aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/yourporn.py
blob: a9951f3b83090ec076d0f5549f8c5c7a5f09efe4 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
from __future__ import unicode_literals

from .common import InfoExtractor
from ..utils import urljoin


class YourPornIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?yourporn\.sexy/post/(?P<id>[^/?#&.]+)'
    _TEST = {
        'url': 'https://yourporn.sexy/post/57ffcb2e1179b.html',
        'md5': '6f8682b6464033d87acaa7a8ff0c092e',
        'info_dict': {
            'id': '57ffcb2e1179b',
            'ext': 'mp4',
            'title': 'md5:c9f43630bd968267672651ba905a7d35',
            'thumbnail': r're:^https?://.*\.jpg$',
        },
    }

    def _real_extract(self, url):
        video_id = self._match_id(url)

        webpage = self._download_webpage(url, video_id)

        video_url = urljoin(url, self._parse_json(
            self._search_regex(
                r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
                group='data'),
            video_id)[video_id]).replace('/cdn/', '/cdn2/')

        title = (self._search_regex(
            r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',
            default=None) or self._og_search_description(webpage)).strip()
        thumbnail = self._og_search_thumbnail(webpage)

        return {
            'id': video_id,
            'url': video_url,
            'title': title,
            'thumbnail': thumbnail,
        }