yt_dlp/extractor/weiqitv.py

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