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 (
   7     ExtractorError,
   8     lowercase_escape,
   9     url_or_none,
  10 )
  11
  12
  13 class ChaturbateIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
  15     _TESTS = [{
  16         'url': 'https://www.chaturbate.com/siswet19/',
  17         'info_dict': {
  18             'id': 'siswet19',
  19             'ext': 'mp4',
  20             'title': 're:^siswet19 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  21             'age_limit': 18,
  22             'is_live': True,
  23         },
  24         'params': {
  25             'skip_download': True,
  26         },
  27         'skip': 'Room is offline',
  28     }, {
  29         'url': 'https://chaturbate.com/fullvideo/?b=caylin',
  30         'only_matching': True,
  31     }, {
  32         'url': 'https://en.chaturbate.com/siswet19/',
  33         'only_matching': True,
  34     }]
  35
  36     _ROOM_OFFLINE = 'Room is currently offline'
  37
  38     def _real_extract(self, url):
  39         video_id = self._match_id(url)
  40
  41         webpage = self._download_webpage(
  42             'https://chaturbate.com/%s/' % video_id, video_id,
  43             headers=self.geo_verification_headers())
  44
  45         found_m3u8_urls = []
  46
  47         data = self._parse_json(
  48             self._search_regex(
  49                 r'initialRoomDossier\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
  50                 webpage, 'data', default='{}', group='value'),
  51             video_id, transform_source=lowercase_escape, fatal=False)
  52         if data:
  53             m3u8_url = url_or_none(data.get('hls_source'))
  54             if m3u8_url:
  55                 found_m3u8_urls.append(m3u8_url)
  56
  57         if not found_m3u8_urls:
  58             for m in re.finditer(
  59                     r'(\\u002[27])(?P<url>http.+?\.m3u8.*?)\1', webpage):
  60                 found_m3u8_urls.append(lowercase_escape(m.group('url')))
  61
  62         if not found_m3u8_urls:
  63             for m in re.finditer(
  64                     r'(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage):
  65                 found_m3u8_urls.append(m.group('url'))
  66
  67         m3u8_urls = []
  68         for found_m3u8_url in found_m3u8_urls:
  69             m3u8_fast_url, m3u8_no_fast_url = found_m3u8_url, found_m3u8_url.replace('_fast', '')
  70             for m3u8_url in (m3u8_fast_url, m3u8_no_fast_url):
  71                 if m3u8_url not in m3u8_urls:
  72                     m3u8_urls.append(m3u8_url)
  73
  74         if not m3u8_urls:
  75             error = self._search_regex(
  76                 [r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
  77                  r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'],
  78                 webpage, 'error', group='error', default=None)
  79             if not error:
  80                 if any(p in webpage for p in (
  81                         self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')):
  82                     error = self._ROOM_OFFLINE
  83             if error:
  84                 raise ExtractorError(error, expected=True)
  85             raise ExtractorError('Unable to find stream URL')
  86
  87         formats = []
  88         for m3u8_url in m3u8_urls:
  89             for known_id in ('fast', 'slow'):
  90                 if '_%s' % known_id in m3u8_url:
  91                     m3u8_id = known_id
  92                     break
  93             else:
  94                 m3u8_id = None
  95             formats.extend(self._extract_m3u8_formats(
  96                 m3u8_url, video_id, ext='mp4',
  97                 # ffmpeg skips segments for fast m3u8
  98                 preference=-10 if m3u8_id == 'fast' else None,
  99                 m3u8_id=m3u8_id, fatal=False, live=True))
 100         self._sort_formats(formats)
 101
 102         return {
 103             'id': video_id,
 104             'title': self._live_title(video_id),
 105             'thumbnail': 'https://roomimg.stream.highwebmedia.com/ri/%s.jpg' % video_id,
 106             'age_limit': self._rta_search(webpage),
 107             'is_live': True,
 108             'formats': formats,
 109         }