1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
str_to_int,
)
class PornoXOIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?pornoxo\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)\.html'
_TEST = {
'url': 'http://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary.html',
'md5': '582f28ecbaa9e6e24cb90f50f524ce87',
'info_dict': {
'id': '7564',
'ext': 'flv',
'title': 'Striptease From Sexy Secretary!',
'description': 'Striptease From Sexy Secretary!',
'categories': list, # NSFW
'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
video_url = self._html_search_regex(
r'\'file\'\s*:\s*"([^"]+)"', webpage, 'video_url')
title = self._html_search_regex(
r'<title>([^<]+)\s*-\s*PornoXO', webpage, 'title')
description = self._html_search_regex(
r'<meta name="description" content="([^"]+)\s*featuring',
webpage, 'description', fatal=False)
thumbnail = self._html_search_regex(
r'\'image\'\s*:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
view_count = str_to_int(self._html_search_regex(
r'[vV]iews:\s*([0-9,]+)', webpage, 'view count', fatal=False))
categories_str = self._html_search_regex(
r'<meta name="description" content=".*featuring\s*([^"]+)"',
webpage, 'categories', fatal=False)
categories = (
None if categories_str is None
else categories_str.split(','))
return {
'id': video_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
'categories': categories,
'view_count': view_count,
'age_limit': 18,
}
|
