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': 'da120c8722d8632eec6ced937536cc98',
  11         'info_dict': {
  12             'id': 'lqm3kl',
  13             'ext': 'mp4',
  14             'title': "Comprendre l'affaire Bygmalion en 5 minutes",
  15             'thumbnail': r're:^https?://.*\.jpg',
  16             'duration': 309,
  17             'upload_date': '20160119',
  18             'timestamp': 1453194778,
  19             'uploader_id': '3pmkp',
  20         },
  21     }, {
  22         # standard iframe embed
  23         'url': 'http://www.lemonde.fr/les-decodeurs/article/2016/10/18/tout-comprendre-du-ceta-le-petit-cousin-du-traite-transatlantique_5015920_4355770.html',
  24         'info_dict': {
  25             'id': 'uzsxms',
  26             'ext': 'mp4',
  27             'title': "CETA : quelles suites pour l'accord commercial entre l'Europe et le Canada ?",
  28             'thumbnail': r're:^https?://.*\.jpg',
  29             'duration': 325,
  30             'upload_date': '20161021',
  31             'timestamp': 1477044540,
  32             'uploader_id': '3pmkp',
  33         },
  34         'params': {
  35             'skip_download': True,
  36         },
  37     }, {
  38         'url': 'http://redaction.actu.lemonde.fr/societe/video/2016/01/18/calais-debut-des-travaux-de-defrichement-dans-la-jungle_4849233_3224.html',
  39         'only_matching': True,
  40     }, {
  41         # YouTube embeds
  42         'url': 'http://www.lemonde.fr/pixels/article/2016/12/09/pourquoi-pewdiepie-superstar-de-youtube-a-menace-de-fermer-sa-chaine_5046649_4408996.html',
  43         'only_matching': True,
  44     }]
  45
  46     def _real_extract(self, url):
  47         display_id = self._match_id(url)
  48
  49         webpage = self._download_webpage(url, display_id)
  50
  51         digiteka_url = self._proto_relative_url(self._search_regex(
  52             r'url\s*:\s*(["\'])(?P<url>(?:https?://)?//(?:www\.)?(?:digiteka\.net|ultimedia\.com)/deliver/.+?)\1',
  53             webpage, 'digiteka url', group='url', default=None))
  54
  55         if digiteka_url:
  56             return self.url_result(digiteka_url, 'Digiteka')
  57
  58         return self.url_result(url, 'Generic')