github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

Fix some improper Youtube URLs

Browse source 
Eg: https://www.youtube.com/watch?list=UUXIkr0SRTnZO4_QpZozvCCA
This commit is contained in:
pukkandan 2020-11-27 00:27:53 +05:30
parent a62cf34298
commit f0c532a430
1 changed files with 9 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
youtube_dlc/extractor/youtube.py
View file

@ -3256,11 +3256,20 @@ def _real_extract(self, url):
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
video_id = qs.get('v', [None])[0] video_id = qs.get('v', [None])[0]
playlist_id = qs.get('list', [None])[0] playlist_id = qs.get('list', [None])[0]
if is_home.group('not_channel').startswith('watch') and not video_id:
if playlist_id:
self._downloader.report_warning('%s is not a valid Youtube URL. Trying to download playlist %s' % (url, playlist_id))
url = 'https://www.youtube.com/playlist?list=%s' % playlist_id
# return self.url_result(playlist_id, ie=YoutubePlaylistIE.ie_key())
else:
raise ExtractorError('Unable to recognize tab page')
if video_id and playlist_id: if video_id and playlist_id:
if self._downloader.params.get('noplaylist'): if self._downloader.params.get('noplaylist'):
self.to_screen('Downloading just video %s because of --no-playlist' % video_id) self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id) return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
webpage = self._download_webpage(url, item_id) webpage = self._download_webpage(url, item_id)
identity_token = self._search_regex( identity_token = self._search_regex(
r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage, r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,