-import re
-import json
+from __future__ import unicode_literals
from .common import InfoExtractor
class DefenseGouvFrIE(InfoExtractor):
- _IE_NAME = 'defense.gouv.fr'
- _VALID_URL = (r'http://.*?\.defense\.gouv\.fr/layout/set/'
- r'ligthboxvideo/base-de-medias/webtv/(.*)')
+ IE_NAME = 'defense.gouv.fr'
+ _VALID_URL = r'https?://.*?\.defense\.gouv\.fr/layout/set/ligthboxvideo/base-de-medias/webtv/(?P<id>[^/?#]*)'
_TEST = {
- u'url': (u'http://www.defense.gouv.fr/layout/set/ligthboxvideo/'
- u'base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1'),
- u'file': u'11213.mp4',
- u'md5': u'75bba6124da7e63d2d60b5244ec9430c',
- "info_dict": {
- "title": "attaque-chimique-syrienne-du-21-aout-2013-1"
+ 'url': 'http://www.defense.gouv.fr/layout/set/ligthboxvideo/base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1',
+ 'md5': '75bba6124da7e63d2d60b5244ec9430c',
+ 'info_dict': {
+ 'id': '11213',
+ 'ext': 'mp4',
+ 'title': 'attaque-chimique-syrienne-du-21-aout-2013-1'
}
}
def _real_extract(self, url):
- title = re.match(self._VALID_URL, url).group(1)
+ title = self._match_id(url)
webpage = self._download_webpage(url, title)
+
video_id = self._search_regex(
r"flashvars.pvg_id=\"(\d+)\";",
webpage, 'ID')
-
- json_url = ('http://static.videos.gouv.fr/brightcovehub/export/json/'
- + video_id)
- info = self._download_webpage(json_url, title,
- 'Downloading JSON config')
- video_url = json.loads(info)['renditions'][0]['url']
-
- return {'id': video_id,
- 'ext': 'mp4',
- 'url': video_url,
- 'title': title,
- }
+
+ json_url = (
+ 'http://static.videos.gouv.fr/brightcovehub/export/json/%s' %
+ video_id)
+ info = self._download_json(json_url, title, 'Downloading JSON config')
+ video_url = info['renditions'][0]['url']
+
+ return {
+ 'id': video_id,
+ 'ext': 'mp4',
+ 'url': video_url,
+ 'title': title,
+ }