youtube_dl/extractor/defense.py



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