X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fchaturbate.py;h=242fba311fd10380cf7ed4b67e3074eddc279cb2;hb=8a609c32fdf8d99f7c868c74d64a05d9a936044d;hp=5e24e1e4fbfeff5b1e3418364e4f2ce907cc17d9;hpb=1bd390358205728823ff38a51b12ae35f9468929;p=youtube-dl diff --git a/youtube_dl/extractor/chaturbate.py b/youtube_dl/extractor/chaturbate.py index 5e24e1e4f..242fba311 100644 --- a/youtube_dl/extractor/chaturbate.py +++ b/youtube_dl/extractor/chaturbate.py @@ -1,24 +1,59 @@ -# encoding: utf-8 +from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import ExtractorError class ChaturbateIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?chaturbate\.com/(?P[^/]+)/?$' + _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?P[^/?#]+)' + _TESTS = [{ + 'url': 'https://www.chaturbate.com/siswet19/', + 'info_dict': { + 'id': 'siswet19', + 'ext': 'mp4', + 'title': 're:^siswet19 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'age_limit': 18, + 'is_live': True, + }, + 'params': { + 'skip_download': True, + } + }, { + 'url': 'https://en.chaturbate.com/siswet19/', + 'only_matching': True, + }] + + _ROOM_OFFLINE = 'Room is currently offline' def _real_extract(self, url): video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - m3u8_url = self._search_regex(r"'(https?://.*?\.m3u8)'", webpage, 'playlist') + m3u8_url = self._search_regex( + r'src=(["\'])(?Phttp.+?\.m3u8.*?)\1', webpage, + 'playlist', default=None, group='url') + + if not m3u8_url: + error = self._search_regex( + [r']+class=(["\'])desc_span\1[^>]*>(?P[^<]+)', + r']+id=(["\'])defchat\1[^>]*>\s*

(?P[^<]+)<'], + webpage, 'error', group='error', default=None) + if not error: + if any(p not in webpage for p in ( + self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')): + error = self._ROOM_OFFLINE + if error: + raise ExtractorError(error, expected=True) + raise ExtractorError('Unable to find stream URL') formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4') return { 'id': video_id, 'title': self._live_title(video_id), - 'description': self._html_search_meta('description', webpage, 'description'), + 'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % video_id, + 'age_limit': self._rta_search(webpage), 'is_live': True, - 'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % (video_id,), 'formats': formats, }