[youtube] Fix sigfunc name extraction (closes #26134, closes #26135, closes #26136...

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

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 43c5eff1f4ed9e3e3fd61041875ed4f67dc04bad..b35bf03aafc7c7c45b3c35735a68d00f86aed988 100644 (file)
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -303,7 +303,7 @@ class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
                     # Downloading page may result in intermittent 5xx HTTP error
                     # that is usually worked around with a retry
                     more = self._download_json(
-                        'https://youtube.com/%s' % mobj.group('more'), playlist_id,
+                        'https://www.youtube.com/%s' % mobj.group('more'), playlist_id,
                         'Downloading page #%s%s'
                         % (page_num, ' (retry #%d)' % count if count else ''),
                         transform_source=uppercase_escape,
@@ -1384,7 +1384,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         funcname = self._search_regex(
             (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'\b(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
+             r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
              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$]+)\(',
@@ -1930,7 +1930,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             ''', replace_url, video_description)
             video_description = clean_html(video_description)
         else:
-            video_description = self._html_search_meta('description', video_webpage) or video_details.get('shortDescription')
+            video_description = video_details.get('shortDescription') or self._html_search_meta('description', video_webpage)
 
         if not smuggled_data.get('force_singlefeed', False):
             if not self._downloader.params.get('noplaylist'):
@@ -2776,7 +2776,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
         ids = []
         last_id = playlist_id[-11:]
         for n in itertools.count(1):
-            url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
+            url = 'https://www.youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
             webpage = self._download_webpage(
                 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
             new_ids = orderedSet(re.findall(
@@ -3289,7 +3289,7 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
                 break
 
             more = self._download_json(
-                'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
+                'https://www.youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
                 'Downloading page #%s' % page_num,
                 transform_source=uppercase_escape,
                 headers=self._YOUTUBE_CLIENT_HEADERS)