yt_dlp/extractor/recurbate.py

   1 from .common import InfoExtractor
   2 from ..networking.exceptions import HTTPError
   3 from ..utils import ExtractorError, merge_dicts
   4
   5
   6 class RecurbateIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?recurbate\.com/play\.php\?video=(?P<id>\d+)'
   8     _TESTS = [{
   9         'url': 'https://recurbate.com/play.php?video=39161415',
  10         'md5': 'dd2b4ec57aa3e3572cb5cf0997fca99f',
  11         'info_dict': {
  12             'id': '39161415',
  13             'ext': 'mp4',
  14             'description': 'md5:db48d09e4d93fc715f47fd3d6b7edd51',
  15             'title': 'Performer zsnicole33 show on 2022-10-25 20:23, Chaturbate Archive – Recurbate',
  16             'age_limit': 18,
  17         },
  18         'skip': 'Website require membership.',
  19     }]
  20
  21     def _real_extract(self, url):
  22         SUBSCRIPTION_MISSING_MESSAGE = 'This video is only available for registered users; Set your authenticated browser user agent via the --user-agent parameter.'
  23         video_id = self._match_id(url)
  24         try:
  25             webpage = self._download_webpage(url, video_id)
  26         except ExtractorError as e:
  27             if isinstance(e.cause, HTTPError) and e.cause.status == 403:
  28                 self.raise_login_required(msg=SUBSCRIPTION_MISSING_MESSAGE, method='cookies')
  29             raise
  30         token = self._html_search_regex(r'data-token="([^"]+)"', webpage, 'token')
  31         video_url = f'https://recurbate.com/api/get.php?video={video_id}&token={token}'
  32
  33         video_webpage = self._download_webpage(video_url, video_id)
  34         if video_webpage == 'shall_subscribe':
  35             self.raise_login_required(msg=SUBSCRIPTION_MISSING_MESSAGE, method='cookies')
  36         entries = self._parse_html5_media_entries(video_url, video_webpage, video_id)
  37         return merge_dicts({
  38             'id': video_id,
  39             'title': self._html_extract_title(webpage, 'title'),
  40             'description': self._og_search_description(webpage),
  41             'age_limit': self._rta_search(webpage),
  42         }, entries[0])