2 from __future__ import unicode_literals
4 from .common import InfoExtractor
7 class LentaIE(InfoExtractor):
8 _VALID_URL = r'https?://(?:www\.)?lenta\.ru/[^/]+/\d+/\d+/\d+/(?P<id>[^/?#&]+)'
10 'url': 'https://lenta.ru/news/2018/03/22/savshenko_go/',
14 'title': 'Надежду Савченко задержали',
15 'thumbnail': r're:^https?://.*\.jpg$',
20 'skip_download': True,
23 # EaglePlatform iframe embed
24 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
28 'title': 'Навальный вышел на свободу',
29 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
30 'thumbnail': r're:^https?://.*\.jpg$',
36 'skip_download': True,
40 def _real_extract(self, url):
41 display_id = self._match_id(url)
43 webpage = self._download_webpage(url, display_id)
45 video_id = self._search_regex(
46 r'vid\s*:\s*["\']?(\d+)', webpage, 'eagleplatform id',
49 return self.url_result(
50 'eagleplatform:lentaru.media.eagleplatform.com:%s' % video_id,
51 ie='EaglePlatform', video_id=video_id)
53 return self.url_result(url, ie='Generic')