youtube_dl/extractor/jeuxvideo.py

   1 import json
   2 import re
   3
   4 from .common import InfoExtractor
   5
   6 class JeuxVideoIE(InfoExtractor):
   7     _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
   8
   9     def _real_extract(self, url):
  10         mobj = re.match(self._VALID_URL, url)
  11         title = re.match(self._VALID_URL, url).group(1)
  12         webpage = self._download_webpage(url, title)
  13         m_download = re.search(r'<param name="flashvars" value="config=(.*?)" />', webpage)
  14
  15         xml_link = m_download.group(1)
  16
  17         id = re.search(r'http://www.jeuxvideo.com/config/\w+/0011/(.*?)/\d+_player\.xml', xml_link).group(1)
  18
  19         xml_config = self._download_webpage(xml_link, title,
  20                                                   'Downloading XML config')
  21         info = re.search(r'<format\.json>(.*?)</format\.json>',
  22                          xml_config, re.MULTILINE|re.DOTALL).group(1)
  23         info = json.loads(info)['versions'][0]
  24
  25         video_url = 'http://video720.jeuxvideo.com/' + info['file']
  26
  27         track_info = {'id':id,
  28                       'title' : title,
  29                       'ext' :   'mp4',
  30                       'url' :   video_url
  31                       }
  32
  33         return [track_info]