[generic] Add support for rutube embeds

This commit is contained in:
Sergey M․ 2017-03-04 00:46:33 +07:00
parent bc82f22879
commit eb3079b6ce
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
2 changed files with 30 additions and 0 deletions

View file

@ -84,6 +84,7 @@ from .twentymin import TwentyMinutenIE
from .ustream import UstreamIE from .ustream import UstreamIE
from .openload import OpenloadIE from .openload import OpenloadIE
from .videopress import VideoPressIE from .videopress import VideoPressIE
from .rutube import RutubeIE
class GenericIE(InfoExtractor): class GenericIE(InfoExtractor):
@ -1502,6 +1503,23 @@ class GenericIE(InfoExtractor):
}, },
'add_ie': [VideoPressIE.ie_key()], 'add_ie': [VideoPressIE.ie_key()],
}, },
{
# Rutube embed
'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
'info_dict': {
'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
'ext': 'flv',
'title': 'Магаззино: Казань 2',
'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
'uploader': 'Магаззино',
'upload_date': '20170228',
'uploader_id': '996642',
},
'params': {
'skip_download': True,
},
'add_ie': [RutubeIE.ie_key()],
},
{ {
# ThePlatform embedded with whitespaces in URLs # ThePlatform embedded with whitespaces in URLs
'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm', 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
@ -2480,6 +2498,12 @@ class GenericIE(InfoExtractor):
return _playlist_from_matches( return _playlist_from_matches(
videopress_urls, ie=VideoPressIE.ie_key()) videopress_urls, ie=VideoPressIE.ie_key())
# Look for Rutube embeds
rutube_urls = RutubeIE._extract_urls(webpage)
if rutube_urls:
return _playlist_from_matches(
rutube_urls, ie=RutubeIE.ie_key())
# Looking for http://schema.org/VideoObject # Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld( json_ld = self._search_json_ld(
webpage, video_id, default={}, expected_type='VideoObject') webpage, video_id, default={}, expected_type='VideoObject')

View file

@ -44,6 +44,12 @@ class RutubeIE(InfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
@staticmethod
def _extract_urls(webpage):
return [mobj.group('url') for mobj in re.finditer(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/embed/[\da-z]{32}.*?)\1',
webpage)]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
video = self._download_json( video = self._download_json(