diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-05 17:37:42 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-05 17:37:42 +0000 |
commit | c7bab7c39fd51c0812f70020172766303191bc01 (patch) | |
tree | 56c05fbdd4fc47409d48ba318a4b621a7b0d299a /yt_dlp/extractor/yourporn.py | |
parent | Initial commit. (diff) | |
download | yt-dlp-upstream.tar.xz yt-dlp-upstream.zip |
Adding upstream version 2023.03.04.upstream/2023.03.04upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'yt_dlp/extractor/yourporn.py')
-rw-r--r-- | yt_dlp/extractor/yourporn.py | 65 |
1 files changed, 65 insertions, 0 deletions
diff --git a/yt_dlp/extractor/yourporn.py b/yt_dlp/extractor/yourporn.py new file mode 100644 index 0000000..38f42a9 --- /dev/null +++ b/yt_dlp/extractor/yourporn.py @@ -0,0 +1,65 @@ +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + parse_duration, + urljoin, +) + + +class YourPornIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?sxyprn\.com/post/(?P<id>[^/?#&.]+)' + _TESTS = [{ + 'url': 'https://sxyprn.com/post/57ffcb2e1179b.html', + 'md5': '6f8682b6464033d87acaa7a8ff0c092e', + 'info_dict': { + 'id': '57ffcb2e1179b', + 'ext': 'mp4', + 'title': 'md5:c9f43630bd968267672651ba905a7d35', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 165, + 'age_limit': 18, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://sxyprn.com/post/57ffcb2e1179b.html', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + parts = self._parse_json( + self._search_regex( + r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info', + group='data'), + video_id)[video_id].split('/') + + num = 0 + for c in parts[6] + parts[7]: + if c.isnumeric(): + num += int(c) + parts[5] = compat_str(int(parts[5]) - num) + parts[1] += '8' + video_url = urljoin(url, '/'.join(parts)) + + title = (self._search_regex( + r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title', + default=None) or self._og_search_description(webpage)).strip() + thumbnail = self._og_search_thumbnail(webpage) + duration = parse_duration(self._search_regex( + r'duration\s*:\s*<[^>]+>([\d:]+)', webpage, 'duration', + default=None)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'age_limit': 18, + 'ext': 'mp4', + } |