[yourporn] Add extractor (closes #17298)
[youtube-dl] / youtube_dl / extractor / yourporn.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4 from ..utils import urljoin
5
6
7 class YourPornIE(InfoExtractor):
8     _VALID_URL = r'https?://(?:www\.)?yourporn\.sexy/post/(?P<id>[^/?#&.]+)'
9     _TEST = {
10         'url': 'https://yourporn.sexy/post/57ffcb2e1179b.html',
11         'md5': '6f8682b6464033d87acaa7a8ff0c092e',
12         'info_dict': {
13             'id': '57ffcb2e1179b',
14             'ext': 'mp4',
15             'title': 'md5:c9f43630bd968267672651ba905a7d35',
16             'thumbnail': r're:^https?://.*\.jpg$',
17         },
18     }
19
20     def _real_extract(self, url):
21         video_id = self._match_id(url)
22
23         webpage = self._download_webpage(url, video_id)
24
25         video_url = urljoin(url, self._parse_json(
26             self._search_regex(
27                 r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
28                 group='data'),
29             video_id)[video_id])
30
31         title = (self._search_regex(
32             r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',
33             default=None) or self._og_search_description(webpage)).strip()
34         thumbnail = self._og_search_thumbnail(webpage)
35
36         return {
37             'id': video_id,
38             'url': video_url,
39             'title': title,
40             'thumbnail': thumbnail,
41         }