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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class WeiqiTVIE(InfoExtractor):
   8     IE_DESC = 'WQTV'
   9     _VALID_URL = r'https?://(?:www\.)?weiqitv\.com/index/video_play\?videoId=(?P<id>[A-Za-z0-9]+)'
  10
  11     _TESTS = [{
  12         'url': 'http://www.weiqitv.com/index/video_play?videoId=53c744f09874f0e76a8b46f3',
  13         'md5': '26450599afd64c513bc77030ad15db44',
  14         'info_dict': {
  15             'id': '53c744f09874f0e76a8b46f3',
  16             'ext': 'mp4',
  17             'title': '2013年度盘点',
  18         },
  19     }, {
  20         'url': 'http://www.weiqitv.com/index/video_play?videoId=567379a2d4c36cca518b4569',
  21         'info_dict': {
  22             'id': '567379a2d4c36cca518b4569',
  23             'ext': 'mp4',
  24             'title': '民国围棋史',
  25         },
  26     }, {
  27         'url': 'http://www.weiqitv.com/index/video_play?videoId=5430220a9874f088658b4567',
  28         'info_dict': {
  29             'id': '5430220a9874f088658b4567',
  30             'ext': 'mp4',
  31             'title': '二路托过的手段和运用',
  32         },
  33     }]
  34
  35     def _real_extract(self, url):
  36         media_id = self._match_id(url)
  37         page = self._download_webpage(url, media_id)
  38
  39         info_json_str = self._search_regex(
  40             r'var\s+video\s*=\s*(.+});', page, 'info json str')
  41         info_json = self._parse_json(info_json_str, media_id)
  42
  43         letvcloud_url = self._search_regex(
  44             r'var\s+letvurl\s*=\s*"([^"]+)', page, 'letvcloud url')
  45
  46         return {
  47             '_type': 'url_transparent',
  48             'ie_key': 'LetvCloud',
  49             'url': letvcloud_url,
  50             'title': info_json['name'],
  51             'id': media_id,
  52         }