lumni.py 1.0 KB

1234567891011121314151617181920212223
  1. from .francetv import FranceTVBaseInfoExtractor
  2. class LumniIE(FranceTVBaseInfoExtractor):
  3. _VALID_URL = r'https?://(?:www\.)?lumni\.fr/video/(?P<id>[\w-]+)'
  4. _TESTS = [{
  5. 'url': 'https://www.lumni.fr/video/l-homme-et-son-environnement-dans-la-revolution-industrielle',
  6. 'md5': '960e8240c4f2c7a20854503a71e52f5e',
  7. 'info_dict': {
  8. 'id': 'd2b9a4e5-a526-495b-866c-ab72737e3645',
  9. 'ext': 'mp4',
  10. 'title': "L'homme et son environnement dans la révolution industrielle - L'ère de l'homme",
  11. 'thumbnail': 'https://assets.webservices.francetelevisions.fr/v1/assets/images/a7/17/9f/a7179f5f-63a5-4e11-8d4d-012ab942d905.jpg',
  12. 'duration': 230,
  13. },
  14. }]
  15. def _real_extract(self, url):
  16. display_id = self._match_id(url)
  17. webpage = self._download_webpage(url, display_id)
  18. video_id = self._html_search_regex(
  19. r'<div[^>]+data-factoryid\s*=\s*["\']([^"\']+)', webpage, 'video id')
  20. return self._make_url_result(video_id, url=url)