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

   1 # coding: utf-8
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7
   8
   9 class TudouIE(InfoExtractor):
  10     _VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs)/(?:view|(.+?))/(?:([^/]+)|([^/]+))(?:\.html)?'
  11     _TEST = {
  12         u'url': u'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html',
  13         u'file': u'159448201.f4v',
  14         u'md5': u'140a49ed444bd22f93330985d8475fcb',
  15         u'info_dict': {
  16             u"title": u"卡马乔国足开大脚长传冲吊集锦"
  17         }
  18     }
  19
  20     def _url_for_id(self, id, quality = None):
  21         info_url = "http://v2.tudou.com/f?id="+str(id)
  22         if quality:
  23             info_url += '&hd' + quality
  24         webpage = self._download_webpage(info_url, id, "Opening the info webpage")
  25         final_url = self._html_search_regex('>(.+?)</f>',webpage, 'video url')
  26         return final_url
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group(2)
  31         webpage = self._download_webpage(url, video_id)
  32         title = re.search(",kw:\"(.+)\"",webpage)
  33         if title is None:
  34             title = re.search(",kw: \'(.+)\'",webpage)
  35         title = title.group(1)
  36         thumbnail_url = re.search(",pic: \'(.+?)\'",webpage)
  37         if thumbnail_url is None:
  38             thumbnail_url = re.search(",pic:\"(.+?)\"",webpage)
  39         thumbnail_url = thumbnail_url.group(1)
  40
  41         segs_json = self._search_regex(r'segs: \'(.*)\'', webpage, 'segments')
  42         segments = json.loads(segs_json)
  43         # It looks like the keys are the arguments that have to be passed as
  44         # the hd field in the request url, we pick the higher
  45         quality = sorted(segments.keys())[-1]
  46         parts = segments[quality]
  47         result = []
  48         len_parts = len(parts)
  49         if len_parts > 1:
  50             self.to_screen(u'%s: found %s parts' % (video_id, len_parts))
  51         for part in parts:
  52             part_id = part['k']
  53             final_url = self._url_for_id(part_id, quality)
  54             ext = (final_url.split('?')[0]).split('.')[-1]
  55             part_info = {'id': part_id,
  56                           'url': final_url,
  57                           'ext': ext,
  58                           'title': title,
  59                           'thumbnail': thumbnail_url,
  60                           }
  61             result.append(part_info)
  62
  63         return result