import re
from .common import InfoExtractor
-from ..utils import determine_ext
+from ..utils import (
+ determine_ext,
+ int_or_none,
+)
class OnionStudiosIE(InfoExtractor):
'id': '2937',
'ext': 'mp4',
'title': 'Hannibal charges forward, stops for a cocktail',
- 'description': 'md5:545299bda6abf87e5ec666548c6a9448',
+ 'description': 'md5:e786add7f280b7f0fe237b64cc73df76',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'The A.V. Club',
'uploader_id': 'TheAVClub',
formats = []
for src in re.findall(r'<source[^>]+src="([^"]+)"', webpage):
- if determine_ext(src) != 'm3u8': # m3u8 always results in 403
+ ext = determine_ext(src)
+ if ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ src, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+ else:
+ height = int_or_none(self._search_regex(
+ r'/(\d+)\.%s' % ext, src, 'height', default=None))
formats.append({
+ 'format_id': ext + ('-%sp' % height if height else ''),
'url': src,
+ 'height': height,
+ 'ext': ext,
+ 'preference': 1,
})
self._sort_formats(formats)
title = self._search_regex(
- r'share_title\s*=\s*"([^"]+)"', webpage, 'title')
+ r'share_title\s*=\s*(["\'])(?P<title>[^\1]+?)\1',
+ webpage, 'title', group='title')
description = self._search_regex(
- r'share_description\s*=\s*"([^"]+)"', webpage,
- 'description', default=None)
+ r'share_description\s*=\s*(["\'])(?P<description>[^\1]+?)\1',
+ webpage, 'description', default=None, group='description')
thumbnail = self._search_regex(
- r'poster="([^"]+)"', webpage, 'thumbnail', default=False)
+ r'poster\s*=\s*(["\'])(?P<thumbnail>[^\1]+?)\1',
+ webpage, 'thumbnail', default=False, group='thumbnail')
uploader_id = self._search_regex(
- r'twitter_handle\s*=\s*"([^"]+)"',
- webpage, 'uploader id', fatal=False)
+ r'twitter_handle\s*=\s*(["\'])(?P<uploader_id>[^\1]+?)\1',
+ webpage, 'uploader id', fatal=False, group='uploader_id')
uploader = self._search_regex(
- r'window\.channelName\s*=\s*"Embedded:([^"]+)"',
- webpage, 'uploader', default=False)
+ r'window\.channelName\s*=\s*(["\'])Embedded:(?P<uploader>[^\1]+?)\1',
+ webpage, 'uploader', default=False, group='uploader')
return {
'id': video_id,