yt_dlp/extractor/jeuxvideo.py

   1 from .common import InfoExtractor
   2
   3
   4 class JeuxVideoIE(InfoExtractor):
   5     _WORKING = False
   6     _ENABLED = None  # XXX: pass through to GenericIE
   7     _VALID_URL = r'https?://.*?\.jeuxvideo\.com/.*/(.*?)\.htm'
   8
   9     _TESTS = [{
  10         'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
  11         'md5': '046e491afb32a8aaac1f44dd4ddd54ee',
  12         'info_dict': {
  13             'id': '114765',
  14             'ext': 'mp4',
  15             'title': 'Tearaway : GC 2013 : Tearaway nous présente ses papiers d\'identité',
  16             'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.',
  17         },
  18     }, {
  19         'url': 'http://www.jeuxvideo.com/videos/chroniques/434220/l-histoire-du-jeu-video-la-saturn.htm',
  20         'only_matching': True,
  21     }]
  22
  23     def _real_extract(self, url):
  24         mobj = self._match_valid_url(url)
  25         title = mobj.group(1)
  26         webpage = self._download_webpage(url, title)
  27         title = self._html_search_meta('name', webpage) or self._og_search_title(webpage)
  28         config_url = self._html_search_regex(
  29             r'data-src(?:set-video)?="(/contenu/medias/video\.php.*?)"',
  30             webpage, 'config URL')
  31         config_url = 'http://www.jeuxvideo.com' + config_url
  32
  33         video_id = self._search_regex(
  34             r'id=(\d+)',
  35             config_url, 'video ID')
  36
  37         config = self._download_json(
  38             config_url, title, 'Downloading JSON config')
  39
  40         formats = [{
  41             'url': source['file'],
  42             'format_id': source['label'],
  43             'resolution': source['label'],
  44         } for source in reversed(config['sources'])]
  45
  46         return {
  47             'id': video_id,
  48             'title': title,
  49             'formats': formats,
  50             'description': self._og_search_description(webpage),
  51             'thumbnail': config.get('image'),
  52         }