]>
Commit | Line | Data |
---|---|---|
8d9b9022 | 1 | # coding: utf-8 |
2 | from __future__ import unicode_literals | |
3 | ||
4 | from .common import InfoExtractor | |
5 | from ..utils import ( | |
6 | int_or_none, | |
7 | parse_duration, | |
8 | parse_iso8601 | |
9 | ) | |
10 | ||
11 | ||
12 | class PornFlipIE(InfoExtractor): | |
13 | _VALID_URL = r'https?://(?:www\.)?pornflip\.com/(?:(embed|sv|v)/)?(?P<id>[^/]+)' | |
14 | _TESTS = [ | |
15 | { | |
16 | 'url': 'https://www.pornflip.com/dzv9Mtw1qj2/sv/brazzers-double-dare-two-couples-fucked-jenna-reid-maya-bijou', | |
17 | 'info_dict': { | |
18 | 'id': 'dzv9Mtw1qj2', | |
19 | 'ext': 'mp4', | |
20 | 'title': 'Brazzers - Double Dare Two couples fucked Jenna Reid Maya Bijou', | |
21 | 'description': 'md5:d2b69e6cc743c5fd158e162aa7f05821', | |
22 | 'duration': 476, | |
23 | 'like_count': int, | |
24 | 'dislike_count': int, | |
25 | 'view_count': int, | |
26 | 'timestamp': 1617846819, | |
27 | 'upload_date': '20210408', | |
28 | 'uploader': 'Brazzers', | |
29 | 'age_limit': 18, | |
30 | }, | |
31 | 'params': { | |
8d9b9022 | 32 | 'skip_download': True, |
33 | }, | |
34 | }, | |
35 | { | |
36 | 'url': 'https://www.pornflip.com/v/IrJEC40i21L', | |
37 | 'only_matching': True, | |
38 | }, | |
39 | { | |
40 | 'url': 'https://www.pornflip.com/Z3jzbChC5-P/sexintaxi-e-sereyna-gomez-czech-naked-couple', | |
41 | 'only_matching': True, | |
42 | }, | |
43 | { | |
44 | 'url': 'https://www.pornflip.com/embed/bLcDFxnrZnU', | |
45 | 'only_matching': True, | |
46 | }, | |
47 | ] | |
48 | _HOST = 'www.pornflip.com' | |
49 | ||
50 | def _real_extract(self, url): | |
51 | video_id = self._match_id(url) | |
52 | webpage = self._download_webpage( | |
53 | 'https://{}/sv/{}'.format(self._HOST, video_id), video_id, headers={'host': self._HOST}) | |
54 | description = self._html_search_regex(r'&p\[summary\]=(.*?)\s*&p', webpage, 'description', fatal=False) | |
55 | duration = self._search_regex(r'"duration":\s+"([^"]+)",', webpage, 'duration', fatal=False) | |
56 | view_count = self._search_regex(r'"interactionCount":\s+"([^"]+)"', webpage, 'view_count', fatal=False) | |
57 | title = self._html_search_regex(r'id="mediaPlayerTitleLink"[^>]*>(.+)</a>', webpage, 'title', fatal=False) | |
58 | uploader = self._html_search_regex(r'class="title-chanel"[^>]*>[^<]*<a[^>]*>([^<]+)<', webpage, 'uploader', fatal=False) | |
59 | upload_date = self._search_regex(r'"uploadDate":\s+"([^"]+)",', webpage, 'upload_date', fatal=False) | |
60 | likes = self._html_search_regex( | |
61 | r'class="btn btn-up-rating[^>]*>[^<]*<i[^>]*>[^<]*</i>[^>]*<span[^>]*>[^0-9]*([0-9]+)[^<0-9]*<', webpage, 'like_count', fatal=False) | |
62 | dislikes = self._html_search_regex( | |
63 | r'class="btn btn-down-rating[^>]*>[^<]*<i[^>]*>[^<]*</i>[^>]*<span[^>]*>[^0-9]*([0-9]+)[^<0-9]*<', webpage, 'dislike_count', fatal=False) | |
64 | mpd_url = self._search_regex(r'"([^"]+userscontent.net/dash/[0-9]+/manifest.mpd[^"]*)"', webpage, 'mpd_url').replace('&', '&') | |
65 | formats = self._extract_mpd_formats(mpd_url, video_id, mpd_id='dash') | |
66 | self._sort_formats(formats) | |
67 | ||
68 | return { | |
69 | 'age_limit': 18, | |
70 | 'description': description, | |
71 | 'dislike_count': int_or_none(dislikes), | |
72 | 'duration': parse_duration(duration), | |
73 | 'formats': formats, | |
74 | 'id': video_id, | |
75 | 'like_count': int_or_none(likes), | |
76 | 'timestamp': parse_iso8601(upload_date), | |
77 | 'thumbnail': self._og_search_thumbnail(webpage), | |
78 | 'title': title, | |
79 | 'uploader': uploader, | |
80 | 'view_count': int_or_none(view_count), | |
81 | } |