yt_dlp/extractor/defense.py

   1 from .common import InfoExtractor
   2
   3
   4 class DefenseGouvFrIE(InfoExtractor):
   5     IE_NAME = 'defense.gouv.fr'
   6     _VALID_URL = r'https?://.*?\.defense\.gouv\.fr/layout/set/ligthboxvideo/base-de-medias/webtv/(?P<id>[^/?#]*)'
   7
   8     _TEST = {
   9         'url': 'http://www.defense.gouv.fr/layout/set/ligthboxvideo/base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1',
  10         'md5': '75bba6124da7e63d2d60b5244ec9430c',
  11         'info_dict': {
  12             'id': '11213',
  13             'ext': 'mp4',
  14             'title': 'attaque-chimique-syrienne-du-21-aout-2013-1'
  15         }
  16     }
  17
  18     def _real_extract(self, url):
  19         title = self._match_id(url)
  20         webpage = self._download_webpage(url, title)
  21
  22         video_id = self._search_regex(
  23             r"flashvars.pvg_id=\"(\d+)\";",
  24             webpage, 'ID')
  25
  26         json_url = (
  27             'http://static.videos.gouv.fr/brightcovehub/export/json/%s' %
  28             video_id)
  29         info = self._download_json(json_url, title, 'Downloading JSON config')
  30         video_url = info['renditions'][0]['url']
  31
  32         return {
  33             'id': video_id,
  34             'ext': 'mp4',
  35             'url': video_url,
  36             'title': title,
  37         }