fenix
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[chaturbate] Fix extraction

This commit is contained in:
einstein95 2017-01-22 02:00:38 +13:00 committed by Sergey M․
parent 94629e537f
commit 42697bab3c
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 11 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
youtube_dl/extractor/chaturbate.py
View File

@ -1,5 +1,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ExtractorError from ..utils import ExtractorError
@ -31,30 +33,32 @@ class ChaturbateIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
m3u8_url = self._search_regex( m3u8_urls = re.findall(
r'src=(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage, r'var hlsSource.+? = (["\'])(?P<url>http.+?\.m3u8)', webpage)
'playlist', default=None, group='url')
if not m3u8_url: if not m3u8_urls:
error = self._search_regex( error = self._search_regex(
[r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>', [r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'], r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'],
webpage, 'error', group='error', default=None) webpage, 'error', group='error', default=None)
if not error: 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')): self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')):
error = self._ROOM_OFFLINE error = self._ROOM_OFFLINE
if error: if error:
raise ExtractorError(error, expected=True) raise ExtractorError(error, expected=True)
raise ExtractorError('Unable to find stream URL') 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) self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,
'title': self._live_title(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), 'age_limit': self._rta_search(webpage),
'is_live': True, 'is_live': True,
'formats': formats, 'formats': formats,