[youtube] Fix extraction.
[youtube-dl] / youtube_dl / extractor / twentyfourvideo.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     parse_iso8601,
9     int_or_none,
10     xpath_attr,
11     xpath_element,
12 )
13
14
15 class TwentyFourVideoIE(InfoExtractor):
16     IE_NAME = '24video'
17     _VALID_URL = r'''(?x)
18                     https?://
19                         (?P<host>
20                             (?:(?:www|porno?)\.)?24video\.
21                             (?:net|me|xxx|sexy?|tube|adult|site|vip)
22                         )/
23                         (?:
24                             video/(?:(?:view|xml)/)?|
25                             player/new24_play\.swf\?id=
26                         )
27                         (?P<id>\d+)
28                     '''
29
30     _TESTS = [{
31         'url': 'http://www.24video.net/video/view/1044982',
32         'md5': 'e09fc0901d9eaeedac872f154931deeb',
33         'info_dict': {
34             'id': '1044982',
35             'ext': 'mp4',
36             'title': 'Эротика каменного века',
37             'description': 'Как смотрели порно в каменном веке.',
38             'thumbnail': r're:^https?://.*\.jpg$',
39             'uploader': 'SUPERTELO',
40             'duration': 31,
41             'timestamp': 1275937857,
42             'upload_date': '20100607',
43             'age_limit': 18,
44             'like_count': int,
45             'dislike_count': int,
46         },
47     }, {
48         'url': 'http://www.24video.net/player/new24_play.swf?id=1044982',
49         'only_matching': True,
50     }, {
51         'url': 'http://www.24video.me/video/view/1044982',
52         'only_matching': True,
53     }, {
54         'url': 'http://www.24video.tube/video/view/2363750',
55         'only_matching': True,
56     }, {
57         'url': 'https://www.24video.site/video/view/2640421',
58         'only_matching': True,
59     }, {
60         'url': 'https://porno.24video.net/video/2640421-vsya-takaya-gibkaya-i-v-masle',
61         'only_matching': True,
62     }, {
63         'url': 'https://www.24video.vip/video/view/1044982',
64         'only_matching': True,
65     }, {
66         'url': 'https://porn.24video.net/video/2640421-vsya-takay',
67         'only_matching': True,
68     }]
69
70     def _real_extract(self, url):
71         mobj = re.match(self._VALID_URL, url)
72         video_id = mobj.group('id')
73         host = mobj.group('host')
74
75         webpage = self._download_webpage(
76             'http://%s/video/view/%s' % (host, video_id), video_id)
77
78         title = self._og_search_title(webpage)
79         description = self._html_search_regex(
80             r'<(p|span)[^>]+itemprop="description"[^>]*>(?P<description>[^<]+)</\1>',
81             webpage, 'description', fatal=False, group='description')
82         thumbnail = self._og_search_thumbnail(webpage)
83         duration = int_or_none(self._og_search_property(
84             'duration', webpage, 'duration', fatal=False))
85         timestamp = parse_iso8601(self._search_regex(
86             r'<time[^>]+\bdatetime="([^"]+)"[^>]+itemprop="uploadDate"',
87             webpage, 'upload date', fatal=False))
88
89         uploader = self._html_search_regex(
90             r'class="video-uploaded"[^>]*>\s*<a href="/jsecUser/movies/[^"]+"[^>]*>([^<]+)</a>',
91             webpage, 'uploader', fatal=False)
92
93         view_count = int_or_none(self._html_search_regex(
94             r'<span class="video-views">(\d+) просмотр',
95             webpage, 'view count', fatal=False))
96         comment_count = int_or_none(self._html_search_regex(
97             r'<a[^>]+href="#tab-comments"[^>]*>(\d+) комментари',
98             webpage, 'comment count', default=None))
99
100         # Sets some cookies
101         self._download_xml(
102             r'http://%s/video/xml/%s?mode=init' % (host, video_id),
103             video_id, 'Downloading init XML')
104
105         video_xml = self._download_xml(
106             'http://%s/video/xml/%s?mode=play' % (host, video_id),
107             video_id, 'Downloading video XML')
108
109         video = xpath_element(video_xml, './/video', 'video', fatal=True)
110
111         formats = [{
112             'url': xpath_attr(video, '', 'url', 'video URL', fatal=True),
113         }]
114
115         like_count = int_or_none(video.get('ratingPlus'))
116         dislike_count = int_or_none(video.get('ratingMinus'))
117         age_limit = 18 if video.get('adult') == 'true' else 0
118
119         return {
120             'id': video_id,
121             'title': title,
122             'description': description,
123             'thumbnail': thumbnail,
124             'uploader': uploader,
125             'duration': duration,
126             'timestamp': timestamp,
127             'view_count': view_count,
128             'comment_count': comment_count,
129             'like_count': like_count,
130             'dislike_count': dislike_count,
131             'age_limit': age_limit,
132             'formats': formats,
133         }