youtube-dl/youtube_dl/extractor/defense.py

40 lines
1.3 KiB
Python
Raw Normal View History

2013-09-02 23:51:17 +00:00
import re
import json
from .common import InfoExtractor
class DefenseGouvFrIE(InfoExtractor):
_IE_NAME = 'defense.gouv.fr'
_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 = {
2013-09-03 10:03:19 +00:00
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"
}
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,
}