yt_dlp/extractor/jeuxvideo.py

   1 from .common import InfoExtractor
   2
   3
   4 class JeuxVideoIE(InfoExtractor):
   5     _VALID_URL = r'https?://.*?\.jeuxvideo\.com/.*/(.*?)\.htm'
   6
   7     _TESTS = [{
   8         'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
   9         'md5': '046e491afb32a8aaac1f44dd4ddd54ee',
  10         'info_dict': {
  11             'id': '114765',
  12             'ext': 'mp4',
  13             'title': 'Tearaway : GC 2013 : Tearaway nous présente ses papiers d\'identité',
  14             'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.',
  15         },
  16     }, {
  17         'url': 'http://www.jeuxvideo.com/videos/chroniques/434220/l-histoire-du-jeu-video-la-saturn.htm',
  18         'only_matching': True,
  19     }]
  20
  21     def _real_extract(self, url):
  22         mobj = self._match_valid_url(url)
  23         title = mobj.group(1)
  24         webpage = self._download_webpage(url, title)
  25         title = self._html_search_meta('name', webpage) or self._og_search_title(webpage)
  26         config_url = self._html_search_regex(
  27             r'data-src(?:set-video)?="(/contenu/medias/video\.php.*?)"',
  28             webpage, 'config URL')
  29         config_url = 'http://www.jeuxvideo.com' + config_url
  30
  31         video_id = self._search_regex(
  32             r'id=(\d+)',
  33             config_url, 'video ID')
  34
  35         config = self._download_json(
  36             config_url, title, 'Downloading JSON config')
  37
  38         formats = [{
  39             'url': source['file'],
  40             'format_id': source['label'],
  41             'resolution': source['label'],
  42         } for source in reversed(config['sources'])]
  43
  44         return {
  45             'id': video_id,
  46             'title': title,
  47             'formats': formats,
  48             'description': self._og_search_description(webpage),
  49             'thumbnail': config.get('image'),
  50         }