diff options
author | megustamucho <megustamucho@users.noreply.github.com> | 2014-09-20 22:41:45 +1000 |
---|---|---|
committer | megustamucho <megustamucho@users.noreply.github.com> | 2014-09-20 22:41:45 +1000 |
commit | 34e14a9beb3abe76bcda1154030978979c6c1d1d (patch) | |
tree | b773b8f873084056eea80826e776569de90ec090 /youtube_dl/extractor/behindkink.py | |
parent | a8aa99442f0bd6e3c65bd6c464dfd0a87c99f65d (diff) | |
parent | ffb5b05db1f55b9b6e188d2c86befe0493829927 (diff) |
Merge remote-tracking branch 'upstream/master'
Diffstat (limited to 'youtube_dl/extractor/behindkink.py')
-rw-r--r-- | youtube_dl/extractor/behindkink.py | 53 |
1 files changed, 53 insertions, 0 deletions
diff --git a/youtube_dl/extractor/behindkink.py b/youtube_dl/extractor/behindkink.py new file mode 100644 index 000000000..31fdc0dcc --- /dev/null +++ b/youtube_dl/extractor/behindkink.py @@ -0,0 +1,53 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import url_basename + + +class BehindKinkIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)' + _TEST = { + 'url': 'http://www.behindkink.com/2014/08/14/ab1576-performers-voice-finally-heard-the-bill-is-killed/', + 'md5': '41ad01222b8442089a55528fec43ec01', + 'info_dict': { + 'id': '36370', + 'ext': 'mp4', + 'title': 'AB1576 - PERFORMERS VOICE FINALLY HEARD - THE BILL IS KILLED!', + 'description': 'The adult industry voice was finally heard as Assembly Bill 1576 remained\xa0 in suspense today at the Senate Appropriations Hearing. AB1576 was, among other industry damaging issues, a condom mandate...', + 'upload_date': '20140814', + 'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/08/36370_AB1576_Win.jpg', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') + year = mobj.group('year') + month = mobj.group('month') + day = mobj.group('day') + upload_date = year + month + day + + webpage = self._download_webpage(url, display_id) + + video_url = self._search_regex( + r"'file':\s*'([^']+)'", + webpage, 'URL base') + + video_id = url_basename(video_url) + video_id = video_id.split('_')[0] + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'title': self._og_search_title(webpage), + 'display_id': display_id, + 'thumbnail': self._og_search_thumbnail(webpage), + 'description': self._og_search_description(webpage), + 'upload_date': upload_date, + 'age_limit': 18, + } |