[sexykarma] Add age_limit designation
[ytdl] / youtube_dl / extractor / sexykarma.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8     unified_strdate,
9     parse_duration,
10     int_or_none,
11 )
12
13
14 class SexyKarmaIE(InfoExtractor):
15     IE_DESC = 'Sexy Karma and Watch Indian Porn'
16     _VALID_URL = r'https?://(?:www\.)?(?:sexykarma\.com|watchindianporn\.net)/(?:[^/]+/)*video/(?P<display_id>[^/]+)-(?P<id>[a-zA-Z0-9]+)\.html'
17     _TESTS = [{
18         'url': 'http://www.sexykarma.com/gonewild/video/taking-a-quick-pee-yHI70cOyIHt.html',
19         'md5': 'b9798e7d1ef1765116a8f516c8091dbd',
20         'info_dict': {
21             'id': 'yHI70cOyIHt',
22             'display_id': 'taking-a-quick-pee',
23             'ext': 'mp4',
24             'title': 'Taking a quick pee.',
25             'thumbnail': 're:^https?://.*\.jpg$',
26             'uploader': 'wildginger7',
27             'upload_date': '20141008',
28             'duration': 22,
29             'view_count': int,
30             'comment_count': int,
31             'categories': list,
32         }
33     }, {
34         'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html',
35         'md5': 'dd216c68d29b49b12842b9babe762a5d',
36         'info_dict': {
37             'id': '8Id6EZPbuHf',
38             'display_id': 'pot-pixie-tribute',
39             'ext': 'mp4',
40             'title': 'pot_pixie tribute',
41             'thumbnail': 're:^https?://.*\.jpg$',
42             'uploader': 'banffite',
43             'upload_date': '20141013',
44             'duration': 16,
45             'view_count': int,
46             'comment_count': int,
47             'categories': list,
48             'age_limit': 18,
49         }
50     }, {
51         'url': 'http://www.watchindianporn.net/video/desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number-dW2mtctxJfs.html',
52         'md5': '9afb80675550406ed9a63ac2819ef69d',
53         'info_dict': {
54             'id': 'dW2mtctxJfs',
55             'display_id': 'desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number',
56             'ext': 'mp4',
57             'title': 'Desi dancer namrata stripping completely nude and dancing on a hot number',
58             'thumbnail': 're:^https?://.*\.jpg$',
59             'uploader': 'Don',
60             'upload_date': '20140213',
61             'duration': 83,
62             'view_count': int,
63             'comment_count': int,
64             'categories': list,
65             'age_limit': 18,
66         }
67     }]
68
69     def _real_extract(self, url):
70         mobj = re.match(self._VALID_URL, url)
71         video_id = mobj.group('id')
72         display_id = mobj.group('display_id')
73
74         webpage = self._download_webpage(url, display_id)
75
76         video_url = self._html_search_regex(
77             r"url: escape\('([^']+)'\)", webpage, 'url')
78
79         title = self._html_search_regex(
80             r'<h2 class="he2"><span>(.*?)</span>',
81             webpage, 'title')
82         thumbnail = self._html_search_regex(
83             r'<span id="container"><img\s+src="([^"]+)"',
84             webpage, 'thumbnail', fatal=False)
85
86         uploader = self._html_search_regex(
87             r'class="aupa">\s*(.*?)</a>',
88             webpage, 'uploader')
89         upload_date = unified_strdate(self._html_search_regex(
90             r'Added: <strong>(.+?)</strong>', webpage, 'upload date', fatal=False))
91
92         duration = parse_duration(self._search_regex(
93             r'<td>Time:\s*</td>\s*<td align="right"><span>\s*(.+?)\s*</span>',
94             webpage, 'duration', fatal=False))
95
96         view_count = int_or_none(self._search_regex(
97             r'<td>Views:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
98             webpage, 'view count', fatal=False))
99         comment_count = int_or_none(self._search_regex(
100             r'<td>Comments:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
101             webpage, 'comment count', fatal=False))
102
103         categories = re.findall(
104             r'<a href="[^"]+/search/video/desi"><span>([^<]+)</span></a>',
105             webpage)
106
107         return {
108             'id': video_id,
109             'display_id': display_id,
110             'url': video_url,
111             'title': title,
112             'thumbnail': thumbnail,
113             'uploader': uploader,
114             'upload_date': upload_date,
115             'duration': duration,
116             'view_count': view_count,
117             'comment_count': comment_count,
118             'categories': categories,
119             'age_limit': 18,
120         }