0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-25 02:45:12 +00:00
yt-dlp/yt_dlp/extractor/slutload.py

64 lines
2.2 KiB
Python
Raw Normal View History

2014-05-12 08:28:56 +00:00
from .common import InfoExtractor
2014-05-13 08:04:29 +00:00
2014-05-12 08:28:56 +00:00
class SlutloadIE(InfoExtractor):
_VALID_URL = r'https?://(?:\w+\.)?slutload\.com/(?:video/[^/]+|embed_player|watch)/(?P<id>[^/]+)'
2017-12-30 18:41:07 +00:00
_TESTS = [{
2014-05-13 08:04:29 +00:00
'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
2016-10-01 11:57:18 +00:00
'md5': '868309628ba00fd488cf516a113fd717',
2014-05-13 08:04:29 +00:00
'info_dict': {
'id': 'TD73btpBqSxc',
'ext': 'mp4',
2016-02-14 09:37:17 +00:00
'title': 'virginie baisee en cam',
'age_limit': 18,
'thumbnail': r're:https?://.*?\.jpg',
},
2017-12-30 18:41:07 +00:00
}, {
# 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 18:41:07 +00:00
}]
2014-05-12 08:28:56 +00:00
def _real_extract(self, url):
2016-10-01 11:57:18 +00:00
video_id = self._match_id(url)
2017-12-30 18:41:07 +00:00
embed_page = self._download_webpage(
f'http://www.slutload.com/embed_player/{video_id}', video_id,
'Downloading embed page', fatal=False)
2014-05-12 08:28:56 +00:00
if embed_page:
def extract(what):
return self._html_search_regex(
rf'data-video-{what}=(["\'])(?P<url>(?:(?!\1).)+)\1',
embed_page, f'video {what}', default=None, group='url')
2014-05-13 08:04:29 +00:00
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 08:04:29 +00:00
webpage = self._download_webpage(
f'http://www.slutload.com/video/_/{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 08:04:29 +00:00
'id': video_id,
'title': title,
'age_limit': 18,
})
return info