youtube-dl/youtube_dl/extractor/defense.py

41 lines
1.3 KiB
Python
Raw Normal View History

2014-01-07 17:45:40 +09:00
from __future__ import unicode_literals
2013-09-03 08:51:17 +09:00
import re
import json
from .common import InfoExtractor
class DefenseGouvFrIE(InfoExtractor):
2014-01-07 17:45:58 +09:00
IE_NAME = 'defense.gouv.fr'
2013-09-03 08:51:17 +09:00
_VALID_URL = (r'http://.*?\.defense\.gouv\.fr/layout/set/'
2013-09-03 19:03:19 +09:00
r'ligthboxvideo/base-de-medias/webtv/(.*)')
2013-09-03 08:51:17 +09:00
_TEST = {
2014-01-07 17:45:40 +09:00
'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 19:03:19 +09:00
"info_dict": {
"title": "attaque-chimique-syrienne-du-21-aout-2013-1"
}
2013-09-03 08:51:17 +09:00
}
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')
2014-11-24 04:41:03 +09:00
2013-09-03 08:51:17 +09:00
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']
2014-11-24 04:41:03 +09:00
2013-09-03 08:51:17 +09:00
return {'id': video_id,
'ext': 'mp4',
'url': video_url,
'title': title,
}