Update yt-dlp to latest version + remove code no longer needed from bluesky dropin

poetry.lock

@@ -3077,14 +3077,14 @@ h11 = ">=0.9.0,<1"
 
 [[package]]
 name = "yt-dlp"
-version = "2025.1.12"
+version = "2025.1.26"
 description = "A feature-rich command-line audio/video downloader"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "yt_dlp-2025.1.12-py3-none-any.whl", hash = "sha256:f7ea19afb64f8e457a1b9598ddb67f8deaa313bf1d57abd5612db9272ab10795"},
-    {file = "yt_dlp-2025.1.12.tar.gz", hash = "sha256:8e7e246e2a5a2cff0a9c13db46844a37a547680702012058c94ec18fce0ca25a"},
+    {file = "yt_dlp-2025.1.26-py3-none-any.whl", hash = "sha256:3e76bd896b9f96601021ca192ca0fbdd195e3c3dcc28302a3a34c9bc4979da7b"},
+    {file = "yt_dlp-2025.1.26.tar.gz", hash = "sha256:1c9738266921ad43c568ad01ac3362fb7c7af549276fbec92bd72f140da16240"},
 ]
 
 [package.extras]
@@ -3100,4 +3100,4 @@ test = ["pytest (>=8.1,<9.0)", "pytest-rerunfailures (>=14.0,<15.0)"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.10,<3.13"
-content-hash = "5a54c84ba388db7b77d1c28973b710fc99aa3822a2860b30acaf5b02ba1927bd"
+content-hash = "9ca114395e73af8982abbccc25b385bbca62e50ba7cca8239e52e5c1227cb4b0"

pyproject.toml

@@ -46,7 +46,7 @@ dependencies = [
     "cryptography (>=41.0.0,<42.0.0)",
     "boto3 (>=1.28.0,<2.0.0)",
     "dataclasses-json (>=0.0.0)",
-    "yt-dlp (==2025.1.12)",
+    "yt-dlp (>=2025.1.26,<2026.0.0)",
     "numpy (==2.1.3)",
     "vk-url-scraper (>=0.0.0)",
     "requests[socks] (>=0.0.0)",

src/auto_archiver/modules/generic_extractor/bluesky.py

@@ -23,19 +23,8 @@ class Bluesky(GenericDropin):
 
     def extract_post(self, url: str, ie_instance: InfoExtractor) -> dict:
         # TODO: If/when this PR (https://github.com/yt-dlp/yt-dlp/pull/12098) is merged on ytdlp, remove the comments and delete the code below
-        # handle, video_id = ie_instance._match_valid_url(url).group('handle', 'id')
-        # return ie_instance._extract_post(handle=handle, post_id=video_id)
-
         handle, video_id = ie_instance._match_valid_url(url).group('handle', 'id')
-        return ie_instance._download_json(
-            'https://public.api.bsky.app/xrpc/app.bsky.feed.getPostThread',
-            video_id, query={
-                'uri': f'at://{handle}/app.bsky.feed.post/{video_id}',
-                'depth': 0,
-                'parentHeight': 0,
-            })['thread']['post']
-
-
+        return ie_instance._extract_post(handle=handle, post_id=video_id)
 
     def _download_bsky_embeds(self, post: dict, archiver: Extractor) -> list[Media]:
         """

src/auto_archiver/modules/generic_extractor/facebook.py

@@ -0,0 +1,17 @@
+from .dropin import GenericDropin
+
+
+class Facebook(GenericDropin):
+    def extract_post(self, url: str, ie_instance):
+        video_id = ie_instance._match_valid_url(url).group('id')
+        ie_instance._download_webpage(
+            url.replace('://m.facebook.com/', '://www.facebook.com/'), video_id)
+        webpage = ie_instance._download_webpage(url, ie_instance._match_valid_url(url).group('id'))
+
+        post_data = ie_instance._extract_from_url.extract_metadata(webpage)
+        return post_data
+    
+    def create_metadata(self, post: dict, ie_instance, archiver, url):
+        metadata = archiver.create_metadata(url)
+        metadata.set_title(post.get('title')).set_content(post.get('description')).set_post_data(post)
+        return metadata