yt_dlp/extractor/bokecc.py

   1 import urllib.parse
   2
   3 from .common import InfoExtractor
   4 from ..utils import ExtractorError
   5
   6
   7 class BokeCCBaseIE(InfoExtractor):
   8     def _extract_bokecc_formats(self, webpage, video_id, format_id=None):
   9         player_params_str = self._html_search_regex(
  10             r'<(?:script|embed)[^>]+src=(?P<q>["\'])(?:https?:)?//p\.bokecc\.com/(?:player|flash/player\.swf)\?(?P<query>.+?)(?P=q)',
  11             webpage, 'player params', group='query')
  12
  13         player_params = urllib.parse.parse_qs(player_params_str)
  14
  15         info_xml = self._download_xml(
  16             'http://p.bokecc.com/servlet/playinfo?uid={}&vid={}&m=1'.format(
  17                 player_params['siteid'][0], player_params['vid'][0]), video_id)
  18
  19         return [{
  20             'format_id': format_id,
  21             'url': quality.find('./copy').attrib['playurl'],
  22             'quality': int(quality.attrib['value']),
  23         } for quality in info_xml.findall('./video/quality')]
  24
  25
  26 class BokeCCIE(BokeCCBaseIE):
  27     _IE_DESC = 'CC视频'
  28     _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
  29
  30     _TESTS = [{
  31         'url': 'http://union.bokecc.com/playvideo.bo?vid=E0ABAE9D4F509B189C33DC5901307461&uid=FE644790DE9D154A',
  32         'info_dict': {
  33             'id': 'FE644790DE9D154A_E0ABAE9D4F509B189C33DC5901307461',
  34             'ext': 'flv',
  35             'title': 'BokeCC Video',
  36         },
  37     }]
  38
  39     def _real_extract(self, url):
  40         qs = urllib.parse.parse_qs(self._match_valid_url(url).group('query'))
  41         if not qs.get('vid') or not qs.get('uid'):
  42             raise ExtractorError('Invalid URL', expected=True)
  43
  44         video_id = '{}_{}'.format(qs['uid'][0], qs['vid'][0])
  45
  46         webpage = self._download_webpage(url, video_id)
  47
  48         return {
  49             'id': video_id,
  50             'title': 'BokeCC Video',  # no title provided in the webpage
  51             'formats': self._extract_bokecc_formats(webpage, video_id),
  52         }