yt-dlp/yt_dlp/extractor/behindkink.py

43 lines
1.6 KiB
Python
Raw Normal View History

2014-09-13 17:47:19 +02:00
from .common import InfoExtractor
from ..utils import url_basename
class BehindKinkIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
2014-09-13 17:47:19 +02:00
_TEST = {
'url': 'http://www.behindkink.com/2014/12/05/what-are-you-passionate-about-marley-blaze/',
'md5': '507b57d8fdcd75a41a9a7bdb7989c762',
2014-09-13 17:47:19 +02:00
'info_dict': {
'id': '37127',
2014-09-13 17:47:19 +02:00
'ext': 'mp4',
'title': 'What are you passionate about Marley Blaze',
2014-12-11 15:06:19 +01:00
'description': 'md5:aee8e9611b4ff70186f752975d9b94b4',
'upload_date': '20141205',
'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/12/blaze-1.jpg',
2014-09-13 17:47:19 +02:00
'age_limit': 18,
},
2014-09-13 17:47:19 +02:00
}
def _real_extract(self, url):
mobj = self._match_valid_url(url)
2014-09-13 17:47:19 +02:00
display_id = mobj.group('id')
webpage = self._download_webpage(url, display_id)
2014-09-13 17:47:19 +02:00
video_url = self._search_regex(
2014-12-11 15:06:19 +01:00
r'<source src="([^"]+)"', webpage, 'video URL')
video_id = url_basename(video_url).split('_')[0]
2014-12-11 15:06:19 +01:00
upload_date = mobj.group('year') + mobj.group('month') + mobj.group('day')
2014-09-13 17:47:19 +02:00
return {
'id': video_id,
2014-12-11 15:06:19 +01:00
'display_id': display_id,
2014-09-13 17:47:19 +02:00
'url': video_url,
'title': self._og_search_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage),
'upload_date': upload_date,
'age_limit': 18,
}