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     _TEST = {
   9         u'url': u'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html',
  10         u'file': u'159447792.f4v',
  11         u'md5': u'ad7c358a01541e926a1e413612c6b10a',
  12         u'info_dict': {
  13             u"title": u"\u5361\u9a6c\u4e54\u56fd\u8db3\u5f00\u5927\u811a\u957f\u4f20\u51b2\u540a\u96c6\u9526"
  14         }
  15     }
  16
  17     def _real_extract(self, url):
  18         mobj = re.match(self._VALID_URL, url)
  19         video_id = mobj.group(2).replace('.html','')
  20         webpage = self._download_webpage(url, video_id)
  21         video_id = re.search('"k":(.+?),',webpage).group(1)
  22         title = re.search(",kw:\"(.+)\"",webpage)
  23         if title is None:
  24             title = re.search(",kw: \'(.+)\'",webpage)
  25         title = title.group(1)
  26         thumbnail_url = re.search(",pic: \'(.+?)\'",webpage)
  27         if thumbnail_url is None:
  28             thumbnail_url = re.search(",pic:\"(.+?)\"",webpage)
  29         thumbnail_url = thumbnail_url.group(1)
  30         info_url = "http://v2.tudou.com/f?id="+str(video_id)
  31         webpage = self._download_webpage(info_url, video_id, "Opening the info webpage")
  32         final_url = re.search('\>(.+?)\<\/f\>',webpage).group(1)
  33         ext = (final_url.split('?')[0]).split('.')[-1]
  34         return [{
  35             'id':        video_id,
  36             'url':       final_url,
  37             'ext':       ext,
  38             'title':     title,
  39             'thumbnail': thumbnail_url,
  40         }]