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

   1 # encoding: utf-8
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import ExtractorError
   8
   9
  10 class SohuIE(InfoExtractor):
  11     _VALID_URL = r'https?://tv\.sohu\.com/\d+?/n(?P<id>\d+)\.shtml.*?'
  12
  13     _TEST = {
  14         u'url': u'http://tv.sohu.com/20130724/n382479172.shtml#super',
  15         u'file': u'382479172.mp4',
  16         u'md5': u'bde8d9a6ffd82c63a1eefaef4eeefec7',
  17         u'info_dict': {
  18             u'title': u'MV：Far East Movement《The Illest》',
  19         },
  20     }
  21
  22     def _real_extract(self, url):
  23
  24         def _fetch_data(vid_id):
  25             base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid='
  26             data_url = base_data_url + str(vid_id)
  27             data_json = self._download_webpage(
  28                 data_url, video_id,
  29                 note=u'Downloading JSON data for ' + str(vid_id))
  30             return json.loads(data_json)
  31
  32         mobj = re.match(self._VALID_URL, url)
  33         video_id = mobj.group('id')
  34
  35         webpage = self._download_webpage(url, video_id)
  36         raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>',
  37                                             webpage, u'video title')
  38         title = raw_title.partition('-')[0].strip()
  39
  40         vid = self._html_search_regex(r'var vid="(\d+)"', webpage,
  41                                       u'video path')
  42         data = _fetch_data(vid)
  43
  44         QUALITIES = ('ori', 'super', 'high', 'nor')
  45         vid_ids = [data['data'][q + 'Vid']
  46                    for q in QUALITIES
  47                    if data['data'][q + 'Vid'] != 0]
  48         if not vid_ids:
  49             raise ExtractorError(u'No formats available for this video')
  50
  51         # For now, we just pick the highest available quality
  52         vid_id = vid_ids[-1]
  53
  54         format_data = data if vid == vid_id else _fetch_data(vid_id)
  55         part_count = format_data['data']['totalBlocks']
  56         allot = format_data['allot']
  57         prot = format_data['prot']
  58         clipsURL = format_data['data']['clipsURL']
  59         su = format_data['data']['su']
  60
  61         playlist = []
  62         for i in range(part_count):
  63             part_url = ('http://%s/?prot=%s&file=%s&new=%s' %
  64                         (allot, prot, clipsURL[i], su[i]))
  65             part_str = self._download_webpage(
  66                 part_url, video_id,
  67                 note=u'Downloading part %d of %d' % (i+1, part_count))
  68
  69             part_info = part_str.split('|')
  70             video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3])
  71
  72             video_info = {
  73                 'id': '%s_part%02d' % (video_id, i + 1),
  74                 'title': title,
  75                 'url': video_url,
  76                 'ext': 'mp4',
  77             }
  78             playlist.append(video_info)
  79
  80         if len(playlist) == 1:
  81             info = playlist[0]
  82             info['id'] = video_id
  83         else:
  84             info = {
  85                 '_type': 'playlist',
  86                 'entries': playlist,
  87                 'id': video_id,
  88             }
  89
  90         return info