diff options
Diffstat (limited to 'youtube_dl/extractor/youtube.py')
| -rw-r--r-- | youtube_dl/extractor/youtube.py | 20 |
1 files changed, 18 insertions, 2 deletions
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index b7b91f354..3b3678c6e 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -809,6 +809,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): player_url = None # Get video info + embed_webpage = None if re.search(r'player-age-gate-content">', video_webpage) is not None: age_gate = True # We simulate the access to the video from www.youtube.com/v/{video_id} @@ -1016,10 +1017,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): url += '&signature=' + url_data['sig'][0] elif 's' in url_data: encrypted_sig = url_data['s'][0] + ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' jsplayer_url_json = self._search_regex( - r'"assets":.+?"js":\s*("[^"]+")', - embed_webpage if age_gate else video_webpage, 'JS player URL') + ASSETS_RE, + embed_webpage if age_gate else video_webpage, + 'JS player URL (1)', default=None) + if not jsplayer_url_json and not age_gate: + # We need the embed website after all + if embed_webpage is None: + embed_url = proto + '://www.youtube.com/embed/%s' % video_id + embed_webpage = self._download_webpage( + embed_url, video_id, 'Downloading embed webpage') + jsplayer_url_json = self._search_regex( + ASSETS_RE, embed_webpage, 'JS player URL') + player_url = json.loads(jsplayer_url_json) if player_url is None: player_url_json = self._search_regex( @@ -1688,6 +1700,7 @@ class YoutubeTruncatedURLIE(InfoExtractor): feature=[a-z_]+| annotation_id=annotation_[^&]+| x-yt-cl=[0-9]+| + hl=[^&]*| )? | attribution_link\?a=[^&]+ @@ -1707,6 +1720,9 @@ class YoutubeTruncatedURLIE(InfoExtractor): }, { 'url': 'https://www.youtube.com/watch?feature=foo', 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/watch?hl=en-GB', + 'only_matching': True, }] def _real_extract(self, url): |