aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/odnoklassniki.py
blob: 184c7a323afad57f77e8d9b8c7402e68c721e705 (plain)
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
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote
from ..utils import (
    ExtractorError,
    unified_strdate,
    int_or_none,
    qualities,
    unescapeHTML,
)


class OdnoklassnikiIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?(?:odnoklassniki|ok)\.ru/(?:video(?:embed)?|web-api/video/moviePlayer)/(?P<id>[\d-]+)'
    _TESTS = [{
        # metadata in JSON
        'url': 'http://ok.ru/video/20079905452',
        'md5': '6ba728d85d60aa2e6dd37c9e70fdc6bc',
        'info_dict': {
            'id': '20079905452',
            'ext': 'mp4',
            'title': 'Культура меняет нас (прекрасный ролик!))',
            'duration': 100,
            'upload_date': '20141207',
            'uploader_id': '330537914540',
            'uploader': 'Виталий Добровольский',
            'like_count': int,
            'age_limit': 0,
        },
        'skip': 'Video has been blocked',
    }, {
        # metadataUrl
        'url': 'http://ok.ru/video/63567059965189-0',
        'md5': '9676cf86eff5391d35dea675d224e131',
        'info_dict': {
            'id': '63567059965189-0',
            'ext': 'mp4',
            'title': 'Девушка без комплексов ...',
            'duration': 191,
            'upload_date': '20150518',
            'uploader_id': '534380003155',
            'uploader': '☭ Андрей Мещанинов ☭',
            'like_count': int,
            'age_limit': 0,
        },
    }, {
        # YouTube embed (metadataUrl, provider == USER_YOUTUBE)
        'url': 'http://ok.ru/video/64211978996595-1',
        'md5': '5d7475d428845cd2e13bae6f1a992278',
        'info_dict': {
            'id': '64211978996595-1',
            'ext': 'mp4',
            'title': 'Космическая среда от 26 августа 2015',
            'description': 'md5:848eb8b85e5e3471a3a803dae1343ed0',
            'duration': 440,
            'upload_date': '20150826',
            'uploader_id': '750099571',
            'uploader': 'Алина П',
            'age_limit': 0,
        },
    }, {
        'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
        'only_matching': True,
    }, {
        'url': 'http://www.ok.ru/video/20648036891',
        'only_matching': True,
    }, {
        'url': 'http://www.ok.ru/videoembed/20648036891',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)

        webpage = self._download_webpage(
            'http://ok.ru/video/%s' % video_id, video_id)

        error = self._search_regex(
            r'[^>]+class="vp_video_stub_txt"[^>]*>([^<]+)<',
            webpage, 'error', default=None)
        if error:
            raise ExtractorError(error, expected=True)

        player = self._parse_json(
            unescapeHTML(self._search_regex(
                r'data-options=(?P<quote>["\'])(?P<player>{.+?%s.+?})(?P=quote)' % video_id,
                webpage, 'player', group='player')),
            video_id)

        flashvars = player['flashvars']

        metadata = flashvars.get('metadata')
        if metadata:
            metadata = self._parse_json(metadata, video_id)
        else:
            metadata = self._download_json(
                compat_urllib_parse_unquote(flashvars['metadataUrl']),
                video_id, 'Downloading metadata JSON')

        movie = metadata['movie']
        title = movie['title']
        thumbnail = movie.get('poster')
        duration = int_or_none(movie.get('duration'))

        author = metadata.get('author', {})
        uploader_id = author.get('id')
        uploader = author.get('name')

        upload_date = unified_strdate(self._html_search_meta(
            'ya:ovs:upload_date', webpage, 'upload date', default=None))

        age_limit = None
        adult = self._html_search_meta(
            'ya:ovs:adult', webpage, 'age limit', default=None)
        if adult:
            age_limit = 18 if adult == 'true' else 0

        like_count = int_or_none(metadata.get('likeCount'))

        info = {
            'id': video_id,
            'title': title,
            'thumbnail': thumbnail,
            'duration': duration,
            'upload_date': upload_date,
            'uploader': uploader,
            'uploader_id': uploader_id,
            'like_count': like_count,
            'age_limit': age_limit,
        }

        if metadata.get('provider') == 'USER_YOUTUBE':
            info.update({
                '_type': 'url_transparent',
                'url': movie['contentId'],
            })
            return info

        quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd'))

        formats = [{
            'url': f['url'],
            'ext': 'mp4',
            'format_id': f['name'],
            'quality': quality(f['name']),
        } for f in metadata['videos']]
        self._sort_formats(formats)

        info['formats'] = formats
        return info