Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/defense.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class DefenseGouvFrIE(InfoExtractor):
   7     IE_NAME = 'defense.gouv.fr'
   8     _VALID_URL = r'http://.*?\.defense\.gouv\.fr/layout/set/ligthboxvideo/base-de-medias/webtv/(?P<id>[^/?#]*)'
   9
  10     _TEST = {
  11         'url': 'http://www.defense.gouv.fr/layout/set/ligthboxvideo/base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1',
  12         'md5': '75bba6124da7e63d2d60b5244ec9430c',
  13         'info_dict': {
  14             'id': '11213',
  15             'ext': 'mp4',
  16             'title': 'attaque-chimique-syrienne-du-21-aout-2013-1'
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         title = self._match_id(url)
  22         webpage = self._download_webpage(url, title)
  23
  24         video_id = self._search_regex(
  25             r"flashvars.pvg_id=\"(\d+)\";",
  26             webpage, 'ID')
  27
  28         json_url = ('http://static.videos.gouv.fr/brightcovehub/export/json/'
  29                     + video_id)
  30         info = self._download_json(json_url, title, 'Downloading JSON config')
  31         video_url = info['renditions'][0]['url']
  32
  33         return {
  34             'id': video_id,
  35             'ext': 'mp4',
  36             'url': video_url,
  37             'title': title,
  38         }