youtube-dl/youtube_dl/extractor/canalc2.py

38 lines
1.2 KiB
Python
Raw Normal View History

2013-08-22 11:54:23 +00:00
# coding: utf-8
import re
from .common import InfoExtractor
2013-08-27 08:35:20 +00:00
2013-08-22 11:54:23 +00:00
class Canalc2IE(InfoExtractor):
2013-09-10 10:13:22 +00:00
IE_NAME = 'canalc2.tv'
_VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?.*?idVideo=(?P<id>\d+)'
2013-08-22 11:54:23 +00:00
_TEST = {
u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
u'file': u'12163.mp4',
2013-08-27 08:35:20 +00:00
u'md5': u'060158428b650f896c542dfbb3d6487f',
2013-08-22 11:54:23 +00:00
u'info_dict': {
u'title': u'Terrasses du Numérique'
}
}
def _real_extract(self, url):
video_id = re.match(self._VALID_URL, url).group('id')
# We need to set the voir field for getting the file name
url = 'http://www.canalc2.tv/video.asp?idVideo=%s&voir=oui' % video_id
2013-08-22 11:54:23 +00:00
webpage = self._download_webpage(url, video_id)
2013-08-27 08:35:20 +00:00
file_name = self._search_regex(
r"so\.addVariable\('file','(.*?)'\);",
webpage, 'file name')
2013-08-22 11:54:23 +00:00
video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
2013-08-27 08:35:20 +00:00
title = self._html_search_regex(
r'class="evenement8">(.*?)</a>', webpage, u'title')
2013-08-22 11:54:23 +00:00
return {'id': video_id,
2013-08-27 08:35:20 +00:00
'ext': 'mp4',
'url': video_url,
'title': title,
2013-08-22 11:54:23 +00:00
}