w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[mailru] Fix issues and improve (closes #14904)

Browse source
This commit is contained in:
Sergey M․ 2017-12-17 18:36:19 +07:00
parent 25475dfab3
commit 549bb416f5
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 28 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

43
youtube_dl/extractor/mailru.py
View file

@ -13,7 +13,15 @@ from ..utils import (
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'https?://(?:(?:www|m)\.)?my\.mail\.ru/(?:video/.*#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|(?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html|video/embed/(?P<meta_id>\d+))' _VALID_URL = r'''(?x)
https?://
(?:(?:www|m)\.)?my\.mail\.ru/
(?:
video/.*\#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|
(?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html|
(?:video/embed|\+/video/meta)/(?P<metaid>\d+)
)
'''
_TESTS = [ _TESTS = [
{ {
'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76', 'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76',
@ -22,7 +30,7 @@ class MailRuIE(InfoExtractor):
'id': '46301138_76', 'id': '46301138_76',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро', 'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро',
'timestamp': 1393232740, 'timestamp': 1393235077,
'upload_date': '20140224', 'upload_date': '20140224',
'uploader': 'sonypicturesrus', 'uploader': 'sonypicturesrus',
'uploader_id': 'sonypicturesrus@mail.ru', 'uploader_id': 'sonypicturesrus@mail.ru',
@ -39,7 +47,7 @@ class MailRuIE(InfoExtractor):
'title': 'Samsung Galaxy S5 Hammer Smash Fail Battery Explosion', 'title': 'Samsung Galaxy S5 Hammer Smash Fail Battery Explosion',
'timestamp': 1397039888, 'timestamp': 1397039888,
'upload_date': '20140409', 'upload_date': '20140409',
'uploader': 'hitech@corp.mail.ru', 'uploader': 'hitech',
'uploader_id': 'hitech@corp.mail.ru', 'uploader_id': 'hitech@corp.mail.ru',
'duration': 245, 'duration': 245,
}, },
@ -68,33 +76,38 @@ class MailRuIE(InfoExtractor):
{ {
'url': 'https://my.mail.ru/video/embed/7949340477499637815', 'url': 'https://my.mail.ru/video/embed/7949340477499637815',
'only_matching': True, 'only_matching': True,
},
{
'url': 'http://my.mail.ru/+/video/meta/7949340477499637815',
'only_matching': True,
} }
] ]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
meta_id = mobj.group('meta_id') meta_id = mobj.group('metaid')
page_config = None
video_data = None
video_id = None video_id = None
if not meta_id: if meta_id:
meta_url = 'https://my.mail.ru/+/video/meta/%s' % meta_id
else:
video_id = mobj.group('idv1') video_id = mobj.group('idv1')
if not video_id: if not video_id:
video_id = mobj.group('idv2prefix') + mobj.group('idv2suffix') video_id = mobj.group('idv2prefix') + mobj.group('idv2suffix')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
page_config = self._parse_json(self._search_regex( page_config = self._parse_json(self._search_regex(
r'(?s)<script[^>]+class="sp-video__page-config"[^>]*>(.+?)</script>', r'(?s)<script[^>]+class="sp-video__page-config"[^>]*>(.+?)</script>',
webpage, 'page config', default='{}'), video_id, fatal=False) webpage, 'page config', default='{}'), video_id, fatal=False)
if page_config or meta_id:
if page_config: if page_config:
meta_url = page_config.get('metaUrl') or page_config.get('video', {}).get('metaUrl') meta_url = page_config.get('metaUrl') or page_config.get('video', {}).get('metaUrl')
elif meta_id: else:
meta_url = 'https://my.mail.ru/+/video/meta/' + meta_id meta_url = None
if meta_url:
video_data = self._download_json( video_data = None
meta_url, video_id, 'Downloading video meta JSON', fatal=False) if meta_url:
video_data = self._download_json(
meta_url, video_id or meta_id, 'Downloading video meta JSON',
fatal=not video_id)
# Fallback old approach # Fallback old approach
if not video_data: if not video_data: