github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[chaturbate] Improve and capture error message

Browse source
This commit is contained in:
Sergey M․ 2015-10-11 20:35:22 +06:00
parent 1bd3903582
commit 0f61db4469
1 changed files with 31 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

36
youtube_dl/extractor/chaturbate.py
View file

@ -1,24 +1,50 @@
# encoding: utf-8 from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ExtractorError
class ChaturbateIE(InfoExtractor): class ChaturbateIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?chaturbate\.com/(?P<id>[^/]+)/?$' _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.chaturbate.com/siswet19/',
'info_dict': {
'id': 'siswet19',
'ext': 'mp4',
'title': 're:^siswet19 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'age_limit': 18,
'is_live': True,
},
'params': {
'skip_download': True,
}
}, {
'url': 'https://en.chaturbate.com/siswet19/',
'only_matching': True,
}]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
m3u8_url = self._search_regex(r"'(https?://.*?\.m3u8)'", webpage, 'playlist') m3u8_url = self._search_regex(
r'src=(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage,
'playlist', default=None, group='url')
if not m3u8_url:
error = self._search_regex(
r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
webpage, 'error', group='error')
raise ExtractorError(error, expected=True)
formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4') formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
return { return {
'id': video_id, 'id': video_id,
'title': self._live_title(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, 'is_live': True,
'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % (video_id,),
'formats': formats, 'formats': formats,
} }