yt_dlp/extractor/stripchat.py

   1 from .common import InfoExtractor
   2 from ..compat import (
   3     compat_str,
   4 )
   5 from ..utils import (
   6     ExtractorError,
   7     lowercase_escape,
   8     try_get,
   9 )
  10
  11
  12 class StripchatIE(InfoExtractor):
  13     _VALID_URL = r'https?://stripchat\.com/(?P<id>[0-9A-Za-z-_]+)'
  14     _TESTS = [{
  15         'url': 'https://stripchat.com/feel_me',
  16         'info_dict': {
  17             'id': 'feel_me',
  18             'ext': 'mp4',
  19             'title': 're:^feel_me [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  20             'description': str,
  21             'is_live': True,
  22             'age_limit': 18,
  23         },
  24         'skip': 'Room is offline',
  25     }]
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         webpage = self._download_webpage(
  30             'https://stripchat.com/%s/' % video_id, video_id,
  31             headers=self.geo_verification_headers())
  32
  33         data = self._parse_json(
  34             self._search_regex(
  35                 r'<script\b[^>]*>\s*window\.__PRELOADED_STATE__\s*=(?P<value>.*?)<\/script>',
  36                 webpage, 'data', default='{}', group='value'),
  37             video_id, transform_source=lowercase_escape, fatal=False)
  38         if not data:
  39             raise ExtractorError('Unable to find configuration for stream.')
  40
  41         if try_get(data, lambda x: x['viewCam']['show'], dict):
  42             raise ExtractorError('Model is in private show', expected=True)
  43         elif not try_get(data, lambda x: x['viewCam']['model']['isLive'], bool):
  44             raise ExtractorError('Model is offline', expected=True)
  45
  46         server = try_get(data, lambda x: x['viewCam']['viewServers']['flashphoner-hls'], compat_str)
  47         host = try_get(data, lambda x: x['config']['data']['hlsStreamHost'], compat_str)
  48         model_id = try_get(data, lambda x: x['viewCam']['model']['id'], int)
  49
  50         formats = self._extract_m3u8_formats(
  51             'https://b-%s.%s/hls/%d/%d.m3u8' % (server, host, model_id, model_id),
  52             video_id, ext='mp4', m3u8_id='hls', fatal=False, live=True)
  53         self._sort_formats(formats)
  54
  55         return {
  56             'id': video_id,
  57             'title': video_id,
  58             'description': self._og_search_description(webpage),
  59             'is_live': True,
  60             'formats': formats,
  61             # Stripchat declares the RTA meta-tag, but in an non-standard format so _rta_search() can't be used
  62             'age_limit': 18,
  63         }