Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tudou.py

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5
   6 class TudouIE(InfoExtractor):
   7     _VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs)/(?:view|(.+?))/(?:([^/]+)|([^/]+)\.html)'
   8
   9     def _real_extract(self, url):
  10         mobj = re.match(self._VALID_URL, url)
  11         video_id = mobj.group(2).replace('.html','')
  12         webpage = self._download_webpage(url, video_id)
  13         video_id = re.search('"k":(.+?),',webpage).group(1)
  14         title = re.search(",kw:\"(.+)\"",webpage)
  15         if title is None:
  16             title = re.search(",kw: \'(.+)\'",webpage)
  17         title = title.group(1)
  18         thumbnail_url = re.search(",pic: \'(.+?)\'",webpage)
  19         if thumbnail_url is None:
  20             thumbnail_url = re.search(",pic:\"(.+?)\"",webpage)
  21         thumbnail_url = thumbnail_url.group(1)
  22         info_url = "http://v2.tudou.com/f?id="+str(video_id)
  23         webpage = self._download_webpage(info_url, video_id, "Opening the info webpage")
  24         final_url = re.search('\>(.+?)\<\/f\>',webpage).group(1)
  25         ext = (final_url.split('?')[0]).split('.')[-1]
  26         return [{
  27             'id':        video_id,
  28             'url':       final_url,
  29             'ext':       ext,
  30             'title':     title,
  31             'thumbnail': thumbnail_url,
  32         }]