1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-18 00:45:03 +01:00
yt-dlp/yt_dlp/extractor/yourporn.py

68 lines
2.0 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
parse_duration,
2019-01-29 17:56:42 +01:00
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$',
2019-01-29 17:56:42 +01:00
'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)
2019-01-29 17:56:42 +01:00
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,
2019-01-29 17:56:42 +01:00
'duration': duration,
'age_limit': 18,
'ext': 'mp4',
}