diff options
| author | einstein95 <einstein95@users.noreply.github.com> | 2017-01-22 02:00:38 +1300 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2017-01-22 02:58:40 +0700 |
| commit | 42697bab3c4d65a232054d5d5482cc177da12c72 (patch) | |
| tree | 4ab0eafb72d3a8a21e16b6a0f0d73279b3e6e90f | |
| parent | 94629e537f2f6ed80b19e3863456f9ba8073af36 (diff) | |
[chaturbate] Fix extraction
| -rw-r--r-- | youtube_dl/extractor/chaturbate.py | 18 |
1 files changed, 11 insertions, 7 deletions
diff --git a/youtube_dl/extractor/chaturbate.py b/youtube_dl/extractor/chaturbate.py index 29a8820d5..1c2f065df 100644 --- a/youtube_dl/extractor/chaturbate.py +++ b/youtube_dl/extractor/chaturbate.py @@ -1,5 +1,7 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ExtractorError @@ -31,30 +33,32 @@ class ChaturbateIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - m3u8_url = self._search_regex( - r'src=(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage, - 'playlist', default=None, group='url') + m3u8_urls = re.findall( + r'var hlsSource.+? = (["\'])(?P<url>http.+?\.m3u8)', webpage) - if not m3u8_url: + if not m3u8_urls: error = self._search_regex( [r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>', r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'], webpage, 'error', group='error', default=None) if not error: - if any(p not in webpage for p in ( + if any(p 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') + formats = [] + for m3u8_url in m3u8_urls: + formats.append(self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')[0]) + self._sort_formats(formats) return { 'id': video_id, 'title': self._live_title(video_id), - 'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % video_id, + 'thumbnail': 'https://roomimg.stream.highwebmedia.com/ri/%s.jpg' % video_id, 'age_limit': self._rta_search(webpage), 'is_live': True, 'formats': formats, |