]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/yourporn.py
debian/README.source: Change 'markup'.
[youtubedl] / youtube_dl / extractor / yourporn.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4 from ..utils import (
5 parse_duration,
6 urljoin,
7 )
8
9
10 class YourPornIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:www\.)?(?:yourporn\.sexy|sxyprn\.com)/post/(?P<id>[^/?#&.]+)'
12 _TESTS = [{
13 'url': 'https://yourporn.sexy/post/57ffcb2e1179b.html',
14 'md5': '6f8682b6464033d87acaa7a8ff0c092e',
15 'info_dict': {
16 'id': '57ffcb2e1179b',
17 'ext': 'mp4',
18 'title': 'md5:c9f43630bd968267672651ba905a7d35',
19 'thumbnail': r're:^https?://.*\.jpg$',
20 'duration': 165,
21 'age_limit': 18,
22 },
23 'params': {
24 'skip_download': True,
25 },
26 }, {
27 'url': 'https://sxyprn.com/post/57ffcb2e1179b.html',
28 'only_matching': True,
29 }]
30
31 def _real_extract(self, url):
32 video_id = self._match_id(url)
33
34 webpage = self._download_webpage(url, video_id)
35
36 video_url = urljoin(url, self._parse_json(
37 self._search_regex(
38 r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
39 group='data'),
40 video_id)[video_id]).replace('/cdn/', '/cdn5/')
41
42 title = (self._search_regex(
43 r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',
44 default=None) or self._og_search_description(webpage)).strip()
45 thumbnail = self._og_search_thumbnail(webpage)
46 duration = parse_duration(self._search_regex(
47 r'duration\s*:\s*<[^>]+>([\d:]+)', webpage, 'duration',
48 default=None))
49
50 return {
51 'id': video_id,
52 'url': video_url,
53 'title': title,
54 'thumbnail': thumbnail,
55 'duration': duration,
56 'age_limit': 18,
57 }