[BUGFIX] Use proper extractor key for download archive (#840)

For less popular sites, ytdl-sub's custom download archive was not working. This was because we weren't using the right extraction key (though it still worked for YouTube, Bandcamp, Soundcloud, and others). This bugfix should now exactly match yt-dlp's and never be a problem again.

Huge thanks to @Svagtlys for root-causing this 🤝

src/ytdl_sub/entries/base_entry.py

@@ -13,7 +13,6 @@ from yt_dlp.utils import sanitize_filename
 
 from ytdl_sub.entries.variables.kwargs import DESCRIPTION
 from ytdl_sub.entries.variables.kwargs import EPOCH
-from ytdl_sub.entries.variables.kwargs import EXTRACTOR
 from ytdl_sub.entries.variables.kwargs import IE_KEY
 from ytdl_sub.entries.variables.kwargs import TITLE
 from ytdl_sub.entries.variables.kwargs import UID
@@ -100,12 +99,12 @@ class BaseEntryVariables:
         Returns
         -------
         str
-            The ytdl extractor name
+            The ytdl extractor name used in the download archive
         """
         # pylint: disable=line-too-long
         # Taken from https://github.com/yt-dlp/yt-dlp/blob/e6ab678e36c40ded0aae305bbb866cdab554d417/yt_dlp/YoutubeDL.py#L3514
         # pylint: enable=line-too-long
-        return self.kwargs_get(EXTRACTOR) or self.kwargs(IE_KEY)
+        return str(self.kwargs_get("extractor_key") or self.kwargs(IE_KEY)).lower()
 
     @property
     def epoch(self: "BaseEntry") -> int:

tests/e2e/soundcloud/test_soundcloud_discography.py

@@ -1,7 +1,9 @@
 import pytest
+from conftest import assert_logs
 from expected_download import assert_expected_downloads
 from expected_transaction_log import assert_transaction_log_matches
 
+from ytdl_sub.downloaders.ytdlp import YTDLP
 from ytdl_sub.subscriptions.subscription import Subscription
 
 
@@ -48,3 +50,19 @@ class TestSoundcloudDiscography:
             dry_run=dry_run,
             expected_download_summary_file_name="soundcloud/test_soundcloud_discography.json",
         )
+
+        # Ensure another invocation will hit ExistingVideoReached
+        if not dry_run:
+            with assert_logs(
+                logger=YTDLP.logger,
+                expected_message="ExistingVideoReached, stopping additional downloads",
+                log_level="debug",
+            ):
+                transaction_log = discography_subscription.download()
+
+            assert transaction_log.is_empty
+            assert_expected_downloads(
+                output_directory=output_directory,
+                dry_run=dry_run,
+                expected_download_summary_file_name="soundcloud/test_soundcloud_discography.json",
+            )

tests/resources/expected_downloads_summaries/bandcamp/test_artist_url.json

@@ -1,5 +1,5 @@
 {
-  ".ytdl-sub-Sithu Aye-download-archive.json": "0c58919b660f699f6aea2ec523c812c5",
+  ".ytdl-sub-Sithu Aye-download-archive.json": "ca37a404a860a2a6b6b0f38b659c9f17",
   "Sithu Aye/[2021] 10 Years： Remixes and Reimaginings/01 - Double Helix Reimagined.mp3": "56f7ee579031f4795230e68b63b15f6b",
   "Sithu Aye/[2021] 10 Years： Remixes and Reimaginings/02 - Skye Reimagined.mp3": "dfb24e0ef03e203d471bb81f854f5cd3",
   "Sithu Aye/[2021] 10 Years： Remixes and Reimaginings/03 - Baryofusion.mp3": "95bd9ab2238e5372f445c59daafd0138",

tests/unit/conftest.py

@@ -68,6 +68,7 @@ def mock_entry_dict_factory(mock_downloaded_file_path) -> Callable:
             PLAYLIST_INDEX: playlist_index,
             PLAYLIST_COUNT: playlist_count,
             EXTRACTOR: "mock-entry-dict",
+            "extractor_key": "mock-entry-dict",
             TITLE: f"Mock Entry {uid}",
             EXT: "mp4",
             UPLOAD_DATE: upload_date,

tests/unit/entries/conftest.py

@@ -163,6 +163,7 @@ def mock_entry_kwargs(
         "id": uid,
         "epoch": 1596878400,
         "extractor": extractor,
+        "extractor_key": extractor,
         "title": title,
         "ext": ext,
         "upload_date": upload_date,