yt_dlp/extractor/weiqitv.py

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