You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

26 lines
953 B

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  3. from .common import InfoExtractor
  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. def _real_extract(self, url):
  17. video_id = self._match_id(url)
  18. webpage = self._download_webpage(url, video_id)
  19. wat_id = self._search_regex(
  20. (r'data-watid=[\'"](\d+)', r'idwat["\']?\s*:\s*["\']?(\d+)'),
  21. webpage, 'wat id')
  22. return self.url_result('wat:' + wat_id, 'Wat', wat_id)