youtube_dl/extractor/chaturbate.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import ExtractorError
   5
   6
   7 class ChaturbateIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?P<id>[^/?#]+)'
   9     _TESTS = [{
  10         'url': 'https://www.chaturbate.com/siswet19/',
  11         'info_dict': {
  12             'id': 'siswet19',
  13             'ext': 'mp4',
  14             'title': 're:^siswet19 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  15             'age_limit': 18,
  16             'is_live': True,
  17         },
  18         'params': {
  19             'skip_download': True,
  20         }
  21     }, {
  22         'url': 'https://en.chaturbate.com/siswet19/',
  23         'only_matching': True,
  24     }]
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28
  29         webpage = self._download_webpage(url, video_id)
  30
  31         m3u8_url = self._search_regex(
  32             r'src=(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage,
  33             'playlist', default=None, group='url')
  34
  35         if not m3u8_url:
  36             error = self._search_regex(
  37                 r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
  38                 webpage, 'error', group='error')
  39             raise ExtractorError(error, expected=True)
  40
  41         formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
  42
  43         return {
  44             'id': video_id,
  45             'title': self._live_title(video_id),
  46             'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % video_id,
  47             'age_limit': self._rta_search(webpage),
  48             'is_live': True,
  49             'formats': formats,
  50         }