[youtube] Update signature function patterns (closes #21469, closes #21476)

[youtube-dl] / youtube_dl / extractor / youtube.py

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 963c73a2d9cafb3c26e8e5b8bd3c9b52d76b2f44..83b6ac1346580a65221b6c1db90751e7e4141915 100644 (file)
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -500,6 +500,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
         # RTMP (unnamed)
         '_rtmp': {'protocol': 'rtmp'},
+
+        # av01 video only formats sometimes served with "unknown" codecs
+        '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
+        '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
+        '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
+        '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
     }
     _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
 
@@ -1306,11 +1312,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
     def _parse_sig_js(self, jscode):
         funcname = self._search_regex(
-            (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+            (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             # Obsolete patterns
+             r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
              r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
-             r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?(?P<sig>[a-zA-Z0-9$]+)\(',
-             r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
-             r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
+             r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
             jscode, 'Initial JS player signature function name', group='sig')
 
         jsi = JSInterpreter(jscode)
@@ -1575,8 +1587,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         return video_id
 
     def _extract_annotations(self, video_id):
-        url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
-        return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
+        return self._download_webpage(
+            'https://www.youtube.com/annotations_invideo', video_id,
+            note='Downloading annotations',
+            errnote='Unable to download video annotations', fatal=False,
+            query={
+                'features': 1,
+                'legacy': 1,
+                'video_id': video_id,
+            })
 
     @staticmethod
     def _extract_chapters(description, duration):