1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-12-05 22:57:54 +01:00
youtube-dl/youtube_dl/extractor/slutload.py

66 lines
2.3 KiB
Python
Raw Normal View History

2014-05-13 10:04:29 +02:00
from __future__ import unicode_literals
2014-05-12 10:28:56 +02:00
from .common import InfoExtractor
2014-05-13 10:04:29 +02:00
2014-05-12 10:28:56 +02:00
class SlutloadIE(InfoExtractor):
_VALID_URL = r'https?://(?:\w+\.)?slutload\.com/(?:video/[^/]+|embed_player|watch)/(?P<id>[^/]+)'
2017-12-30 19:41:07 +01:00
_TESTS = [{
2014-05-13 10:04:29 +02:00
'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
2016-10-01 13:57:18 +02:00
'md5': '868309628ba00fd488cf516a113fd717',
2014-05-13 10:04:29 +02:00
'info_dict': {
'id': 'TD73btpBqSxc',
'ext': 'mp4',
2016-02-14 10:37:17 +01:00
'title': 'virginie baisee en cam',
'age_limit': 18,
'thumbnail': r're:https?://.*?\.jpg'
},
2017-12-30 19:41:07 +01:00
}, {
# mobile site
'url': 'http://mobile.slutload.com/video/masturbation-solo/fviFLmc6kzJ/',
'only_matching': True,
}, {
'url': 'http://www.slutload.com/embed_player/TD73btpBqSxc/',
'only_matching': True,
}, {
'url': 'http://www.slutload.com/watch/TD73btpBqSxc/Virginie-Baisee-En-Cam.html',
'only_matching': True,
2017-12-30 19:41:07 +01:00
}]
2014-05-12 10:28:56 +02:00
def _real_extract(self, url):
2016-10-01 13:57:18 +02:00
video_id = self._match_id(url)
2017-12-30 19:41:07 +01:00
embed_page = self._download_webpage(
'http://www.slutload.com/embed_player/%s' % video_id, video_id,
'Downloading embed page', fatal=False)
2014-05-12 10:28:56 +02:00
if embed_page:
def extract(what):
return self._html_search_regex(
r'data-video-%s=(["\'])(?P<url>(?:(?!\1).)+)\1' % what,
embed_page, 'video %s' % what, default=None, group='url')
2014-05-13 10:04:29 +02:00
video_url = extract('url')
if video_url:
title = self._html_search_regex(
r'<title>([^<]+)', embed_page, 'title', default=video_id)
return {
'id': video_id,
'url': video_url,
'title': title,
'thumbnail': extract('preview'),
'age_limit': 18
}
2014-05-13 10:04:29 +02:00
webpage = self._download_webpage(
'http://www.slutload.com/video/_/%s/' % video_id, video_id)
title = self._html_search_regex(
r'<h1><strong>([^<]+)</strong>', webpage, 'title').strip()
info = self._parse_html5_media_entries(url, webpage, video_id)[0]
info.update({
2014-05-13 10:04:29 +02:00
'id': video_id,
'title': title,
'age_limit': 18,
})
return info