[youtube:playlist] Relax _VIDEO_RE (closes #21844)

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

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 7b630b191f628998811f9664cdc3cbaced519d7b..aa316ba88abf9eb91c093e1d7f85c25c13b39542 100644 (file)
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -27,6 +27,7 @@ from ..compat import (
     compat_str,
 )
 from ..utils import (
+    bool_or_none,
     clean_html,
     dict_get,
     error_to_compat_str,
@@ -116,6 +117,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
                 'f.req': json.dumps(f_req),
                 'flowName': 'GlifWebSignIn',
                 'flowEntry': 'ServiceLogin',
+                # TODO: reverse actual botguard identifier generation algo
+                'bgRequest': '["identifier",""]',
             })
             return self._download_json(
                 url, None, note=note, errnote=errnote,
@@ -368,10 +371,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             (?:www\.)?hooktube\.com/|
                             (?:www\.)?yourepeat\.com/|
                             tube\.majestyc\.net/|
+                            # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
                             (?:(?:www|dev)\.)?invidio\.us/|
-                            (?:www\.)?invidiou\.sh/|
-                            (?:www\.)?invidious\.snopyta\.org/|
+                            (?:(?:www|no)\.)?invidiou\.sh/|
+                            (?:(?:www|fi|de)\.)?invidious\.snopyta\.org/|
                             (?:www\.)?invidious\.kabi\.tk/|
+                            (?:www\.)?invidious\.enkirton\.net/|
+                            (?:www\.)?invidious\.13ad\.de/|
+                            (?:www\.)?invidious\.mastodon\.host/|
+                            (?:www\.)?tube\.poal\.co/|
                             (?:www\.)?vid\.wxzm\.sx/|
                             youtube\.googleapis\.com/)                        # the various hostnames, with wildcard subdomains
                          (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
@@ -1312,11 +1320,18 @@ 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$]+)\(',
+             r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
+             # 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)
@@ -1581,8 +1596,15 @@ 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):
@@ -1874,6 +1896,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         if view_count is None and video_details:
             view_count = int_or_none(video_details.get('viewCount'))
 
+        if is_live is None:
+            is_live = bool_or_none(video_details.get('isLive'))
+
         # Check for "rental" videos
         if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
             raise ExtractorError('"rental" videos not supported. See https://github.com/ytdl-org/youtube-dl/issues/359 for more information.', expected=True)
@@ -2407,7 +2432,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
                         (%(playlist_id)s)
                      )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
     _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
-    _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
+    _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:&amp;(?:[^"]*?index=(?P<index>\d+))?(?:[^>]+>(?P<title>[^<]+))?)?'
     IE_NAME = 'youtube:playlist'
     _TESTS = [{
         'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
@@ -2531,6 +2556,16 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
             'noplaylist': True,
             'skip_download': True,
         },
+    }, {
+        # https://github.com/ytdl-org/youtube-dl/issues/21844
+        'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
+        'info_dict': {
+            'title': 'Data Analysis with Dr Mike Pound',
+            'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
+            'uploader_id': 'Computerphile',
+            'uploader': 'Computerphile',
+        },
+        'playlist_mincount': 11,
     }, {
         'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
         'only_matching': True,