Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/chaturbate.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import ExtractorError
   7
   8
   9 class ChaturbateIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?P<id>[^/?#]+)'
  11     _TESTS = [{
  12         'url': 'https://www.chaturbate.com/siswet19/',
  13         'info_dict': {
  14             'id': 'siswet19',
  15             'ext': 'mp4',
  16             'title': 're:^siswet19 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  17             'age_limit': 18,
  18             'is_live': True,
  19         },
  20         'params': {
  21             'skip_download': True,
  22         },
  23         'skip': 'Room is offline',
  24     }, {
  25         'url': 'https://en.chaturbate.com/siswet19/',
  26         'only_matching': True,
  27     }]
  28
  29     _ROOM_OFFLINE = 'Room is currently offline'
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33
  34         webpage = self._download_webpage(
  35             url, video_id, headers=self.geo_verification_headers())
  36
  37         m3u8_urls = []
  38
  39         for m in re.finditer(
  40                 r'(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage):
  41             m3u8_fast_url, m3u8_no_fast_url = m.group('url'), m.group(
  42                 'url').replace('_fast', '')
  43             for m3u8_url in (m3u8_fast_url, m3u8_no_fast_url):
  44                 if m3u8_url not in m3u8_urls:
  45                     m3u8_urls.append(m3u8_url)
  46
  47         if not m3u8_urls:
  48             error = self._search_regex(
  49                 [r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
  50                  r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'],
  51                 webpage, 'error', group='error', default=None)
  52             if not error:
  53                 if any(p in webpage for p in (
  54                         self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')):
  55                     error = self._ROOM_OFFLINE
  56             if error:
  57                 raise ExtractorError(error, expected=True)
  58             raise ExtractorError('Unable to find stream URL')
  59
  60         formats = []
  61         for m3u8_url in m3u8_urls:
  62             m3u8_id = 'fast' if '_fast' in m3u8_url else 'slow'
  63             formats.extend(self._extract_m3u8_formats(
  64                 m3u8_url, video_id, ext='mp4',
  65                 # ffmpeg skips segments for fast m3u8
  66                 preference=-10 if m3u8_id == 'fast' else None,
  67                 m3u8_id=m3u8_id, fatal=False, live=True))
  68         self._sort_formats(formats)
  69
  70         return {
  71             'id': video_id,
  72             'title': self._live_title(video_id),
  73             'thumbnail': 'https://roomimg.stream.highwebmedia.com/ri/%s.jpg' % video_id,
  74             'age_limit': self._rta_search(webpage),
  75             'is_live': True,
  76             'formats': formats,
  77         }