]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/spankbang.py
50433d0f678f27c348031dbe0d6fcc3774d021b7
[youtubedl] / youtube_dl / extractor / spankbang.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6
7
8 class SpankBangIE(InfoExtractor):
9 _VALID_URL = r'https?://(?:(?:www|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
10 _TESTS = [{
11 'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
12 'md5': '1cc433e1d6aa14bc376535b8679302f7',
13 'info_dict': {
14 'id': '3vvn',
15 'ext': 'mp4',
16 'title': 'fantasy solo',
17 'description': 'dillion harper masturbates on a bed',
18 'thumbnail': 're:^https?://.*\.jpg$',
19 'uploader': 'silly2587',
20 'age_limit': 18,
21 }
22 }, {
23 # 480p only
24 'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
25 'only_matching': True,
26 }]
27
28 def _real_extract(self, url):
29 video_id = self._match_id(url)
30 webpage = self._download_webpage(url, video_id)
31
32 stream_key = self._html_search_regex(
33 r'''var\s+stream_key\s*=\s*['"](.+?)['"]''',
34 webpage, 'stream key')
35
36 formats = [{
37 'url': 'http://spankbang.com/_%s/%s/title/%sp__mp4' % (video_id, stream_key, height),
38 'ext': 'mp4',
39 'format_id': '%sp' % height,
40 'height': int(height),
41 } for height in re.findall(r'<(?:span|li|p)[^>]+[qb]_(\d+)p', webpage)]
42 self._check_formats(formats, video_id)
43 self._sort_formats(formats)
44
45 title = self._html_search_regex(
46 r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
47 description = self._search_regex(
48 r'class="desc"[^>]*>([^<]+)',
49 webpage, 'description', default=None)
50 thumbnail = self._og_search_thumbnail(webpage)
51 uploader = self._search_regex(
52 r'class="user"[^>]*>([^<]+)',
53 webpage, 'uploader', fatal=False)
54
55 age_limit = self._rta_search(webpage)
56
57 return {
58 'id': video_id,
59 'title': title,
60 'description': description,
61 'thumbnail': thumbnail,
62 'uploader': uploader,
63 'formats': formats,
64 'age_limit': age_limit,
65 }