]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/spankbang.py
Imported Upstream version 2015.05.15
[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 _TEST = {
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
24 def _real_extract(self, url):
25 video_id = self._match_id(url)
26 webpage = self._download_webpage(url, video_id)
27
28 stream_key = self._html_search_regex(
29 r'''var\s+stream_key\s*=\s*['"](.+?)['"]''',
30 webpage, 'stream key')
31
32 formats = [{
33 'url': 'http://spankbang.com/_%s/%s/title/%sp__mp4' % (video_id, stream_key, height),
34 'ext': 'mp4',
35 'format_id': '%sp' % height,
36 'height': int(height),
37 } for height in re.findall(r'<span[^>]+q_(\d+)p', webpage)]
38 self._sort_formats(formats)
39
40 title = self._html_search_regex(
41 r'(?s)<h1>(.+?)</h1>', webpage, 'title')
42 description = self._search_regex(
43 r'class="desc"[^>]*>([^<]+)',
44 webpage, 'description', default=None)
45 thumbnail = self._og_search_thumbnail(webpage)
46 uploader = self._search_regex(
47 r'class="user"[^>]*>([^<]+)',
48 webpage, 'uploader', fatal=False)
49
50 age_limit = self._rta_search(webpage)
51
52 return {
53 'id': video_id,
54 'title': title,
55 'description': description,
56 'thumbnail': thumbnail,
57 'uploader': uploader,
58 'formats': formats,
59 'age_limit': age_limit,
60 }