midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[youtube] Use redirected video id if any (closes #25063)

Browse source
This commit is contained in:
Sergey M․ 2020-05-01 00:40:38 +07:00
parent 2468a6fa64
commit 011e75e641
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 24 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

25
youtube_dl/extractor/youtube.py
View file

@ -1227,6 +1227,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q', 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
'only_matching': True, 'only_matching': True,
}, },
{
# invalid -> valid video id redirection
'url': 'DJztXj2GPfl',
'info_dict': {
'id': 'DJztXj2GPfk',
'ext': 'mp4',
'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
'description': 'md5:bf577a41da97918e94fa9798d9228825',
'upload_date': '20090125',
'uploader': 'Prochorowka',
'uploader_id': 'Prochorowka',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
'artist': 'Panjabi MC',
'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
'album': 'Beware of the Boys (Mundian To Bach Ke)',
},
'params': {
'skip_download': True,
},
}
] ]
def __init__(self, *args, **kwargs): def __init__(self, *args, **kwargs):
@ -1678,7 +1698,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# Get video webpage # Get video webpage
url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
video_webpage = self._download_webpage(url, video_id) video_webpage, urlh = self._download_webpage_handle(url, video_id)
qs = compat_parse_qs(compat_urllib_parse_urlparse(urlh.geturl()).query)
video_id = qs.get('v', [None])[0] or video_id
# Attempt to extract SWF player URL # Attempt to extract SWF player URL
mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)