Raphaël G. Git Repositories - youtubedl/blob - 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         'skip': 'Room is offline',
  22     }, {
  23         'url': 'https://en.chaturbate.com/siswet19/',
  24         'only_matching': True,
  25     }]
  26
  27     _ROOM_OFFLINE = 'Room is currently offline'
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31
  32         webpage = self._download_webpage(url, video_id)
  33
  34         m3u8_url = self._search_regex(
  35             r'src=(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage,
  36             'playlist', default=None, group='url')
  37
  38         if not m3u8_url:
  39             error = self._search_regex(
  40                 [r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
  41                  r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'],
  42                 webpage, 'error', group='error', default=None)
  43             if not error:
  44                 if any(p not in webpage for p in (
  45                         self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')):
  46                     error = self._ROOM_OFFLINE
  47             if error:
  48                 raise ExtractorError(error, expected=True)
  49             raise ExtractorError('Unable to find stream URL')
  50
  51         formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
  52         self._sort_formats(formats)
  53
  54         return {
  55             'id': video_id,
  56             'title': self._live_title(video_id),
  57             'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % video_id,
  58             'age_limit': self._rta_search(webpage),
  59             'is_live': True,
  60             'formats': formats,
  61         }