aboutsummaryrefslogtreecommitdiffhomepage
path: root/youtube_dl/extractor/xiami.py
blob: 86abef25704bbc9e8a1494ecc2146b5c5bfabe32 (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
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote
from ..utils import int_or_none


class XiamiBaseIE(InfoExtractor):
    _API_BASE_URL = 'http://www.xiami.com/song/playlist/cat/json/id'

    def _download_webpage(self, *args, **kwargs):
        webpage = super(XiamiBaseIE, self)._download_webpage(*args, **kwargs)
        if '>Xiami is currently not available in your country.<' in webpage:
            self.raise_geo_restricted('Xiami is currently not available in your country')
        return webpage

    def _extract_track(self, track, track_id=None):
        title = track['title']
        track_url = self._decrypt(track['location'])

        subtitles = {}
        lyrics_url = track.get('lyric_url') or track.get('lyric')
        if lyrics_url and lyrics_url.startswith('http'):
            subtitles['origin'] = [{'url': lyrics_url}]

        return {
            'id': track.get('song_id') or track_id,
            'url': track_url,
            'title': title,
            'thumbnail': track.get('pic') or track.get('album_pic'),
            'duration': int_or_none(track.get('length')),
            'creator': track.get('artist', '').split(';')[0],
            'track': title,
            'album': track.get('album_name'),
            'artist': track.get('artist'),
            'subtitles': subtitles,
        }

    def _extract_tracks(self, item_id, typ=None):
        playlist = self._download_json(
            '%s/%s%s' % (self._API_BASE_URL, item_id, '/type/%s' % typ if typ else ''), item_id)
        return [
            self._extract_track(track, item_id)
            for track in playlist['data']['trackList']]

    @staticmethod
    def _decrypt(origin):
        n = int(origin[0])
        origin = origin[1:]
        short_lenth = len(origin) // n
        long_num = len(origin) - short_lenth * n
        l = tuple()
        for i in range(0, n):
            length = short_lenth
            if i < long_num:
                length += 1
            l += (origin[0:length], )
            origin = origin[length:]
        ans = ''
        for i in range(0, short_lenth + 1):
            for j in range(0, n):
                if len(l[j]) > i:
                    ans += l[j][i]
        return compat_urllib_parse_unquote(ans).replace('^', '0')


class XiamiSongIE(XiamiBaseIE):
    IE_NAME = 'xiami:song'
    IE_DESC = '虾米音乐'
    _VALID_URL = r'https?://(?:www\.)?xiami\.com/song/(?P<id>[0-9]+)'
    _TESTS = [{
        'url': 'http://www.xiami.com/song/1775610518',
        'md5': '521dd6bea40fd5c9c69f913c232cb57e',
        'info_dict': {
            'id': '1775610518',
            'ext': 'mp3',
            'title': 'Woman',
            'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
            'duration': 265,
            'creator': 'HONNE',
            'track': 'Woman',
            'album': 'Woman',
            'artist': 'HONNE',
            'subtitles': {
                'origin': [{
                    'ext': 'lrc',
                }],
            },
        },
        'skip': 'Georestricted',
    }, {
        'url': 'http://www.xiami.com/song/1775256504',
        'md5': '932a3abd45c6aa2b1fdbe028fcb4c4fc',
        'info_dict': {
            'id': '1775256504',
            'ext': 'mp3',
            'title': '悟空',
            'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
            'duration': 200,
            'creator': '戴荃',
            'track': '悟空',
            'album': '悟空',
            'artist': '戴荃',
            'subtitles': {
                'origin': [{
                    'ext': 'lrc',
                }],
            },
        },
        'skip': 'Georestricted',
    }]

    def _real_extract(self, url):
        return self._extract_tracks(self._match_id(url))[0]


class XiamiPlaylistBaseIE(XiamiBaseIE):
    def _real_extract(self, url):
        item_id = self._match_id(url)
        return self.playlist_result(self._extract_tracks(item_id, self._TYPE), item_id)


class XiamiAlbumIE(XiamiPlaylistBaseIE):
    IE_NAME = 'xiami:album'
    IE_DESC = '虾米音乐 - 专辑'
    _VALID_URL = r'https?://(?:www\.)?xiami\.com/album/(?P<id>[0-9]+)'
    _TYPE = '1'
    _TESTS = [{
        'url': 'http://www.xiami.com/album/2100300444',
        'info_dict': {
            'id': '2100300444',
        },
        'playlist_count': 10,
        'skip': 'Georestricted',
    }, {
        'url': 'http://www.xiami.com/album/512288?spm=a1z1s.6843761.1110925389.6.hhE9p9',
        'only_matching': True,
    }]


class XiamiArtistIE(XiamiPlaylistBaseIE):
    IE_NAME = 'xiami:artist'
    IE_DESC = '虾米音乐 - 歌手'
    _VALID_URL = r'https?://(?:www\.)?xiami\.com/artist/(?P<id>[0-9]+)'
    _TYPE = '2'
    _TEST = {
        'url': 'http://www.xiami.com/artist/2132?spm=0.0.0.0.dKaScp',
        'info_dict': {
            'id': '2132',
        },
        'playlist_count': 20,
        'skip': 'Georestricted',
    }


class XiamiCollectionIE(XiamiPlaylistBaseIE):
    IE_NAME = 'xiami:collection'
    IE_DESC = '虾米音乐 - 精选集'
    _VALID_URL = r'https?://(?:www\.)?xiami\.com/collect/(?P<id>[0-9]+)'
    _TYPE = '3'
    _TEST = {
        'url': 'http://www.xiami.com/collect/156527391?spm=a1z1s.2943601.6856193.12.4jpBnr',
        'info_dict': {
            'id': '156527391',
        },
        'playlist_mincount': 29,
        'skip': 'Georestricted',
    }