Merge pull request #9367 from codesparkle/master
[youtube-dl] / youtube_dl / extractor / xiami.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..compat import compat_urllib_parse_unquote
6 from ..utils import int_or_none
7
8
9 class XiamiBaseIE(InfoExtractor):
10     _API_BASE_URL = 'http://www.xiami.com/song/playlist/cat/json/id'
11
12     def _download_webpage(self, *args, **kwargs):
13         webpage = super(XiamiBaseIE, self)._download_webpage(*args, **kwargs)
14         if '>Xiami is currently not available in your country.<' in webpage:
15             self.raise_geo_restricted('Xiami is currently not available in your country')
16
17     def _extract_track(self, track, track_id=None):
18         title = track['title']
19         track_url = self._decrypt(track['location'])
20
21         subtitles = {}
22         lyrics_url = track.get('lyric_url') or track.get('lyric')
23         if lyrics_url and lyrics_url.startswith('http'):
24             subtitles['origin'] = [{'url': lyrics_url}]
25
26         return {
27             'id': track.get('song_id') or track_id,
28             'url': track_url,
29             'title': title,
30             'thumbnail': track.get('pic') or track.get('album_pic'),
31             'duration': int_or_none(track.get('length')),
32             'creator': track.get('artist', '').split(';')[0],
33             'track': title,
34             'album': track.get('album_name'),
35             'artist': track.get('artist'),
36             'subtitles': subtitles,
37         }
38
39     def _extract_tracks(self, item_id, typ=None):
40         playlist = self._download_json(
41             '%s/%s%s' % (self._API_BASE_URL, item_id, '/type/%s' % typ if typ else ''), item_id)
42         return [
43             self._extract_track(track, item_id)
44             for track in playlist['data']['trackList']]
45
46     @staticmethod
47     def _decrypt(origin):
48         n = int(origin[0])
49         origin = origin[1:]
50         short_lenth = len(origin) // n
51         long_num = len(origin) - short_lenth * n
52         l = tuple()
53         for i in range(0, n):
54             length = short_lenth
55             if i < long_num:
56                 length += 1
57             l += (origin[0:length], )
58             origin = origin[length:]
59         ans = ''
60         for i in range(0, short_lenth + 1):
61             for j in range(0, n):
62                 if len(l[j]) > i:
63                     ans += l[j][i]
64         return compat_urllib_parse_unquote(ans).replace('^', '0')
65
66
67 class XiamiSongIE(XiamiBaseIE):
68     IE_NAME = 'xiami:song'
69     IE_DESC = '虾米音乐'
70     _VALID_URL = r'https?://(?:www\.)?xiami\.com/song/(?P<id>[0-9]+)'
71     _TESTS = [{
72         'url': 'http://www.xiami.com/song/1775610518',
73         'md5': '521dd6bea40fd5c9c69f913c232cb57e',
74         'info_dict': {
75             'id': '1775610518',
76             'ext': 'mp3',
77             'title': 'Woman',
78             'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
79             'duration': 265,
80             'creator': 'HONNE',
81             'track': 'Woman',
82             'album': 'Woman',
83             'artist': 'HONNE',
84             'subtitles': {
85                 'origin': [{
86                     'ext': 'lrc',
87                 }],
88             },
89         },
90         'skip': 'Georestricted',
91     }, {
92         'url': 'http://www.xiami.com/song/1775256504',
93         'md5': '932a3abd45c6aa2b1fdbe028fcb4c4fc',
94         'info_dict': {
95             'id': '1775256504',
96             'ext': 'mp3',
97             'title': '悟空',
98             'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
99             'duration': 200,
100             'creator': '戴荃',
101             'track': '悟空',
102             'album': '悟空',
103             'artist': '戴荃',
104             'subtitles': {
105                 'origin': [{
106                     'ext': 'lrc',
107                 }],
108             },
109         },
110         'skip': 'Georestricted',
111     }]
112
113     def _real_extract(self, url):
114         return self._extract_tracks(self._match_id(url))[0]
115
116
117 class XiamiPlaylistBaseIE(XiamiBaseIE):
118     def _real_extract(self, url):
119         item_id = self._match_id(url)
120         return self.playlist_result(self._extract_tracks(item_id, self._TYPE), item_id)
121
122
123 class XiamiAlbumIE(XiamiPlaylistBaseIE):
124     IE_NAME = 'xiami:album'
125     IE_DESC = '虾米音乐 - 专辑'
126     _VALID_URL = r'https?://(?:www\.)?xiami\.com/album/(?P<id>[0-9]+)'
127     _TYPE = '1'
128     _TESTS = [{
129         'url': 'http://www.xiami.com/album/2100300444',
130         'info_dict': {
131             'id': '2100300444',
132         },
133         'playlist_count': 10,
134         'skip': 'Georestricted',
135     }, {
136         'url': 'http://www.xiami.com/album/512288?spm=a1z1s.6843761.1110925389.6.hhE9p9',
137         'only_matching': True,
138     }]
139
140
141 class XiamiArtistIE(XiamiPlaylistBaseIE):
142     IE_NAME = 'xiami:artist'
143     IE_DESC = '虾米音乐 - 歌手'
144     _VALID_URL = r'https?://(?:www\.)?xiami\.com/artist/(?P<id>[0-9]+)'
145     _TYPE = '2'
146     _TEST = {
147         'url': 'http://www.xiami.com/artist/2132?spm=0.0.0.0.dKaScp',
148         'info_dict': {
149             'id': '2132',
150         },
151         'playlist_count': 20,
152         'skip': 'Georestricted',
153     }
154
155
156 class XiamiCollectionIE(XiamiPlaylistBaseIE):
157     IE_NAME = 'xiami:collection'
158     IE_DESC = '虾米音乐 - 精选集'
159     _VALID_URL = r'https?://(?:www\.)?xiami\.com/collect/(?P<id>[0-9]+)'
160     _TYPE = '3'
161     _TEST = {
162         'url': 'http://www.xiami.com/collect/156527391?spm=a1z1s.2943601.6856193.12.4jpBnr',
163         'info_dict': {
164             'id': '156527391',
165         },
166         'playlist_mincount': 29,
167         'skip': 'Georestricted',
168     }