]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/behindkink.py
Prepare for upload.
[youtubedl] / youtube_dl / extractor / behindkink.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import url_basename
8
9
10 class BehindKinkIE(InfoExtractor):
11 _VALID_URL = r'http://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
12 _TEST = {
13 'url': 'http://www.behindkink.com/2014/08/14/ab1576-performers-voice-finally-heard-the-bill-is-killed/',
14 'md5': '41ad01222b8442089a55528fec43ec01',
15 'info_dict': {
16 'id': '36370',
17 'ext': 'mp4',
18 'title': 'AB1576 - PERFORMERS VOICE FINALLY HEARD - THE BILL IS KILLED!',
19 '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...',
20 'upload_date': '20140814',
21 'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/08/36370_AB1576_Win.jpg',
22 'age_limit': 18,
23 }
24 }
25
26 def _real_extract(self, url):
27 mobj = re.match(self._VALID_URL, url)
28 display_id = mobj.group('id')
29 year = mobj.group('year')
30 month = mobj.group('month')
31 day = mobj.group('day')
32 upload_date = year + month + day
33
34 webpage = self._download_webpage(url, display_id)
35
36 video_url = self._search_regex(
37 r"'file':\s*'([^']+)'",
38 webpage, 'URL base')
39
40 video_id = url_basename(video_url)
41 video_id = video_id.split('_')[0]
42
43 return {
44 'id': video_id,
45 'url': video_url,
46 'ext': 'mp4',
47 'title': self._og_search_title(webpage),
48 'display_id': display_id,
49 'thumbnail': self._og_search_thumbnail(webpage),
50 'description': self._og_search_description(webpage),
51 'upload_date': upload_date,
52 'age_limit': 18,
53 }