youtube_dl/extractor/defense.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7
   8
   9 class DefenseGouvFrIE(InfoExtractor):
  10     IE_NAME = 'defense.gouv.fr'
  11     _VALID_URL = (r'http://.*?\.defense\.gouv\.fr/layout/set/'
  12         r'ligthboxvideo/base-de-medias/webtv/(.*)')
  13
  14     _TEST = {
  15         'url': 'http://www.defense.gouv.fr/layout/set/ligthboxvideo/base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1',
  16         'file': '11213.mp4',
  17         'md5': '75bba6124da7e63d2d60b5244ec9430c',
  18         "info_dict": {
  19             "title": "attaque-chimique-syrienne-du-21-aout-2013-1"
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         title = re.match(self._VALID_URL, url).group(1)
  25         webpage = self._download_webpage(url, title)
  26         video_id = self._search_regex(
  27             r"flashvars.pvg_id=\"(\d+)\";",
  28             webpage, 'ID')
  29
  30         json_url = ('http://static.videos.gouv.fr/brightcovehub/export/json/'
  31             + video_id)
  32         info = self._download_webpage(json_url, title,
  33                                                   'Downloading JSON config')
  34         video_url = json.loads(info)['renditions'][0]['url']
  35
  36         return {'id': video_id,
  37                 'ext': 'mp4',
  38                 'url': video_url,
  39                 'title': title,
  40                 }