Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/lemonde.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class LemondeIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:.+?\.)?lemonde\.fr/(?:[^/]+/)*(?P<id>[^/]+)\.html'
   8     _TESTS = [{
   9         'url': 'http://www.lemonde.fr/police-justice/video/2016/01/19/comprendre-l-affaire-bygmalion-en-cinq-minutes_4849702_1653578.html',
  10         'md5': '01fb3c92de4c12c573343d63e163d302',
  11         'info_dict': {
  12             'id': 'lqm3kl',
  13             'ext': 'mp4',
  14             'title': "Comprendre l'affaire Bygmalion en 5 minutes",
  15             'thumbnail': 're:^https?://.*\.jpg',
  16             'duration': 320,
  17             'upload_date': '20160119',
  18             'timestamp': 1453194778,
  19             'uploader_id': '3pmkp',
  20         },
  21     }, {
  22         'url': 'http://redaction.actu.lemonde.fr/societe/video/2016/01/18/calais-debut-des-travaux-de-defrichement-dans-la-jungle_4849233_3224.html',
  23         'only_matching': True,
  24     }]
  25
  26     def _real_extract(self, url):
  27         display_id = self._match_id(url)
  28
  29         webpage = self._download_webpage(url, display_id)
  30
  31         digiteka_url = self._proto_relative_url(self._search_regex(
  32             r'url\s*:\s*(["\'])(?P<url>(?:https?://)?//(?:www\.)?(?:digiteka\.net|ultimedia\.com)/deliver/.+?)\1',
  33             webpage, 'digiteka url', group='url'))
  34         return self.url_result(digiteka_url, 'Digiteka')