aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/yandexmusic.py
blob: 6842f834f0c80578c5e1944f100d5dd054a4cef6 (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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
# coding: utf-8
from __future__ import unicode_literals

import re
import hashlib

from .common import InfoExtractor
from ..compat import (
    compat_str,
    compat_urllib_parse,
    compat_urllib_request,
)
from ..utils import (
    int_or_none,
    float_or_none,
)


class YandexMusicTrackIE(InfoExtractor):
    IE_NAME = 'yandexmusic:track'
    IE_DESC = 'Яндекс.Музыка - Трек'
    _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/album/(?P<album_id>\d+)/track/(?P<id>\d+)'

    _TEST = {
        'url': 'http://music.yandex.ru/album/540508/track/4878838',
        'md5': 'f496818aa2f60b6c0062980d2e00dc20',
        'info_dict': {
            'id': '4878838',
            'ext': 'mp3',
            'title': 'Carlo Ambrosio - Gypsy Eyes 1',
            'filesize': 4628061,
            'duration': 193.04,
        }
    }

    def _get_track_url(self, storage_dir, track_id):
        data = self._download_json(
            'http://music.yandex.ru/api/v1.5/handlers/api-jsonp.jsx?action=getTrackSrc&p=download-info/%s'
            % storage_dir,
            track_id, 'Downloading track location JSON')

        key = hashlib.md5(('XGRlBW9FXlekgbPrRHuSiA' + data['path'][1:] + data['s']).encode('utf-8')).hexdigest()
        storage = storage_dir.split('.')

        return ('http://%s/get-mp3/%s/%s?track-id=%s&from=service-10-track&similarities-experiment=default'
                % (data['host'], key, data['ts'] + data['path'], storage[1]))

    def _get_track_info(self, track):
        album = track['albums'][0]
        a_thumb = None

        if 'coverUri' in album:
            a_thumb = album['coverUri']
            if a_thumb:
                a_thumb = 'http://' + a_thumb.replace('%%', '1000x1000')

        return {
            'id': track['id'],
            'ext': 'mp3',
            'url': self._get_track_url(track['storageDir'], track['id']),
            'title': '%s - %s' % (track['artists'][0]['name'], track['title']),
            'filesize': int_or_none(track.get('fileSize')),
            'duration': float_or_none(track.get('durationMs'), 1000),
            'thumbnail': a_thumb,
        }

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        album_id, track_id = mobj.group('album_id'), mobj.group('id')

        track = self._download_json(
            'http://music.yandex.ru/handlers/track.jsx?track=%s:%s' % (track_id, album_id),
            track_id, 'Downloading track JSON')['track']

        return self._get_track_info(track)


class YandexMusicPlaylistBaseIE(InfoExtractor):
    def _build_playlist(self, tracks):
        return [
            self.url_result(
                'http://music.yandex.ru/album/%s/track/%s' % (track['albums'][0]['id'], track['id']))
            for track in tracks if track.get('albums') and isinstance(track.get('albums'), list)]


class YandexMusicAlbumIE(YandexMusicPlaylistBaseIE):
    IE_NAME = 'yandexmusic:album'
    IE_DESC = 'Яндекс.Музыка - Альбом'
    _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/album/(?P<id>\d+)/?(\?|$)'

    _TEST = {
        'url': 'http://music.yandex.ru/album/540508',
        'info_dict': {
            'id': '540508',
            'title': 'Carlo Ambrosio - Gypsy Soul (2009)',
        },
        'playlist_count': 50,
    }

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

        album = self._download_json(
            'http://music.yandex.ru/handlers/album.jsx?album=%s' % album_id,
            album_id, 'Downloading album JSON')

        entries = self._build_playlist(album['volumes'][0])

        title = '%s - %s' % (album['artists'][0]['name'], album['title'])
        year = album.get('year')
        if year:
            title += ' (%s)' % year

        return self.playlist_result(entries, compat_str(album['id']), title)


class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE):
    IE_NAME = 'yandexmusic:playlist'
    IE_DESC = 'Яндекс.Музыка - Плейлист'
    _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/users/[^/]+/playlists/(?P<id>\d+)'

    _TESTS = [{
        'url': 'http://music.yandex.ru/users/music.partners/playlists/1245',
        'info_dict': {
            'id': '1245',
            'title': 'Что слушают Enter Shikari',
            'description': 'md5:3b9f27b0efbe53f2ee1e844d07155cc9',
        },
        'playlist_count': 6,
    }, {
        # playlist exceeding the limit of 150 tracks shipped with webpage (see
        # https://github.com/rg3/youtube-dl/issues/6666)
        'url': 'https://music.yandex.ru/users/ya.playlist/playlists/1036',
        'info_dict': {
            'id': '1036',
            'title': 'Музыка 90-х',
        },
        'playlist_count': 310,
    }]

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

        webpage = self._download_webpage(url, playlist_id)

        mu = self._parse_json(
            self._search_regex(
                r'var\s+Mu\s*=\s*({.+?});\s*</script>', webpage, 'player'),
            playlist_id)

        playlist = mu['pageData']['playlist']
        tracks, track_ids = playlist['tracks'], playlist['trackIds']

        # tracks dictionary shipped with webpage is limited to 150 tracks,
        # missing tracks should be retrieved manually.
        if len(tracks) < len(track_ids):
            present_track_ids = set([compat_str(track['id']) for track in tracks if track.get('id')])
            missing_track_ids = set(map(compat_str, track_ids)) - set(present_track_ids)
            request = compat_urllib_request.Request(
                'https://music.yandex.ru/handlers/track-entries.jsx',
                compat_urllib_parse.urlencode({
                    'entries': ','.join(missing_track_ids),
                    'lang': mu.get('settings', {}).get('lang', 'en'),
                    'external-domain': 'music.yandex.ru',
                    'overembed': 'false',
                    'sign': mu.get('authData', {}).get('user', {}).get('sign'),
                    'strict': 'true',
                }).encode('utf-8'))
            request.add_header('Referer', url)
            request.add_header('X-Requested-With', 'XMLHttpRequest')

            missing_tracks = self._download_json(
                request, playlist_id, 'Downloading missing tracks JSON', fatal=False)
            if missing_tracks:
                tracks.extend(missing_tracks)

        return self.playlist_result(
            self._build_playlist(tracks),
            compat_str(playlist_id),
            playlist['title'], playlist.get('description'))