2014-01-07 08:45:40 +00:00
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
2013-09-02 23:51:17 +00:00
|
|
|
import re
|
|
|
|
|
import json
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class DefenseGouvFrIE(InfoExtractor):
|
2014-01-07 08:45:58 +00:00
|
|
|
IE_NAME = 'defense.gouv.fr'
|
2013-09-02 23:51:17 +00:00
|
|
|
_VALID_URL = (r'http://.*?\.defense\.gouv\.fr/layout/set/'
|
2013-09-03 10:03:19 +00:00
|
|
|
r'ligthboxvideo/base-de-medias/webtv/(.*)')
|
2013-09-02 23:51:17 +00:00
|
|
|
|
|
|
|
|
_TEST = {
|
2014-01-07 08:45:40 +00:00
|
|
|
'url': 'http://www.defense.gouv.fr/layout/set/ligthboxvideo/base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1',
|
|
|
|
|
'file': '11213.mp4',
|
|
|
|
|
'md5': '75bba6124da7e63d2d60b5244ec9430c',
|
2013-09-03 10:03:19 +00:00
|
|
|
"info_dict": {
|
|
|
|
|
"title": "attaque-chimique-syrienne-du-21-aout-2013-1"
|
|
|
|
|
}
|
2013-09-02 23:51:17 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
title = re.match(self._VALID_URL, url).group(1)
|
|
|
|
|
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,
|
|
|
|
|
}
|
