yt_dlp/extractor/lenta.py

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