yt_dlp/extractor/camsoda.py

   1 import random
   2
   3 from .common import InfoExtractor
   4 from ..utils import ExtractorError, traverse_obj
   5
   6
   7 class CamsodaIE(InfoExtractor):
   8     _VALID_URL = r'https?://www\.camsoda\.com/(?P<id>[\w-]+)'
   9     _TESTS = [{
  10         'url': 'https://www.camsoda.com/lizzhopf',
  11         'info_dict': {
  12             'id': 'lizzhopf',
  13             'ext': 'mp4',
  14             'title': 'lizzhopf (lizzhopf) Nude on Cam. Free Live Sex Chat Room - CamSoda',
  15             'description': str,
  16             'is_live': True,
  17             'age_limit': 18,
  18         },
  19         'skip': 'Room is offline',
  20     }]
  21
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24         webpage = self._download_webpage(url, video_id, headers=self.geo_verification_headers())
  25
  26         data = self._download_json(
  27             f'https://camsoda.com/api/v1/video/vtoken/{video_id}', video_id,
  28             query={'username': f'guest_{random.randrange(10000, 99999)}'},
  29             headers=self.geo_verification_headers())
  30         if not data:
  31             raise ExtractorError('Unable to find configuration for stream.')
  32         elif data.get('private_servers'):
  33             raise ExtractorError('Model is in private show.', expected=True)
  34         elif not data.get('stream_name'):
  35             raise ExtractorError('Model is offline.', expected=True)
  36
  37         stream_name = traverse_obj(data, 'stream_name', expected_type=str)
  38         token = traverse_obj(data, 'token', expected_type=str)
  39
  40         formats = []
  41         for server in traverse_obj(data, ('edge_servers', ...)):
  42             formats = self._extract_m3u8_formats(
  43                 f'https://{server}/{stream_name}_v1/index.m3u8?token={token}',
  44                 video_id, ext='mp4', m3u8_id='hls', fatal=False, live=True)
  45             if formats:
  46                 break
  47         if not formats:
  48             self.raise_no_formats('No active streams found', expected=True)
  49
  50         return {
  51             'id': video_id,
  52             'title': self._html_extract_title(webpage),
  53             'description': self._html_search_meta('description', webpage, default=None),
  54             'is_live': True,
  55             'formats': formats,
  56             'age_limit': 18,
  57         }