lenta.py (1682B)
1 # coding: utf-8 2 from __future__ import unicode_literals 3 4 from .common import InfoExtractor 5 6 7 class LentaIE(InfoExtractor): 8 _VALID_URL = r'https?://(?:www\.)?lenta\.ru/[^/]+/\d+/\d+/\d+/(?P<id>[^/?#&]+)' 9 _TESTS = [{ 10 'url': 'https://lenta.ru/news/2018/03/22/savshenko_go/', 11 'info_dict': { 12 'id': '964400', 13 'ext': 'mp4', 14 'title': 'Надежду Савченко задержали', 15 'thumbnail': r're:^https?://.*\.jpg$', 16 'duration': 61, 17 'view_count': int, 18 }, 19 'params': { 20 'skip_download': True, 21 }, 22 }, { 23 # EaglePlatform iframe embed 24 'url': 'http://lenta.ru/news/2015/03/06/navalny/', 25 'info_dict': { 26 'id': '227304', 27 'ext': 'mp4', 28 'title': 'Навальный вышел на свободу', 29 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5', 30 'thumbnail': r're:^https?://.*\.jpg$', 31 'duration': 87, 32 'view_count': int, 33 'age_limit': 0, 34 }, 35 'params': { 36 'skip_download': True, 37 }, 38 }] 39 40 def _real_extract(self, url): 41 display_id = self._match_id(url) 42 43 webpage = self._download_webpage(url, display_id) 44 45 video_id = self._search_regex( 46 r'vid\s*:\s*["\']?(\d+)', webpage, 'eagleplatform id', 47 default=None) 48 if video_id: 49 return self.url_result( 50 'eagleplatform:lentaru.media.eagleplatform.com:%s' % video_id, 51 ie='EaglePlatform', video_id=video_id) 52 53 return self.url_result(url, ie='Generic')