defense.py (1242B)
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'https?://.*?\.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 = ( 29 'http://static.videos.gouv.fr/brightcovehub/export/json/%s' % 30 video_id) 31 info = self._download_json(json_url, title, 'Downloading JSON config') 32 video_url = info['renditions'][0]['url'] 33 34 return { 35 'id': video_id, 36 'ext': 'mp4', 37 'url': video_url, 38 'title': title, 39 }