yt_dlp/extractor/lemonde.py

   1 from .common import InfoExtractor
   2
   3
   4 class LemondeIE(InfoExtractor):
   5     _VALID_URL = r'https?://(?:.+?\.)?lemonde\.fr/(?:[^/]+/)*(?P<id>[^/]+)\.html'
   6     _TESTS = [{
   7         'url': 'http://www.lemonde.fr/police-justice/video/2016/01/19/comprendre-l-affaire-bygmalion-en-cinq-minutes_4849702_1653578.html',
   8         'md5': 'da120c8722d8632eec6ced937536cc98',
   9         'info_dict': {
  10             'id': 'lqm3kl',
  11             'ext': 'mp4',
  12             'title': "Comprendre l'affaire Bygmalion en 5 minutes",
  13             'thumbnail': r're:^https?://.*\.jpg',
  14             'duration': 309,
  15             'upload_date': '20160119',
  16             'timestamp': 1453194778,
  17             'uploader_id': '3pmkp',
  18         },
  19     }, {
  20         # standard iframe embed
  21         'url': 'http://www.lemonde.fr/les-decodeurs/article/2016/10/18/tout-comprendre-du-ceta-le-petit-cousin-du-traite-transatlantique_5015920_4355770.html',
  22         'info_dict': {
  23             'id': 'uzsxms',
  24             'ext': 'mp4',
  25             'title': "CETA : quelles suites pour l'accord commercial entre l'Europe et le Canada ?",
  26             'thumbnail': r're:^https?://.*\.jpg',
  27             'duration': 325,
  28             'upload_date': '20161021',
  29             'timestamp': 1477044540,
  30             'uploader_id': '3pmkp',
  31         },
  32         'params': {
  33             'skip_download': True,
  34         },
  35     }, {
  36         'url': 'http://redaction.actu.lemonde.fr/societe/video/2016/01/18/calais-debut-des-travaux-de-defrichement-dans-la-jungle_4849233_3224.html',
  37         'only_matching': True,
  38     }, {
  39         # YouTube embeds
  40         'url': 'http://www.lemonde.fr/pixels/article/2016/12/09/pourquoi-pewdiepie-superstar-de-youtube-a-menace-de-fermer-sa-chaine_5046649_4408996.html',
  41         'only_matching': True,
  42     }]
  43
  44     def _real_extract(self, url):
  45         display_id = self._match_id(url)
  46
  47         webpage = self._download_webpage(url, display_id)
  48
  49         digiteka_url = self._proto_relative_url(self._search_regex(
  50             r'url\s*:\s*(["\'])(?P<url>(?:https?://)?//(?:www\.)?(?:digiteka\.net|ultimedia\.com)/deliver/.+?)\1',
  51             webpage, 'digiteka url', group='url', default=None))
  52
  53         if digiteka_url:
  54             return self.url_result(digiteka_url, 'Digiteka')
  55
  56         return self.url_result(url, 'Generic')