | None = json.loads(self._source_file.read_text())
except Exception as exc:
LOG.exception("Failed to read %s: %s. Ignoring", self._source_file, exc)
LOG.exception(
"Failed to read tasks migration file '%s'. Ignoring.",
self._source_file,
extra={"file_path": str(self._source_file), "exception_type": type(exc).__name__},
)
await self._move_file(self._source_file)
return
@ -54,7 +58,11 @@ class Migration(FeatureMigration):
await self._repo.create(normalized)
inserted += 1
except Exception as exc:
LOG.exception("Failed to insert task '%s': %s", normalized["name"], exc)
LOG.exception(
"Failed to insert task '%s'.",
normalized["name"],
extra={"task_name": normalized["name"], "exception_type": type(exc).__name__},
)
LOG.info("Migrated %s task(s) from %s.", inserted, self._source_file)
await self._move_file(self._source_file)

View file

@ -1,29 +1,48 @@
from __future__ import annotations
import logging
from typing import TYPE_CHECKING, Any
from sqlalchemy import func, or_, select
from app.features.core.deps import get_session
from app.features.tasks.models import TaskModel
from app.library.log import get_logger
from app.library.Singleton import Singleton
if TYPE_CHECKING:
from collections.abc import AsyncGenerator
from collections.abc import Callable
from contextlib import AbstractAsyncContextManager
from sqlalchemy.engine.result import Result
from sqlalchemy.ext.asyncio import AsyncSession
from sqlalchemy.sql.elements import ColumnElement
from sqlalchemy.sql.selectable import Select
LOG: logging.Logger = logging.getLogger(__name__)
SessionFactory = Callable[[], AbstractAsyncContextManager[AsyncSession]]
LOG = get_logger()
def _model_from_payload(payload: dict[str, Any]) -> TaskModel:
model = TaskModel()
for key, value in payload.items():
if not hasattr(model, key):
msg = f"'{key}' is an invalid keyword argument for TaskModel"
raise TypeError(msg)
setattr(model, key, value)
return model
def _coerce_model(payload: TaskModel | dict[str, Any]) -> TaskModel:
if isinstance(payload, TaskModel):
return payload
return _model_from_payload(payload)
class TasksRepository(metaclass=Singleton):
def __init__(self, session: AsyncGenerator[AsyncSession] | None = None) -> None:
def __init__(self, session: SessionFactory | None = None) -> None:
self._migrated = False
self.session = session or get_session
self.session: SessionFactory = session or get_session
async def run_migrations(self) -> None:
if self._migrated:
@ -38,7 +57,7 @@ class TasksRepository(metaclass=Singleton):
def get_instance() -> TasksRepository:
return TasksRepository()
async def list(self) -> list[TaskModel]:
async def all(self) -> list[TaskModel]:
async with self.session() as session:
result: Result[tuple[TaskModel]] = await session.execute(select(TaskModel).order_by(TaskModel.name.asc()))
return list(result.scalars().all())
@ -90,7 +109,7 @@ class TasksRepository(metaclass=Singleton):
"""Get all enabled tasks."""
async with self.session() as session:
result: Result[tuple[TaskModel]] = await session.execute(
select(TaskModel).where(TaskModel.enabled == True).order_by(TaskModel.name.asc()) # noqa: E712
select(TaskModel).where(TaskModel.enabled).order_by(TaskModel.name.asc())
)
return list(result.scalars().all())
@ -102,11 +121,11 @@ class TasksRepository(metaclass=Singleton):
)
return list(result.scalars().all())
async def create(self, payload: TaskModel | dict) -> TaskModel:
async def create(self, payload: TaskModel | dict[str, Any]) -> TaskModel:
async with self.session() as session:
model: TaskModel = TaskModel(**payload) if isinstance(payload, dict) else payload
model = _coerce_model(payload)
if model.id is not None:
model.id = None
model.id = None # ty: ignore
if await self.get_by_name(name=model.name) is not None:
msg: str = f"Task with name '{model.name}' already exists."

View file

@ -1,5 +1,4 @@
import asyncio
import logging
from typing import TYPE_CHECKING, Any
from aiohttp import web
@ -18,6 +17,7 @@ from app.library.ag_utils import ag
from app.library.config import Config
from app.library.encoder import Encoder
from app.library.Events import EventBus, Events
from app.library.log import get_logger
from app.library.router import route
from app.library.Utils import get_channel_images, get_file, validate_url
@ -25,7 +25,7 @@ if TYPE_CHECKING:
from pathlib import Path
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
TIMER_SLOTS_PER_HOUR: int = 12
@ -94,7 +94,11 @@ def _offset_timer(timer: str, index: int) -> str:
return f"{minute} {hour} {dom} {month} {dow}"
except Exception as e:
LOG.warning(f"Failed to offset timer '{timer}': {e}")
LOG.warning(
"Failed to offset task timer.",
extra={"timer": timer, "index": index, "error": str(e), "exception_type": type(e).__name__},
exc_info=True,
)
return timer
@ -137,10 +141,15 @@ async def _get_info(url: str, preset: str) -> tuple[str | None, str | None]:
return (name, converted_url)
except TimeoutError:
LOG.debug(f"Timeout while inferring name from '{url}'")
LOG.debug("Timeout while inferring name from '%s'.", url, extra={"url": url, "preset": preset})
return (None, None)
except Exception as e:
LOG.debug(f"Failed to infer name from '{url}': {e}")
LOG.debug(
"Failed to infer a task name from '%s' because %s.",
url,
e,
extra={"url": url, "preset": preset, "error": str(e)},
)
return (None, None)
@ -234,12 +243,12 @@ async def tasks_add(
for idx, item in enumerate(data):
if not isinstance(item, dict):
LOG.warning(f"Skipping item {idx}: not a dict")
LOG.warning("Skipping item %s: not a dict.", idx, extra={"index": idx})
continue
url = str(item.get("url", "")).strip()
if not url:
LOG.debug(f"Skipping item {idx}: empty URL")
LOG.debug("Skipping item %s: empty URL.", idx, extra={"index": idx})
continue
inferred_name, converted_url = await _get_info(url, item.get("preset", first_task.preset))
@ -293,7 +302,11 @@ async def tasks_add(
data=ConfigEvent(feature=CEFeature.TASKS, action=CEAction.CREATE, data=saved),
)
except ValueError as exc:
LOG.warning(f"Failed to create task {idx}: {exc}")
LOG.warning(
"Failed to create task from request item %s.",
idx,
extra={"index": idx, "error": str(exc), "exception_type": type(exc).__name__},
)
continue
if len(created_tasks) == 0:
@ -482,7 +495,16 @@ async def task_handler_inspect(request: Request, handler: TaskHandle, encoder: E
url=url, preset=preset, handler_name=handler_name, static_only=static_only
)
except Exception as e:
LOG.exception(e)
LOG.exception(
"Failed to inspect task handler for '%s'.",
url,
extra={
"handler_name": handler_name,
"url": url,
"static_only": static_only,
"exception_type": type(e).__name__,
},
)
return web.json_response(
{"error": "Failed to inspect handler.", "message": str(e)},
status=web.HTTPInternalServerError.status_code,
@ -631,7 +653,12 @@ async def task_metadata(request: Request, repo: TasksRepository, config: Config,
if not save_path.exists():
save_path.mkdir(parents=True, exist_ok=True)
except Exception as e:
LOG.warning(f"Failed to resolve final path from outtmpl. '{e!s}'")
LOG.warning(
"Failed to resolve the metadata output path for task '%s'.",
task.name,
extra={"task_id": task.id, "task_name": task.name, "error": str(e)},
exc_info=True,
)
info = {
"id": ag(metadata, ["id", "channel_id"]),
@ -649,7 +676,12 @@ async def task_metadata(request: Request, repo: TasksRepository, config: Config,
data={"error": "Failed to get title from metadata."}, status=web.HTTPBadRequest.status_code
)
LOG.info(f"Generating metadata for task '{task.name}' in '{save_path!s}'")
LOG.info(
"Generating metadata for task '%s' in '%s'.",
task.name,
save_path,
extra={"task_id": task.id, "task_name": task.name, "save_path": str(save_path)},
)
from yt_dlp.utils import sanitize_filename
@ -673,8 +705,9 @@ async def task_metadata(request: Request, repo: TasksRepository, config: Config,
xml_content += f' <uniqueid type="{NFOMakerPP._escape_text(info.get("id_type"))}" default="true">{NFOMakerPP._escape_text(info.get("id"))}</uniqueid>\n'
if info.get("uploader"):
xml_content += f" <studio>{NFOMakerPP._escape_text(info.get('uploader'))}</studio>\n"
if info.get("tags", []):
for tag in info.get("tags", []):
tags = info.get("tags", [])
if isinstance(tags, list):
for tag in tags:
xml_content += f" <tag>{NFOMakerPP._escape_text(tag)}</tag>\n"
if info.get("year"):
xml_content += f" <year>{info.get('year')}</year>\n"
@ -706,14 +739,25 @@ async def task_metadata(request: Request, repo: TasksRepository, config: Config,
url: str | None = None
try:
url = thumbnails.get(key)
LOG.info(f"Fetching thumbnail '{key}' from '{url}'")
LOG.info(
"Fetching '%s' thumbnail for task '%s'.",
key,
task.name,
extra={"task_id": task.id, "task_name": task.name, "thumbnail": key, "url": url},
)
if not url:
continue
try:
await asyncio.to_thread(validate_url, url, config.allow_internal_urls)
except ValueError:
LOG.warning(f"Invalid thumbnail url '{url}'")
except ValueError as exc:
LOG.warning(
"Task '%s' has an invalid '%s' thumbnail URL because %s.",
task.name,
key,
exc,
extra={"task_id": task.id, "task_name": task.name, "thumbnail": key, "url": url},
)
continue
resp = await client.request(
@ -727,11 +771,27 @@ async def task_metadata(request: Request, repo: TasksRepository, config: Config,
img_file.write_bytes(resp.content)
thumbnails[key] = str(img_file.relative_to(config.download_path))
except Exception as e:
url_log = url or "unknown"
LOG.warning(f"Failed to fetch thumbnail '{key}' from '{url_log}'. '{e!s}'")
LOG.warning(
"Failed to fetch '%s' thumbnail for task '%s'.",
key,
task.name,
extra={
"task_id": task.id,
"task_name": task.name,
"thumbnail": key,
"url": url,
"error": str(e),
},
exc_info=True,
)
continue
except Exception as e:
LOG.warning(f"Failed to fetch thumbnails. '{e!s}'")
LOG.warning(
"Failed to fetch metadata thumbnails for task '%s'.",
task.name,
extra={"task_id": task.id, "task_name": task.name, "error": str(e)},
exc_info=True,
)
return web.json_response(data=info, status=web.HTTPOk.status_code, dumps=encoder.encode)
except ValueError as e:

View file

@ -1,12 +1,12 @@
from __future__ import annotations
import logging
from typing import TYPE_CHECKING
from app.features.core.schemas import CEAction, CEFeature, ConfigEvent
from app.features.tasks.models import TaskModel
from app.features.tasks.utils import cron_time
from app.library.Events import Event, EventBus, Events
from app.library.log import get_logger
from app.library.Scheduler import Scheduler
from app.library.Services import Services
from app.library.Singleton import Singleton
@ -14,7 +14,7 @@ from app.library.Singleton import Singleton
if TYPE_CHECKING:
from aiohttp import web
LOG: logging.Logger = logging.getLogger("tasks.service")
LOG = get_logger()
class Tasks(metaclass=Singleton):
@ -51,7 +51,7 @@ class Tasks(metaclass=Singleton):
pass
async def _load_tasks(self) -> None:
tasks = await self._repo.list()
tasks = await self._repo.all()
for task in tasks:
if not task.timer or not task.enabled:
@ -59,10 +59,23 @@ class Tasks(metaclass=Singleton):
try:
self._scheduler.add(timer=task.timer, func=self._runner, args=(task,), id=f"task-cronjob-{task.id}")
LOG.info(f"Task '{task.id}: {task.name}' queued to be executed '{cron_time(task.timer)}'.")
LOG.info(
"Queued task '%s' to run at '%s'.",
task.name,
cron_time(task.timer),
extra={"task_id": task.id, "task_name": task.name, "timer": task.timer},
)
except Exception as e:
LOG.exception(e)
LOG.error(f"Failed to queue task '{task.name}'. '{e!s}'.")
LOG.exception(
"Failed to queue task '%s'.",
task.name,
extra={
"task_id": task.id,
"task_name": task.name,
"timer": task.timer,
"exception_type": type(e).__name__,
},
)
async def _init_handlers_service(self, scheduler) -> None:
"""Initialize the handlers service after migrations."""
@ -95,7 +108,12 @@ class Tasks(metaclass=Singleton):
if task.timer and task.enabled:
self._scheduler.add(timer=task.timer, func=self._runner, args=(task,), id=task_id)
LOG.info(f"Task '{task.id}: {task.name}' queued to be executed '{cron_time(task.timer)}'.")
LOG.info(
"Queued task '%s' to run at '%s'.",
task.name,
cron_time(task.timer),
extra={"task_id": task.id, "task_name": task.name, "timer": task.timer},
)
async def _runner(self, task: TaskModel) -> None:
"""
@ -113,17 +131,29 @@ class Tasks(metaclass=Singleton):
from app.library.ItemDTO import Item
timeNow: str = datetime.now(UTC).isoformat()
task_id = task.id
task_name = task.name
try:
if not (task := await self._repo.get(task.id)):
LOG.info(f"Task '{task.name}' no longer exists.")
current_task = await self._repo.get(task_id)
if not current_task:
LOG.info("Task '%s' no longer exists.", task_name, extra={"task_id": task_id, "task_name": task_name})
return
task = current_task
if not task.enabled:
LOG.debug(f"Task '{task.name}' is disabled. Skipping execution.")
LOG.debug(
"Task '%s' is disabled. Skipping execution.",
task.name,
extra={"task_id": task.id, "task_name": task.name},
)
return
if not task.url:
LOG.error(f"Failed to dispatch '{task.name}'. No URL found.")
LOG.error(
"Failed to dispatch task '%s' because it has no URL.",
task.name,
extra={"task_id": task.id, "task_name": task.name},
)
return
started: float = time.time()
@ -156,7 +186,19 @@ class Tasks(metaclass=Singleton):
timeNow = datetime.now(UTC).isoformat()
ended: float = time.time()
LOG.info(f"Task '{task.name}' completed at '{timeNow}' took '{ended - started:.2f}' seconds.")
LOG.info(
"Task '%s' completed in %.2f seconds.",
task.name,
ended - started,
extra={
"task_id": task.id,
"task_name": task.name,
"url": task.url,
"preset": preset,
"elapsed_s": round(ended - started, 2),
"status": status.get("status") if isinstance(status, dict) else None,
},
)
notify.emit(
Events.TASK_DISPATCHED,
@ -171,7 +213,17 @@ class Tasks(metaclass=Singleton):
message=f"Task '{task.name}' completed in '{ended - started:.2f}'.",
)
except Exception as e:
LOG.error(f"Failed to execute '{task.name}' at '{timeNow}'. '{e!s}'.")
LOG.exception(
"Failed to execute scheduled task '%s'.",
task.name,
extra={
"task_id": task.id,
"task_name": task.name,
"url": task.url,
"time": timeNow,
"exception_type": type(e).__name__,
},
)
EventBus.get_instance().emit(
Events.LOG_ERROR,
data={"preset": task.preset},

View file

@ -260,7 +260,7 @@ class TestTasksRepository:
await repo.create({"name": "Alice", "url": "https://example.com"})
await repo.create({"name": "Bob", "url": "https://example.com"})
items = await repo.list()
items = await repo.all()
assert items[0].name == "Alice", "Should be alphabetically first"
assert items[1].name == "Bob", "Should be alphabetically second"

View file

@ -1,6 +1,7 @@
from __future__ import annotations
from types import SimpleNamespace
from typing import Any
import pytest
import pytest_asyncio
@ -41,13 +42,13 @@ def patch_get_info(monkeypatch: pytest.MonkeyPatch) -> None:
def _json_request(method: str, path: str, payload: object, *, match_info: dict[str, str] | None = None) -> web.Request:
request = make_mocked_request(method, path, match_info=match_info or {}, app=SimpleNamespace())
mock_request: Any = make_mocked_request(method, path, match_info=match_info or {}, app=SimpleNamespace())
async def _json() -> object:
return payload
request.json = _json # type: ignore[attr-defined]
return request
mock_request.json = _json
return mock_request
class _Notify:
@ -85,7 +86,7 @@ async def test_add_requires_timer_without_handler(repo) -> None:
assert response.status == web.HTTPBadRequest.status_code
assert b"requires a timer" in response.body
assert await repo.list() == []
assert await repo.all() == []
@pytest.mark.asyncio
@ -109,7 +110,7 @@ async def test_add_all_or_nothing(repo) -> None:
assert response.status == web.HTTPBadRequest.status_code
assert b"requires a timer" in response.body
assert await repo.list() == []
assert await repo.all() == []
@pytest.mark.asyncio
@ -123,7 +124,7 @@ async def test_add_allows_handler_only(repo) -> None:
response = await router.tasks_add(request, repo, Encoder(), _Notify(), _Handler(matched=True))
assert response.status == web.HTTPOk.status_code
items = await repo.list()
items = await repo.all()
assert len(items) == 1
assert items[0].name == "Handler Only"

View file

@ -1,6 +1,6 @@
import logging
from app.library.log import get_logger
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
def cron_time(timer: str) -> str:
@ -12,5 +12,9 @@ def cron_time(timer: str) -> str:
cs = CronSim(timer, datetime.now(UTC))
return cs.explain()
except Exception as exc:
LOG.exception(exc)
LOG.exception(
"Failed to explain task timer '%s'.",
timer,
extra={"timer": timer, "exception_type": type(exc).__name__},
)
return timer

View file

@ -1,12 +1,12 @@
import logging
import os
import threading
import time
from pathlib import Path
from app.library.log import get_logger
from app.library.Singleton import ThreadSafe
LOG: logging.Logger = logging.getLogger("Archiver")
LOG = get_logger()
class _Entry:
@ -169,12 +169,21 @@ class Archiver(metaclass=ThreadSafe):
continue
ids.add(s)
except OSError as e:
LOG.error(f"Failed to read archive file '{key}': {e!s}")
LOG.exception(
"Failed to read archive file '%s'.",
key,
extra={"archive_file": key, "operation": "read", "exception_type": type(e).__name__},
)
ids = set()
try:
elapsed_ms: float = (time.perf_counter() - start) * 1000.0
LOG.debug(f"_ensure_loaded took {elapsed_ms:.2f}ms (loaded={len(ids)})")
LOG.debug(
"_ensure_loaded took %.2fms (loaded=%s)",
elapsed_ms,
len(ids),
extra={"archive_file": key, "elapsed_ms": round(elapsed_ms, 2), "loaded_count": len(ids)},
)
except Exception:
pass
@ -283,7 +292,17 @@ class Archiver(metaclass=ThreadSafe):
f.write("".join(f"{x}\n" for x in new_ids))
except OSError as e:
LOG.error(f"Failed to write to archive file '{key}': {e!s}")
LOG.exception(
"Failed to write %s item(s) to archive file '%s'.",
len(new_ids),
key,
extra={
"archive_file": key,
"operation": "add",
"item_count": len(new_ids),
"exception_type": type(e).__name__,
},
)
return False
entry.ids.update(new_ids)
@ -335,7 +354,17 @@ class Archiver(metaclass=ThreadSafe):
continue
kept_lines.append(line)
except OSError as e:
LOG.error(f"Failed reading archive for delete '{key}': {e!s}")
LOG.exception(
"Failed to read archive file '%s' before deleting %s item(s).",
key,
len(remove_ids),
extra={
"archive_file": key,
"operation": "delete_read",
"item_count": len(remove_ids),
"exception_type": type(e).__name__,
},
)
return False
if not changed:
@ -351,7 +380,17 @@ class Archiver(metaclass=ThreadSafe):
with path.open("w", encoding="utf-8") as f:
f.writelines(kept_lines)
except OSError as e:
LOG.error(f"Failed writing archive after delete '{key}': {e!s}")
LOG.exception(
"Failed to write archive file '%s' after deleting %s item(s).",
key,
len(remove_ids),
extra={
"archive_file": key,
"operation": "delete_write",
"item_count": len(remove_ids),
"exception_type": type(e).__name__,
},
)
return False
if entry.loaded:

View file

@ -12,25 +12,43 @@ from aiohttp import web
from app.features.ytdlp.utils import _DATA, LogWrapper, get_archive_id
from app.features.ytdlp.ytdlp import YTDLP
from app.library.log import get_logger
from app.library.Services import Services
from app.library.Singleton import Singleton
LOG: logging.Logger = logging.getLogger("downloads.extractor")
LOG = get_logger()
LIVE_REEXTRACT_STATUSES: set[str] = {"is_live", "post_live"}
REEXTRACT_INFO_KEY = "_ytptube_reextract"
def _ytdlp_logger(target: logging.Logger):
def _log(level: int, msg: str, *args: Any, **kwargs: Any) -> None:
return _YTDLPLogger(target)
class _YTDLPLogger:
def __init__(self, target: logging.Logger) -> None:
self.target = target
def __call__(self, level: int, msg: str, *args: Any, **kwargs: Any) -> None:
kwargs.setdefault("stacklevel", 4)
if level <= logging.DEBUG and isinstance(msg, str) and msg.startswith("[debug] "):
target.debug(msg.removeprefix("[debug] "), *args, **kwargs)
self.target.debug(msg.removeprefix("[debug] "), *args, **kwargs)
return
if level <= logging.DEBUG:
target.info(msg, *args, **kwargs)
self.target.info(msg, *args, **kwargs)
return
target.log(level, msg, *args, **kwargs)
self.target.log(level, msg, *args, **kwargs)
return _log
class _LogCapture:
def __init__(self, logs: list[str]) -> None:
self.logs = logs
def __call__(self, _: int, msg: str, *args: Any, **__: Any) -> None:
self.logs.append(msg % args if args else msg)
def _get_process_pool_kwargs() -> dict[str, Any]:
@ -102,7 +120,7 @@ class ExtractorPool(metaclass=Singleton):
def attach(self, app: web.Application) -> None:
"""Attach the extractor pool to the application (no-op for now)."""
app.on_shutdown.append(self.shutdown)
Services.get_instance().add(__class__.__name__, self)
Services.get_instance().add(type(self).__name__, self)
def _ensure_initialized(self, config: ExtractorConfig) -> None:
"""
@ -163,7 +181,10 @@ class ExtractorPool(metaclass=Singleton):
self._pool.shutdown(wait=False, cancel_futures=False)
LOG.debug("Extractor process pool shutdown complete")
except Exception as exc:
LOG.error("Error shutting down extractor process pool: %s", exc)
LOG.exception(
"Failed to shut down the extractor process pool.",
extra={"exception_type": type(exc).__name__},
)
else:
self._pool = None
@ -233,6 +254,23 @@ def _sanitize_config(config: dict[str, Any]) -> dict[str, Any]:
return sanitized
def needs_reextract(info: dict[str, Any]) -> bool:
return bool(info.get("is_live") or info.get("live_status") in LIVE_REEXTRACT_STATUSES)
def _process_safe_info(info: dict[str, Any]) -> dict[str, Any]:
if needs_reextract(info):
info = dict(info)
info[REEXTRACT_INFO_KEY] = True
for key in ("formats", "requested_formats", "requested_downloads", "fragments"):
info.pop(key, None)
if _is_picklable(info):
return info
return YTDLP.sanitize_info(info, remove_private_keys=False)
def extract_info_sync(
config: dict[str, Any],
url: str,
@ -241,8 +279,9 @@ def extract_info_sync(
follow_redirect: bool = False,
sanitize_info: bool = False,
capture_logs: int | None = None,
process_safe: bool = False,
**kwargs,
) -> tuple[dict[str, Any] | None, list[dict[str, Any]]]:
) -> tuple[dict[str, Any] | None, list[str]]:
"""
Extract video information from a URL.
@ -254,10 +293,11 @@ def extract_info_sync(
follow_redirect: Follow URL redirects
sanitize_info: Sanitize the extracted information
capture_logs: If provided (e.g., logging.WARNING), capture logs at this level.
process_safe: Strip non-pickleable data for safe inter-process communication.
**kwargs: Additional arguments
Returns:
tuple[dict | None, list[dict]]: Extracted information and captured logs.
tuple[dict | None, list[str]]: Extracted information and captured logs.
"""
params: dict[str, Any] = {**config, **_DATA.YTDLP_PARAMS, "simulate": True}
@ -286,7 +326,7 @@ def extract_info_sync(
captured_logs: list[str] = kwargs.get("captured_logs", [])
if capture_logs is not None:
log_wrapper.add_target(
target=lambda _, msg: captured_logs.append(msg),
target=_LogCapture(captured_logs),
level=capture_logs,
name="log-capture",
)
@ -316,6 +356,7 @@ def extract_info_sync(
follow_redirect=follow_redirect,
sanitize_info=sanitize_info,
capture_logs=capture_logs,
process_safe=process_safe,
captured_logs=captured_logs,
**kwargs,
)
@ -334,6 +375,9 @@ def extract_info_sync(
result = YTDLP.sanitize_info(data, remove_private_keys=True) if sanitize_info else data
if process_safe and isinstance(result, dict):
result = _process_safe_info(result)
return (result, captured_logs)
finally:
logging.Logger.manager.loggerDict.pop(logger_name, None)
@ -350,7 +394,7 @@ async def fetch_info(
extractor_config: ExtractorConfig | None = None,
budget_sleep: bool = False,
**kwargs,
) -> tuple[dict[str, Any] | None, list[dict[str, Any]]]:
) -> tuple[dict[str, Any] | None, list[str]]:
"""
Extract video information from a URL.
@ -370,7 +414,7 @@ async def fetch_info(
**kwargs: Additional arguments
Returns:
tuple[dict | None, list[dict]]: Extracted information and captured logs.
tuple[dict | None, list[str]]: Extracted information and captured logs.
"""
if extractor_config is None:
@ -390,6 +434,8 @@ async def fetch_info(
loop = asyncio.get_running_loop()
safe_config = _sanitize_config(config)
safe_kwargs = _sanitize_picklable(kwargs)
safe_kwargs.pop("process_safe", None)
timeout = _sleep_timeout(safe_config, extractor_config.timeout, budget_sleep)
try:
@ -408,7 +454,8 @@ async def fetch_info(
follow_redirect=follow_redirect,
sanitize_info=sanitize_info,
capture_logs=capture_logs,
**kwargs,
process_safe=True,
**safe_kwargs,
),
),
timeout=timeout,
@ -418,8 +465,23 @@ async def fetch_info(
raise
except Exception as exc:
LOG.exception(exc)
LOG.warning("extract_info process pool failed, falling back to thread pool url=%s error=%s", url, exc)
LOG.warning(
"yt-dlp extraction for '%s' fell back to the thread pool after the process pool failed.",
url,
extra={
"url": url,
"timeout": timeout,
"concurrency": extractor_config.concurrency,
"pool": "process",
"fallback": "thread",
"follow_redirect": follow_redirect,
"no_archive": no_archive,
"sanitize_info": sanitize_info,
"capture_logs_level": capture_logs,
"exception_type": type(exc).__name__,
},
exc_info=True,
)
return await asyncio.wait_for(
fut=loop.run_in_executor(
None,

View file

@ -1,9 +1,10 @@
import logging
import subprocess
import sys
from typing import Any
LOG: logging.Logger = logging.getLogger("ytdlp.utils")
from app.library.log import get_logger
LOG = get_logger()
def patch_metadataparser() -> None:
@ -14,7 +15,12 @@ def patch_metadataparser() -> None:
from yt_dlp.postprocessor.metadataparser import MetadataParserPP
from yt_dlp.utils import Namespace
except Exception as exc:
LOG.warning(f"Unable to import yt_dlp metadata parser for patching: {exc!s}")
LOG.warning(
"Unable to import yt-dlp metadata parser for patching: %s",
exc,
extra={"patch": "metadata_parser", "exception_type": type(exc).__name__},
exc_info=True,
)
return
if getattr(MetadataParserPP.Actions, "_ytptube_patched", False):
@ -61,7 +67,12 @@ def patch_windows_popen_wait() -> None:
try:
from yt_dlp.utils import Popen
except Exception as exc:
LOG.warning(f"Unable to import yt_dlp Popen for patching: {exc!s}")
LOG.warning(
"Unable to import yt-dlp Popen for patching: %s",
exc,
extra={"patch": "windows_popen_wait", "exception_type": type(exc).__name__},
exc_info=True,
)
return
if getattr(Popen, "_ytptube_wait_patched", False):

View file

@ -18,10 +18,11 @@ from app.library.cache import Cache
from app.library.config import Config
from app.library.encoder import Encoder
from app.library.ItemDTO import Item
from app.library.log import get_logger
from app.library.router import route
from app.library.Utils import validate_url
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
def _get_preset_archive(preset: str) -> str | None:
@ -37,7 +38,12 @@ def _get_preset_archive(preset: str) -> str | None:
try:
opts: dict = YTDLPOpts.get_instance().preset(preset).get_all()
except Exception as e:
LOG.error(f"Failed to build yt-dlp opts for preset '{preset}'. {e!s}")
LOG.exception(
"Failed to build yt-dlp options for preset '%s': %s.",
preset,
e,
extra={"preset": preset, "exception_type": type(e).__name__},
)
return None
if not (archive_file := opts.get("download_archive")):
@ -125,7 +131,19 @@ async def archiver_get(request: Request) -> Response:
data={"file": archive_file, "items": data, "count": len(data)}, status=web.HTTPOk.status_code
)
except Exception as e:
LOG.exception(e)
LOG.exception(
"Failed to read archive file '%s' for preset '%s': %s.",
archive_file,
preset,
e,
extra={
"route": "api/archiver/",
"action": "read_archive",
"preset": preset,
"archive_file": archive_file,
"ids": ids,
},
)
return web.json_response(
data={"error": f"Failed to read archive file for preset '{preset}'.", "message": str(e)},
status=web.HTTPInternalServerError.status_code,
@ -171,7 +189,21 @@ async def archiver_add(request: Request) -> Response:
status=web.HTTPOk.status_code if status else web.HTTPNotModified.status_code,
)
except Exception as e:
LOG.exception(e)
LOG.exception(
"Failed to add %s item(s) to archive file '%s' for preset '%s': %s.",
len(items),
archive_file,
preset,
e,
extra={
"route": "api/archiver/",
"action": "add_archive_items",
"preset": preset,
"archive_file": archive_file,
"item_count": len(items),
"skip_check": skip_check,
},
)
return web.json_response(
data={"error": f"Failed to add items to archive for preset '{preset}'.", "message": str(e)},
status=web.HTTPInternalServerError.status_code,
@ -215,7 +247,20 @@ async def archiver_delete(request: Request) -> Response:
status=web.HTTPOk.status_code if status else web.HTTPNotModified.status_code,
)
except Exception as e:
LOG.exception(e)
LOG.exception(
"Failed to delete %s item(s) from archive file '%s' for preset '%s': %s.",
len(items),
archive_file,
preset,
e,
extra={
"route": "api/archiver/",
"action": "delete_archive_items",
"preset": preset,
"archive_file": archive_file,
"item_count": len(items),
},
)
return web.json_response(
data={"error": f"Failed to delete items from archive for preset '{preset}'.", "message": str(e)},
status=web.HTTPInternalServerError.status_code,
@ -241,7 +286,7 @@ async def convert(request: Request) -> Response:
return web.json_response(data={"error": "args param is required."}, status=web.HTTPBadRequest.status_code)
try:
response = {"opts": {}, "output_template": None, "download_path": None}
response: dict[str, Any] = {"opts": {}, "output_template": None, "download_path": None}
data = arg_converter(args, dumps=True)
@ -339,6 +384,8 @@ async def get_info(request: Request, cache: Cache, config: Config) -> Response:
if cache.has(key) and not request.query.get("force", False):
data: Any | None = cache.get(key)
if data is None:
data = {}
data["_cached"] = {
"status": "hit",
"preset": preset,
@ -348,7 +395,7 @@ async def get_info(request: Request, cache: Cache, config: Config) -> Response:
"ttl_left": data.get("_cached", {}).get("expires", time.time() + 300) - time.time(),
"expires": data.get("_cached", {}).get("expires", time.time() + 300),
}
return web.json_response(body=json.dumps(data, indent=4, default=str), status=web.HTTPOk.status_code)
return web.json_response(text=json.dumps(data, indent=4, default=str), status=web.HTTPOk.status_code)
ytdlp_opts: dict = opts.get_all()
@ -405,10 +452,21 @@ async def get_info(request: Request, cache: Cache, config: Config) -> Response:
cache.set(key=key, value=data, ttl=300)
return web.json_response(body=json.dumps(data, indent=4, default=str), status=web.HTTPOk.status_code)
return web.json_response(text=json.dumps(data, indent=4, default=str), status=web.HTTPOk.status_code)
except Exception as e:
LOG.exception(e)
LOG.error(f"Error encountered while getting video info for '{url}'. '{e!s}'.")
LOG.exception(
"Failed to get video info for '%s': %s.",
url,
e,
extra={
"route": "api/yt-dlp/url/info/",
"action": "get_video_info",
"url": url,
"preset": preset,
"cache_key": key if "key" in locals() else None,
"has_cli_args": bool(cli_args),
},
)
return web.json_response(
data={
"error": "failed to get video info.",
@ -430,7 +488,7 @@ async def get_options() -> Response:
"""
from app.features.ytdlp.ytdlp import ytdlp_options
return web.json_response(body=json.dumps(ytdlp_options(), indent=4, default=str), status=web.HTTPOk.status_code)
return web.json_response(text=json.dumps(ytdlp_options(), indent=4, default=str), status=web.HTTPOk.status_code)
@route("POST", "api/yt-dlp/archive_id/", "get_archive_ids")
@ -452,7 +510,11 @@ async def get_archive_ids(request: Request, config: Config) -> Response:
response = []
for i, url in enumerate(data):
dct = {"index": i, "url": url}
dct: dict[str, Any] = {"index": i, "url": url}
if not isinstance(url, str):
dct.update({"id": None, "ie_key": None, "archive_id": None, "error": "URL must be a string."})
response.append(dct)
continue
try:
await asyncio.to_thread(validate_url, url, config.allow_internal_urls)
dct.update(get_archive_id(url))
@ -496,7 +558,19 @@ async def make_command(request: Request, config: Config, encoder: Encoder) -> Re
try:
command, info = YTDLPCli(item=it, config=config).build()
except Exception as e:
LOG.exception(e)
LOG.exception(
"Failed to build yt-dlp command for '%s': %s.",
it.url,
e,
extra={
"route": "api/yt-dlp/command/",
"action": "build_command",
"url": it.url,
"preset": it.preset,
"has_cookies": bool(it.cookies),
"exception_type": type(e).__name__,
},
)
return web.json_response(
data={"error": "Failed to build CLI command"},
status=web.HTTPBadRequest.status_code,

View file

@ -1,13 +1,18 @@
import logging
import pickle
from unittest.mock import MagicMock, patch
from app.features.ytdlp.extractor import (
ExtractorConfig,
ExtractorPool,
REEXTRACT_INFO_KEY,
_LogCapture,
_get_process_pool_kwargs,
_process_safe_info,
_ytdlp_logger,
extract_info_sync,
)
from app.features.ytdlp.utils import LogWrapper
class TestProcessPoolConfiguration:
@ -117,6 +122,7 @@ class TestExtractInfo:
{}, "https://example.com/video", debug=True, capture_logs=logging.WARNING
)
assert result is not None
assert result["id"] == "test123"
assert logs == ["[generic_browser] Browser fallback warning"]
assert (logging.INFO, "[generic_browser] Using remote browser for https://example.com/video") in seen
@ -150,11 +156,50 @@ class TestExtractInfo:
{}, "https://example.com/video", debug=False, capture_logs=logging.WARNING
)
assert result is not None
assert result["id"] == "test123"
assert logs == ["[generic_browser] Browser fallback warning"]
assert (logging.INFO, "[generic_browser] Using remote browser for https://example.com/video") in seen
assert (logging.WARNING, "[generic_browser] Browser fallback warning") in seen
def test_process_safe_live(self) -> None:
data = {
"id": "live-id",
"is_live": True,
"formats": [{"format_id": "dash", "fragments": ({"url": "https://example.test/sq/1"} for _ in range(1))}],
"requested_formats": [{"format_id": "dash"}],
}
result = _process_safe_info(data)
assert result[REEXTRACT_INFO_KEY] is True
assert "formats" not in result
assert "requested_formats" not in result
pickle.dumps(result)
def test_process_safe_post_live(self) -> None:
data = {
"id": "post-live-id",
"live_status": "post_live",
"formats": [{"format_id": "dash", "fragments": ({"url": "https://example.test/sq/1"} for _ in range(1))}],
}
result = _process_safe_info(data)
assert result[REEXTRACT_INFO_KEY] is True
assert "formats" not in result
pickle.dumps(result)
def test_process_safe_lazy(self) -> None:
from yt_dlp.utils import LazyList
data = {"id": "video-id", "formats": LazyList({"format_id": str(i)} for i in range(2))}
result = _process_safe_info(data)
assert result["formats"] == [{"format_id": "0"}, {"format_id": "1"}]
pickle.dumps(result)
class TestYtdlpLogger:
def test_debug_prefix_uses_debug(self) -> None:
@ -162,11 +207,26 @@ class TestYtdlpLogger:
_ytdlp_logger(logger)(logging.DEBUG, "[debug] hello")
logger.debug.assert_called_once_with("hello")
logger.debug.assert_called_once_with("hello", stacklevel=4)
def test_screen_style_debug_uses_info(self) -> None:
logger = MagicMock()
_ytdlp_logger(logger)(logging.DEBUG, "screen line")
logger.info.assert_called_once_with("screen line")
logger.info.assert_called_once_with("screen line", stacklevel=4)
def test_targets_are_picklable(self) -> None:
logs: list[str] = []
wrapper = LogWrapper()
wrapper.add_target(_ytdlp_logger(logging.getLogger("yt-dlp.test")), level=logging.DEBUG, name="yt-dlp.test")
wrapper.add_target(_LogCapture(logs), level=logging.WARNING, name="log-capture")
pickle.dumps(wrapper)
def test_capture_formats_args(self) -> None:
logs: list[str] = []
_LogCapture(logs)(logging.WARNING, "hello %s", "world")
assert logs == ["hello world"]

View file

@ -1,5 +1,6 @@
import importlib
from pathlib import Path
from typing import Any
from unittest.mock import MagicMock, Mock, patch
import pytest
@ -219,7 +220,8 @@ class TestYTDLP:
"""Test _delete_downloaded_files skips cleanup when _interrupted is True."""
with patch("app.features.ytdlp.ytdlp.yt_dlp.YoutubeDL.__init__", return_value=None):
ytdlp = YTDLP(params={})
ytdlp.to_screen = Mock()
mock_obj: Any = ytdlp
mock_obj.to_screen = Mock()
# Set interrupted flag
ytdlp._interrupted = True
@ -229,7 +231,7 @@ class TestYTDLP:
# Should not call super method
mock_super_delete.assert_not_called()
# Should show message
ytdlp.to_screen.assert_called_once_with("[info] Cancelled — skipping temp cleanup.")
mock_obj.to_screen.assert_called_once_with("[info] Cancelled — skipping temp cleanup.")
# Should return None
assert result is None
@ -349,6 +351,14 @@ class TestYTDLP:
assert len(result) == 8
assert result.isalnum()
def test_exec_init(self) -> None:
YTDLP(
params={
"compat_opts": set(),
"postprocessors": [{"key": "Exec", "exec_cmd": "echo %(title)q"}],
}
)
def test_outtmpl_reuses_value(self) -> None:
ytdlp = YTDLP(params={"outtmpl": {"default": "%(title)s"}})

View file

@ -442,7 +442,7 @@ class TestYTDLPOpts:
opts = YTDLPOpts()
opts.get_all(keep=True)
mock_log.debug.assert_called_once_with(f"Final yt-dlp options: '{test_data!s}'.")
mock_log.debug.assert_called_once_with("Prepared final yt-dlp options.", extra={"ytdlp_options": test_data})
def test_cookie_loading_error_handling(self):
"""Test error handling when cookie loading fails."""
@ -475,11 +475,12 @@ class TestYTDLPOpts:
opts = YTDLPOpts()
opts.preset("cookie_preset")
# Should log error but not raise
mock_log.error.assert_called_once()
error_args = mock_log.error.call_args[0][0]
assert "Failed to load" in error_args
assert "Cookie Preset" in error_args
# Should log exception but not raise
mock_log.exception.assert_called_once()
error_fields = mock_log.exception.call_args.kwargs["extra"]
assert error_fields["preset"] == "Cookie Preset"
assert error_fields["has_cookies"] is True
assert error_fields["exception_type"] == "ValueError"
assert "cookiefile" not in opts._preset_opts, "cookiefile should not be set"
@ -775,7 +776,7 @@ class TestYTDLPCli:
from app.features.ytdlp.ytdlp_opts import YTDLPCli
with pytest.raises(ValueError, match="Expected Item instance"):
YTDLPCli(item="not an item") # type: ignore
YTDLPCli(item="not an item")
@patch("app.features.presets.service.Presets")
@patch("app.features.ytdlp.ytdlp_opts.Config")

View file

@ -46,7 +46,8 @@ class TestLogWrapper:
def test_add_target_type_validation(self) -> None:
lw = LogWrapper()
with pytest.raises(TypeError, match=r"Target must be a logging\.Logger instance or a callable"):
lw.add_target(123) # type: ignore[arg-type]
bad: Any = 123
lw.add_target(bad)
def test_add_target_names(self) -> None:
lw = LogWrapper()
@ -90,6 +91,7 @@ class TestLogWrapper:
assert len(cap.records) == 1
assert cap.records[0].levelno == logging.INFO
assert cap.records[0].getMessage() == "hello X"
assert cap.records[0].funcName == "test_level_filtering_and_dispatch"
assert len(calls) == 0
# WARNING hits both
@ -127,7 +129,7 @@ class TestExtractYtdlpLogs:
def test_extract_ytdlp_logs_with_filters(self):
"""Test log extraction with filters."""
logs = ["INFO: Downloading", "ERROR: Failed", "WARNING: Deprecated"]
filters = [re.compile(r"ERROR")]
filters: list[str | re.Pattern[str]] = [re.compile(r"ERROR")]
result = extract_ytdlp_logs(logs, filters)
assert result == ["ERROR: Failed"]
@ -311,9 +313,12 @@ class TestGetThumbnail:
def test_non_list(self):
"""Test that None is returned for non-list input."""
assert get_thumbnail(None) is None
assert get_thumbnail("not a list") is None
assert get_thumbnail({"not": "list"}) is None
bad_none: Any = None
bad_str: Any = "not a list"
bad_dict: Any = {"not": "list"}
assert get_thumbnail(bad_none) is None
assert get_thumbnail(bad_str) is None
assert get_thumbnail(bad_dict) is None
def test_thumbnail_preference(self):
"""Test that the thumbnail with highest preference is returned."""
@ -348,6 +353,7 @@ class TestGetThumbnail:
]
result = get_thumbnail(thumbnails)
assert result is not None
assert result["url"] == "with_pref.jpg"
def test_all_equal(self):
@ -364,12 +370,15 @@ class TestGetThumbnail:
class TestGetExtras:
def test_none(self):
"""Test that empty dict is returned for None input."""
assert get_extras(None) == {}
bad: Any = None
assert get_extras(bad) == {}
def test_non_dict(self):
"""Test that empty dict is returned for non-dict input."""
assert get_extras("not a dict") == {}
assert get_extras([]) == {}
bad_str: Any = "not a dict"
bad_list: Any = []
assert get_extras(bad_str) == {}
assert get_extras(bad_list) == {}
def test_extracts_video_information(self):
"""Test extracting information from a video entry."""

View file

@ -11,9 +11,10 @@ from typing import Any
from app.features.ytdlp.patches import apply_ytdlp_patches
from app.features.ytdlp.ytdlp import YTDLP
from app.library.log import get_logger
from app.library.Utils import merge_dict, timed_lru_cache
LOG: logging.Logger = logging.getLogger("ytdlp.utils")
LOG = get_logger()
class _DATA:
@ -100,12 +101,12 @@ class LogWrapper:
name (str|None): The name of the logging target. Defaults to None.
"""
if not isinstance(target, logging.Logger | Callable):
if not isinstance(target, logging.Logger) and not callable(target):
msg = "Target must be a logging.Logger instance or a callable."
raise TypeError(msg)
if name is None:
name = target.name if isinstance(target, logging.Logger) else target.__name__
name = target.name if isinstance(target, logging.Logger) else getattr(target, "__name__", "callable")
self.targets.append(
LogTarget(
@ -130,9 +131,11 @@ class LogWrapper:
if level < target.level:
continue
if target.logger:
target.target.log(level, msg, *args, **kwargs)
else:
if isinstance(target.target, logging.Logger):
log_kwargs: dict[str, Any] = {**kwargs}
log_kwargs.setdefault("stacklevel", 3)
target.target.log(level, msg, *args, **log_kwargs)
elif callable(target.target):
target.target(level, msg, *args, **kwargs)
def debug(self, msg, *args, **kwargs):
@ -176,13 +179,17 @@ def arg_converter(
create_parser = yt_dlp.options.create_parser
def _default_opts(args: str):
def _default_opts(args: str | list[str]):
patched_parser = create_parser()
def patched_create_parser():
return patched_parser
try:
yt_dlp.options.create_parser = lambda: patched_parser
yt_dlp.options.__dict__["create_parser"] = patched_create_parser
return yt_dlp.parse_options(args)
finally:
yt_dlp.options.create_parser = create_parser
yt_dlp.options.__dict__["create_parser"] = create_parser
apply_ytdlp_patches()
@ -235,7 +242,7 @@ def arg_converter(
return diff
def extract_ytdlp_logs(logs: list[str], filters: list[str | re.Pattern] = None) -> list[str]:
def extract_ytdlp_logs(logs: list[str], filters: list[str | re.Pattern[str]] | None = None) -> list[str]:
"""
Extract yt-dlp log lines matching built-in filters plus any extras.
@ -329,7 +336,7 @@ def get_ytdlp(params: dict | None = None) -> YTDLP:
return _DATA.YTDLP_INFO_CLS
def get_thumbnail(thumbnails: list) -> str | None:
def get_thumbnail(thumbnails: list) -> dict | None:
"""
Extract thumbnail URL from a yt-dlp entry.
@ -337,7 +344,7 @@ def get_thumbnail(thumbnails: list) -> str | None:
thumbnails (list): The list of thumbnail dictionaries from yt-dlp entry.
Returns:
str | None: The thumbnail URL if available, otherwise None.
dict | None: The best thumbnail dict if available, otherwise None.
"""
if not thumbnails or not isinstance(thumbnails, list):
@ -378,7 +385,7 @@ def get_extras(entry: dict, kind: str = "video") -> dict:
extras[f"playlist_{property}"] = val
if thumbnail := get_thumbnail(entry.get("thumbnails", [])):
extras["thumbnail"] = thumbnail.get("url")
extras["thumbnail"] = thumbnail.get("url") if isinstance(thumbnail, dict) else thumbnail
elif thumbnail := entry.get("thumbnail"):
extras["thumbnail"] = thumbnail
@ -436,7 +443,7 @@ def get_archive_id(url: str) -> dict[str, str | None]:
}
"""
idDict: dict[str, None] = {
idDict: dict[str, str | None] = {
"id": None,
"ie_key": None,
"archive_id": None,
@ -460,8 +467,12 @@ def get_archive_id(url: str) -> dict[str, str | None]:
idDict["archive_id"] = make_archive_id(_ie, temp_id)
break
except Exception as e:
LOG.exception(e)
LOG.error(f"Error getting archive ID: {e}")
LOG.exception(
"Failed to get archive ID for '%s' with extractor '%s'.",
url,
key,
extra={"url": url, "extractor": key, "exception_type": type(e).__name__},
)
return idDict

View file

@ -1,5 +1,4 @@
# flake8: noqa: F401, RUF100, W291, I001
import logging
import sys
from typing import Any
@ -10,6 +9,7 @@ from yt_dlp.utils import make_archive_id
from app.features.ytdlp.outtmpl import rewrite_outtmpl
from app.features.ytdlp.patches import apply_ytdlp_patches
from app.library.cf_solver_handler import set_cf_handler
from app.library.log import get_logger
class _ArchiveProxy:
@ -67,7 +67,7 @@ class YTDLP(yt_dlp.YoutubeDL):
postprocessors.value.update({"NFOMakerPP": NFOMakerPP})
YTDLP._registered = True
except Exception:
logging.getLogger("ytdlp.wrapper").exception("Failed to register yt-dlp plugins")
get_logger().exception("Failed to register yt-dlp plugins")
# Avoid yt-dlp preloading the archive file by stripping the param first
orig_file = None
@ -81,6 +81,9 @@ class YTDLP(yt_dlp.YoutubeDL):
except Exception:
patched_params = params
self._ytptube_outtmpl_info: dict[str, Any] | None = None
self._ytptube_outtmpl_cache: dict[str, Any] = {}
super().__init__(params=patched_params, auto_init=auto_init)
# Restore param and replace upstream archive set with our proxy
@ -90,8 +93,6 @@ class YTDLP(yt_dlp.YoutubeDL):
except Exception:
pass
self._ytptube_outtmpl_info: dict[str, Any] | None = None
self._ytptube_outtmpl_cache: dict[str, Any] = {}
self.archive = _ArchiveProxy(orig_file)
def _delete_downloaded_files(self, *args, **kwargs) -> None:
@ -105,14 +106,14 @@ class YTDLP(yt_dlp.YoutubeDL):
self._ytptube_outtmpl_info = None
self._ytptube_outtmpl_cache = {}
def prepare_outtmpl(self, outtmpl, info_dict, sanitize=False):
def prepare_outtmpl(self, outtmpl, info_dict, sanitize=False, *, _exec=False):
if self._ytptube_outtmpl_info is not info_dict:
self._ytptube_outtmpl_info = info_dict
self._ytptube_outtmpl_cache = {}
outtmpl, enriched = rewrite_outtmpl(outtmpl, info_dict, cache=self._ytptube_outtmpl_cache)
return super().prepare_outtmpl(outtmpl, enriched, sanitize=sanitize)
return super().prepare_outtmpl(outtmpl, enriched, sanitize=sanitize, _exec=_exec)
def process_info(self, info_dict):
try:

View file

@ -1,4 +1,3 @@
import logging
import shlex
from pathlib import Path
from typing import Any
@ -6,9 +5,10 @@ from typing import Any
from app.features.presets.schemas import Preset
from app.features.ytdlp.utils import arg_converter
from app.library.config import Config
from app.library.log import get_logger
from app.library.Utils import calc_download_path, create_cookies_file, merge_dict
LOG: logging.Logger = logging.getLogger("ytdlp.ytdlp_opts")
LOG = get_logger()
class ARGSMerger:
@ -50,12 +50,12 @@ class ARGSMerger:
"""
return str(self)
def as_dict(self) -> dict:
def as_dict(self) -> list[str]:
"""
Get all the options as a dict.
Get all the options as a shell argument list.
Returns:
dict: The options as a dict
list[str]: The options as shell arguments.
"""
return shlex.split(shlex.join(self.args))
@ -335,7 +335,12 @@ class YTDLPOpts:
if file and file.exists():
self._preset_opts["cookiefile"] = str(file)
except ValueError as e:
LOG.error(f"Failed to load '{preset.name}' cookies. {e!s}")
LOG.exception(
"Failed to load cookies for preset '%s': %s.",
preset.name,
e,
extra={"preset": preset.name, "has_cookies": True, "exception_type": type(e).__name__},
)
if preset.template:
self._preset_opts["outtmpl"] = {"default": preset.template, "chapter": self._config.output_template_chapter}
@ -392,6 +397,30 @@ class YTDLPOpts:
data: dict = merge_dict(user_cli, merge_dict(self._item_opts, merge_dict(self._preset_opts, default_opts)))
if self._config.disable_exec:
stripped: list[str] = []
if data.pop("netrc_cmd", None):
stripped.append("netrc_cmd")
if "postprocessors" in data:
exec_pps = [
pp for pp in data["postprocessors"] if isinstance(pp, dict) and pp.get("key", "").startswith("Exec")
]
if exec_pps:
stripped.extend(pp.get("key") for pp in exec_pps)
data["postprocessors"] = [
pp
for pp in data["postprocessors"]
if not (isinstance(pp, dict) and pp.get("key", "").startswith("Exec"))
]
if stripped:
LOG.warning(
"Stripped %d dangerous options from yt-dlp options.",
len(stripped),
extra={"stripped": stripped, "reason": "YTP_DISABLE_EXEC is enabled"},
)
if not keep:
self.reset()
@ -403,7 +432,7 @@ class YTDLPOpts:
data["format"] = data["format"][1:]
if self._config.debug:
LOG.debug(f"Final yt-dlp options: '{data!s}'.")
LOG.debug("Prepared final yt-dlp options.", extra={"ytdlp_options": data})
return data

View file

@ -1,15 +1,16 @@
import asyncio
import inspect
import logging
import threading
from queue import Empty, Queue
from aiohttp import web
from app.library.log import get_logger
from .Services import Services
from .Singleton import Singleton
LOG: logging.Logger = logging.getLogger("BackgroundWorker")
LOG = get_logger()
class CloseThread:
@ -28,7 +29,7 @@ class BackgroundWorker(metaclass=Singleton):
"The queue to hold the tasks."
self.running = True
"Whether the background worker is running or not."
self.thread: threading.Thread = None
self.thread: threading.Thread | None = None
"The thread that runs the background worker."
@staticmethod
@ -39,19 +40,23 @@ class BackgroundWorker(metaclass=Singleton):
Services.get_instance().add("background_worker", self)
app.on_shutdown.append(self.on_shutdown)
LOG.debug("Starting background worker...")
LOG.debug("Started background worker thread.")
self.thread = threading.Thread(target=self._run, daemon=True)
self.thread.start()
async def on_shutdown(self, _: web.Application):
self.running = False
try:
LOG.debug("Shutting down background worker...")
LOG.debug("Stopping background worker thread.")
self.queue.put((CloseThread, (), {}))
self.thread.join(timeout=5)
LOG.debug("Background worker has been shut down.")
if self.thread:
self.thread.join(timeout=5)
LOG.debug("Background worker thread has been shut down.")
except Exception as e:
LOG.error(f"Failed to shut down background worker: {e}")
LOG.exception(
"Failed to shut down background worker thread.",
extra={"exception_type": type(e).__name__},
)
def _run(self):
asyncio.set_event_loop(asyncio.new_event_loop())
@ -79,8 +84,16 @@ class BackgroundWorker(metaclass=Singleton):
if inspect.iscoroutine(result):
loop.call_soon_threadsafe(loop.create_task, result)
except Exception as e:
LOG.exception(e)
LOG.error(f"Failed to run '{fn.__name__}'. {e!s}")
function = getattr(fn, "__name__", fn.__class__.__name__)
LOG.exception(
"Failed to run background worker function '%s'.",
function,
extra={
"function": function,
"thread_name": threading.current_thread().name,
"exception_type": type(e).__name__,
},
)
except Empty:
continue
@ -88,9 +101,12 @@ class BackgroundWorker(metaclass=Singleton):
loop.call_soon_threadsafe(loop.stop)
loop_thread.join(timeout=5)
loop.close()
LOG.debug("Event loop has been stopped and closed.")
LOG.debug("Stopped background worker event loop.")
except Exception as e:
LOG.error(f"Failed to stop the event loop: {e!s}")
LOG.exception(
"Failed to stop background worker event loop.",
extra={"thread_name": loop_thread.name, "exception_type": type(e).__name__},
)
def submit(self, fn, *args, **kwargs):
self.queue.put((fn, args, kwargs))

View file

@ -1,15 +1,16 @@
import copy
import logging
from collections import OrderedDict
from collections.abc import Iterable
from enum import Enum
from app.library.log import get_logger
from .downloads import Download
from .ItemDTO import ItemDTO
from .operations import matches_condition
from .sqlite_store import SqliteStore
LOG = logging.getLogger("datastore")
LOG = get_logger()
class StoreType(str, Enum):
@ -165,6 +166,12 @@ class DataStore:
def items(self):
return self._dict.items()
def __contains__(self, key: str) -> bool:
return key in self._dict
def __len__(self) -> int:
return len(self._dict)
async def put(self, value: Download, no_notify: bool = False) -> Download:
_ = no_notify
self._dict[value.info._id] = value

View file

@ -1,16 +1,16 @@
import asyncio
import datetime
import logging
from collections.abc import Callable
from dataclasses import dataclass, field
from typing import Any
from app.features.core.utils import gen_random
from app.library.log import get_logger
from .BackgroundWorker import BackgroundWorker
from .Singleton import Singleton
LOG: logging.Logger = logging.getLogger("events")
LOG = get_logger()
class Events:
@ -34,6 +34,7 @@ class Events:
ITEM_ADDED: str = "item_added"
ITEM_UPDATED: str = "item_updated"
ITEM_PROGRESS: str = "item_progress"
ITEM_COMPLETED: str = "item_completed"
ITEM_CANCELLED: str = "item_cancelled"
ITEM_DELETED: str = "item_deleted"
@ -86,6 +87,7 @@ class Events:
Events.LOG_SUCCESS,
Events.ITEM_ADDED,
Events.ITEM_UPDATED,
Events.ITEM_PROGRESS,
Events.ITEM_CANCELLED,
Events.ITEM_DELETED,
Events.ITEM_BULK_DELETED,
@ -103,7 +105,7 @@ class Events:
list: The list of debug events.
"""
return [Events.ITEM_UPDATED]
return [Events.ITEM_UPDATED, Events.ITEM_PROGRESS]
@dataclass(kw_only=True)
@ -242,7 +244,12 @@ class EventBus(metaclass=Singleton):
event = Events.frontend()
else:
if event not in all_events:
LOG.error(f"'{name}' attempted to listen on '{event}' which does not exist.")
LOG.error(
"Listener '%s' tried to subscribe to unknown event '%s'.",
name,
event,
extra={"listener": name, "event": event},
)
return self
event = [event]
@ -252,7 +259,12 @@ class EventBus(metaclass=Singleton):
for e in event:
if e not in all_events:
LOG.error(f"'{name}' attempted to listen on '{e}' which does not exist.")
LOG.error(
"Listener '%s' tried to subscribe to unknown event '%s'.",
name,
e,
extra={"listener": name, "event": e},
)
continue
if e not in self._listeners:
@ -261,7 +273,7 @@ class EventBus(metaclass=Singleton):
self._listeners[e] = [(n, listener) for n, listener in self._listeners[e] if n != name]
self._listeners[e].append((name, EventListener(name, callback)))
LOG.debug(f"'{name}' subscribed to '{event}'.")
LOG.debug("Listener '%s' has subscribed.", name, extra={"listener": name, "events": event})
return self
@ -289,7 +301,7 @@ class EventBus(metaclass=Singleton):
events.append(e)
if len(events) > 0:
LOG.debug(f"'{name}' unsubscribed from '{events}'.")
LOG.debug("Listener '%s' unsubscribed from '%s'.", name, events, extra={"listener": name, "events": events})
return self
@ -316,7 +328,17 @@ class EventBus(metaclass=Singleton):
ev = Event(event=event, title=title, message=message, data=data)
if self.debug or event not in Events.only_debug():
LOG.debug(f"Emitting event '{ev.id}: {ev.event}'.", extra={"data": data})
LOG.debug(
"Delivering '%s' event to %s listener(s).",
ev.event,
len(self._listeners[event]),
extra={
"event_id": ev.id,
"event": ev.event,
"handler_count": len(self._listeners[event]),
"data": data,
},
)
try:
loop = asyncio.get_running_loop()
@ -329,16 +351,35 @@ class EventBus(metaclass=Singleton):
if asyncio.iscoroutine(coro):
await coro
else:
LOG.warning(f"Expected coroutine from async handler '{handler.name}', got {type(coro)}")
LOG.warning(
"Async handler '%s' returned '%s' instead of a coroutine.",
handler.name,
type(coro).__name__,
extra={"handler": handler.name, "returned_type": type(coro).__name__},
)
else:
await self._call(handler, ev, kwargs)
except Exception as e:
LOG.exception(e)
LOG.error(f"Failed to emit event '{ev.event}' to '{handler.name}'. Error message '{e!s}'.")
LOG.exception(
"Failed to emit '%s' event to listener '%s'.",
ev.event,
handler.name,
extra={
"event_id": ev.id,
"event": ev.event,
"handler": handler.name,
"exception_type": type(e).__name__,
},
)
loop.create_task(execute_handlers())
except RuntimeError:
LOG.debug(f"No event loop detected - using BackgroundWorker for {len(self._listeners[event])} handlers")
LOG.debug(
"No event loop detected; offloading '%s' event to %s background listener(s).",
ev.event,
len(self._listeners[event]),
extra={"event_id": ev.id, "event": ev.event, "handler_count": len(self._listeners[event])},
)
for _, handler in self._listeners[event]:
try:
if not self._offload:
@ -346,8 +387,17 @@ class EventBus(metaclass=Singleton):
self._offload.submit(handler.handle, ev, **kwargs)
except Exception as e:
LOG.exception(e)
LOG.error(f"Failed to emit event '{ev.event}' to '{handler.name}'. Error message '{e!s}'.")
LOG.exception(
"Failed to offload '%s' event to listener '%s'.",
ev.event,
handler.name,
extra={
"event_id": ev.id,
"event": ev.event,
"handler": handler.name,
"exception_type": type(e).__name__,
},
)
def clear(self) -> None:
"""

View file

@ -1,15 +1,19 @@
import base64
import hmac
import inspect
import logging
from collections.abc import Awaitable
from datetime import UTC, datetime, timedelta
from pathlib import Path
from typing import Any, cast
import anyio
from aiohttp import web
from aiohttp.web import Request, RequestHandler, Response
from aiohttp.typedefs import Handler, Middleware
from aiohttp.web import Request, Response
from aiohttp.web_log import AccessLogger
from aiohttp.web_request import BaseRequest
from aiohttp.web_response import StreamResponse
from app.library.log import get_logger
from app.library.Services import Services
from .cache import Cache
@ -19,7 +23,33 @@ from .Events import EventBus
from .router import RouteType, get_routes
from .Utils import decrypt_data, encrypt_data, get_file, load_modules
LOG: logging.Logger = logging.getLogger("http_api")
LOG = get_logger("http")
class HttpAccessLogger(AccessLogger):
def log(self, request: BaseRequest, response: StreamResponse, time: float) -> None:
try:
fmt_info = self._format_line(request, response, time)
values: list[object] = []
extra: dict[str, Any] = {"elapsed_ms": round(time * 1000.0, 2)}
for key, value in fmt_info:
values.append(value)
if isinstance(key, str):
extra[key] = value
else:
parent, child = key
group: dict[str, Any] = extra.get(parent, {}) # type: ignore[assignment]
if not isinstance(group, dict):
group = {}
group[child] = value
extra[parent] = group
message = self._log_format % tuple(values)
self.logger.info(message, extra=extra)
except Exception:
self.logger.exception("Error in logging")
class HttpAPI:
@ -89,7 +119,10 @@ class HttpAPI:
try:
app.on_response_prepare.append(on_prepare)
except Exception as e:
LOG.exception(e)
LOG.exception(
"Failed to register response preparation middleware.",
extra={"operation": "register_on_response_prepare", "exception_type": type(e).__name__},
)
app.on_shutdown.append(self.on_shutdown)
@ -130,7 +163,13 @@ class HttpAPI:
route.path = f"{base_path}/{route.path.lstrip('/')}"
if self.config.debug:
LOG.debug(f"Add ({route.name}) {route.method}: {route.path}.")
LOG.debug(
"Adding route '%s' %s: %s.",
route.name,
route.method,
route.path,
extra={"route_name": route.name, "method": route.method, "path": route.path},
)
app.router.add_route(route.method, route.path, handler=_handle(route.handler), name=route.name)
@ -141,7 +180,7 @@ class HttpAPI:
registered_options.append(route.path)
@staticmethod
def basic_auth(username: str, password: str) -> Awaitable:
def basic_auth(username: str, password: str) -> Middleware:
"""
Middleware to handle basic authentication.
@ -155,7 +194,7 @@ class HttpAPI:
"""
@web.middleware
async def auth_handler(request: Request, handler: RequestHandler) -> Response:
async def auth_handler(request: Request, handler: Handler) -> StreamResponse:
# if OPTIONS request, skip auth
if "OPTIONS" == request.method:
return await handler(request)
@ -168,12 +207,19 @@ class HttpAPI:
auth_cookie = request.cookies.get("auth")
if auth_cookie is not None:
try:
data = decrypt_data(auth_cookie, key=Config.get_instance().secret_key)
data = decrypt_data(auth_cookie, key=cast("bytes", Config.get_instance().secret_key))
if data is not None:
data = base64.b64encode(data.encode()).decode()
auth_header = f"Basic {data}"
except Exception as e:
LOG.exception(e)
LOG.exception(
"Failed to decrypt authentication cookie.",
extra={
"route": str(request.rel_url),
"method": request.method,
"exception_type": type(e).__name__,
},
)
if auth_header is None:
return web.json_response(
@ -207,7 +253,7 @@ class HttpAPI:
},
)
response: Response = await handler(request)
response: StreamResponse = await handler(request)
contentType: str | None = response.headers.get("content-type", None)
if contentType and not contentType.startswith("text/html"):
@ -218,7 +264,7 @@ class HttpAPI:
"auth",
encrypt_data(
f"{user_name}:{user_password}",
key=Config.get_instance().secret_key,
key=cast("bytes", Config.get_instance().secret_key),
),
max_age=60 * 60 * 24 * 7,
expires=(datetime.now(UTC) + timedelta(days=7)).strftime("%a, %d %b %Y %H:%M:%S GMT"),
@ -226,16 +272,20 @@ class HttpAPI:
samesite="Strict",
)
except Exception as e:
LOG.exception(e)
LOG.exception(
"Failed to set authentication cookie for '%s'.",
request.rel_url,
extra={"route": str(request.rel_url), "method": request.method, "exception_type": type(e).__name__},
)
return response
return auth_handler
@staticmethod
def middle_wares(app: web.Application, base_path: str, download_path: str) -> Awaitable:
def middle_wares(app: web.Application, base_path: str, download_path: str) -> Middleware:
@web.middleware
async def middleware_handler(request: Request, handler: RequestHandler) -> Response:
async def middleware_handler(request: Request, handler: Handler) -> StreamResponse:
static_path = str(app.router["download_static"].url_for(filename=""))
if request.path.startswith(static_path):
realFile, status = get_file(
@ -254,12 +304,13 @@ class HttpAPI:
},
)
response: Response = await handler(request)
response: StreamResponse = await handler(request)
contentType: str = str(response.headers.get("content-type", ""))
if contentType.startswith("text/html") and getattr(response, "_path", None):
rewrite_path: str = base_path.rstrip("/")
async with await anyio.open_file(response._path, "rb") as f:
response_path = cast("Any", response)._path
async with await anyio.open_file(response_path, "rb") as f:
content = await f.read()
content: str = (
content.decode("utf-8")
@ -277,13 +328,13 @@ class HttpAPI:
new_response.set_cookie(
morsel.key,
morsel.value,
expires=morsel["expires"],
domain=morsel["domain"],
max_age=morsel["max-age"],
path=morsel["path"],
secure=bool(morsel["secure"]),
httponly=bool(morsel["httponly"]),
samesite=morsel["samesite"] or None,
expires=morsel.get("expires"),
domain=morsel.get("domain"),
max_age=morsel.get("max-age"),
path=morsel.get("path") or "/",
secure=bool(morsel.get("secure")),
httponly=bool(morsel.get("httponly")),
samesite=morsel.get("samesite") or None,
)
return new_response
@ -292,7 +343,7 @@ class HttpAPI:
return middleware_handler
async def _handle(self, handler: RequestHandler, request: Request) -> Response:
async def _handle(self, handler: Handler, request: Request) -> StreamResponse:
"""
Call the handler with the request and return the response.
@ -314,7 +365,16 @@ class HttpAPI:
else:
response = await Services.get_instance().handle_async(handler, request=request)
except TypeError as te:
LOG.exception(te)
LOG.exception(
"Failed to inject route handler dependencies for '%s'.",
getattr(handler, "__name__", handler.__class__.__name__),
extra={
"handler": getattr(handler, "__name__", handler.__class__.__name__),
"route": str(request.rel_url),
"method": request.method,
"exception_type": type(te).__name__,
},
)
if "missing 1 required positional argument" in str(te) and "request" in str(te):
response = await handler(request)
else:
@ -322,7 +382,12 @@ class HttpAPI:
except web.HTTPException as e:
return web.json_response(data={"error": str(e)}, status=e.status_code)
except Exception as e:
LOG.exception(e)
LOG.exception(
"Failed to handle request '%s %s'.",
request.method,
request.rel_url,
extra={"route": str(request.rel_url), "method": request.method, "exception_type": type(e).__name__},
)
response = web.json_response(
data={"error": "Internal Server Error"},
status=web.HTTPInternalServerError.status_code,

View file

@ -1,13 +1,13 @@
import asyncio
import functools
import json
import logging
from pathlib import Path
from typing import Any
from aiohttp import web
from app.features.core.utils import gen_random
from app.library.log import get_logger
from app.library.router import Route, RouteType, get_routes
from app.library.Services import Services
from app.library.Utils import load_modules
@ -17,7 +17,7 @@ from .encoder import Encoder
from .Events import Event, EventBus, Events
from .ItemDTO import Item
LOG: logging.Logger = logging.getLogger("socket_api")
LOG = get_logger()
class WebSocketHub:
@ -104,19 +104,20 @@ class HttpSocket:
}
)
self._notify.subscribe("frontend", event_handler, f"{__class__.__name__}.emit")
self._notify.subscribe("frontend", event_handler, f"{HttpSocket.__name__}.emit")
@staticmethod
def ws_event(func): # type: ignore
def ws_event(func):
"""
Decorator to mark a method as a socket event.
"""
@functools.wraps(func) # type: ignore
@functools.wraps(func)
async def wrapper(*args, **kwargs):
return await func(*args, **kwargs) # type: ignore
return await func(*args, **kwargs)
wrapper._ws_event = func.__name__ # type: ignore
wrapper_with_event: Any = wrapper
wrapper_with_event._ws_event = func.__name__
return wrapper
async def on_shutdown(self, _: web.Application):
@ -134,9 +135,11 @@ class HttpSocket:
if not (data and data.data):
return
await Services.get_instance().get("queue").add(item=Item.format(data.data))
queue = Services.get_instance().get("queue")
if queue is not None:
await queue.add(item=Item.format(data.data))
self._notify.subscribe(Events.ADD_URL, event_handler, f"{__class__.__name__}.add")
self._notify.subscribe(Events.ADD_URL, event_handler, f"{HttpSocket.__name__}.add")
load_modules(self.rootPath, self.rootPath / "routes" / "socket")
@ -145,7 +148,10 @@ class HttpSocket:
for route in socket_routes.values():
if self.config.debug:
LOG.debug(
f"Add ({route.name}) {route.method.value if isinstance(route.method, RouteType) else route.method}: {route.path}."
"Registered socket route '%s' for %s %s.",
route.name,
route.method.value if isinstance(route.method, RouteType) else route.method,
route.path,
)
async def handle_message(sid: str, message: str) -> None:
@ -161,7 +167,7 @@ class HttpSocket:
return
if not (route := socket_routes.get(event)):
LOG.debug(f"Unknown websocket event '{event}'.")
LOG.debug("Unknown WebSocket event '%s'.", event, extra={"sid": sid, "event": event})
return
data = payload.get("data") if isinstance(payload, dict) else None
@ -183,7 +189,7 @@ class HttpSocket:
sid: str = gen_random(14)
self.sio.add(sid, ws)
LOG.debug(f"WebSocket client '{sid}' connected.")
LOG.debug("WebSocket client '%s' connected.", sid, extra={"sid": sid})
await handle_connect(sid)
@ -192,8 +198,11 @@ class HttpSocket:
try:
await handle_message(sid, message)
except Exception as e:
LOG.exception(e)
LOG.error(f"Error handling WebSocket message from client '{sid}': {e}")
LOG.exception(
"Failed to handle WebSocket message from client '%s'.",
sid,
extra={"sid": sid, "message_size": len(message), "exception_type": type(e).__name__},
)
try:
i: int = 0
@ -202,15 +211,22 @@ class HttpSocket:
i = i + 1
asyncio.create_task(handle_message_safe(sid, msg.data), name=f"ws_msg_{sid}_{i}")
elif msg.type == web.WSMsgType.ERROR:
LOG.error(f"WebSocket connection closed with exception {ws.exception()}")
LOG.error(
"WebSocket connection closed with exception %s",
ws.exception(),
extra={
"sid": sid,
"exception": str(ws.exception()) if ws.exception() else None,
},
)
finally:
await handle_disconnect(sid, getattr(ws, "close_reason", None))
self.sio.remove(sid)
LOG.debug(f"WebSocket client '{sid}' disconnected.")
LOG.debug("WebSocket client '%s' disconnected.", sid, extra={"sid": sid})
return ws
if self.config.debug:
LOG.debug(f"Add (ws) GET: {ws_path}.")
LOG.debug("Registered WebSocket endpoint at '%s'.", ws_path, extra={"method": "GET", "path": ws_path})
app.router.add_get(ws_path, ws_handler, name="ws")

View file

@ -1,4 +1,3 @@
import logging
import re
import time
import uuid
@ -10,12 +9,13 @@ from typing import TYPE_CHECKING, Any
from app.features.ytdlp.utils import archive_add, archive_delete, archive_read, get_archive_id
from app.features.ytdlp.ytdlp_opts import YTDLPOpts
from app.library.encoder import Encoder
from app.library.log import get_logger
from app.library.Utils import clean_item, get_file, get_file_sidecar
if TYPE_CHECKING:
from app.features.presets.schemas import Preset
LOG: logging.Logger = logging.getLogger("ItemDTO")
LOG = get_logger()
@dataclass(kw_only=True)
@ -93,7 +93,7 @@ class Item:
bool: True if the item has extras, False otherwise.
"""
return self.extras and len(self.extras) > 0
return bool(self.extras and len(self.extras) > 0)
def add_extras(self, key: str, value: Any) -> None:
"""
@ -117,7 +117,7 @@ class Item:
bool: True if the item has command options for yt, False otherwise.
"""
return self.cli and len(self.cli) > 2
return bool(self.cli and len(self.cli) > 2)
@staticmethod
def _default_preset() -> str:
@ -161,7 +161,7 @@ class Item:
Item: The formatted item.
"""
url: str = item.get("url")
url = item.get("url")
if not url or not isinstance(url, str):
msg = "url param is required."
@ -173,7 +173,7 @@ class Item:
if len(url) >= 11 and re.fullmatch(r"[A-Za-z0-9_-]{11}", url):
url = f"https://www.youtube.com/watch?v={url}"
data: dict[str, str] = {"url": url}
data: dict[str, Any] = {"url": url}
preset: str | None = item.get("preset")
if preset and isinstance(preset, str) and preset != Item._default_preset():
@ -185,24 +185,28 @@ class Item:
data["preset"] = preset
if item.get("folder") and isinstance(item.get("folder"), str):
data["folder"] = item.get("folder")
folder = item.get("folder")
if isinstance(folder, str) and folder:
data["folder"] = folder
if item.get("cookies") and isinstance(item.get("cookies"), str):
data["cookies"] = item.get("cookies")
cookies = item.get("cookies")
if isinstance(cookies, str) and cookies:
data["cookies"] = cookies
if item.get("template") and isinstance(item.get("template"), str):
data["template"] = item.get("template")
template = item.get("template")
if isinstance(template, str) and template:
data["template"] = template
if "auto_start" in item and isinstance(item.get("auto_start"), bool):
data["auto_start"] = bool(item.get("auto_start"))
if isinstance(item.get("auto_start"), bool):
data["auto_start"] = item["auto_start"]
extras: dict | None = item.get("extras")
if extras and isinstance(extras, dict) and len(extras) > 0:
if isinstance(extras, dict) and len(extras) > 0:
data["extras"] = extras
if item.get("requeued") and isinstance(item.get("requeued"), bool):
data["requeued"] = item.get("requeued")
requeued = item.get("requeued")
if isinstance(requeued, bool):
data["requeued"] = requeued
cli: str | None = item.get("cli")
if cli and len(cli) > 2:
@ -574,8 +578,10 @@ class ItemDTO:
self.is_archivable = bool(self._archive_file)
if not self.is_archivable:
self.is_archived = False
else:
elif self.archive_id and self._archive_file:
self.is_archived = len(archive_read(self._archive_file, [self.archive_id])) > 0
else:
self.is_archived = False
def get_archive_file(self) -> str | None:
"""

View file

@ -1,14 +1,15 @@
import importlib
import importlib.metadata
import logging
import os
import subprocess
import sys
from pathlib import Path
from app.library.log import get_logger
from .httpx_client import sync_client
LOG: logging.Logger = logging.getLogger("package_installer")
LOG = get_logger()
def parse_version(v: str) -> tuple[int, ...]:
@ -16,7 +17,7 @@ def parse_version(v: str) -> tuple[int, ...]:
class Packages:
def __init__(self, env: str | None, file: str | None, upgrade: bool = False):
def __init__(self, env: str | None, file: str | Path | None, upgrade: bool = False):
from_env: list[str] = env.split() if env else []
from_file = []
@ -64,19 +65,34 @@ class PackageInstaller:
current_version: str | None = self._get_installed_version(pkg)
if current_version and version and self.compare_versions(current_version, version):
LOG.info(f"'{pkg}' is already installed with the specified version ({version}). Skipping installation.")
LOG.info(
"Package '%s' is already installed at version '%s'; skipping installation.",
pkg,
version,
extra={"package": pkg, "installed_version": current_version, "requested_version": version},
)
return
if upgrade and current_version and not version:
latest_version: str | None = self._get_latest_version(pkg)
if latest_version and parse_version(current_version) >= parse_version(latest_version):
LOG.info(f"'{pkg}' is already the latest version ({current_version}). Skipping upgrade.")
LOG.info(
"Package '%s' is already at the latest version '%s'; skipping upgrade.",
pkg,
current_version,
extra={"package": pkg, "installed_version": current_version, "latest_version": latest_version},
)
return
if current_version:
LOG.info(f"'{pkg}' is already installed (version: {current_version}). Proceeding with upgrade...")
LOG.info(
"Package '%s' is installed at '%s'; proceeding with upgrade.",
pkg,
current_version,
extra={"package": pkg, "installed_version": current_version},
)
else:
LOG.info(f"'{pkg}' is not installed. Installing...")
LOG.info("Package '%s' is not installed; installing it.", pkg, extra={"package": pkg})
self._install_pkg(pkg, version=version)
@ -93,9 +109,20 @@ class PackageInstaller:
resp = client.get(url)
if 200 == resp.status_code:
return resp.json()["info"]["version"]
LOG.warning(f"Failed to fetch '{pkg}' info: HTTP {resp.status_code}")
LOG.warning(
"Failed to fetch PyPI metadata for '%s': HTTP %s.",
pkg,
resp.status_code,
extra={"package": pkg, "status_code": resp.status_code, "url": url},
)
except Exception as e:
LOG.warning(f"Error while querying PyPI for '{pkg}': {e}")
LOG.warning(
"Failed to query PyPI for '%s': %s",
pkg,
e,
extra={"package": pkg, "url": url, "exception_type": type(e).__name__},
exc_info=True,
)
return None
def _install_pkg(self, pkg: str, version: str | None = None) -> bool:
@ -135,7 +162,12 @@ class PackageInstaller:
return 0 == proc.returncode
except subprocess.CalledProcessError as e:
LOG.error(f"Failed to install '{pkg}' (exit {e.returncode}). {e!s}")
LOG.exception(
"Failed to install package '%s' (exit %s).",
pkg,
e.returncode,
extra={"package": pkg, "returncode": e.returncode, "exception_type": type(e).__name__},
)
self.out(out=e.stdout, err=e.stderr)
raise
@ -150,13 +182,20 @@ class PackageInstaller:
if not pkgs.has_packages() or not self.user_site:
return
LOG.info(f"Checking for user pip packages: {', '.join(pkgs.packages)}")
LOG.info("Checking configured user pip packages.", extra={"packages": pkgs.packages})
for package in pkgs.packages:
try:
self.action(package, upgrade=pkgs.allow_upgrade())
except Exception as e:
LOG.error(f"Failed to install or upgrade package '{package}'. Error message: {e!s}")
LOG.exception(e)
LOG.exception(
"Failed to install or upgrade package '%s'.",
package,
extra={
"package": package,
"allow_upgrade": pkgs.allow_upgrade(),
"exception_type": type(e).__name__,
},
)
def compare_versions(self, current: str, target: str) -> bool:
"""

View file

@ -1,13 +1,16 @@
import asyncio
import logging
from collections.abc import Callable
from typing import Any
from aiocron import Cron
from aiohttp import web
from app.library.log import get_logger
from .Events import EventBus, Events
from .Singleton import Singleton
LOG = logging.getLogger("scheduler")
LOG = get_logger()
class Scheduler(metaclass=Singleton):
@ -46,10 +49,13 @@ class Scheduler(metaclass=Singleton):
for job in self._jobs:
try:
self._jobs[job].stop()
LOG.debug(f"Stopped job '{job}'.")
LOG.debug("Stopped job '%s'.", job, extra={"job_id": job})
except Exception as e:
LOG.exception(e)
LOG.error(f"Failed to stop job '{job}'. Error message '{e!s}'.")
LOG.exception(
"Failed to stop scheduler job '%s'.",
job,
extra={"job_id": job, "exception_type": type(e).__name__},
)
self._jobs = {}
@ -62,7 +68,7 @@ class Scheduler(metaclass=Singleton):
if data and data.data:
self.add(**data.data)
EventBus.get_instance().subscribe(Events.SCHEDULE_ADD, event_handler, f"{__class__.__name__}.add")
EventBus.get_instance().subscribe(Events.SCHEDULE_ADD, event_handler, f"{type(self).__name__}.add")
def get_all(self) -> dict[str, Cron]:
"""Return the jobs."""
@ -95,7 +101,7 @@ class Scheduler(metaclass=Singleton):
return id in self._jobs
def add(
self, timer: str, func: callable, args: tuple = (), kwargs: dict | None = None, id: str | None = None
self, timer: str, func: Callable[..., Any], args: tuple = (), kwargs: dict | None = None, id: str | None = None
) -> str:
"""
Add a job to the schedule.
@ -127,7 +133,7 @@ class Scheduler(metaclass=Singleton):
self._jobs[job_id] = job
LOG.debug(f"Added '{job_id}' to the scheduler to run on '{timer}'.")
LOG.debug("Added job '%s' to run on '%s'.", job_id, timer, extra={"job_id": job_id, "timer": timer})
return job_id
@ -151,12 +157,15 @@ class Scheduler(metaclass=Singleton):
try:
self._jobs[id].stop()
except Exception as e:
LOG.exception(e)
LOG.error(f"Failed to stop job '{id}'. Error message '{e!s}'.")
LOG.exception(
"Failed to stop scheduler job '%s'.",
id,
extra={"job_id": id, "exception_type": type(e).__name__},
)
return False
del self._jobs[id]
LOG.debug(f"Removed job '{id}' from the scheduler.")
LOG.debug("Removed job '%s' from the scheduler.", id, extra={"job_id": id})
return True
return False

View file

@ -1,12 +1,13 @@
import inspect
import logging
from collections.abc import Callable
from dataclasses import dataclass
from typing import Annotated, Any, TypeVar, get_args, get_origin, get_type_hints
from app.library.log import get_logger
from app.library.Singleton import Singleton
T = TypeVar("T")
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
def _unwrap_annotation(ann: Any) -> Any:
@ -117,7 +118,7 @@ class Services(metaclass=Singleton):
return candidates[0]
def _build_call_args(self, handler: callable, overrides: dict[str, Any]) -> dict[str, Any]:
def _build_call_args(self, handler: Callable[..., Any], overrides: dict[str, Any]) -> dict[str, Any]:
sig: inspect.Signature = inspect.signature(handler)
try:
@ -169,10 +170,10 @@ class Services(metaclass=Singleton):
return resolved
async def handle_async(self, handler: callable, **kwargs) -> Any:
async def handle_async(self, handler: Callable[..., Any], **kwargs) -> Any:
resolved: dict[str, Any] = self._build_call_args(handler, kwargs)
return await handler(**resolved)
def handle_sync(self, handler: callable, **kwargs) -> Any:
def handle_sync(self, handler: Callable[..., Any], **kwargs) -> Any:
resolved: dict[str, Any] = self._build_call_args(handler, kwargs)
return handler(**resolved)

View file

@ -3,7 +3,6 @@ from __future__ import annotations
import asyncio
import errno
import json
import logging
import os
import shlex
import shutil
@ -16,6 +15,7 @@ from typing import TYPE_CHECKING, Any
from aiohttp import web
from app.library.config import Config
from app.library.log import get_logger
from app.library.Scheduler import Scheduler
from app.library.Services import Services
from app.library.Singleton import Singleton
@ -26,7 +26,7 @@ if TYPE_CHECKING:
from aiohttp.web import Request
LOG: logging.Logger = logging.getLogger("terminal_manager")
LOG = get_logger()
ACTIVE_FILE_NAME = "active.json"
METADATA_FILE_NAME = "metadata.json"
@ -75,7 +75,7 @@ class TerminalSessionManager(metaclass=Singleton):
self._cleanup_job_id = Scheduler.get_instance().add(
timer=CLEANUP_SCHEDULE,
func=self.cleanup,
id=f"{__class__.__name__}.{__class__.cleanup.__name__}",
id=f"{type(self).__name__}.{type(self).cleanup.__name__}",
)
async def on_startup(self, _: web.Application) -> None:
@ -296,7 +296,7 @@ class TerminalSessionManager(metaclass=Singleton):
master_fd: int | None = None
try:
LOG.info("Cli command from client. '%s'", command)
LOG.info("Starting terminal session '%s' command.", session_id, extra={"session_id": session_id})
args = ["yt-dlp", *shlex.split(command, posix=os.name != "nt")]
env_vars = self._build_env()
@ -343,7 +343,10 @@ class TerminalSessionManager(metaclass=Singleton):
try:
os.close(slave_fd)
except Exception as exc:
LOG.error("Error closing PTY. '%s'.", str(exc))
LOG.exception(
"Failed to close the PTY slave file descriptor.",
extra={"exception_type": type(exc).__name__},
)
read_task = asyncio.create_task(
self._read_process_output(session_id=session_id, proc=proc, use_pty=use_pty, master_fd=master_fd),
@ -356,8 +359,11 @@ class TerminalSessionManager(metaclass=Singleton):
final_status = "interrupted"
except Exception as exc:
final_status = "failed"
LOG.error("CLI execute exception was thrown.")
LOG.exception(exc)
LOG.exception(
"Terminal session '%s' command failed.",
session_id,
extra={"session_id": session_id, "use_pty": use_pty, "exception_type": type(exc).__name__},
)
await self._append_event(session_id, "output", {"type": "stderr", "line": str(exc)})
finally:
final_status = await self._resolve_final_status(session_id=session_id, status=final_status)
@ -371,7 +377,7 @@ class TerminalSessionManager(metaclass=Singleton):
try:
return_code = await asyncio.wait_for(proc.wait(), timeout=self._shutdown_timeout)
except TimeoutError:
LOG.warning("Terminal session '%s' process did not exit cleanly.", session_id)
LOG.warning("Terminal session '%s' did not exit after repeated shutdown attempts.", session_id)
if proc is not None:
proc_returncode = getattr(proc, "returncode", None)

View file

@ -1,10 +1,11 @@
import asyncio
import logging
import re
from typing import Any
from aiohttp import web
from app.library.log import get_logger
from .cache import Cache
from .config import Config
from .Events import EventBus, Events
@ -13,7 +14,7 @@ from .Scheduler import Scheduler
from .Singleton import Singleton
from .version import APP_VERSION
LOG: logging.Logger = logging.getLogger("update_checker")
LOG = get_logger()
class UpdateChecker(metaclass=Singleton):
@ -79,7 +80,7 @@ class UpdateChecker(metaclass=Singleton):
self._notify.subscribe(
event=Events.STARTED,
callback=event_handler,
name=f"{__class__.__name__}.{__class__.attach.__name__}",
name=f"{UpdateChecker.__name__}.{type(self).attach.__name__}",
)
self._schedule_check()
@ -107,7 +108,7 @@ class UpdateChecker(metaclass=Singleton):
self._job_id = self._scheduler.add(
timer=timer,
func=lambda: asyncio.create_task(self.check_for_updates()),
id=f"{__class__.__name__}.{self.check_for_updates.__name__}",
id=f"{UpdateChecker.__name__}.{self.check_for_updates.__name__}",
)
async def check_for_updates(self) -> tuple[tuple[str, str | None], tuple[str, str | None]]:
@ -145,7 +146,11 @@ class UpdateChecker(metaclass=Singleton):
strip_v_prefix: bool = False,
) -> tuple[str, str | None]:
try:
LOG.info(f"Checking for {name} updates...")
LOG.info(
"Checking whether %s has an update available.",
name,
extra={"target_name": name, "api_url": api_url, "current_version": current_version},
)
client = get_async_client(use_curl=False)
response = await client.get(
@ -155,32 +160,59 @@ class UpdateChecker(metaclass=Singleton):
)
if 200 != response.status_code:
LOG.warning(f"Failed to check for {name} updates: HTTP {response.status_code}")
LOG.warning(
"Failed to check for %s updates: HTTP %s",
name,
response.status_code,
extra={"target_name": name, "api_url": api_url, "status_code": response.status_code},
)
return ("error", None)
data: dict[str, Any] = response.json()
latest_tag: str = data.get("tag_name", "")
if not latest_tag:
LOG.warning(f"No tag_name found in {name} GitHub release data.")
LOG.warning(
"No tag_name found in %s GitHub release data.",
name,
extra={"target_name": name, "api_url": api_url},
)
return ("error", None)
compare_current: str = current_version.lstrip("v") if strip_v_prefix else current_version
compare_latest: str = latest_tag.lstrip("v") if strip_v_prefix else latest_tag
if self._compare_versions(compare_current, compare_latest):
LOG.warning(f"{name} update available: {current_version} -> {latest_tag}")
LOG.warning(
"%s has an update available: %s -> %s.",
name,
current_version,
latest_tag,
extra={"target_name": name, "current_version": current_version, "latest_version": latest_tag},
)
result = ("update_available", latest_tag)
await self._cache.aset(cache_key, result, self.CACHE_DURATION)
return result
LOG.info(f"No {name} updates available.")
LOG.info(
"%s is already up to date.",
name,
extra={"target_name": name, "current_version": current_version},
)
result = ("up_to_date", None)
await self._cache.aset(cache_key, result, self.CACHE_DURATION)
return result
except Exception as e:
LOG.exception(e)
LOG.error(f"Error checking for {name} updates: {e!s}")
LOG.exception(
"Failed to check whether %s has an update available.",
name,
extra={
"target_name": name,
"api_url": api_url,
"cache_key": cache_key,
"exception_type": type(e).__name__,
},
)
return ("error", None)
async def _check_app_version(self) -> tuple[str, str | None]:
@ -203,7 +235,7 @@ class UpdateChecker(metaclass=Singleton):
async def _check_ytdlp_version(self) -> tuple[str, str | None]:
current_version: str = self._config._ytdlp_version()
if not current_version or "0.0.0" == current_version:
LOG.warning("Could not determine yt-dlp version, skipping yt-dlp update check.")
LOG.warning("Skipping the yt-dlp update check because the current version could not be determined.")
return ("error", None)
status, new_version = await self._check_github_version(
@ -238,5 +270,12 @@ class UpdateChecker(metaclass=Singleton):
return parse_version(latest) > parse_version(current)
except Exception as e:
LOG.warning(f"Error comparing versions '{current}' vs '{latest}': {e}")
LOG.warning(
"Failed to compare versions '%s' and '%s' because %s.",
current,
latest,
e,
extra={"current_version": current, "latest_version": latest, "exception_type": type(e).__name__},
exc_info=True,
)
return False

View file

@ -2,11 +2,13 @@ import base64
import copy
import glob
import ipaddress
import json
import logging
import os
import re
import socket
import time
import traceback
import uuid
from datetime import UTC, datetime, timedelta
from functools import lru_cache, wraps
@ -16,7 +18,9 @@ from typing import Any
from Crypto.Cipher import AES
LOG: logging.Logger = logging.getLogger("Utils")
from app.library.log import get_logger
LOG = get_logger()
ALLOWED_SUBS_EXTENSIONS: set[str] = {".srt", ".vtt", ".ass"}
"Allowed subtitle file extensions."
@ -36,11 +40,179 @@ TAG_REGEX: re.Pattern[str] = re.compile(r"%{([^:}]+)(?::([^}]*))?}c")
class FileLogFormatter(logging.Formatter):
def formatTime(self, record, datefmt=None): # noqa: ARG002, N802
def formatTime(self, record, datefmt=None): # noqa: N802
_ = datefmt
return datetime.fromtimestamp(record.created).astimezone().isoformat(timespec="milliseconds")
def timed_lru_cache(ttl_seconds: int, max_size: int = 128):
LOG_RECORD_ATTRS: set[str] = set(logging.makeLogRecord({}).__dict__) | {"asctime", "message"}
SKIP_LOG_FIELD = object()
class JsonLogFormatter(logging.Formatter):
def format(self, record: logging.LogRecord) -> str:
source = {
"path": record.pathname,
"file": record.filename,
"module": record.module,
"function": record.funcName,
"line": record.lineno,
}
data: dict[str, Any] = {
"id": str(uuid.uuid4()),
"datetime": self.formatTime(record),
"level": record.levelname.lower(),
"levelno": record.levelno,
"logger": record.name,
"message": record.getMessage(),
"source": source,
"process": {"id": record.process, "name": record.processName},
"thread": {"id": record.thread, "name": record.threadName},
"fields": self._extra(record),
}
if record.exc_info:
exception = self._exception(record.exc_info)
if exception is not None:
data["exception"] = exception
data["source"].update(self._exception_source(exception))
return json.dumps(data, ensure_ascii=False, default=str)
def formatTime(self, record, datefmt=None): # noqa: N802
_ = datefmt
return datetime.fromtimestamp(record.created).astimezone().isoformat(timespec="milliseconds")
@staticmethod
def _extra(record: logging.LogRecord) -> dict[str, Any]:
extra: dict[str, Any] = {}
for key, value in record.__dict__.items():
if key in LOG_RECORD_ATTRS or key.startswith("_"):
continue
value = JsonLogFormatter._field(value)
if value is not SKIP_LOG_FIELD:
extra[key] = value
return extra
@staticmethod
def _field(value: Any) -> Any:
if isinstance(value, str | int | float | bool) or value is None:
return value
if isinstance(value, Path):
return str(value)
if isinstance(value, dict):
data: dict[str, Any] = {}
for key, item in value.items():
if not isinstance(key, str) or key.startswith("_"):
continue
item = JsonLogFormatter._field(item)
if item is not SKIP_LOG_FIELD:
data[key] = item
return data
if isinstance(value, list):
data: list[Any] = []
for item in value:
item = JsonLogFormatter._field(item)
if item is not SKIP_LOG_FIELD:
data.append(item)
return data
return SKIP_LOG_FIELD
@staticmethod
def _exception(
exc_info: tuple[type[BaseException], BaseException, Any] | tuple[None, None, None],
) -> dict[str, Any] | None:
exc = exc_info[1]
if exc is None:
return None
stack = JsonLogFormatter._exception_stack(exc_info)
data: dict[str, Any] = {"type": JsonLogFormatter._exception_type(exc)}
message = str(exc).strip()
if message:
data["message"] = message
if stack:
origin = stack[-1]
data["file"] = origin["path"]
data["line"] = origin["line"]
data["stack"] = stack
return data
@staticmethod
def _exception_type(exc: BaseException) -> str:
module = exc.__class__.__module__
name = exc.__class__.__qualname__
return name if module == "builtins" else f"{module}.{name}"
@staticmethod
def _exception_stack(
exc_info: tuple[type[BaseException], BaseException, Any] | tuple[None, None, None],
) -> list[dict[str, Any]]:
exc = exc_info[1]
tb = exc_info[2] if len(exc_info) > 2 else None
if tb is None and exc is not None:
tb = exc.__traceback__
if tb is None:
return []
return [JsonLogFormatter._frame(frame) for frame in traceback.extract_tb(tb)]
@staticmethod
def _frame(frame: traceback.FrameSummary) -> dict[str, Any]:
path = frame.filename
file_path = Path(path)
return {
"path": path,
"file": file_path.name,
"module": file_path.stem,
"function": frame.name,
"line": frame.lineno,
}
@staticmethod
def _exception_source(exception: dict[str, Any]) -> dict[str, Any]:
source: dict[str, Any] = {}
path = exception.get("file")
if isinstance(path, str) and path:
file_path = Path(path)
source["path"] = path
source["file"] = file_path.name
source["module"] = file_path.stem
line = exception.get("line")
if isinstance(line, int):
source["line"] = line
stack = exception.get("stack")
if isinstance(stack, list) and stack:
frame = stack[-1]
if isinstance(frame, dict):
function = frame.get("function")
if isinstance(function, str) and function:
source["function"] = function
module = frame.get("module")
if isinstance(module, str) and module:
source["module"] = module
return source
def timed_lru_cache(ttl_seconds: float, max_size: int = 128):
"""
Decorator that applies an LRU cache with a time-to-live (TTL) to a function.
Supports both synchronous and asynchronous functions.
@ -110,8 +282,9 @@ def timed_lru_cache(ttl_seconds: int, max_size: int = 128):
return _CacheInfo(hits=0, misses=len(cache), maxsize=max_size, currsize=len(cache))
async_wrapper.cache_clear = cache_clear
async_wrapper.cache_info = cache_info
async_wrapper_cache: Any = async_wrapper
async_wrapper_cache.cache_clear = cache_clear
async_wrapper_cache.cache_info = cache_info
return async_wrapper
# For sync functions, use the original implementation
@ -139,8 +312,9 @@ def timed_lru_cache(ttl_seconds: int, max_size: int = 128):
return result
# expose cache_clear, cache_info
sync_wrapper.cache_clear = cached.cache_clear
sync_wrapper.cache_info = cached.cache_info
sync_wrapper_cache: Any = sync_wrapper
sync_wrapper_cache.cache_clear = cached.cache_clear
sync_wrapper_cache.cache_info = cached.cache_info
return sync_wrapper
return decorator
@ -211,7 +385,12 @@ def _is_safe_key(key: Any) -> bool:
def merge_dict(
source: dict, destination: dict, max_depth: int = 50, max_list_size: int = 10000, _depth: int = 0, _seen: set = None
source: dict,
destination: dict,
max_depth: int = 50,
max_list_size: int = 10000,
_depth: int = 0,
_seen: set | None = None,
) -> dict:
"""
Merge data from source into destination.
@ -302,7 +481,7 @@ def merge_dict(
return destination_copy
def check_id(file: Path) -> bool | str:
def check_id(file: Path) -> bool | Path:
"""
Check if we are able to get an id from the file name.
if so check if any video file with the same id exists.
@ -321,6 +500,8 @@ def check_id(file: Path) -> bool | str:
return False
id: str | None = match.groupdict().get("id")
if id is None:
return False
try:
if not file.parent.exists():
@ -335,7 +516,11 @@ def check_id(file: Path) -> bool | str:
return f.absolute()
except OSError as e:
LOG.error(f"Error checking file '{file}': {e!s}")
LOG.exception(
"Failed to check for a matching file for '%s'.",
file,
extra={"file_path": str(file), "operation": "check_id", "exception_type": type(e).__name__},
)
return False
return False
@ -371,9 +556,9 @@ def validate_url(url: str, allow_internal: bool = False) -> bool:
from yarl import URL
parsed_url = URL(url)
except ValueError:
except ValueError as exc:
msg = "Invalid URL."
raise ValueError(msg) # noqa: B904
raise ValueError(msg) from exc
# Check allowed schemes
if parsed_url.scheme not in ["http", "https"]:
@ -391,7 +576,11 @@ def validate_url(url: str, allow_internal: bool = False) -> bool:
msg = "Access to internal urls or private networks is not allowed."
raise ValueError(msg)
except socket.gaierror as e:
LOG.error(f"Error resolving hostname '{hostname}': {e!s}")
LOG.exception(
"Failed to resolve hostname '%s'.",
hostname,
extra={"hostname": hostname, "exception_type": type(e).__name__},
)
msg = "Invalid hostname."
raise ValueError(msg) from e
@ -418,7 +607,7 @@ def validate_uuid(uuid_str: str, version: int = 4) -> bool:
@timed_lru_cache(ttl_seconds=60, max_size=256)
def get_file_sidecar(file: Path | None = None) -> dict[dict]:
def get_file_sidecar(file: Path | None = None) -> dict[str, list[dict[str, Any]]]:
"""
Get sidecar files for the given file.
@ -519,16 +708,46 @@ def rename_file(old_path: Path, new_name: str) -> tuple[Path, list[tuple[Path, P
renamed_sidecar: Path = old_sidecar.rename(new_sidecar)
renamed_sidecars.append((old_sidecar, renamed_sidecar))
except OSError as e:
LOG.error(f"Failed to rename sidecar '{old_sidecar}': {e}")
LOG.exception(
"Failed to rename sidecar '%s' to '%s'.",
old_sidecar,
new_sidecar,
extra={
"old_path": str(old_sidecar),
"new_path": str(new_sidecar),
"operation": "rename_sidecar",
"exception_type": type(e).__name__,
},
)
try:
renamed_main.rename(old_path)
except OSError:
LOG.error(f"Failed to rollback main file rename from '{renamed_main}' to '{old_path}'")
except OSError as rollback_error:
LOG.exception(
"Failed to roll back main file rename from '%s' to '%s'.",
renamed_main,
old_path,
extra={
"old_path": str(renamed_main),
"new_path": str(old_path),
"operation": "rename_rollback",
"exception_type": type(rollback_error).__name__,
},
)
raise
return renamed_main, renamed_sidecars
except OSError as e:
LOG.error(f"Failed to rename '{old_path}' to '{new_path}': {e}")
LOG.exception(
"Failed to rename '%s' to '%s'.",
old_path,
new_path,
extra={
"old_path": str(old_path),
"new_path": str(new_path),
"operation": "rename",
"exception_type": type(e).__name__,
},
)
raise
@ -586,24 +805,62 @@ def move_file(old_path: Path, target_dir: Path) -> tuple[Path, list[tuple[Path,
moved_sidecar: Path = old_sidecar.rename(new_sidecar)
renamed_sidecars.append((old_sidecar, moved_sidecar))
except OSError as e:
LOG.error(f"Failed to move sidecar '{old_sidecar}': {e}")
LOG.exception(
"Failed to move sidecar '%s' to '%s'.",
old_sidecar,
new_sidecar,
extra={
"old_path": str(old_sidecar),
"new_path": str(new_sidecar),
"operation": "move_sidecar",
"exception_type": type(e).__name__,
},
)
try:
moved_main.rename(old_path)
# Rollback any sidecars that were already moved
for rolled_back_old, rolled_back_new in renamed_sidecars:
try:
rolled_back_new.rename(rolled_back_old)
except OSError:
LOG.error(
f"Failed to rollback sidecar move from '{rolled_back_new}' to '{rolled_back_old}'"
except OSError as rollback_error:
LOG.exception(
"Failed to roll back sidecar move from '%s' to '%s'.",
rolled_back_new,
rolled_back_old,
extra={
"old_path": str(rolled_back_new),
"new_path": str(rolled_back_old),
"operation": "move_sidecar_rollback",
"exception_type": type(rollback_error).__name__,
},
)
except OSError:
LOG.error(f"Failed to rollback main file move from '{moved_main}' to '{old_path}'")
except OSError as rollback_error:
LOG.exception(
"Failed to roll back main file move from '%s' to '%s'.",
moved_main,
old_path,
extra={
"old_path": str(moved_main),
"new_path": str(old_path),
"operation": "move_rollback",
"exception_type": type(rollback_error).__name__,
},
)
raise
return moved_main, renamed_sidecars
except OSError as e:
LOG.error(f"Failed to move '{old_path}' to '{new_path}': {e}")
LOG.exception(
"Failed to move '%s' to '%s'.",
old_path,
new_path,
extra={
"old_path": str(old_path),
"new_path": str(new_path),
"operation": "move",
"exception_type": type(e).__name__,
},
)
raise
@ -679,18 +936,22 @@ def get_file(download_path: str | Path, file: str | Path) -> tuple[Path, int]:
download_path = Path(download_path)
try:
realFile: str = Path(calc_download_path(base_path=download_path, folder=str(file), create_path=False))
realFile: Path = Path(calc_download_path(base_path=download_path, folder=str(file), create_path=False))
if realFile.exists():
return (realFile, 200)
except Exception as e:
LOG.error(f"Error calculating download path. {e!s}")
LOG.exception(
"Failed to resolve download file path for '%s'.",
file,
extra={"file_path": str(file), "download_path": str(download_path), "exception_type": type(e).__name__},
)
return (Path(file), 404)
possibleFile: bool | str = check_id(file=realFile)
if not possibleFile:
possibleFile: bool | Path = check_id(file=realFile)
if not isinstance(possibleFile, Path):
return (realFile, 404)
return (Path(possibleFile), 302)
return (possibleFile, 302)
def encrypt_data(data: str, key: bytes) -> str:
@ -712,7 +973,7 @@ def encrypt_data(data: str, key: bytes) -> str:
return base64.urlsafe_b64encode(iv + ciphertext + tag).decode()
def decrypt_data(data: str, key: bytes) -> str:
def decrypt_data(data: str, key: bytes) -> str | None:
"""
Decrypts AES-GCM encrypted data
@ -725,8 +986,8 @@ def decrypt_data(data: str, key: bytes) -> str:
"""
try:
data = base64.urlsafe_b64decode(data)
iv, ciphertext, tag = data[:12], data[12:-16], data[-16:]
raw: bytes = base64.urlsafe_b64decode(data)
iv, ciphertext, tag = raw[:12], raw[12:-16], raw[-16:]
cipher = AES.new(key, AES.MODE_GCM, nonce=iv)
plaintext = cipher.decrypt_and_verify(ciphertext, tag)
return plaintext.decode()
@ -737,7 +998,7 @@ def decrypt_data(data: str, key: bytes) -> str:
def get(
data: dict | list,
path: str | list | None = None,
default: any = None,
default: Any = None,
separator=".",
):
"""
@ -854,22 +1115,42 @@ def get_files(
try:
dir_path = dir_path.resolve()
except OSError as e:
LOG.warning(f"Failed to resolve '{dir}' - {e}")
return []
LOG.warning(
"Failed to resolve '%s': %s",
dir,
e,
extra={"requested_dir": dir, "base_path": str(base_path), "exception_type": type(e).__name__},
exc_info=True,
)
return [], 0
try:
dir_path.relative_to(base_path)
except ValueError:
LOG.warning(f"Invalid path: '{dir_path}' - must be inside '{base_path}'.")
return []
LOG.warning(
"Invalid path '%s': must be inside '%s'.",
dir_path,
base_path,
extra={"path": str(dir_path), "base_path": str(base_path)},
)
return [], 0
if not str(dir_path).startswith(str(base_path)):
LOG.warning(f"Invalid path: '{dir_path}' - must be inside '{base_path}'.")
return []
LOG.warning(
"Invalid path '%s': must be inside '%s'.",
dir_path,
base_path,
extra={"path": str(dir_path), "base_path": str(base_path)},
)
return [], 0
if not dir_path.is_dir():
LOG.warning(f"Invalid path: '{dir_path}' - must be a directory.")
return []
LOG.warning(
"Invalid path '%s': must be a directory.",
dir_path,
extra={"path": str(dir_path), "base_path": str(base_path)},
)
return [], 0
contents: list = []
for file in dir_path.iterdir():
@ -882,13 +1163,28 @@ def get_files(
test: Path = file.resolve()
test.relative_to(base_path)
if not str(test).startswith(str(base_path)):
LOG.warning(f"Invalid symlink: '{file}' - must resolve inside '{base_path}'.")
LOG.warning(
"Invalid symlink '%s': must resolve inside '%s'.",
file,
base_path,
extra={"path": str(file), "resolved_path": str(test), "base_path": str(base_path)},
)
continue
except ValueError:
LOG.warning(f"Invalid symlink: '{file}' - must resolve inside '{base_path}'.")
LOG.warning(
"Invalid symlink '%s': must resolve inside '%s'.",
file,
base_path,
extra={"path": str(file), "base_path": str(base_path)},
)
continue
except OSError:
LOG.warning(f"Skipping broken symlink: {file}")
except OSError as e:
LOG.warning(
"Skipping broken symlink '%s'.",
file,
extra={"path": str(file), "base_path": str(base_path), "exception_type": type(e).__name__},
exc_info=True,
)
continue
content_type = None
@ -1013,7 +1309,7 @@ def load_cookies(file: str | Path) -> tuple[bool, MozillaCookieJar]:
try:
from http.cookiejar import MozillaCookieJar
cookies = MozillaCookieJar(str(file), None, None)
cookies = MozillaCookieJar(str(file), delayload=False, policy=None)
cookies.load()
return (True, cookies)
@ -1078,7 +1374,11 @@ def delete_dir(dir: Path) -> bool:
dir.rmdir()
return True
except Exception as e:
LOG.error(f"Failed to delete directory '{dir}': {e}")
LOG.exception(
"Failed to delete directory '%s'.",
dir,
extra={"dir": str(dir), "exception_type": type(e).__name__},
)
return False
@ -1126,7 +1426,11 @@ def load_modules(root_path: Path, directory: Path):
try:
importlib.import_module(full_name)
except ImportError as e:
LOG.error(f"Failed to import module '{full_name}': {e}")
LOG.exception(
"Failed to import module '%s'.",
full_name,
extra={"module_name": full_name, "exception_type": type(e).__name__},
)
def parse_tags(text: str) -> tuple[str, dict[str, str | bool]]:
@ -1184,35 +1488,6 @@ def str_to_dt(time_str: str, now=None) -> datetime:
return dt
def list_folders(path: Path, base: Path, depth_limit: int) -> list[str]:
"""
List all folders relative to a base path, up to a specified depth limit.
Args:
path (Path): The path to start listing folders from.
base (Path): The base path to which the folders should be relative.
depth_limit (int): The maximum depth to traverse from the base path.
Returns:
list[str]: A list of folder paths relative to the base path, up to the specified
"""
if "/" == str(path):
return []
rel_depth: int = len(path.relative_to(base).parts)
if rel_depth > depth_limit:
return []
folders: list[str] = []
for entry in path.iterdir():
if entry.is_dir():
folders.append(str(entry.relative_to(base)))
folders.extend(list_folders(entry, base, depth_limit))
return folders
def get_channel_images(thumbnails: list[dict]) -> dict:
"""
Extract channel images from a list of thumbnail dictionaries.

View file

@ -1,6 +1,20 @@
import sys
from typing import Any
def _dict_value(data: dict[Any, Any], key: Any) -> tuple[bool, Any]:
if key not in data or data[key] is None:
return False, None
return True, data[key]
def _dict_delete(data: dict[Any, Any], key: Any) -> bool:
if key not in data:
return False
del data[key]
return True
def get_value(value: Any) -> Any:
"""
Return the result of calling `value` if it is callable, else return `value`.
@ -91,14 +105,19 @@ def ag(
return val
return get_value(default)
key = path
if isinstance(array, dict) and key in array and array[key] is not None:
return array[key]
if isinstance(array, dict):
found, value = _dict_value(array, key)
if found:
return value
if not isinstance(key, str) or separator not in key:
return get_value(default)
current = array
for segment in key.split(separator):
if isinstance(current, dict) and segment in current and current[segment] is not None:
current = current[segment]
if isinstance(current, dict):
found, value = _dict_value(current, segment)
if not found:
return get_value(default)
current = value
elif isinstance(current, list):
try:
idx = int(segment)
@ -150,7 +169,8 @@ def ag_exists(data: dict[Any, Any] | list[Any] | object, path: str | int, separa
except TypeError:
return False
if isinstance(data, dict):
if path in data and data[path] is not None:
found, _ = _dict_value(data, path)
if found:
return True
elif isinstance(data, list) and isinstance(path, int):
return 0 <= path < len(data) and data[path] is not None
@ -158,8 +178,11 @@ def ag_exists(data: dict[Any, Any] | list[Any] | object, path: str | int, separa
segments = path_str.split(separator)
current = data
for seg in segments:
if isinstance(current, dict) and seg in current and current[seg] is not None:
current = current[seg]
if isinstance(current, dict):
found, value = _dict_value(current, seg)
if not found:
return False
current = value
elif isinstance(current, list):
try:
idx = int(seg)
@ -189,17 +212,16 @@ def ag_delete(
The modified structure.
"""
if isinstance(path, list | tuple):
for p in path:
ag_delete(data, p, separator)
return data
if not isinstance(data, dict | list):
try:
data = vars(data)
except TypeError:
return data # type: ignore
if isinstance(data, dict) and path in data:
del data[path]
if isinstance(path, list | tuple):
for p in path:
ag_delete(data, p, separator)
return data
if isinstance(data, dict) and _dict_delete(data, path):
return data
if isinstance(data, list) and isinstance(path, int):
if 0 <= path < len(data):
@ -210,8 +232,12 @@ def ag_delete(
last = segments.pop()
current = data
for seg in segments:
if isinstance(current, dict) and seg in current:
current = current[seg]
if isinstance(current, dict):
found, value = _dict_value(current, seg)
if not found:
current = None
break
current = value
elif isinstance(current, list):
try:
idx = int(seg)
@ -228,8 +254,8 @@ def ag_delete(
break
if current is None:
return data
if isinstance(current, dict) and last in current:
del current[last]
if isinstance(current, dict):
_dict_delete(current, last)
elif isinstance(current, list):
try:
idx = int(last)
@ -246,10 +272,12 @@ def run_tests():
assert ag_set(d, "a.c.d", 42) == {"a": {"b": 1, "c": {"d": 42}}}
def test_ag_set_overwrite_error():
error = ""
try:
ag_set({"a": 1}, "a.b", 2)
except RuntimeError as e:
assert "Cannot set value at path" in str(e) # noqa: PT017
error = str(e)
assert "Cannot set value at path" in error
def test_ag_get_value_callable_and_value():
assert get_value(5) == 5
@ -320,9 +348,9 @@ def run_tests():
]:
try:
test()
print(f"PASS: {test.__name__}") # noqa: T201
sys.stdout.write(f"PASS: {test.__name__}\n")
except AssertionError:
print(f"FAIL {test.__name__}") # noqa: T201
sys.stdout.write(f"FAIL {test.__name__}\n")
if __name__ == "__main__":

View file

@ -1,17 +1,17 @@
import hashlib
import logging
import threading
import time
from typing import Any
from aiohttp import web
from app.library.log import get_logger
from app.library.Services import Services
from .Scheduler import Scheduler
from .Singleton import ThreadSafe
LOG = logging.getLogger("cache")
LOG = get_logger()
class Cache(metaclass=ThreadSafe):
@ -38,7 +38,7 @@ class Cache(metaclass=ThreadSafe):
Scheduler.get_instance().add(
timer="* * * * *",
func=self.cleanup,
id=f"{__class__.__name__}.{__class__.cleanup.__name__}",
id=f"{type(self).__name__}.{type(self).cleanup.__name__}",
)
def set(self, key: str, value: Any, ttl: float | None = None) -> None:
@ -175,4 +175,8 @@ class Cache(metaclass=ThreadSafe):
del self._cache[key]
if expired_keys:
LOG.debug(f"Cleaned up {len(expired_keys)} expired cache entries.")
LOG.debug(
"Cleaned up %s expired cache entries.",
len(expired_keys),
extra={"expired_count": len(expired_keys)},
)

View file

@ -1,10 +1,9 @@
from __future__ import annotations
import http.cookiejar
import logging
from abc import ABC
from collections.abc import Callable
from typing import Any, ClassVar
from typing import Any, ClassVar, cast
from yt_dlp.networking.common import (
_REQUEST_HANDLERS,
@ -20,8 +19,9 @@ from yt_dlp.networking.exceptions import HTTPError
from yt_dlp.utils.networking import clean_headers
from app.library.cf_solver_shared import CACHE, is_cf_challenge, solver
from app.library.log import get_logger
LOG: logging.Logger = logging.getLogger(__name__)
LOG = get_logger()
SolverFn = Callable[[Request, Response, RequestHandler], Request | None]
@ -215,7 +215,7 @@ class CFSolverRH(RequestHandler, ABC):
def _send(self, request: Request) -> Response:
host: str = self._get_host(request.url)
if host and (cached := CACHE.get(host)):
LOG.info(f"Injecting cached Cloudflare cookies for '{host}'.")
LOG.info("Injecting cached Cloudflare cookies for '%s'.", host, extra={"host": host})
self._apply_solution(cached, request.url, request.headers, self._get_cookiejar(request))
director: RequestDirector = self._build_fallback()
@ -223,11 +223,13 @@ class CFSolverRH(RequestHandler, ABC):
try:
response: Response = director.send(request)
except HTTPError as error:
if error.response and is_cf_challenge(getattr(error.response, "status", None), error.response.headers):
if error.response and is_cf_challenge(
getattr(error.response, "status", None), cast("Any", error.response.headers)
):
return self._retry_with_clearance(request, error.response, director)
raise
if is_cf_challenge(getattr(response, "status", None), response.headers):
if is_cf_challenge(getattr(response, "status", None), cast("Any", response.headers)):
return self._retry_with_clearance(request, response, director)
return response

View file

@ -1,17 +1,20 @@
# flake8: noqa: S310
from __future__ import annotations
import json
import logging
import time
import urllib.request
from typing import Any
from typing import TYPE_CHECKING, Any
from urllib.parse import urlparse
from app.library.log import get_logger
from .cache import Cache
if TYPE_CHECKING:
from collections.abc import Mapping
CACHE: Cache = Cache()
LOG: logging.Logger = logging.getLogger("cf_solver")
LOG = get_logger()
def solver(url: str, cookies: list[dict[str, Any]], user_agent: str | None) -> dict[str, Any] | None:
@ -56,23 +59,36 @@ def solver(url: str, cookies: list[dict[str, Any]], user_agent: str | None) -> d
if user_agent:
payload.setdefault("headers", {})["User-Agent"] = user_agent
req = urllib.request.Request(
req = urllib.request.Request( # noqa: S310
endpoint,
data=json.dumps(payload).encode("utf-8"),
headers={"Content-Type": "application/json"},
method="POST",
)
LOG.info(f"Solving Cloudflare challenge for '{host}' via FlareSolverr.")
LOG.info(
"Solving Cloudflare challenge for '%s' via FlareSolverr.", host, extra={"host": host, "endpoint": endpoint}
)
start_time = time.time()
with urllib.request.urlopen(req, timeout=float(config.flaresolverr_client_timeout)) as resp:
with urllib.request.urlopen(req, timeout=float(config.flaresolverr_client_timeout)) as resp: # noqa: S310
result = json.loads(resp.read().decode("utf-8"))
if "ok" != result.get("status"):
LOG.error(f"FlareSolverr failed to solve challenge for '{host}': {result.get('message')}")
LOG.error(
"FlareSolverr failed to solve challenge for '%s': %s",
host,
result.get("message"),
extra={"host": host, "endpoint": endpoint, "solver_message": result.get("message")},
)
return None
LOG.info(f"FlareSolverr successfully solved challenge for '{host}'. (Took {time.time() - start_time:.2f} seconds)")
elapsed_s: float = time.time() - start_time
LOG.info(
"FlareSolverr solved challenge for '%s' in %.2f seconds.",
host,
elapsed_s,
extra={"host": host, "endpoint": endpoint, "elapsed_s": round(elapsed_s, 2)},
)
solution = result.get("solution") or {}
CACHE.set(
@ -84,7 +100,7 @@ def solver(url: str, cookies: list[dict[str, Any]], user_agent: str | None) -> d
return CACHE.get(host)
def is_cf_challenge(status: int | None, headers: dict[str, Any] | None) -> bool:
def is_cf_challenge(status: int | None, headers: Mapping[str, Any] | None) -> bool:
"""
Determine whether a response indicates a Cloudflare challenge.
"""

View file

@ -2,6 +2,7 @@ import logging
import multiprocessing
import os
import re
import shutil
import sys
import time
from logging.handlers import TimedRotatingFileHandler
@ -12,14 +13,25 @@ from typing import TYPE_CHECKING, Any
import coloredlogs
from dotenv import load_dotenv
from app.library.log import get_logger
from .Singleton import Singleton
from .Utils import FileLogFormatter
from .Utils import JsonLogFormatter
from .version import APP_BRANCH, APP_BUILD_DATE, APP_COMMIT_SHA, APP_VERSION
APP_THIRD_PARTY_LOG_LEVELS: tuple[tuple[str, int], ...] = (
("httpx", logging.WARNING),
("urllib3.connectionpool", logging.WARNING),
("apprise", logging.WARNING),
("httpcore", logging.INFO),
("aiosqlite", logging.INFO),
("asyncio", logging.INFO),
)
if TYPE_CHECKING:
from subprocess import CompletedProcess
SUPPORTED_CODECS: tuple[str] = ("h264_qsv", "h264_nvenc", "h264_amf", "h264_videotoolbox", "h264_vaapi", "libx264")
SUPPORTED_CODECS: tuple[str, ...] = ("h264_qsv", "h264_nvenc", "h264_amf", "h264_videotoolbox", "h264_vaapi", "libx264")
"Supported encoder names in order of preference."
@ -36,9 +48,6 @@ class Config(metaclass=Singleton):
download_path: str = "."
"""The path to the download directory."""
download_path_depth: int = 2
"""How many subdirectories to show in auto complete."""
download_info_expires: int = 10800
"""How long (in seconds) the download info is valid before it needs to be re-extracted."""
@ -75,9 +84,6 @@ class Config(metaclass=Singleton):
log_level: str = "info"
"""The log level to use for the application."""
log_level_file: str = "info"
"""The log level to use for the file logging."""
base_path: str = "/"
"""The base path to use for the application."""
@ -102,6 +108,9 @@ class Config(metaclass=Singleton):
auth_password: str | None = None
"""The password to use for basic authentication."""
disable_exec: bool = False
"""Strip some dangerous yt-dlp options."""
remove_files: bool = False
"""Remove downloaded files when removing the record."""
@ -171,7 +180,7 @@ class Config(metaclass=Singleton):
file_logging: bool = True
"Enable file logging."
secret_key: str
secret_key: str | bytes
"The secret key to use for the application."
tasks_handler_timer: str = "15 */1 * * *"
@ -219,6 +228,9 @@ class Config(metaclass=Singleton):
default_pagination: int = 50
"""The default number of items per page for pagination."""
queue_display_limit: int = 100
"""Maximum number of queued downloads returned to the UI. 0 means unlimited."""
task_handler_random_delay: float = 60.0
"""The maximum random delay in seconds before starting a task handler."""
@ -271,10 +283,10 @@ class Config(metaclass=Singleton):
"max_workers_per_extractor",
"extract_info_timeout",
"debugpy_port",
"download_path_depth",
"download_info_expires",
"auto_clear_history_days",
"default_pagination",
"queue_display_limit",
"extract_info_concurrency",
"thumb_concurrency",
"flaresolverr_max_timeout",
@ -304,6 +316,7 @@ class Config(metaclass=Singleton):
"check_for_updates",
"thumb_generate",
"thumb_sidecar",
"disable_exec",
)
"The variables that are booleans."
@ -313,6 +326,7 @@ class Config(metaclass=Singleton):
_frontend_vars: tuple = (
"download_path",
"keep_archive",
"log_level",
"output_template",
"started",
"remove_files",
@ -333,6 +347,7 @@ class Config(metaclass=Singleton):
"app_build_date",
"app_branch",
"default_pagination",
"queue_display_limit",
"check_for_updates",
"new_version",
"yt_new_version",
@ -360,12 +375,13 @@ class Config(metaclass=Singleton):
def __init__(self, is_native: bool = False):
baseDefaultPath: str = str(Path(__file__).parent.parent.parent.absolute())
LOG = get_logger()
self.config_path = os.environ.get("YTP_CONFIG_PATH", None) or str(Path(baseDefaultPath) / "var" / "config")
envFile: str = Path(self.config_path) / ".env"
envFile: Path = Path(self.config_path) / ".env"
if envFile.exists():
logging.info(f"Loading environment variables from '{envFile}'.")
LOG.info("Loading environment variables from '%s'.", envFile)
load_dotenv(envFile)
self.is_native = is_native
@ -373,7 +389,7 @@ class Config(metaclass=Singleton):
self.download_path = os.environ.get("YTP_DOWNLOAD_PATH", None) or str(
Path(baseDefaultPath) / "var" / "downloads"
)
self.app_path = Path(__file__).parent.parent.absolute()
self.app_path = str(Path(__file__).parent.parent.absolute())
for k, v in self._get_attributes().items():
if k.startswith("_") or k in self._manual_vars:
@ -395,7 +411,7 @@ class Config(metaclass=Singleton):
for key in re.findall(r"\{.*?\}", v):
localKey: str = key[1:-1]
if localKey not in self.__dict__:
logging.error(f"Config variable '{k}' had non-existing config reference '{key}'.")
LOG.error("Config variable '%s' had non-existing config reference '%s'.", k, key)
sys.exit(1)
v: str = v.replace(key, str(getattr(self, localKey)))
@ -433,18 +449,23 @@ class Config(metaclass=Singleton):
encoding="utf-8",
)
LOG: logging.Logger = logging.getLogger("config")
if self.debug:
try:
import debugpy
debugpy.listen(("0.0.0.0", self.debugpy_port), in_process_debug_adapter=True)
LOG.info(f"starting debugpy server on '0.0.0.0:{self.debugpy_port}'.")
LOG.info(
"Starting debugpy server on '0.0.0.0:%s'.",
self.debugpy_port,
extra={"host": "0.0.0.0", "port": self.debugpy_port},
)
except ImportError:
LOG.error("debugpy package not found, install it with 'uv sync'.")
LOG.error("debugpy package not found; install it with 'uv sync'.")
except Exception as e:
LOG.error(f"Error starting debugpy server at '0.0.0.0:{self.debugpy_port}'. {e}")
LOG.exception(
"Failed to start debugpy server.",
extra={"host": "0.0.0.0", "port": self.debugpy_port, "exception_type": type(e).__name__},
)
if (Path(self.config_path) / "ytdlp.cli").exists():
LOG.error("Support for ./ytdlp.cli file is removed, migrate to presets and remove the file.")
@ -453,12 +474,16 @@ class Config(metaclass=Singleton):
LOG.warning("Keep temp files option is enabled.")
if self.auth_password and self.auth_username:
LOG.info(f"Authentication enabled with username '{self.auth_username}'.")
LOG.info(
"Basic authentication is enabled for user '%s'.",
self.auth_username,
extra={"auth_username": self.auth_username},
)
if self.file_logging:
log_level_file: int | None = getattr(logging, self.log_level_file.upper(), None)
if not isinstance(log_level_file, int):
msg = f"Invalid file log level '{self.log_level_file}' specified."
file_log_level: int | None = getattr(logging, self.log_level.upper(), None)
if not isinstance(file_log_level, int):
msg = f"Invalid log level '{self.log_level}' specified."
raise TypeError(msg)
loggingPath: Path = Path(self.config_path) / "logs"
@ -466,18 +491,18 @@ class Config(metaclass=Singleton):
loggingPath.mkdir(parents=True, exist_ok=True)
handler = TimedRotatingFileHandler(
filename=loggingPath / "app.log",
filename=loggingPath / "app.jsonl",
when="midnight",
backupCount=3,
encoding="utf-8",
)
handler.setLevel(log_level_file)
formatter = FileLogFormatter("%(asctime)s [%(levelname)s.%(name)s]: %(message)s")
handler.setLevel(file_log_level)
formatter = JsonLogFormatter()
handler.setFormatter(formatter)
logging.getLogger().addHandler(handler)
key_file: str = Path(self.config_path) / "secret.key"
key_file: Path = Path(self.config_path) / "secret.key"
if key_file.exists() and key_file.stat().st_size > 2:
with open(key_file, "rb") as f:
@ -487,16 +512,9 @@ class Config(metaclass=Singleton):
with open(key_file, "wb") as f:
f.write(self.secret_key)
self.started = time.time()
self.started = int(time.time())
_log_levels = (
("httpx", logging.WARNING),
("urllib3.connectionpool", logging.WARNING),
("apprise", logging.WARNING),
("httpcore", logging.INFO),
("aiosqlite", logging.INFO),
)
for _tool, _level in _log_levels:
for _tool, _level in APP_THIRD_PARTY_LOG_LEVELS:
logging.getLogger(_tool).setLevel(_level)
if self.app_env not in ("production", "development"):
@ -528,7 +546,7 @@ class Config(metaclass=Singleton):
def _get_attributes(self) -> dict:
attrs: dict = {}
vClass: str = self.__class__
vClass: type = self.__class__
for attribute in vClass.__dict__:
if attribute.startswith("_"):
@ -571,6 +589,9 @@ class Config(metaclass=Singleton):
data: dict[str, Any] = {k: getattr(self, k) for k in self._frontend_vars}
data["ytdlp_version"] = Config._ytdlp_version()
from app.library.log_control import get_runtime_log_level
data["runtime_log_level"] = get_runtime_log_level()
return data
def get_replacers(self) -> dict[str, str]:
@ -581,7 +602,7 @@ class Config(metaclass=Singleton):
dict[str, str]: The replacer variables.
"""
keys: tuple[str] = ("os_sep", "download_path", "temp_path", "config_path", "archive_file")
keys: tuple[str, ...] = ("os_sep", "download_path", "temp_path", "config_path", "archive_file")
return {k: getattr(self, k) for k in keys}
@staticmethod
@ -598,15 +619,21 @@ class Config(metaclass=Singleton):
Updates the version of the application using git tags.
This is used to set the version to the latest git tag.
"""
git_path: str = Path(__file__).parent / ".." / ".." / ".git"
LOG = get_logger()
git_path: Path = Path(__file__).parent / ".." / ".." / ".git"
if not git_path.exists():
return
try:
import subprocess
git = shutil.which("git")
if not git:
LOG.warning("Git executable was not found.")
return
branch_result: CompletedProcess[str] = subprocess.run(
["git", "-c", f"safe.directory={git_path.parent!s}", "rev-parse", "--abbrev-ref", "HEAD"], # noqa: S607
[git, "-c", f"safe.directory={git_path.parent!s}", "rev-parse", "--abbrev-ref", "HEAD"],
cwd=os.path.dirname(git_path),
capture_output=True,
text=True,
@ -615,16 +642,16 @@ class Config(metaclass=Singleton):
)
if 0 != branch_result.returncode:
logging.error(f"Git rev-parse failed: {branch_result.stderr.strip()}")
LOG.error("Git rev-parse failed: %s", branch_result.stderr.strip())
return
branch_name: str = branch_result.stdout.strip()
if not branch_name:
logging.warning("Git branch name is empty.")
LOG.warning("Git branch name is empty.")
return
commit_result: CompletedProcess[str] = subprocess.run(
["git", "-c", f"safe.directory={git_path.parent!s}", "log", "-1", "--format=%ct_%H"], # noqa: S607
[git, "-c", f"safe.directory={git_path.parent!s}", "log", "-1", "--format=%ct_%H"],
cwd=os.path.dirname(git_path),
capture_output=True,
text=True,
@ -633,12 +660,12 @@ class Config(metaclass=Singleton):
)
if 0 != commit_result.returncode:
logging.error(f"Git log failed: {commit_result.stderr.strip()}")
LOG.error("Git log failed: %s", commit_result.stderr.strip())
return
commit_info: str = commit_result.stdout.strip()
if not commit_info:
logging.warning("Git commit info is empty.")
LOG.warning("Git commit info is empty.")
return
commit_date, commit_sha = commit_info.split("_", 1)
@ -654,6 +681,6 @@ class Config(metaclass=Singleton):
"commit": self.app_commit_sha,
"build_date": self.app_build_date,
}
logging.info(f"Application version info set to '{version_data}'")
LOG.info("Application version info set to '%s'", version_data)
except Exception as e:
logging.error(f"Error while getting git version: {e!s}")
LOG.error("Error while getting git version: %s", e)

760
app/library/diagnostics.py Normal file
View file

@ -0,0 +1,760 @@
from __future__ import annotations
import asyncio
import importlib.metadata
import os
import platform
import re
import shutil
import sqlite3
import subprocess
import sys
import time
import urllib.parse
from dataclasses import dataclass, field
from pathlib import Path
from typing import Any, Literal
from app.library.config import Config
from app.library.httpx_client import resolve_curl_transport
CheckStatus = Literal["pass", "fail", "warn", "skip"]
ReportStatus = Literal["ok", "degraded", "error"]
MIN_PYTHON: tuple[int, int] = (3, 13)
@dataclass(kw_only=True)
class DiagnosticCheck:
id: str
label: str
group: str
required: bool
status: CheckStatus
description: str
message: str
details: dict[str, Any] = field(default_factory=dict)
def to_dict(self) -> dict[str, Any]:
return {
"id": self.id,
"label": self.label,
"group": self.group,
"required": self.required,
"status": self.status,
"description": self.description,
"message": self.message,
"details": self.details,
}
@dataclass(frozen=True, kw_only=True)
class CheckMeta:
group: str
description: str
BINARY_META: dict[str, CheckMeta] = {
"ffmpeg": CheckMeta(
group="core", description="Used for thumbnails and streaming and various media processing tasks."
),
"ffprobe": CheckMeta(group="core", description="Used for media inspection and metadata extraction."),
"deno": CheckMeta(group="youtube", description="Used for yt-dlp YouTube support."),
"yt_dlp_cli": CheckMeta(group="core", description="Used by the built-in terminal."),
"aria2c": CheckMeta(group="advanced", description="External downloader for yt-dlp."),
"mkvpropedit": CheckMeta(group="advanced", description="Edit Matroska container properties without remux."),
"mkvextract": CheckMeta(group="advanced", description="Extract tracks from Matroska containers."),
"mp4box": CheckMeta(group="advanced", description="MP4 container manipulation tool."),
}
DIRECTORY_DESCRIPTIONS: dict[str, str] = {
"config_path": "Directory for config files and app data.",
"download_path": "Directory where downloads are saved.",
"temp_path": "Directory used for temporary files.",
}
def _first_line(*parts: str) -> str:
for part in parts:
for line in part.splitlines():
if line := line.strip():
return line
return ""
def _bin_version(value: str) -> str:
if not (line := value.strip()):
return ""
if match := re.match(r"^deno\s+([0-9][^\s]*)", line, flags=re.IGNORECASE):
return match.group(1).strip()
if match := re.match(r"^mkv\w+\s+v([0-9][^\s]*)", line, flags=re.IGNORECASE):
return match.group(1).strip()
if match := re.search(r"\bversion\s+(.+?)(?:\s+Copyright\b|$)", line, flags=re.IGNORECASE):
return match.group(1).strip()
return line
def _parse_browser_url(value: str) -> tuple[str, str]:
if value.startswith(("selenium+http://", "selenium+https://")):
return "selenium", value.removeprefix("selenium+")
if value.startswith(("playwright+ws://", "playwright+wss://")):
return "playwright", value.removeprefix("playwright+")
if value.startswith("playwright+cdp://"):
return "playwright", f"http://{value.removeprefix('playwright+cdp://')}"
if value.startswith("playwright+cdp+"):
return "playwright", value.removeprefix("playwright+cdp+")
return "unknown", value
def _safe_url(url: str) -> str:
try:
parsed = urllib.parse.urlsplit(url)
except Exception:
return "***"
if not parsed.scheme or not parsed.netloc:
return "***"
netloc = parsed.netloc
if parsed.username or parsed.password:
host = parsed.hostname or ""
if parsed.port:
host = f"{host}:{parsed.port}"
netloc = f"***:***@{host}" if host else "***:***"
path = "/***" if parsed.path and parsed.path != "/" else parsed.path
query = "***" if parsed.query else ""
fragment = "***" if parsed.fragment else ""
return urllib.parse.urlunsplit((parsed.scheme, netloc, path, query, fragment))
def _package_version(name: str) -> str | None:
try:
return importlib.metadata.version(name)
except importlib.metadata.PackageNotFoundError:
return None
def _package_check(
name: str,
*,
label: str,
group: str,
required: bool,
description: str,
present_message: str = "Installed.",
missing_message: str = "Missing.",
missing_status: CheckStatus = "skip",
check_id: str | None = None,
details: dict[str, Any] | None = None,
) -> DiagnosticCheck:
version = _package_version(name)
installed = version is not None
base_details: dict[str, Any] = {"package": name, "version": version}
if details:
base_details.update(details)
return DiagnosticCheck(
id=check_id or name.replace("-", "_"),
label=label,
group=group,
required=required,
status="pass" if installed else ("fail" if required else missing_status),
description=description,
message=present_message if installed else missing_message,
details=base_details,
)
def _check_ytdlp_package() -> DiagnosticCheck:
version = Config._ytdlp_version()
installed = version != "0.0.0"
return DiagnosticCheck(
id="yt_dlp_package",
label="yt-dlp package",
group="core",
required=True,
status="pass" if installed else "fail",
description="Main downloader library used by the app.",
message="Installed." if installed else "Missing.",
details={"version": version},
)
def _check_apprise_package(config: Config) -> DiagnosticCheck:
configured = Path(config.apprise_config).exists()
return _package_check(
"apprise",
label="Apprise",
group="notifications",
required=False,
description="Sends notification targets.",
present_message="Installed.",
missing_message="Missing." if configured else "Not installed.",
missing_status="warn" if configured else "skip",
check_id="apprise",
details={"config": str(config.apprise_config) if configured else None},
)
def _check_curl_transport() -> DiagnosticCheck:
available = resolve_curl_transport(use_curl=True)
version = _package_version("httpx-curl-cffi")
return DiagnosticCheck(
id="curl_transport",
label="curl-cffi transport",
group="advanced",
required=False,
status="pass" if available else "skip",
description="Transport for impersonation support.",
message="Installed." if available else "Not installed.",
details={"package": "httpx-curl-cffi", "version": version},
)
def _check_pot_provider_package() -> DiagnosticCheck:
return _package_check(
"bgutil-ytdlp-pot-provider",
check_id="pot_provider_plugin",
label="POT provider plugin",
group="youtube",
required=False,
description="Optional plugin for external POT token providers for youtube.",
present_message="Installed.",
missing_message="Not installed.",
)
def _check_configured_pip_packages(config: Config) -> list[DiagnosticCheck]:
checks: list[DiagnosticCheck] = []
for raw_pkg in config.pip_packages.split(" "):
pkg = raw_pkg.strip()
if not pkg:
continue
name = pkg.split("==", 1)[0].split(">=", 1)[0].split("<=", 1)[0].strip()
installed = False
version = None
try:
version = importlib.metadata.version(name)
installed = True
except importlib.metadata.PackageNotFoundError:
installed = False
checks.append(
DiagnosticCheck(
id=f"pip_{name.replace('-', '_')}",
label=name,
group="custom",
required=False,
status="pass" if installed else "warn",
description="Configured extra pip package.",
message="Installed." if installed else "Missing.",
details={"package": name, "requested": pkg, "version": version},
)
)
return checks
def _check_browser_endpoint() -> DiagnosticCheck:
raw_url = (os.environ.get("YTP_BROWSER_URL") or "").strip()
if not raw_url:
return DiagnosticCheck(
id="browser_endpoint",
label="Remote browser",
group="advanced",
required=False,
status="skip",
description="Endpoint used by the browser extractor.",
message="Not configured.",
details={},
)
engine, parsed_url = _parse_browser_url(raw_url)
if engine == "unknown":
return DiagnosticCheck(
id="browser_endpoint",
label="Remote browser",
group="advanced",
required=False,
status="warn",
description="Endpoint used by the browser extractor.",
message="Invalid URL.",
details={"endpoint": _safe_url(raw_url)},
)
return DiagnosticCheck(
id="browser_endpoint",
label="Remote browser",
group="advanced",
required=False,
status="pass",
description="Endpoint used by the browser extractor.",
message="Configured.",
details={
"engine": engine,
"endpoint": _safe_url(parsed_url),
},
)
def _check_browser_client() -> DiagnosticCheck:
raw_url = (os.environ.get("YTP_BROWSER_URL") or "").strip()
if not raw_url:
return DiagnosticCheck(
id="browser_client",
label="Browser client",
group="advanced",
required=False,
status="skip",
description="Client package required for the configured browser backend.",
message="Not configured.",
details={},
)
engine, _ = _parse_browser_url(raw_url)
if engine == "unknown":
return DiagnosticCheck(
id="browser_client",
label="Browser client",
group="advanced",
required=False,
status="skip",
description="Client package required for the configured browser backend.",
message="Invalid URL.",
details={},
)
package_name = "selenium" if engine == "selenium" else "playwright"
version = _package_version(package_name)
return DiagnosticCheck(
id="browser_client",
label="Browser client",
group="advanced",
required=False,
status="pass" if version else "warn",
description="Client package required for the configured browser backend.",
message="Installed." if version else "Missing.",
details={"package": package_name, "version": version},
)
def _check_flaresolverr(config: Config) -> DiagnosticCheck:
endpoint = (config.flaresolverr_url or "").strip()
if not endpoint:
return DiagnosticCheck(
id="flaresolverr",
label="FlareSolverr",
group="advanced",
required=False,
status="skip",
description="Optional Cloudflare challenge bypass service.",
message="Not configured.",
details={},
)
parsed = urllib.parse.urlsplit(endpoint)
valid = parsed.scheme in {"http", "https"} and bool(parsed.netloc)
return DiagnosticCheck(
id="flaresolverr",
label="FlareSolverr",
group="advanced",
required=False,
status="pass" if valid else "warn",
description="Optional Cloudflare challenge bypass service.",
message="Configured." if valid else "Invalid URL.",
details={"endpoint": _safe_url(endpoint)},
)
def _probe_directory(path: Path) -> tuple[CheckStatus, str]:
if not path.exists():
return "fail", "Directory does not exist."
if not path.is_dir():
return "fail", "Path is not a directory."
if not os.access(path, os.R_OK | os.W_OK | os.X_OK):
return "fail", "Not readable or writable."
return "pass", "Writable."
async def _check_directory(path: Path, *, check_id: str, label: str) -> DiagnosticCheck:
status, message = await asyncio.to_thread(_probe_directory, path)
return DiagnosticCheck(
id=check_id,
label=label,
group="core",
required=True,
status=status,
description=DIRECTORY_DESCRIPTIONS.get(check_id, "Directory check."),
message=message,
details={"path": str(path)},
)
def _probe_db_file(path: Path) -> tuple[CheckStatus, str]:
if not path.exists():
return "fail", "Missing."
if not path.is_file():
return "fail", "Invalid path."
if not os.access(path, os.R_OK):
return "fail", "Not readable."
if not os.access(path, os.W_OK):
return "fail", "Not writable."
try:
uri = f"file:{urllib.parse.quote(str(path))}?mode=ro"
with sqlite3.connect(uri, timeout=3, uri=True) as conn:
conn.execute("SELECT name FROM sqlite_master LIMIT 1")
except sqlite3.Error as exc:
return "fail", f"SQLite error. {exc!s}"
return "pass", "Ready."
async def _check_db_file(path: Path) -> DiagnosticCheck:
status, message = await asyncio.to_thread(_probe_db_file, path)
return DiagnosticCheck(
id="database",
label="SQLite database",
group="core",
required=True,
status=status,
description="Local database used for app state and history.",
message=message,
details={"path": str(path)},
)
async def _run_command(command: str, *args: str, wait_seconds: float = 5.0) -> tuple[int, str, str]:
proc = await asyncio.create_subprocess_exec(
command,
*args,
stdout=asyncio.subprocess.PIPE,
stderr=asyncio.subprocess.PIPE,
creationflags=subprocess.CREATE_NO_WINDOW if os.name == "nt" else 0,
)
try:
stdout, stderr = await asyncio.wait_for(proc.communicate(), timeout=wait_seconds)
except TimeoutError:
proc.kill()
await proc.communicate()
raise
return proc.returncode or 0, stdout.decode("utf-8", errors="replace"), stderr.decode("utf-8", errors="replace")
def _binary_meta(check_id: str) -> CheckMeta:
return BINARY_META.get(check_id, CheckMeta(group="core", description="Command line tool."))
def _make_binary_check(
command: str,
*,
check_id: str,
label: str,
required: bool,
status: CheckStatus,
message: str,
path: str | None = None,
version: str | None = None,
) -> DiagnosticCheck:
meta = _binary_meta(check_id)
details: dict[str, Any] = {"command": command}
if path:
details["path"] = path
if version:
details["version"] = version
return DiagnosticCheck(
id=check_id,
label=label,
group=meta.group,
required=required,
status=status,
description=meta.description,
message=message,
details=details,
)
def _resolve_binary(*names: str) -> tuple[str, str | None]:
for name in names:
path = shutil.which(name)
if path:
return name, path
return names[0], None
async def _check_binary(
command: str,
*,
check_id: str,
label: str,
required: bool,
args: tuple[str, ...] = ("--version",),
enabled: bool = True,
disabled_message: str = "Check is not applicable.",
missing_status: CheckStatus | None = None,
aliases: tuple[str, ...] = (),
) -> DiagnosticCheck:
if not enabled:
return _make_binary_check(
command,
check_id=check_id,
label=label,
required=required,
status="skip",
message=disabled_message,
)
resolved_name, command_path = _resolve_binary(command, *aliases)
not_found_status: CheckStatus = missing_status or ("fail" if required else "warn")
if not command_path:
return _make_binary_check(
resolved_name,
check_id=check_id,
label=label,
required=required,
status=not_found_status,
message="Missing." if not_found_status == "fail" else "Not installed.",
)
try:
return_code, stdout, stderr = await _run_command(resolved_name, *args)
except FileNotFoundError:
return _make_binary_check(
resolved_name,
check_id=check_id,
label=label,
required=required,
status=not_found_status,
message="Missing." if not_found_status == "fail" else "Not installed.",
path=command_path,
)
except TimeoutError:
return _make_binary_check(
resolved_name,
check_id=check_id,
label=label,
required=required,
status="fail" if required else "warn",
message="Timed out.",
path=command_path,
)
except Exception as exc:
return _make_binary_check(
resolved_name,
check_id=check_id,
label=label,
required=required,
status="fail" if required else "warn",
message=f"Error. {exc!s}",
path=command_path,
)
version: str = _bin_version(_first_line(stdout, stderr))
status: CheckStatus = "pass" if return_code == 0 else ("fail" if required else "warn")
message: str = "Available." if return_code == 0 else f"Exit code {return_code}."
return _make_binary_check(
resolved_name,
check_id=check_id,
label=label,
required=required,
status=status,
message=message,
path=command_path,
version=version,
)
def _make_runtime(config: Config) -> dict[str, Any]:
started = int(config.started) if config.started else 0
uptime_seconds = max(int(time.time()) - started, 0) if started else 0
return {
"app_version": config.app_version,
"app_branch": config.app_branch,
"app_commit_sha": config.app_commit_sha,
"app_build_date": config.app_build_date,
"started": started,
"uptime_seconds": uptime_seconds,
"platform": platform.system().lower(),
"platform_release": platform.release(),
"platform_machine": platform.machine(),
"python_version": platform.python_version(),
"python_minimum": f"{MIN_PYTHON[0]}.{MIN_PYTHON[1]}",
"is_native": config.is_native,
"console_enabled": config.console_enabled,
}
def _requirements() -> dict[str, Any]:
return {
"python": {
"current": platform.python_version(),
"required": f"{MIN_PYTHON[0]}.{MIN_PYTHON[1]}",
"supported": sys.version_info[:2] >= MIN_PYTHON,
"note": "",
}
}
def _summarize(checks: list[DiagnosticCheck]) -> tuple[ReportStatus, dict[str, int]]:
summary = {"total": len(checks), "pass": 0, "fail": 0, "warn": 0, "skip": 0, "required_failed": 0}
for check in checks:
summary[check.status] += 1
if check.required and check.status == "fail":
summary["required_failed"] += 1
if summary["required_failed"] > 0:
status: ReportStatus = "error"
elif summary["warn"] > 0 or any(check.status == "fail" for check in checks):
status = "degraded"
else:
status = "ok"
return status, summary
def _make_report(config: Config, checks: list[DiagnosticCheck]) -> dict[str, Any]:
status, summary = _summarize(checks)
return {
"status": status,
"generated_at": int(time.time()),
"summary": summary,
"runtime": _make_runtime(config),
"requirements": _requirements(),
"checks": [check.to_dict() for check in checks],
}
def diagnostics_error_report(config: Config) -> dict[str, Any]:
return _make_report(
config,
[
DiagnosticCheck(
id="diagnostics",
label="Diagnostics",
group="core",
required=True,
status="fail",
description="Diagnostics collector.",
message="Diagnostics collection failed.",
details={},
)
],
)
async def collect_diagnostics(config: Config) -> dict[str, Any]:
checks: list[DiagnosticCheck] = [
_check_ytdlp_package(),
_check_apprise_package(config),
_check_curl_transport(),
_check_pot_provider_package(),
_check_browser_endpoint(),
_check_browser_client(),
_check_flaresolverr(config),
]
checks.extend(_check_configured_pip_packages(config))
storage_checks, binary_checks = await asyncio.gather(
asyncio.gather(
_check_directory(Path(config.config_path), check_id="config_path", label="Config directory"),
_check_directory(Path(config.download_path), check_id="download_path", label="Download directory"),
_check_directory(Path(config.temp_path), check_id="temp_path", label="Temp directory"),
_check_db_file(Path(config.db_file)),
),
asyncio.gather(
_check_binary(
"ffmpeg",
check_id="ffmpeg",
label="ffmpeg",
required=True,
args=("-version",),
),
_check_binary(
"ffprobe",
check_id="ffprobe",
label="ffprobe",
required=True,
args=("-version",),
),
_check_binary(
"deno",
check_id="deno",
label="deno",
required=True,
),
_check_binary(
"yt-dlp",
check_id="yt_dlp_cli",
label="yt-dlp CLI",
required=True,
enabled=config.console_enabled,
disabled_message="Disabled.",
),
_check_binary(
"aria2c",
check_id="aria2c",
label="aria2c",
required=False,
missing_status="skip",
),
_check_binary(
"mkvpropedit",
check_id="mkvpropedit",
label="mkvpropedit",
required=False,
missing_status="skip",
),
_check_binary(
"mkvextract",
check_id="mkvextract",
label="mkvextract",
required=False,
missing_status="skip",
),
_check_binary(
"MP4Box",
check_id="mp4box",
label="MP4Box",
required=False,
missing_status="skip",
args=("-version",),
aliases=("mp4box",),
),
),
)
checks.extend(storage_checks)
checks.extend(binary_checks)
return _make_report(config, checks)

View file

@ -19,9 +19,10 @@ from app.features.ytdlp.utils import extract_ytdlp_logs
from app.features.ytdlp.ytdlp import YTDLP
from app.library.config import Config
from app.library.Events import EventBus, Events
from app.library.log import get_logger
from app.library.Utils import create_cookies_file
from ...features.ytdlp.extractor import extract_info_sync
from ...features.ytdlp.extractor import REEXTRACT_INFO_KEY, extract_info_sync
from .hooks import HookHandlers, NestedLogger
from .process_manager import ProcessManager
from .status_tracker import StatusTracker
@ -38,6 +39,14 @@ if TYPE_CHECKING:
class Download:
update_task: asyncio.Task | None = None
@staticmethod
def _raise_no_formats(msg: str) -> None:
raise ValueError(msg)
@staticmethod
def _raise_interrupted() -> None:
raise SystemExit(130)
def __init__(self, info: ItemDTO, info_dict: dict | None = None, logs: list[str] | None = None):
"""
Initialize download task.
@ -50,7 +59,7 @@ class Download:
"""
config: Config = Config.get_instance()
self.download_dir: str = info.download_dir
self.download_dir: str = info.download_dir or ""
self.temp_dir: str | None = info.temp_dir
self.template: str | None = info.template
self.template_chapter: str | None = info.template_chapter
@ -64,7 +73,7 @@ class Download:
self.max_workers = int(config.max_workers)
self.is_live: bool = bool(info.is_live) or info.live_in is not None
self.info_dict: dict | None = info_dict
self.logger: logging.Logger = logging.getLogger(f"Download.{info.id or info._id}")
self.logger: logging.Logger = get_logger()
self.started_time = 0
self.queue_time: datetime = datetime.now(tz=UTC)
self.logs: list[str] = logs or []
@ -97,6 +106,16 @@ class Download:
params: dict[str, Any] = {}
download_skipped = False
hook_handlers = self._hook_handlers
if hook_handlers is None:
msg = "_hook_handlers must be initialized before _download(). Call start() first."
raise RuntimeError(msg)
status_queue = self.status_queue
if status_queue is None:
msg = "status_queue must be initialized before _download(). Call start() first."
raise RuntimeError(msg)
try:
params = (
self.info.get_ytdlp_opts()
@ -124,9 +143,9 @@ class Download:
params.update(
{
"progress_hooks": [self._hook_handlers.progress_hook],
"postprocessor_hooks": [self._hook_handlers.postprocessor_hook],
"post_hooks": [self._hook_handlers.post_hook],
"progress_hooks": [hook_handlers.progress_hook],
"postprocessor_hooks": [hook_handlers.postprocessor_hook],
"post_hooks": [hook_handlers.post_hook],
}
)
@ -136,30 +155,96 @@ class Download:
if self.info.cookies:
try:
cookie_file = Path(self._temp_manager.temp_path or self.temp_dir) / f"cookie_{self.info._id}.txt"
cookie_file = (
Path(self._temp_manager.temp_path or self.temp_dir or self.download_dir)
/ f"cookie_{self.info._id}.txt"
)
self.logger.debug(
f"Creating cookie file for '{self.info.id}: {self.info.title}' - '{cookie_file}'."
f"Creating cookie file for '{self.info.title}' at '{cookie_file}'.",
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"path": str(cookie_file),
"has_cookies": True,
}
},
)
params["cookiefile"] = str(create_cookies_file(self.info.cookies, cookie_file))
except Exception as e:
err_msg: str = f"Failed to create cookie file for '{self.info.id}: {self.info.title}'. '{e!s}'."
self.logger.error(err_msg)
self.logger.error(
err_msg,
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"has_cookies": True,
"exception_type": type(e).__name__,
}
},
)
raise ValueError(err_msg) from e
if self.info_dict and isinstance(self.info_dict, dict):
if self.info_dict.get("extractor_key") in GENERIC_EXTRACTORS and self.info.get_preset().default:
self.logger.debug(f"Removing 'download_archive' for generic extractor. url={self.info.url}")
if self.info_dict.get(REEXTRACT_INFO_KEY):
self.logger.info(
f"Info dict for '{self.info.url}' marked for re-extraction, ignoring pre-extracted info."
)
self.info_dict = None
elif self.info_dict.get("extractor_key") in GENERIC_EXTRACTORS and (
(preset := self.info.get_preset()) is not None and preset.default
):
self.logger.debug(
"Removing download archive option for generic extractor on '%s'.",
self.info.url,
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"url": self.info.url,
"extractor": self.info_dict.get("extractor_key"),
}
},
)
params.pop("download_archive", None)
if self.download_info_expires > 0:
if self.info_dict and self.download_info_expires > 0:
_ts: int | None = self.info_dict.get("epoch", self.info_dict.get("timestamp", None))
_ts_dt = datetime.fromtimestamp(_ts, tz=UTC) if _ts else None
if not _ts_dt or (datetime.now(tz=UTC) - _ts_dt).total_seconds() > self.download_info_expires:
self.info_dict = None
self.logger.warning(f"Info for '{self.info.url}' has expired, re-extracting info.")
self.logger.warning(
"Pre-extracted info for '%s' expired; extracting again.",
self.info.url,
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"url": self.info.url,
"expires_s": self.download_info_expires,
}
},
)
if not self.info_dict or not isinstance(self.info_dict, dict):
self.logger.info(f"Extracting info for '{self.info.url}'.")
self.logger.info(
f"Extracting info for '{self.info.url}'.",
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"url": self.info.url,
"preset": self.info.preset,
"has_cookies": bool(params.get("cookiefile")),
}
},
)
ie_params: dict = params.copy()
(info, logs) = extract_info_sync(
@ -183,7 +268,20 @@ class Download:
deletedOpts.append(opt)
if len(deletedOpts) > 0:
self.logger.warning(f"Live stream detected for '{self.info.title}', deleted opts: {deletedOpts}")
self.logger.warning(
"Removed unsupported live stream options before downloading '%s'.",
self.info.title,
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"url": self.info.url,
"removed_options": deletedOpts,
"is_live": self.is_live,
}
},
)
if isinstance(self.info_dict, dict) and not (
len(self.info_dict.get("formats", [])) > 0 or self.info_dict.get("url")
@ -192,14 +290,39 @@ class Download:
if filtered_logs := extract_ytdlp_logs(self.logs):
msg += " " + ", ".join(filtered_logs)
raise ValueError(msg) # noqa: TRY301
self._raise_no_formats(msg)
self.logger.info(
f'Download {self.info.name()}, preset="{self.info.preset}", cookies="{bool(params.get("cookiefile"))}" started.'
f"Downloading '{self.info.title}' from '{self.info.url}' to '{self.download_dir}'.",
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"url": self.info.url,
"path": self.download_dir,
"preset": self.info.preset,
"has_cookies": bool(params.get("cookiefile")),
"download_skipped": download_skipped,
}
},
)
if self.debug:
self.logger.debug(f"Params before passing to yt-dlp. {params}")
self.logger.debug(
"Prepared yt-dlp parameters for '%s'.",
self.info.title,
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"url": self.info.url,
"option_keys": sorted(str(key) for key in params),
"has_cookies": bool(params.get("cookiefile")),
}
},
)
params["logger"] = NestedLogger(self.logger)
@ -227,14 +350,26 @@ class Download:
def mark_cancelled(*_) -> None:
cls._interrupted = True
cls.to_screen("[info] Interrupt received, exiting cleanly...")
raise SystemExit(130) # noqa: TRY301
self._raise_interrupted()
signal.signal(signal.SIGUSR1, mark_cancelled)
self.status_queue.put({"id": self.id, "status": "downloading", "download_skipped": download_skipped})
status_queue.put({"id": self.id, "status": "downloading", "download_skipped": download_skipped})
if isinstance(self.info_dict, dict) and len(self.info_dict) > 1:
self.logger.debug(f"Downloading '{self.info.url}' using pre-info.")
self.logger.debug(
"Downloading '%s' using pre-extracted info.",
self.info.title,
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"url": self.info.url,
"preset": self.info.preset,
}
},
)
_dct: dict = self.info_dict.copy()
if isinstance(self.info.extras, dict) and len(self.info.extras) > 0:
_dct.update(
@ -259,10 +394,22 @@ class Download:
cls.process_ie_result(ie_result=_dct, download=True)
ret: int = cls._download_retcode
else:
self.logger.debug(f"Downloading using url: {self.info.url}")
self.logger.debug(
"Downloading '%s' directly from URL.",
self.info.title,
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"url": self.info.url,
"preset": self.info.preset,
}
},
)
ret = cls.download(url_list=[self.info.url])
self.status_queue.put(
status_queue.put(
{
"id": self.id,
"status": "finished" if 0 == ret else "error",
@ -270,8 +417,20 @@ class Download:
}
)
except yt_dlp.utils.ExistingVideoReached as exc:
self.logger.error(exc)
self.status_queue.put(
self.logger.error(
f"Skipping already downloaded '{self.info.title}' from '{self.info.url}'. {exc!s}",
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"url": self.info.url,
"status": "skip",
"exception_type": type(exc).__name__,
}
},
)
status_queue.put(
{
"id": self.id,
"status": "skip",
@ -280,9 +439,23 @@ class Download:
}
)
except Exception as exc:
self.logger.exception(exc)
self.logger.error(exc)
self.status_queue.put(
self.logger.exception(
f"Failed to download '{self.info.title}' from '{self.info.url}'.",
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"url": self.info.url,
"path": self.download_dir,
"preset": self.info.preset,
"has_cookies": bool(params.get("cookiefile")),
"status": "error",
"exception_type": type(exc).__name__,
}
},
)
status_queue.put(
{
"id": self.id,
"status": "error",
@ -292,16 +465,50 @@ class Download:
}
)
finally:
self.status_queue.put(Terminator())
status_queue.put(Terminator())
if cookie_file and cookie_file.exists():
try:
cookie_file.unlink()
self.logger.debug(f"Deleted cookie file: {cookie_file}")
self.logger.debug(
f"Deleted cookie file for '{self.info.title}' at '{cookie_file}'.",
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"path": str(cookie_file),
"has_cookies": True,
}
},
)
except Exception as e:
self.logger.error(f"Failed to delete cookie file: {cookie_file}. {e}")
self.logger.error(
f"Failed to delete cookie file for '{self.info.title}' at '{cookie_file}'. {e!s}",
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"path": str(cookie_file),
"has_cookies": True,
"exception_type": type(e).__name__,
}
},
)
self.logger.info(
f'Task {self.info.name()} preset="{self.info.preset}" cookies="{bool(params.get("cookiefile"))}" completed.'
f"Download task finished for '{self.info.title}'.",
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"url": self.info.url,
"path": self.download_dir,
"preset": self.info.preset,
"has_cookies": bool(params.get("cookiefile")),
}
},
)
async def start(self) -> int | None:
@ -315,24 +522,24 @@ class Download:
Process exit code or None
"""
self.status_queue = Config.get_manager().Queue()
status_queue: Any = Config.get_manager().Queue()
self.status_queue = status_queue
if temp_path := self._temp_manager.create_temp_path():
self.info.temp_path = str(temp_path)
temp_path = self._temp_manager.create_temp_path()
self._status_tracker = StatusTracker(
info=self.info,
download_id=self.id,
download_dir=self.download_dir,
temp_path=temp_path,
status_queue=self.status_queue,
status_queue=status_queue,
logger=self.logger,
debug=self.debug,
)
self._hook_handlers = HookHandlers(
download_id=self.id,
status_queue=self.status_queue,
status_queue=status_queue,
logger=self.logger,
debug=self.debug,
)
@ -345,7 +552,8 @@ class Download:
EventBus.get_instance().emit(Events.ITEM_UPDATED, data=self.info)
asyncio.create_task(self._status_tracker.progress_update(), name=f"update-{self.id}")
ret = await asyncio.get_running_loop().run_in_executor(None, self._process_manager.proc.join)
proc = self._process_manager.proc
ret = await asyncio.get_running_loop().run_in_executor(None, proc.join) if proc else None
if self._status_tracker.final_update:
return ret
@ -388,8 +596,19 @@ class Download:
return True
except Exception as e:
self.logger.error(f"Failed to close process. {e}")
self.logger.exception(e)
self.logger.exception(
f"Failed to close download process for '{self.info.title}'.",
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"url": self.info.url,
"status": self.info.status,
"exception_type": type(e).__name__,
}
},
)
return False
@ -417,12 +636,28 @@ class Download:
"""
if self.started_time < 1:
self.logger.debug(f"Download task '{self.info.name()}' not started yet.")
self.logger.debug(
"Download task for '%s' has not started yet.",
self.info.title,
extra={"download": {"download_id": self.id, "item_id": self.info.id, "title": self.info.title}},
)
return False
elapsed = int(time.time()) - self.started_time
if elapsed < 300:
self.logger.debug(f"Download task '{self.info.title}: {self.info.id}' started for '{elapsed}' seconds.")
self.logger.debug(
"Download task for '%s' has been running for %s seconds.",
self.info.title,
elapsed,
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"elapsed_s": elapsed,
}
},
)
return False
status: str = self.info.status or "unknown"

View file

@ -33,9 +33,19 @@ class HookHandlers:
if self.debug:
try:
d_safe = create_debug_safe_dict(data)
self.logger.debug(f"PG Hook: {d_safe}")
self.logger.debug(
"Received a yt-dlp progress update for download '%s'.",
self.id,
extra={"download": {"download_id": self.id, "hook": "progress", "status": d_safe}},
)
except Exception as e:
self.logger.debug(f"PG Hook: Error creating debug info: {e}")
self.logger.exception(
"Failed to create progress hook debug info for download '%s'.",
self.id,
extra={
"download": {"download_id": self.id, "hook": "progress", "exception_type": type(e).__name__}
},
)
self.status_queue.put(
{
@ -62,9 +72,23 @@ class HookHandlers:
try:
d_safe = create_debug_safe_dict(data)
d_safe["postprocessor"] = data.get("postprocessor")
self.logger.debug(f"PP Hook: {d_safe}")
self.logger.debug(
"Received a yt-dlp post-processing update for download '%s'.",
self.id,
extra={"download": {"download_id": self.id, "hook": "postprocessor", "status": d_safe}},
)
except Exception as e:
self.logger.debug(f"PP Hook: Error creating debug info: {e}")
self.logger.exception(
"Failed to create postprocessor hook debug info for download '%s'.",
self.id,
extra={
"download": {
"download_id": self.id,
"hook": "postprocessor",
"exception_type": type(e).__name__,
}
},
)
self.status_queue.put(status)

View file

@ -4,7 +4,7 @@ import time
import uuid
from numbers import Number
from pathlib import Path
from typing import TYPE_CHECKING
from typing import TYPE_CHECKING, Any
import yt_dlp.utils
@ -14,6 +14,7 @@ from app.features.ytdlp.extractor import fetch_info
from app.features.ytdlp.utils import archive_add, archive_read, arg_converter, get_extras, ytdlp_reject
from app.library.Events import Events
from app.library.ItemDTO import ItemDTO
from app.library.log import get_logger
from app.library.Utils import create_cookies_file, merge_dict
from .core import Download
@ -26,7 +27,7 @@ if TYPE_CHECKING:
from .queue_manager import DownloadQueue
LOG: logging.Logger = logging.getLogger("downloads.add")
LOG = get_logger()
def _get_ignored_conditions(extras: dict | None) -> list[str]:
@ -66,7 +67,7 @@ async def add_item(
already=None,
logs: list | None = None,
yt_params: dict | None = None,
) -> dict[str, str]:
) -> dict[str, Any]:
"""
Route an entry to the appropriate processor based on type.
@ -101,7 +102,7 @@ async def add_item(
async def add(
queue: "DownloadQueue", item: "Item", already: set | None = None, entry: dict | None = None
) -> dict[str, str]:
) -> dict[str, Any]:
"""
Add an item to the download queue.
@ -122,7 +123,11 @@ async def add(
try:
arg_converter(args=item.cli, level=True)
except Exception as e:
LOG.error(f"Invalid command options for yt-dlp '{item.cli}'. {e!s}")
LOG.error(
"Invalid yt-dlp command options for '%s'.",
item.url,
extra={"url": item.url, "preset": item.preset, "exception_type": type(e).__name__},
)
return {"status": "error", "msg": f"Invalid command options for yt-dlp '{item.cli}'. {e!s}"}
if _preset:
@ -135,12 +140,27 @@ async def add(
yt_conf = {}
cookie_file: Path = Path(queue.config.temp_path) / f"c_{uuid.uuid4().hex}.txt"
LOG.info(f"Adding '{item!r}'.")
LOG.info(
f"Adding '{item.url}' to downloads.",
extra={
"download": {
"url": item.url,
"preset": item.preset,
"folder": item.folder,
"has_cookies": bool(item.cookies),
"auto_start": item.auto_start,
}
},
)
already = set() if already is None else already
if item.url in already:
LOG.warning(f"Recursion detected with url '{item.url}' skipping.")
LOG.warning(
"Skipping recursive download URL '%s'.",
item.url,
extra={"url": item.url, "preset": item.preset},
)
return {"status": "ok"}
already.add(item.url)
@ -149,7 +169,16 @@ async def add(
yt_conf: dict = item.get_ytdlp_opts().get_all()
if yt_conf.get("external_downloader"):
LOG.warning(f"Using external downloader '{yt_conf.get('external_downloader')}' for '{item.url}'.")
LOG.warning(
"Using external downloader '%s' for '%s'.",
yt_conf.get("external_downloader"),
item.url,
extra={
"url": item.url,
"preset": item.preset,
"external_downloader": yt_conf.get("external_downloader"),
},
)
item.extras.update({"external_downloader": True})
archive_id: str | None = item.get_archive_id()
@ -175,7 +204,7 @@ async def add(
)
if archive_file := dlInfo.info.get_ytdlp_opts().get_all().get("download_archive"):
dlInfo.info.msg += f" Found in archive '{archive_file}'."
dlInfo.info.msg = (dlInfo.info.msg or "") + f" Found in archive '{archive_file}'."
await queue.done.put(dlInfo)
@ -201,14 +230,45 @@ async def add(
yt_conf["cookiefile"] = str(create_cookies_file(item.cookies, cookie_file))
except Exception as e:
msg = f"Failed to create cookie file for '{item.url}'. '{e!s}'."
LOG.error(msg)
LOG.exception(
msg,
extra={
"download": {
"url": item.url,
"preset": item.preset,
"path": str(cookie_file),
"has_cookies": True,
"exception_type": type(e).__name__,
}
},
)
return {"status": "error", "msg": msg}
if entry:
LOG.info(f"[P] Extracting '{item.url}'{' with cookies' if yt_conf.get('cookiefile') else ''}.")
LOG.info(
f"Processing pre-extracted info for '{item.url}'.",
extra={
"download": {
"url": item.url,
"preset": item.preset,
"has_cookies": bool(yt_conf.get("cookiefile")),
"pre_extracted": True,
}
},
)
if not entry:
LOG.info(f"Extracting '{item.url}'{' with cookies' if yt_conf.get('cookiefile') else ''}.")
LOG.info(
f"Extracting info for '{item.url}'.",
extra={
"download": {
"url": item.url,
"preset": item.preset,
"has_cookies": bool(yt_conf.get("cookiefile")),
"pre_extracted": False,
}
},
)
(entry, logs) = await fetch_info(
config=yt_conf,
url=item.url,
@ -221,7 +281,17 @@ async def add(
)
if not entry:
LOG.error(f"Unable to extract info for '{item.url}'. Logs: {logs}")
LOG.error(
f"Unable to extract info for '{item.url}'.",
extra={
"download": {
"url": item.url,
"preset": item.preset,
"has_cookies": bool(yt_conf.get("cookiefile")),
"yt_dlp_logs": logs,
}
},
)
return {"status": "error", "msg": "Unable to extract info." + "\n".join(logs)}
# Sometimes playlists or extractor returns different ID than what we get from the make_archive_id()
@ -236,9 +306,12 @@ async def add(
new_archive_id: str | None = None
if entry.get("extractor_key") and entry.get("id"):
new_archive_id: str = f"{entry.get('extractor_key').lower()} {entry.get('id')}"
if new_archive_id != archive_id:
extra_ids.append(new_archive_id)
_extractor_key = entry.get("extractor_key")
_entry_id = entry.get("id")
if isinstance(_extractor_key, str) and _entry_id is not None:
new_archive_id = f"{_extractor_key.lower()} {_entry_id!s}"
if new_archive_id != archive_id:
extra_ids.append(new_archive_id)
if len(extra_ids) > 0:
archive_ids: list[str] = archive_read(_archive_file, extra_ids)
@ -266,7 +339,7 @@ async def add(
)
)
dlInfo.info.msg += f" Found in archive '{_archive_file}'."
dlInfo.info.msg = (dlInfo.info.msg or "") + f" Found in archive '{_archive_file}'."
await queue.done.put(dlInfo)
queue._notify.emit(
@ -293,7 +366,9 @@ async def add(
):
already.pop()
message = f"Condition '{condition.name}' matched for '{item!r}'."
display = str(entry.get("title") or entry.get("webpage_url") or entry.get("url") or item.url)
message = f"Condition '{condition.name}' matched for '{display}'."
if condition.cli:
message += f" Re-queuing with '{condition.cli}'."
@ -302,18 +377,18 @@ async def add(
if condition.extras.get("ignore_download", False):
extra_msg: str = ""
if _archive_file and not condition.extras.get("no_archive", False):
if _archive_file and not condition.extras.get("no_archive", False) and archive_id:
archive_add(_archive_file, [archive_id])
extra_msg = f" and added to archive file '{_archive_file}'"
_name = entry.get("title", entry.get("id"))
log_message = f"Ignoring download of '{_name!r}' as per condition '{condition.name}'{extra_msg}."
_name = str(entry.get("title") or entry.get("id") or item.url)
log_message = f"Ignoring download of '{_name}' as per condition '{condition.name}'{extra_msg}."
store_type, dlInfo = await queue.get_item(archive_id=archive_id)
if not store_type:
dlInfo = Download(
info=ItemDTO(
id=entry.get("id"),
id=str(entry.get("id") or item.url),
title=_name,
url=item.url,
preset=item.preset,
@ -329,6 +404,9 @@ async def add(
LOG.info(log_message)
queue._notify.emit(Events.LOG_INFO, data={}, title="Ignored Download", message=log_message)
if dlInfo is None:
msg = "Download info is not available."
raise RuntimeError(msg)
queue._notify.emit(
Events.ITEM_MOVED,
data={"to": "history", "preset": dlInfo.info.preset, "item": dlInfo.info},
@ -339,7 +417,10 @@ async def add(
if condition.extras.get("set_preset") and (target_preset := condition.extras.get("set_preset")):
if Presets.get_instance().has(target_preset):
log_message: str = f"Switching preset from '{item.preset}' to '{target_preset}' for '{item!r}' as per condition '{condition.name}'."
log_message: str = (
f"Switching preset from '{item.preset}' to '{target_preset}' for '{display}' "
f"as per condition '{condition.name}'."
)
LOG.info(log_message)
queue._notify.emit(Events.LOG_INFO, data={}, title="Preset Switched", message=log_message)
item = item.new_with(preset=target_preset)
@ -356,15 +437,61 @@ async def add(
return {"status": "error", "msg": _msg}
end_time = time.perf_counter() - started
LOG.debug(f"extract_info: for 'URL: {item.url}' is done in '{end_time:.3f}'. Length: '{len(entry)}/keys'.")
LOG.debug(
f"Extracted info for '{item.url}' in '{end_time:.3f}' seconds.",
extra={
"download": {
"url": item.url,
"preset": item.preset,
"has_cookies": bool(yt_conf.get("cookiefile")),
"elapsed_seconds": round(end_time, 3),
"entry_keys": len(entry),
}
},
)
except yt_dlp.utils.ExistingVideoReached as exc:
LOG.error(f"Video has been downloaded already and recorded in archive.log file. '{exc!s}'.")
LOG.error(
"Video '%s' is already recorded in the download archive.",
item.url,
extra={
"download": {
"url": item.url,
"preset": item.preset,
"status": "skip",
"exception_type": type(exc).__name__,
}
},
)
return {"status": "error", "msg": "Video has been downloaded already and recorded in archive.log file."}
except yt_dlp.utils.YoutubeDLError as exc:
LOG.error(f"YoutubeDLError: Unable to extract info. '{exc!s}'.")
LOG.exception(
"Failed to extract media info for '%s'.",
item.url,
extra={
"download": {
"url": item.url,
"preset": item.preset,
"has_cookies": bool(yt_conf.get("cookiefile")),
"exception_type": type(exc).__name__,
}
},
)
return {"status": "error", "msg": str(exc)}
except asyncio.exceptions.TimeoutError as exc:
LOG.error(f"TimeoutError: Unable to extract info. '{exc!s}'.")
LOG.exception(
"Timed out extracting media info for '%s' after %s second(s).",
item.url,
queue.config.extract_info_timeout,
extra={
"download": {
"url": item.url,
"preset": item.preset,
"has_cookies": bool(yt_conf.get("cookiefile")),
"timeout_seconds": queue.config.extract_info_timeout,
"exception_type": type(exc).__name__,
}
},
)
return {
"status": "error",
"msg": f"TimeoutError: {queue.config.extract_info_timeout}s reached Unable to extract info.",
@ -375,6 +502,19 @@ async def add(
cookie_file.unlink(missing_ok=True)
yt_conf.pop("cookiefile", None)
except Exception as e:
LOG.error(f"Failed to remove cookie file '{yt_conf['cookiefile']}'. {e!s}")
LOG.exception(
"Failed to remove cookie file for '%s' at '%s'.",
item.url,
yt_conf["cookiefile"],
extra={
"download": {
"url": item.url,
"preset": item.preset,
"path": yt_conf["cookiefile"],
"has_cookies": True,
"exception_type": type(e).__name__,
}
},
)
return await add_item(queue=queue, entry=entry, item=item, already=already, logs=logs, yt_params=yt_conf)

View file

@ -1,6 +1,5 @@
"""Queue monitoring functions."""
import logging
from datetime import UTC, datetime, timedelta
from pathlib import Path
from typing import TYPE_CHECKING
@ -8,12 +7,13 @@ from typing import TYPE_CHECKING
from app.library.ag_utils import ag
from app.library.Events import Events
from app.library.ItemDTO import Item, ItemDTO
from app.library.log import get_logger
from app.library.Utils import dt_delta, str_to_dt
if TYPE_CHECKING:
from .queue_manager import DownloadQueue
LOG: logging.Logger = logging.getLogger("downloads.monitors")
LOG = get_logger()
async def check_for_stale(queue: "DownloadQueue") -> None:
@ -31,16 +31,37 @@ async def check_for_stale(queue: "DownloadQueue") -> None:
return
for _id, item in list(queue.queue.items()):
item_ref = f"{_id=} {item.info.id=} {item.info.title=}"
if not item.is_stale():
continue
try:
LOG.warning(f"Cancelling staled item '{item_ref}' from download queue.")
LOG.warning(
f"Cancelling stale download '{item.info.title}' from queue.",
extra={
"download": {
"download_id": _id,
"item_id": item.info.id,
"title": item.info.title,
"url": item.info.url,
"status": item.info.status,
}
},
)
await queue.cancel([_id])
except Exception as e:
LOG.error(f"Failed to cancel staled item '{item_ref}'. {e!s}")
LOG.exception(e)
LOG.exception(
f"Failed to cancel stale download '{item.info.title}'.",
extra={
"download": {
"download_id": _id,
"item_id": item.info.id,
"title": item.info.title,
"url": item.info.url,
"status": item.info.status,
"exception_type": type(e).__name__,
}
},
)
async def check_live(queue: "DownloadQueue") -> None:
@ -68,9 +89,19 @@ async def check_live(queue: "DownloadQueue") -> None:
if item.info.status not in status:
continue
item_ref: str = f"{id=} {item.info.id=} {item.info.title=}"
if not item.is_live:
LOG.debug(f"Item '{item_ref}' is not a live stream.")
LOG.debug(
"Skipping history item '%s' because it is not a live stream.",
item.info.title,
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"status": item.info.status,
}
},
)
continue
duration: int | None = item.info.extras.get("duration", None)
@ -79,7 +110,17 @@ async def check_live(queue: "DownloadQueue") -> None:
live_in: str | None = item.info.live_in or ag(item.info.extras, ["live_in", "release_in"], None)
if not live_in:
LOG.debug(
f"Item '{item_ref}' marked as {'premiere video' if is_premiere else 'live stream'}, but no date is set."
"Skipping %s '%s' because no start time is set.",
"premiere video" if is_premiere else "live stream",
item.info.title,
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"is_premiere": is_premiere,
}
},
)
continue
@ -87,24 +128,76 @@ async def check_live(queue: "DownloadQueue") -> None:
starts_in = starts_in.replace(tzinfo=UTC) if starts_in.tzinfo is None else starts_in.astimezone(UTC)
if time_now < (starts_in + timedelta(minutes=1)):
LOG.debug(f"Item '{item_ref}' is not yet live. will start at '{dt_delta(starts_in - time_now)}'.")
starts_in_text = dt_delta(starts_in - time_now)
LOG.debug(
"Live item '%s' is not ready yet; starts in %s.",
item.info.title,
starts_in_text,
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"live_in": live_in,
"starts_in": starts_in_text,
}
},
)
continue
if queue.config.prevent_live_premiere and is_premiere and duration:
buffer_time = queue.config.live_premiere_buffer if queue.config.live_premiere_buffer >= 0 else 5
premiere_ends: datetime = starts_in + timedelta(minutes=buffer_time, seconds=duration)
if time_now < premiere_ends:
start_after = premiere_ends.astimezone().isoformat()
LOG.debug(
f"Item '{item_ref}' is premiering, download will start in '{(starts_in + timedelta(minutes=buffer_time, seconds=duration)).astimezone().isoformat()}'"
"Premiere '%s' is still running; download will start after '%s'.",
item.info.title,
start_after,
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"is_premiere": is_premiere,
"start_after": start_after,
}
},
)
continue
LOG.info(f"Retrying item '{item_ref} {item.info.extras=}' for download.")
LOG.info(
f"Retrying live download '{item.info.title}' from '{item.info.url}'.",
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"url": item.info.url,
"preset": item.info.preset,
"live_in": live_in,
"is_premiere": is_premiere,
}
},
)
try:
await queue.clear([item.info._id], remove_file=False)
except Exception as e:
LOG.error(f"Failed to clear item '{item_ref}'. {e!s}")
LOG.exception(
"Failed to clear live download '%s' before retry.",
item.info.title,
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"url": item.info.url,
"preset": item.info.preset,
"exception_type": type(e).__name__,
}
},
)
continue
try:
@ -121,8 +214,21 @@ async def check_live(queue: "DownloadQueue") -> None:
)
except Exception as e:
await queue.done.put(item)
LOG.exception(e)
LOG.error(f"Failed to retry item '{item_ref}'. {e!s}")
LOG.exception(
"Failed to retry live download '%s' from '%s'.",
item.info.title,
item.info.url,
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"url": item.info.url,
"preset": item.info.preset,
"exception_type": type(e).__name__,
}
},
)
async def delete_old_history(queue: "DownloadQueue") -> None:
@ -156,7 +262,19 @@ async def delete_old_history(queue: "DownloadQueue") -> None:
if item_datetime < cutoff_date:
items_to_delete.append((key, info))
except (OSError, ValueError, OverflowError) as e:
LOG.error(f"Failed to parse timestamp '{info.timestamp}' for item '{info.title}': {e}")
LOG.exception(
"Failed to parse timestamp for history item '%s'.",
info.title,
extra={
"download": {
"download_id": key,
"item_id": info.id,
"title": info.title,
"timestamp": info.timestamp,
"exception_type": type(e).__name__,
}
},
)
titles: list[str] = []
for key, info in items_to_delete:
@ -171,7 +289,12 @@ async def delete_old_history(queue: "DownloadQueue") -> None:
await queue.done.delete(key)
if titles:
LOG.info(f"Automatically cleared '{', '.join(titles)}' from download history due to age.")
LOG.info(
"Automatically cleared %s old history item(s), including '%s'.",
len(titles),
titles[0],
extra={"deleted_count": len(titles), "titles": titles},
)
async def cleanup_thumbnails(queue: "DownloadQueue") -> None:
@ -201,7 +324,11 @@ async def cleanup_thumbnails(queue: "DownloadQueue") -> None:
thumb.unlink(missing_ok=True)
removed += 1
except OSError as exc:
LOG.warning(f"Failed to remove orphaned thumbnail '{thumb}'. {exc!s}")
LOG.exception(
"Failed to remove orphaned thumbnail '%s'.",
thumb,
extra={"file_path": str(thumb), "exception_type": type(exc).__name__},
)
if removed > 0:
LOG.info(f"Removed '{removed}' orphaned cached thumbnails.")
LOG.info("Removed %s orphaned cached thumbnail(s).", removed, extra={"removed_count": removed})

View file

@ -1,9 +1,9 @@
"""Playlist processing."""
import logging
from typing import TYPE_CHECKING, Any
from app.features.ytdlp.utils import ytdlp_reject
from app.library.log import get_logger
from app.library.Utils import merge_dict
if TYPE_CHECKING:
@ -11,7 +11,7 @@ if TYPE_CHECKING:
from .queue_manager import DownloadQueue
LOG: logging.Logger = logging.getLogger("downloads.playlist")
LOG = get_logger()
async def process_playlist(
@ -38,7 +38,17 @@ async def process_playlist(
playlist_name: str = f"{entry.get('id')}: {entry.get('title')}"
LOG.info(f"Processing '{playlist_name} ({len(entries)})' Playlist.")
LOG.info(
"Processing playlist '%s' with %s entrie(s).",
playlist_name,
len(entries),
extra={
"playlist_id": entry.get("id"),
"playlist_title": entry.get("title"),
"entry_count": len(entries),
"preset": getattr(item, "preset", None),
},
)
playlistCount = entry.get("playlist_count")
playlistCount: int = int(playlistCount) if playlistCount else len(entries)
@ -62,7 +72,18 @@ async def process_playlist(
item_name: str = (
f"'{entry.get('title')}: {i}/{playlist_keys['n_entries']}' - '{etr.get('id')}: {etr.get('title')}'"
)
LOG.info(f"Processing '{item_name}'.")
LOG.info(
"Processing playlist item '%s'.",
item_name,
extra={
"playlist_id": entry.get("id"),
"playlist_title": entry.get("title"),
"playlist_index": i,
"entry_count": playlist_keys["n_entries"],
"item_id": etr.get("id"),
"title": etr.get("title"),
},
)
_status, _msg = ytdlp_reject(entry=etr, yt_params=yt_params)
if not _status:
@ -100,8 +121,8 @@ async def process_playlist(
max_downloads: int = -1
ytdlp_opts: dict[str, Any] = item.get_ytdlp_opts().get_all()
if ytdlp_opts.get("max_downloads") and isinstance(ytdlp_opts.get("max_downloads"), int):
max_downloads: int = ytdlp_opts.get("max_downloads")
if isinstance(ytdlp_opts.get("max_downloads"), int):
max_downloads = ytdlp_opts["max_downloads"]
results: list[dict[str, str]] = []
for i, etr in enumerate(entries, start=1):
@ -110,12 +131,23 @@ async def process_playlist(
results.append(await process_item(i, etr))
log_msg: str = f"Playlist '{playlist_name}' processing completed with '{len(results)}' entries."
skipped = 0
if max_downloads > 0 and len(entries) > max_downloads:
skipped: int = len(entries) - max_downloads
log_msg += f" Limited to '{max_downloads}' items, skipped '{skipped}' remaining items."
skipped = len(entries) - max_downloads
LOG.info(log_msg)
LOG.info(
"Playlist '%s' processing completed with %s item(s).",
playlist_name,
len(results),
extra={
"playlist_id": entry.get("id"),
"playlist_title": entry.get("title"),
"processed_count": len(results),
"entry_count": len(entries),
"max_downloads": max_downloads,
"skipped_count": skipped,
},
)
if any("error" == res["status"] for res in results):
return {

View file

@ -1,10 +1,10 @@
"""Download pool management - worker coordination and execution."""
import asyncio
import logging
from typing import TYPE_CHECKING
from app.library.Events import EventBus, Events
from app.library.log import get_logger
from app.library.Utils import calc_download_path
from .core import Download
@ -15,7 +15,7 @@ if TYPE_CHECKING:
from .queue_manager import DownloadQueue
LOG: logging.Logger = logging.getLogger("downloads.pool")
LOG = get_logger()
class PoolManager:
@ -78,7 +78,11 @@ class PoolManager:
async def shutdown(self) -> None:
if self._active:
LOG.info(f"Cancelling '{len(self._active)}' active downloads.")
LOG.info(
"Cancelling active downloads (%s item(s)).",
len(self._active),
extra={"active_count": len(self._active), "download_ids": list(self._active)},
)
await self.queue.cancel(list(self._active.keys()))
async def _download_pool(self) -> None:
@ -87,7 +91,7 @@ class PoolManager:
while True:
while not self.queue.queue.has_downloads():
LOG.info("Waiting for item to download.")
LOG.info("Waiting for queued downloads.")
await self.event.wait()
self.event.clear()
adaptive_sleep = 0.2
@ -140,7 +144,11 @@ class PoolManager:
# No items could be processed, back off a bit to avoid busy-waiting.
if 0 == items_processed:
adaptive_sleep: float = min(adaptive_sleep * 1.5, max_sleep)
LOG.debug(f"No download slots available. Backing off for {adaptive_sleep:.2f}s before next attempt.")
LOG.debug(
"No download slots available; backing off for %.2f seconds.",
adaptive_sleep,
extra={"backoff_s": round(adaptive_sleep, 2), "active_count": len(self._active)},
)
else:
adaptive_sleep = 0.2
@ -156,7 +164,22 @@ class PoolManager:
"""
filePath: str = calc_download_path(base_path=self.config.download_path, folder=entry.info.folder)
LOG.info(f"Downloading 'id: {entry.id}', 'Title: {entry.info.title}', 'URL: {entry.info.url}' To '{filePath}'.")
LOG.info(
"Started download for '%s' to '%s'.",
entry.info.title,
filePath,
extra={
"download": {
"download_id": entry.id,
"item_id": entry.info.id,
"title": entry.info.title,
"url": entry.info.url,
"download_dir": filePath,
"preset": entry.info.preset,
"is_live": entry.is_live,
}
},
)
try:
self._active[entry.info._id] = entry
@ -176,7 +199,18 @@ class PoolManager:
await entry.close()
if await self.queue.queue.exists(key=id):
LOG.debug(f"Download Task '{id}' is completed. Removing from queue.")
LOG.debug(
"Removing completed download '%s' from queue.",
entry.info.title,
extra={
"download": {
"download_id": id,
"item_id": entry.info.id,
"title": entry.info.title,
"status": entry.info.status,
}
},
)
await self.queue.queue.delete(key=id)
nTitle: str | None = None
@ -206,12 +240,16 @@ class PoolManager:
await self.queue.done.put(entry)
self._notify.emit(
Events.ITEM_MOVED,
data={"to": "history", "preset": entry.info.preset, "item": entry.info},
data={"from": "queue", "to": "history", "preset": entry.info.preset, "item": entry.info},
title=nTitle,
message=nMessage,
)
else:
LOG.warning(f"Download '{id}' not found in queue.")
LOG.warning(
"Completed download '%s' was not found in the queue.",
entry.info.title or id,
extra={"download_id": id, "title": entry.info.title},
)
if self.event:
self.event.set()

View file

@ -99,54 +99,163 @@ class ProcessManager:
if not self.running():
return False
procId: int | None = self.proc.ident
proc = self.proc
if proc is None:
return False
procId: int | None = proc.ident
try:
self.logger.info(f"Killing download process: PID={self.proc.pid}, ident={procId}.")
self.logger.info(
"Stopping download process PID=%s.",
proc.pid,
extra={
"download": {
"download_id": self.download_id,
"process_id": proc.pid,
"process_ident": procId,
"is_live": self.is_live,
}
},
)
if self.is_live:
self.logger.debug(f"Requesting graceful live cancellation for PID={self.proc.pid}.")
self.logger.debug(
"Requesting graceful live cancellation for PID=%s.",
proc.pid,
extra={
"download": {
"download_id": self.download_id,
"process_id": proc.pid,
"is_live": self.is_live,
}
},
)
self.cancel_event.set()
if wait_for_process_with_timeout(self.proc, 10):
self.logger.debug(f"Process PID={self.proc.pid} terminated gracefully.")
if wait_for_process_with_timeout(proc, 10):
self.logger.debug(
"Download process PID=%s stopped gracefully.",
proc.pid,
extra={
"download": {
"download_id": self.download_id,
"process_id": proc.pid,
"is_live": self.is_live,
}
},
)
return True
self.logger.warning(
f"Process PID={self.proc.pid} did not respond to live cancellation, forcing termination."
"Download process PID=%s did not respond to live cancellation; forcing termination.",
proc.pid,
extra={
"download": {
"download_id": self.download_id,
"process_id": proc.pid,
"is_live": self.is_live,
"force": True,
}
},
)
elif self.proc.pid and "posix" == os.name:
elif proc.pid and "posix" == os.name:
signal_name = "SIGUSR1"
try:
self.logger.debug(f"Sending {signal_name} signal to PID={self.proc.pid}.")
os.kill(self.proc.pid, signal.SIGUSR1)
self.logger.debug(
"Sending %s signal to download process PID=%s.",
signal_name,
proc.pid,
extra={
"download": {
"download_id": self.download_id,
"process_id": proc.pid,
"signal": signal_name,
}
},
)
os.kill(proc.pid, signal.SIGUSR1)
if wait_for_process_with_timeout(self.proc, 5):
self.logger.debug(f"Process PID={self.proc.pid} terminated gracefully.")
if wait_for_process_with_timeout(proc, 5):
self.logger.debug(
"Download process PID=%s stopped gracefully.",
proc.pid,
extra={
"download": {
"download_id": self.download_id,
"process_id": proc.pid,
"signal": signal_name,
}
},
)
return True
self.logger.warning(
f"Process PID={self.proc.pid} did not respond to {signal_name} (regular download), "
f"forcing termination."
"Download process PID=%s did not respond to %s; forcing termination.",
proc.pid,
signal_name,
extra={
"download": {
"download_id": self.download_id,
"process_id": proc.pid,
"signal": signal_name,
"force": True,
}
},
)
except (OSError, AttributeError) as e:
self.logger.debug(f"Failed to send {signal_name} signal: {e}")
self.logger.debug(
"Failed to send %s signal to download process PID=%s. %s",
signal_name,
proc.pid,
e,
extra={
"download": {
"download_id": self.download_id,
"process_id": proc.pid,
"signal": signal_name,
"exception_type": type(e).__name__,
}
},
)
if self.proc.is_alive():
self.logger.info(f"Force-terminating process PID={self.proc.pid}.")
self.proc.terminate()
if proc.is_alive():
self.logger.info(
"Terminating download process PID=%s.",
proc.pid,
extra={"download": {"download_id": self.download_id, "process_id": proc.pid, "force": True}},
)
proc.terminate()
if not wait_for_process_with_timeout(self.proc, 1 if self.is_live else 2):
self.logger.warning(f"Process PID={self.proc.pid} did not respond, killing forcefully.")
self.proc.kill()
wait_for_process_with_timeout(self.proc, 1)
if not wait_for_process_with_timeout(proc, 1 if self.is_live else 2):
self.logger.warning(
"Download process PID=%s did not terminate; killing forcefully.",
proc.pid,
extra={"download": {"download_id": self.download_id, "process_id": proc.pid, "force": True}},
)
proc.kill()
wait_for_process_with_timeout(proc, 1)
self.logger.info(f"Process PID={self.proc.pid} killed.")
self.logger.info(
"Download process PID=%s stopped.",
proc.pid,
extra={"download": {"download_id": self.download_id, "process_id": proc.pid}},
)
return True
except Exception as e:
self.logger.error(f"Failed to kill process PID={self.proc.pid}, ident={procId}. {e}")
self.logger.exception(e)
self.logger.exception(
f"Failed to stop download process PID={proc.pid if proc else None}, ident={procId}.",
extra={
"download": {
"download_id": self.download_id,
"process_id": proc.pid if proc else None,
"process_ident": procId,
"is_live": self.is_live,
"exception_type": type(e).__name__,
}
},
)
return False
@ -164,16 +273,21 @@ class ProcessManager:
return False
self.cancel_in_progress = True
procId: int | None = self.proc.ident
proc = self.proc
procId: int | None = proc.ident if proc else None
if not procId:
if self.proc:
self.proc.close()
if proc:
proc.close()
self.proc = None
self.logger.warning("Attempted to close download process, but it is not running.")
return False
self.logger.info(f"Closing PID='{procId}' download process.")
self.logger.info(
"Closing download process PID='%s'.",
procId,
extra={"download": {"download_id": self.download_id, "process_ident": procId, "is_live": self.is_live}},
)
try:
self.kill()
@ -182,20 +296,43 @@ class ProcessManager:
loop = asyncio.get_running_loop()
if self.proc.is_alive():
self.logger.debug(f"Waiting for PID='{procId}' to close.")
await loop.run_in_executor(None, self.proc.join)
self.logger.debug(f"PID='{procId}' closed.")
current = self.proc
if current is not None and current.is_alive():
self.logger.debug(
"Waiting for download process PID='%s' to close.",
procId,
extra={"download": {"download_id": self.download_id, "process_ident": procId}},
)
await loop.run_in_executor(None, current.join)
self.logger.debug(
"Download process PID='%s' closed.",
procId,
extra={"download": {"download_id": self.download_id, "process_ident": procId}},
)
if self.proc:
self.proc.close()
self.proc = None
self.logger.debug(f"Closed PID='{procId}' download process.")
self.logger.debug(
"Closed download process PID='%s'.",
procId,
extra={"download": {"download_id": self.download_id, "process_ident": procId}},
)
return True
except Exception as e:
self.logger.error(f"Failed to close process: '{procId}'. {e}")
self.logger.exception(e)
self.logger.exception(
f"Failed to close download process PID='{procId}'.",
extra={
"download": {
"download_id": self.download_id,
"process_id": self.proc.pid if self.proc else None,
"process_ident": procId,
"is_live": self.is_live,
"exception_type": type(e).__name__,
}
},
)
return False

View file

@ -1,6 +1,5 @@
import functools
import glob
import logging
from datetime import UTC, datetime
from pathlib import Path
from typing import TYPE_CHECKING
@ -10,6 +9,7 @@ from aiohttp import web
from app.library.config import Config
from app.library.Events import EventBus, Events
from app.library.ItemDTO import Item, ItemDTO
from app.library.log import get_logger
from app.library.Scheduler import Scheduler
from app.library.Services import Services
from app.library.Singleton import Singleton
@ -24,7 +24,7 @@ from .pool_manager import PoolManager
if TYPE_CHECKING:
from app.library.DataStore import StoreType
LOG: logging.Logger = logging.getLogger("downloads.queue")
LOG = get_logger()
class DownloadQueue(metaclass=Singleton):
@ -53,7 +53,7 @@ class DownloadQueue(metaclass=Singleton):
async def event_handler(_, __):
await self.initialize()
self._notify.subscribe(Events.STARTED, event_handler, f"{__class__.__name__}.{__class__.initialize.__name__}")
self._notify.subscribe(Events.STARTED, event_handler, f"{DownloadQueue.__name__}.initialize")
Scheduler.get_instance().add(
timer="* * * * *",
@ -113,7 +113,9 @@ class DownloadQueue(metaclass=Singleton):
except KeyError as e:
status[item_id] = f"not found: {e!s}"
status["status"] = "error"
LOG.warning(f"Start requested for non-existent item {item_id=}.")
LOG.warning(
"Start requested for missing queued download '%s'.", item_id, extra={"download_id": item_id}
)
continue
if item.info.auto_start:
@ -156,7 +158,9 @@ class DownloadQueue(metaclass=Singleton):
except KeyError as e:
status[item_id] = f"not found: {e!s}"
status["status"] = "error"
LOG.warning(f"Start requested for non-existent item {item_id=}.")
LOG.warning(
"Pause requested for missing queued download '%s'.", item_id, extra={"download_id": item_id}
)
continue
if item.started() or item.is_cancelled():
@ -191,7 +195,8 @@ class DownloadQueue(metaclass=Singleton):
if not self.pool.is_paused():
self.pool.pause()
if not shutdown:
LOG.warning(f"Download paused at. {datetime.now(tz=UTC).isoformat()}")
paused_at = datetime.now(tz=UTC).isoformat()
LOG.warning("Paused the download queue.", extra={"paused_at": paused_at})
return True
return False
@ -206,7 +211,8 @@ class DownloadQueue(metaclass=Singleton):
"""
if self.pool.is_paused():
self.pool.resume()
LOG.warning(f"Downloading resumed at. {datetime.now(tz=UTC).isoformat()}")
resumed_at = datetime.now(tz=UTC).isoformat()
LOG.warning("Resumed the download queue.", extra={"resumed_at": resumed_at})
return True
return False
@ -258,20 +264,51 @@ class DownloadQueue(metaclass=Singleton):
except KeyError as e:
status[id] = str(e)
status["status"] = "error"
LOG.warning(f"Requested cancel for non-existent download {id=}. {e!s}")
LOG.warning("Cancel requested for missing queued download '%s'.", id, extra={"download_id": id})
continue
item_ref = f"{id=} {item.info.id=} {item.info.title=}"
if item.running():
LOG.debug(f"Canceling {item_ref}")
LOG.debug(
"Cancelling running download '%s'.",
item.info.title,
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"url": item.info.url,
}
},
)
item.cancel()
LOG.info(f"Cancelled {item_ref}")
LOG.info(
"Cancelled running download '%s'.",
item.info.title,
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"url": item.info.url,
}
},
)
if not item.is_live:
await item.close()
else:
await item.close()
LOG.debug(f"Deleting from queue {item_ref}")
LOG.debug(
"Removing cancelled download '%s' from queue.",
item.info.title,
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"url": item.info.url,
}
},
)
await self.queue.delete(id)
self._notify.emit(
Events.ITEM_CANCELLED,
@ -283,11 +320,23 @@ class DownloadQueue(metaclass=Singleton):
await self.done.put(item)
self._notify.emit(
Events.ITEM_MOVED,
data={"to": "history", "preset": item.info.preset, "item": item.info},
data={"from": "queue", "to": "history", "preset": item.info.preset, "item": item.info},
title="Download Cancelled",
message=f"Download '{item.info.title}' has been cancelled.",
)
LOG.info(f"Deleted from queue {item_ref}")
LOG.info(
"Moved cancelled download '%s' from queue to history.",
item.info.title,
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"url": item.info.url,
"status": item.info.status,
}
},
)
status[id] = "ok"
@ -314,17 +363,28 @@ class DownloadQueue(metaclass=Singleton):
except KeyError as e:
status[id] = str(e)
status["status"] = "error"
LOG.warning(f"Requested delete for non-existent download {id=}. {e!s}")
LOG.warning("Delete requested for missing history download '%s'.", id, extra={"download_id": id})
continue
itemRef: str = f"{id=} {item.info.id=} {item.info.title=}"
removed_files = 0
filename: str = ""
if self.config.remove_files is not True:
remove_file = False
LOG.debug(f"{remove_file=} {itemRef} - Removing local files: {item.info.status=}")
LOG.debug(
"Clearing history download '%s'.",
item.info.title,
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"status": item.info.status,
"remove_file": remove_file,
}
},
)
if remove_file and "finished" == item.info.status and item.info.filename:
filename = str(item.info.filename)
@ -344,16 +404,66 @@ class DownloadQueue(metaclass=Singleton):
for f in rf.parent.glob(f"{glob.escape(rf.stem)}.*"):
if f.is_file() and f.exists() and not f.name.startswith("."):
removed_files += 1
LOG.debug(f"Removing '{itemRef}' local file '{f.name}'.")
LOG.debug(
"Removing local file '%s' for '%s'.",
f.name,
item.info.title,
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"filename": f.name,
}
},
)
f.unlink(missing_ok=True)
else:
LOG.debug(f"Removing '{itemRef}' local file '{rf.name}'.")
LOG.debug(
"Removing local file '%s' for '%s'.",
rf.name,
item.info.title,
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"filename": rf.name,
}
},
)
rf.unlink(missing_ok=True)
removed_files += 1
else:
LOG.warning(f"Failed to remove '{itemRef}' local file '{filename}'. File not found.")
LOG.warning(
"Could not remove local file '%s' for '%s' because it was not found.",
filename,
item.info.title,
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"filename": filename,
}
},
)
except Exception as e:
LOG.error(f"Unable to remove '{itemRef}' local file '{filename}'. {e!s}")
LOG.exception(
"Failed to remove local file '%s' for '%s'.",
filename,
item.info.title,
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"filename": filename,
"remove_file": remove_file,
"exception_type": type(e).__name__,
}
},
)
await self.done.delete(id)
deleted_ids.append(id)
@ -366,11 +476,19 @@ class DownloadQueue(metaclass=Singleton):
message=f"{_status} '{item.info.title}' from history.",
)
msg = f"Deleted completed download '{itemRef}'."
if removed_files > 0:
msg += f" and removed '{removed_files}' local files."
LOG.info(msg=msg)
LOG.info(
"Deleted completed download '%s' from history%s.",
item.info.title,
f" and removed {removed_files} local file(s)" if removed_files > 0 else "",
extra={
"download": {
"download_id": id,
"item_id": item.info.id,
"title": item.info.title,
"removed_files": removed_files,
}
},
)
status[id] = "ok"
if deleted_ids:
@ -382,22 +500,34 @@ class DownloadQueue(metaclass=Singleton):
if not ids:
return {"deleted": 0}
items = await self.done.get_many_by_ids(ids)
items: list[tuple[str, Download]] = await self.done.get_many_by_ids(ids)
if not items:
return {"deleted": 0}
if self.config.remove_files is not True:
remove_file = False
remove_file = False if self.config.remove_files is not True else remove_file
removed_files = 0
deleted_ids: list[str] = []
deleted_titles: list[str] = []
item_summaries: list[dict] = []
for item_id, item in items:
item_ref: str = f"{item_id=} {item.info.id=} {item.info.title=}"
filename: str = ""
LOG.debug(f"{remove_file=} {item_ref} - Removing local files: {item.info.status=}")
LOG.debug(
"Clearing history download '%s'.",
item.info.title,
extra={
"download": {
"download_id": item_id,
"item_id": item.info.id,
"title": item.info.title,
"status": item.info.status,
"remove_file": remove_file,
"preset": item.info.preset,
"path": str(p) if (p := item.info.get_file()) else None,
}
},
)
if remove_file and "finished" == item.info.status and item.info.filename:
filename = str(item.info.filename)
@ -417,65 +547,149 @@ class DownloadQueue(metaclass=Singleton):
for file_ref in rf.parent.glob(f"{glob.escape(rf.stem)}.*"):
if file_ref.is_file() and file_ref.exists() and not file_ref.name.startswith("."):
removed_files += 1
LOG.debug(f"Removing '{item_ref}' local file '{file_ref.name}'.")
LOG.debug(
"Removing local file '%s' for '%s'.",
file_ref.name,
item.info.title,
extra={
"download": {
"download_id": item_id,
"item_id": item.info.id,
"title": item.info.title,
"preset": item.info.preset,
"filename": file_ref.name,
"path": str(file_ref),
}
},
)
file_ref.unlink(missing_ok=True)
else:
LOG.debug(f"Removing '{item_ref}' local file '{rf.name}'.")
LOG.debug(
"Removing local file '%s' for '%s'.",
rf.name,
item.info.title,
extra={
"download": {
"download_id": item_id,
"item_id": item.info.id,
"title": item.info.title,
"filename": rf.name,
"preset": item.info.preset,
"path": str(rf),
}
},
)
rf.unlink(missing_ok=True)
removed_files += 1
else:
LOG.warning(f"Failed to remove '{item_ref}' local file '{filename}'. File not found.")
LOG.warning(
"Could not remove local file '%s' for '%s' because it was not found.",
filename,
item.info.title,
extra={
"download": {
"download_id": item_id,
"item_id": item.info.id,
"title": item.info.title,
"filename": filename,
"preset": item.info.preset,
"path": str(rf),
}
},
)
except Exception as e:
LOG.error(f"Unable to remove '{item_ref}' local file '{filename}'. {e!s}")
LOG.exception(
"Failed to remove local file '%s' for '%s'.",
filename,
item.info.title,
extra={
"download": {
"download_id": item_id,
"item_id": item.info.id,
"title": item.info.title,
"filename": filename,
"preset": item.info.preset,
"remove_file": remove_file,
"exception_type": type(e).__name__,
}
},
)
deleted_ids.append(item_id)
deleted_titles.append(item.info.title or item.info.id or item_id)
item_summaries.append(
{
"id": item_id,
"title": item.info.title,
"url": item.info.url,
"preset": item.info.preset,
"path": str(p) if (p := item.info.get_file()) else None,
}
)
deleted_count = await self.done.bulk_delete(deleted_ids)
deleted_count: int = await self.done.bulk_delete(deleted_ids)
if deleted_count < 1:
return {"deleted": 0}
title = "History Removed" if removed_files > 0 else "History Cleared"
message = f"Removed {deleted_count} item{'s' if deleted_count != 1 else ''} from history."
message: list[str] = [f"Cleared {deleted_count} item{'s' if deleted_count != 1 else ''} from history."]
if removed_files > 0:
message += f" Also removed {removed_files} local file{'s' if removed_files != 1 else ''}."
message.append(f"Also removed {removed_files} local file{'s' if removed_files != 1 else ''}.")
self._notify.emit(
Events.ITEM_BULK_DELETED,
data={"ids": deleted_ids, "count": deleted_count},
title=title,
message=message,
data={"count": deleted_count, "removed_files": removed_files, "items": item_summaries},
title="History Cleared",
message=" ".join(message),
)
summary = ", ".join(deleted_titles[:5])
if deleted_count > 5:
summary += ", ..."
LOG.info(f"Bulk cleared {deleted_count} history item(s): {summary}")
LOG.info(
"Cleared %d history item(s).",
deleted_count,
extra={"deleted_count": deleted_count, "removed_files": removed_files, "items": item_summaries},
)
return {"deleted": deleted_count}
async def clear_by_status(self, status_filter: str, remove_file: bool = False) -> dict[str, int | str]:
if self.config.remove_files is not True:
remove_file = False
if not (items := await self.done.get_many_by_status(status_filter)):
return {"deleted": 0}
if not remove_file:
deleted_count = await self.done.bulk_delete_by_status(status_filter)
if deleted_count < 1:
return {"deleted": 0}
remove_file = False if self.config.remove_files is not True else remove_file
self._notify.emit(
Events.ITEM_BULK_DELETED,
data={"count": deleted_count, "status": status_filter},
title="History Cleared",
message=f"Cleared {deleted_count} item{'s' if deleted_count != 1 else ''} from history.",
)
LOG.info(f"Bulk cleared {deleted_count} history item(s) by status '{status_filter}'.")
return {"deleted": deleted_count}
if remove_file:
return await self.clear_bulk([item_id for item_id, _ in items], remove_file=remove_file)
items = await self.done.get_many_by_status(status_filter)
return await self.clear_bulk([item_id for item_id, _ in items], remove_file=remove_file)
deleted_count: int = await self.done.bulk_delete_by_status(status_filter)
item_summaries: list[dict[str, str | None]] = [
{
"id": item_id,
"title": dto.info.title,
"url": dto.info.url,
"preset": dto.info.preset,
"path": str(p) if (p := dto.info.get_file()) else None,
}
for item_id, dto in items
]
async def get(self, mode: str = "all") -> dict[str, list[dict[str, ItemDTO]]]:
self._notify.emit(
Events.ITEM_BULK_DELETED,
data={"count": deleted_count, "status": status_filter, "items": item_summaries},
title="History Cleared",
message=f"Cleared {deleted_count} item(s) from history.",
)
LOG.info(
"Cleared %d history item(s) with status '%s'.",
deleted_count,
status_filter,
extra={
"deleted_count": deleted_count,
"status_filter": status_filter,
"items": item_summaries,
},
)
return {"deleted": deleted_count}
async def get(self, mode: str = "all") -> dict[str, dict[str, ItemDTO]]:
"""
Get the download queue and the download history.
@ -511,6 +725,32 @@ class DownloadQueue(metaclass=Singleton):
return items
def live_queue(self, limit: int = 0) -> dict[str, int | dict[str, ItemDTO]]:
"""Return a display-limited live queue snapshot with total metadata."""
limit = max(0, int(limit or 0))
items: dict[str, ItemDTO] = {}
active = self.pool.get_active_downloads()
for key, download in active.items():
if key in self.queue:
items[key] = download.info
for key, download in self.queue.items():
if limit > 0 and len(items) >= limit:
break
if key in items:
continue
items[key] = active[key].info if key in active else download.info
return {
"queue": items,
"queue_count": len(self.queue),
"queue_loaded": len(items),
"queue_limit": limit,
}
async def get_item(self, **kwargs) -> tuple["StoreType", Download] | tuple[None, None]:
"""
Get a specific item from the download queue or history.
@ -519,7 +759,7 @@ class DownloadQueue(metaclass=Singleton):
**kwargs: The key-value pair to search for. Supported keys are 'id', 'url'.
Returns:
(StoreType, Download) | None: The requested item if found, otherwise None.
tuple[StoreType, Download] | tuple[None, None]: The requested item if found, otherwise None.
"""
from app.library.DataStore import StoreType

View file

@ -55,7 +55,37 @@ class StatusTracker:
self.final_update = False
self._terminator_sent: bool = False
self._candidate_filepath: Path | None = None
self.update_task: asyncio.Task | None = None
self.update_task: asyncio.Future[Any] | None = None
self._last_progress_time: float = 0.0
self._pending_progress: bool = False
self._progress_interval: float = 0.5
def _progress_payload(self) -> dict:
return {
"_id": self.info._id,
"status": self.info.status,
"percent": self.info.percent,
"speed": self.info.speed,
"eta": self.info.eta,
"downloaded_bytes": self.info.downloaded_bytes,
"total_bytes": self.info.total_bytes,
"msg": self.info.msg,
}
def _emit_progress(self) -> None:
now = time.monotonic()
if (now - self._last_progress_time) >= self._progress_interval:
self._notify.emit(Events.ITEM_PROGRESS, data=self._progress_payload())
self._last_progress_time = now
self._pending_progress = False
else:
self._pending_progress = True
def _flush_progress(self) -> None:
if self._pending_progress:
self._notify.emit(Events.ITEM_PROGRESS, data=self._progress_payload())
self._pending_progress = False
self._last_progress_time = time.monotonic()
async def _finalize_file(self, filepath: Path) -> None:
"""
@ -68,12 +98,36 @@ class StatusTracker:
self.info.datetime = str(formatdate(time.time()))
self.info.filename = safe_relative_path(filepath, Path(self.download_dir))
self.final_update = True
self.logger.debug(f"Final file name: '{filepath}'.")
self.logger.debug(
"Final download file for '%s' is '%s'.",
self.info.title,
filepath,
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"file_path": str(filepath),
}
},
)
try:
filepath.relative_to(self.download_dir)
except ValueError:
self.logger.warning(
f"Final file '{filepath}' is outside of the intended download directory '{self.download_dir}'."
"Final file '%s' for '%s' is outside download directory '%s'.",
filepath,
self.info.title,
self.download_dir,
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"file_path": str(filepath),
"download_dir": self.download_dir,
}
},
)
self.info.filename = None
return
@ -97,8 +151,19 @@ class StatusTracker:
except Exception as e:
self.info.extras["is_video"] = True
self.info.extras["is_audio"] = True
self.logger.exception(e)
self.logger.error(f"Failed to run ffprobe. {e}")
self.logger.exception(
"Failed to inspect completed file '%s' with ffprobe.",
filepath,
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"file_path": str(filepath),
"exception_type": type(e).__name__,
}
},
)
async def process_status_update(self, status: StatusDict) -> None:
"""
@ -115,11 +180,33 @@ class StatusTracker:
return
if status.get("id") != self.id or len(status) < 2:
self.logger.warning(f"Received invalid status update. {status}")
self.logger.warning(
"Received invalid status update for '%s'.",
self.info.title,
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"status": status,
}
},
)
return
if self.debug:
self.logger.debug(f"Status Update: _id={self.info._id} status={status}")
self.logger.debug(
"Received a download status update for '%s'.",
self.info.title,
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"status": status,
}
},
)
if isinstance(status, str):
self._notify.emit(Events.ITEM_UPDATED, data=self.info)
@ -127,6 +214,7 @@ class StatusTracker:
self.tmpfilename = status.get("tmpfilename")
old_status = self.info.status
self.info.status = status.get("status", self.info.status)
if "download_skipped" in status:
self.info.download_skipped = bool(status.get("download_skipped"))
@ -139,7 +227,19 @@ class StatusTracker:
if self.info.status == "error" and "error" in status:
self.info.error = status.get("error")
if self._candidate_filepath and self._candidate_filepath.exists():
self.logger.debug(f"Cleaning up partial file: {self._candidate_filepath}")
self.logger.debug(
"Cleaning up partial file '%s' for '%s'.",
self._candidate_filepath,
self.info.title,
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"file_path": str(self._candidate_filepath),
}
},
)
await self._finalize_file(self._candidate_filepath)
self._notify.emit(
@ -156,7 +256,7 @@ class StatusTracker:
self.info.percent = status["downloaded_bytes"] / total * 100
except ZeroDivisionError:
self.info.percent = 0
self.info.total_bytes = total
self.info.total_bytes = int(total)
self.info.speed = status.get("speed")
self.info.eta = status.get("eta")
@ -166,7 +266,11 @@ class StatusTracker:
await self._finalize_file(Path(final_name))
self.info.status = "finished"
self._notify.emit(Events.ITEM_UPDATED, data=self.info)
if self.info.status != old_status or self.final_update:
self._flush_progress()
self._notify.emit(Events.ITEM_UPDATED, data=self.info)
else:
self._emit_progress()
async def progress_update(self) -> None:
"""
@ -176,12 +280,15 @@ class StatusTracker:
"""
while True:
try:
self.update_task = asyncio.get_running_loop().run_in_executor(None, self.status_queue.get)
status = await self.update_task
update_task = asyncio.get_running_loop().run_in_executor(None, self.status_queue.get)
self.update_task = asyncio.ensure_future(update_task)
status = await update_task
if status is None or isinstance(status, Terminator):
self._flush_progress()
return
await self.process_status_update(status)
except (asyncio.CancelledError, OSError, FileNotFoundError, EOFError, BrokenPipeError, ConnectionError):
self._flush_progress()
return
async def drain_queue(self, max_iterations: int = 50) -> None:
@ -203,7 +310,19 @@ class StatusTracker:
for i in range(drain_count):
if self.final_update:
self.logger.info(f"({max_iterations}/{i}) Draining stopped. Final update received.")
self.logger.info(
"Stopped draining status queue for '%s' after final update.",
self.info.title,
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"max_iterations": max_iterations,
"iteration": i,
}
},
)
break
try:
@ -214,13 +333,27 @@ class StatusTracker:
except (queue.Empty, BrokenPipeError, ConnectionRefusedError, EOFError, OSError):
continue
self._flush_progress()
def cancel_update_task(self) -> None:
"""Cancel the progress update task if it's running."""
try:
if self.update_task and not self.update_task.done():
self.update_task.cancel()
except Exception as e:
self.logger.error(f"Failed to cancel update task. {e}")
self.logger.exception(
"Failed to cancel the progress update task for '%s' because %s.",
self.info.title,
e,
extra={
"download": {
"download_id": self.id,
"item_id": self.info.id,
"title": self.info.title,
"exception_type": type(e).__name__,
}
},
)
def put_terminator(self) -> None:
"""Put a terminator sentinel in the status queue."""

View file

@ -80,7 +80,20 @@ class TempManager:
and self.info.downloaded_bytes
and self.info.downloaded_bytes > 0
):
self.logger.warning(f"Keeping temp folder '{self.temp_path}'. status={self.info.status}")
self.logger.warning(
"Keeping temp folder '%s' for unfinished download '%s'.",
self.temp_path,
self.info.title,
extra={
"download": {
"download_id": self.info._id,
"item_id": self.info.id,
"title": self.info.title,
"temp_path": str(self.temp_path),
"status": self.info.status,
}
},
)
return
tmp_dir = Path(self.temp_path)
@ -89,12 +102,50 @@ class TempManager:
return
if not self.temp_dir or not is_safe_to_delete_dir(tmp_dir, self.temp_dir):
self.logger.warning(f"Refusing to delete video temp folder '{self.temp_path}' as it's temp root.")
self.logger.warning(
"Refusing to delete temp folder '%s' for '%s' because it is not safe.",
self.temp_path,
self.info.title,
extra={
"download": {
"download_id": self.info._id,
"item_id": self.info.id,
"title": self.info.title,
"temp_path": str(self.temp_path),
"temp_dir": self.temp_dir,
}
},
)
return
status: bool = delete_dir(tmp_dir)
if by_pass:
tmp_dir.mkdir(parents=True, exist_ok=True)
self.logger.info(f"Temp folder '{self.temp_path}' emptied.")
self.logger.info(
"Emptied temp folder '%s' for '%s'.",
self.temp_path,
self.info.title,
extra={
"download": {
"download_id": self.info._id,
"item_id": self.info.id,
"title": self.info.title,
"temp_path": str(self.temp_path),
}
},
)
else:
self.logger.info(f"Temp folder '{self.temp_path}' deletion is {'success' if status else 'failed'}.")
self.logger.info(
"Deleted temp folder '%s' for '%s'." if status else "Failed to delete temp folder '%s' for '%s'.",
self.temp_path,
self.info.title,
extra={
"download": {
"download_id": self.info._id,
"item_id": self.info.id,
"title": self.info.title,
"temp_path": str(self.temp_path),
"deleted": status,
}
},
)

View file

@ -128,7 +128,12 @@ def parse_extractor_limit(
limit: int = min(int(env_limit), max_workers)
else:
if env_limit and logger:
logger.warning(f"Invalid extractor limit '{env_limit}' for '{extractor}', using default limit.")
logger.warning(
"Invalid extractor limit '%s' for '%s'; using default limit.",
env_limit,
extractor,
extra={"extractor": extractor, "env_limit": env_limit, "default_limit": default_limit},
)
limit = default_limit
return min(limit, max_workers)
@ -156,7 +161,12 @@ def get_extractor_limit(
if extractor not in LIMITS:
limit = parse_extractor_limit(extractor, max_workers_per_extractor, max_workers, logger)
LIMITS[extractor] = asyncio.Semaphore(limit)
logger.info(f"Created limits container for extractor '{extractor}': {limit}")
logger.info(
"Created download limit for extractor '%s' with %s worker(s).",
extractor,
limit,
extra={"extractor": extractor, "limit": limit, "max_workers": max_workers},
)
return LIMITS[extractor]
@ -247,7 +257,10 @@ def handle_task_exception(task: asyncio.Task, logger: logging.Logger) -> None:
return
task_name: str = task.get_name() if task.get_name() else "unknown_task"
import traceback
tb = "".join(traceback.format_exception(type(exc), exc, exc.__traceback__))
logger.error(f"Unhandled exception in background task '{task_name}': {exc!s}. {tb}")
logger.error(
"Unhandled exception in background task '%s'. %s",
task_name,
exc,
extra={"task_name": task_name, "exception_type": type(exc).__name__},
exc_info=(type(exc), exc, exc.__traceback__),
)

Some files were not shown because too many files have changed in this diff Show more