yt_dlp/extractor/lci.py

   1 from .common import InfoExtractor
   2
   3
   4 class LCIIE(InfoExtractor):
   5     _VALID_URL = r'https?://(?:www\.)?lci\.fr/[^/]+/[\w-]+-(?P<id>\d+)\.html'
   6     _TEST = {
   7         'url': 'http://www.lci.fr/international/etats-unis-a-j-62-hillary-clinton-reste-sans-voix-2001679.html',
   8         'md5': '2fdb2538b884d4d695f9bd2bde137e6c',
   9         'info_dict': {
  10             'id': '13244802',
  11             'ext': 'mp4',
  12             'title': 'Hillary Clinton et sa quinte de toux, en plein meeting',
  13             'description': 'md5:a4363e3a960860132f8124b62f4a01c9',
  14         }
  15     }
  16
  17     def _real_extract(self, url):
  18         video_id = self._match_id(url)
  19         webpage = self._download_webpage(url, video_id)
  20         wat_id = self._search_regex(
  21             (r'data-watid=[\'"](\d+)', r'idwat["\']?\s*:\s*["\']?(\d+)'),
  22             webpage, 'wat id')
  23         return self.url_result('wat:' + wat_id, 'Wat', wat_id)