mirror of https://github.com/yt-dlp/yt-dlp
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
62 lines
1.9 KiB
Python
62 lines
1.9 KiB
Python
![]()
10 years ago
|
from .common import InfoExtractor
|
||
|
|
||
|
|
||
|
class SexuIE(InfoExtractor):
|
||
|
_VALID_URL = r'https?://(?:www\.)?sexu\.com/(?P<id>\d+)'
|
||
|
_TEST = {
|
||
|
'url': 'http://sexu.com/961791/',
|
||
|
'md5': 'ff615aca9691053c94f8f10d96cd7884',
|
||
|
'info_dict': {
|
||
|
'id': '961791',
|
||
|
'ext': 'mp4',
|
||
![]()
10 years ago
|
'title': 'md5:4d05a19a5fc049a63dbbaf05fb71d91b',
|
||
![]()
9 years ago
|
'description': 'md5:2b75327061310a3afb3fbd7d09e2e403',
|
||
![]()
10 years ago
|
'categories': list, # NSFW
|
||
![]()
8 years ago
|
'thumbnail': r're:https?://.*\.jpg$',
|
||
![]()
10 years ago
|
'age_limit': 18,
|
||
|
}
|
||
|
}
|
||
|
|
||
|
def _real_extract(self, url):
|
||
![]()
10 years ago
|
video_id = self._match_id(url)
|
||
![]()
10 years ago
|
webpage = self._download_webpage(url, video_id)
|
||
|
|
||
![]()
9 years ago
|
jwvideo = self._parse_json(
|
||
|
self._search_regex(r'\.setup\(\s*({.+?})\s*\);', webpage, 'jwvideo'),
|
||
|
video_id)
|
||
|
|
||
|
sources = jwvideo['sources']
|
||
|
|
||
![]()
10 years ago
|
formats = [{
|
||
![]()
9 years ago
|
'url': source['file'].replace('\\', ''),
|
||
|
'format_id': source.get('label'),
|
||
![]()
7 years ago
|
'height': int(self._search_regex(
|
||
|
r'^(\d+)[pP]', source.get('label', ''), 'height',
|
||
|
default=None)),
|
||
![]()
9 years ago
|
} for source in sources if source.get('file')]
|
||
![]()
10 years ago
|
self._sort_formats(formats)
|
||
|
|
||
|
title = self._html_search_regex(
|
||
![]()
10 years ago
|
r'<title>([^<]+)\s*-\s*Sexu\.Com</title>', webpage, 'title')
|
||
![]()
10 years ago
|
|
||
![]()
10 years ago
|
description = self._html_search_meta(
|
||
|
'description', webpage, 'description')
|
||
![]()
10 years ago
|
|
||
![]()
9 years ago
|
thumbnail = jwvideo.get('image')
|
||
![]()
10 years ago
|
|
||
![]()
10 years ago
|
categories_str = self._html_search_meta(
|
||
|
'keywords', webpage, 'categories')
|
||
![]()
10 years ago
|
categories = (
|
||
|
None if categories_str is None
|
||
|
else categories_str.split(','))
|
||
|
|
||
|
return {
|
||
|
'id': video_id,
|
||
|
'title': title,
|
||
|
'description': description,
|
||
|
'thumbnail': thumbnail,
|
||
|
'categories': categories,
|
||
|
'formats': formats,
|
||
|
'age_limit': 18,
|
||
|
}
|