Merge pull request #7045 from remitamine/ign
[youtube-dl] / youtube_dl / extractor / twentyfourvideo.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..utils import (
6     parse_iso8601,
7     int_or_none,
8     xpath_attr,
9     xpath_element,
10 )
11
12
13 class TwentyFourVideoIE(InfoExtractor):
14     IE_NAME = '24video'
15     _VALID_URL = r'https?://(?:www\.)?24video\.net/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
16
17     _TESTS = [
18         {
19             'url': 'http://www.24video.net/video/view/1044982',
20             'md5': 'e09fc0901d9eaeedac872f154931deeb',
21             'info_dict': {
22                 'id': '1044982',
23                 'ext': 'mp4',
24                 'title': 'Эротика каменного века',
25                 'description': 'Как смотрели порно в каменном веке.',
26                 'thumbnail': 're:^https?://.*\.jpg$',
27                 'uploader': 'SUPERTELO',
28                 'duration': 31,
29                 'timestamp': 1275937857,
30                 'upload_date': '20100607',
31                 'age_limit': 18,
32                 'like_count': int,
33                 'dislike_count': int,
34             },
35         },
36         {
37             'url': 'http://www.24video.net/player/new24_play.swf?id=1044982',
38             'only_matching': True,
39         }
40     ]
41
42     def _real_extract(self, url):
43         video_id = self._match_id(url)
44
45         webpage = self._download_webpage(
46             'http://www.24video.net/video/view/%s' % video_id, video_id)
47
48         title = self._og_search_title(webpage)
49         description = self._html_search_regex(
50             r'<span itemprop="description">([^<]+)</span>', webpage, 'description', fatal=False)
51         thumbnail = self._og_search_thumbnail(webpage)
52         duration = int_or_none(self._og_search_property(
53             'duration', webpage, 'duration', fatal=False))
54         timestamp = parse_iso8601(self._search_regex(
55             r'<time id="video-timeago" datetime="([^"]+)" itemprop="uploadDate">',
56             webpage, 'upload date'))
57
58         uploader = self._html_search_regex(
59             r'class="video-uploaded"[^>]*>\s*<a href="/jsecUser/movies/[^"]+"[^>]*>([^<]+)</a>',
60             webpage, 'uploader', fatal=False)
61
62         view_count = int_or_none(self._html_search_regex(
63             r'<span class="video-views">(\d+) просмотр',
64             webpage, 'view count', fatal=False))
65         comment_count = int_or_none(self._html_search_regex(
66             r'<div class="comments-title" id="comments-count">(\d+) комментари',
67             webpage, 'comment count', fatal=False))
68
69         # Sets some cookies
70         self._download_xml(
71             r'http://www.24video.net/video/xml/%s?mode=init' % video_id,
72             video_id, 'Downloading init XML')
73
74         video_xml = self._download_xml(
75             'http://www.24video.net/video/xml/%s?mode=play' % video_id,
76             video_id, 'Downloading video XML')
77
78         video = xpath_element(video_xml, './/video', 'video', fatal=True)
79
80         formats = [{
81             'url': xpath_attr(video, '', 'url', 'video URL', fatal=True),
82         }]
83
84         like_count = int_or_none(video.get('ratingPlus'))
85         dislike_count = int_or_none(video.get('ratingMinus'))
86         age_limit = 18 if video.get('adult') == 'true' else 0
87
88         return {
89             'id': video_id,
90             'title': title,
91             'description': description,
92             'thumbnail': thumbnail,
93             'uploader': uploader,
94             'duration': duration,
95             'timestamp': timestamp,
96             'view_count': view_count,
97             'comment_count': comment_count,
98             'like_count': like_count,
99             'dislike_count': dislike_count,
100             'age_limit': age_limit,
101             'formats': formats,
102         }