Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-03 08:19:57 +01:00
Code Issues Packages Projects Releases Wiki Activity

[mailru] Add support for new mail.ru URL format (Closes #3024)

Browse Source
This commit is contained in:
Sergey M․ 2014-06-01 14:38:36 +07:00
parent 1a2f2e1e66
commit ceb7a17f34
1 changed files with 38 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
youtube_dl/extractor/mailru.py
View File

@ -9,29 +9,48 @@
class MailRuIE(InfoExtractor): class MailRuIE(InfoExtractor):
IE_NAME = 'mailru' IE_NAME = 'mailru'
IE_DESC = 'Видео@Mail.Ru' IE_DESC = 'Видео@Mail.Ru'
_VALID_URL = r'http://(?:www\.)?my\.mail\.ru/video/.*#video=/?(?P<id>[^/]+/[^/]+/[^/]+/\d+)' _VALID_URL = r'http://(?:www\.)?my\.mail\.ru/(?:video/.*#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|(?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html)'
_TEST = { _TESTS = [
'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76', {
'md5': 'dea205f03120046894db4ebb6159879a', 'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76',
'info_dict': { 'md5': 'dea205f03120046894db4ebb6159879a',
'id': '46301138', 'info_dict': {
'ext': 'mp4', 'id': '46301138',
'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро', 'ext': 'mp4',
'timestamp': 1393232740, 'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро',
'upload_date': '20140224', 'timestamp': 1393232740,
'uploader': 'sonypicturesrus', 'upload_date': '20140224',
'uploader_id': 'sonypicturesrus@mail.ru', 'uploader': 'sonypicturesrus',
'duration': 184, 'uploader_id': 'sonypicturesrus@mail.ru',
} 'duration': 184,
} },
},
{
'url': 'http://my.mail.ru/corp/hitech/video/news_hi-tech_mail_ru/1263.html',
'md5': '00a91a58c3402204dcced523777b475f',
'info_dict': {
'id': '46843144',
'ext': 'mp4',
'title': 'Samsung Galaxy S5 Hammer Smash Fail Battery Explosion',
'timestamp': 1397217632,
'upload_date': '20140411',
'uploader': 'hitech',
'uploader_id': 'hitech@corp.mail.ru',
'duration': 245,
},
},
]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('idv1')
if not video_id:
video_id = mobj.group('idv2prefix') + mobj.group('idv2suffix')
video_data = self._download_json( video_data = self._download_json(
'http://videoapi.my.mail.ru/videos/%s.json?new=1' % video_id, video_id, 'Downloading video JSON') 'http://api.video.mail.ru/videos/%s.json?new=1' % video_id, video_id, 'Downloading video JSON')
author = video_data['author'] author = video_data['author']
uploader = author['name'] uploader = author['name']
@ -40,6 +59,8 @@ def _real_extract(self, url):
movie = video_data['movie'] movie = video_data['movie']
content_id = str(movie['contentId']) content_id = str(movie['contentId'])
title = movie['title'] title = movie['title']
if title.endswith('.mp4'):
title = title[:-4]
thumbnail = movie['poster'] thumbnail = movie['poster']
duration = movie['duration'] duration = movie['duration']