_ Git - youtube-dl/blob - youtube_dl/extractor/defense.py

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