]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/sexu.py
[sexu] initial support
[yt-dlp.git] / youtube_dl / extractor / sexu.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6
7
8 class SexuIE(InfoExtractor):
9 _VALID_URL = r'https?://(?:www\.)?sexu\.com/(?P<id>\d+)'
10 _TEST = {
11 'url': 'http://sexu.com/961791/',
12 'md5': 'ff615aca9691053c94f8f10d96cd7884',
13 'info_dict': {
14 'id': '961791',
15 'ext': 'mp4',
16 'title': str, # NSFW
17 'description': 'md5:c5ed8625eb386855d5a7967bd7b77a54',
18 'categories': list, # NSFW
19 'thumbnail': 're:https?://.*\.jpg$',
20 'age_limit': 18,
21 }
22 }
23
24 def _real_extract(self, url):
25 mobj = re.match(self._VALID_URL, url)
26 video_id = mobj.group('id')
27
28 webpage = self._download_webpage(url, video_id)
29
30 quality_arr = self._search_regex(r'sources:\s*\[([^\]]+)\]', webpage, 'quality formats')
31
32 formats = [{
33 'url': fmt[0].replace('\\', ''),
34 'format_id': fmt[1],
35 'height': int(fmt[1][:3]),
36 } for fmt in re.findall(r'"file":"([^"]+)","label":"([^"]+)"', quality_arr)]
37 self._sort_formats(formats)
38
39 title = self._html_search_regex(
40 r'<title>([^<]+)\s*-\s*Sexu.Com</title>', webpage, 'title')
41
42 description = self._html_search_meta('description', webpage, 'description')
43
44 thumbnail = self._html_search_regex(
45 r'image:\s*"([^"]+)"',
46 webpage, 'thumbnail', fatal=False)
47
48 categories_str = self._html_search_meta('keywords', webpage, 'categories', fatal=False)
49 categories = (
50 None if categories_str is None
51 else categories_str.split(','))
52
53 return {
54 'id': video_id,
55 'title': title,
56 'description': description,
57 'thumbnail': thumbnail,
58 'categories': categories,
59 'formats': formats,
60 'age_limit': 18,
61 }