Merge branch 'master' of https://github.com/DarkstaIkers/youtube-dl into DarkstaIkers...
[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         return webpage
17
18     def _extract_track(self, track, track_id=None):
19         title = track['title']
20         track_url = self._decrypt(track['location'])
21
22         subtitles = {}
23         lyrics_url = track.get('lyric_url') or track.get('lyric')
24         if lyrics_url and lyrics_url.startswith('http'):
25             subtitles['origin'] = [{'url': lyrics_url}]
26
27         return {
28             'id': track.get('song_id') or track_id,
29             'url': track_url,
30             'title': title,
31             'thumbnail': track.get('pic') or track.get('album_pic'),
32             'duration': int_or_none(track.get('length')),
33             'creator': track.get('artist', '').split(';')[0],
34             'track': title,
35             'album': track.get('album_name'),
36             'artist': track.get('artist'),
37             'subtitles': subtitles,
38         }
39
40     def _extract_tracks(self, item_id, typ=None):
41         playlist = self._download_json(
42             '%s/%s%s' % (self._API_BASE_URL, item_id, '/type/%s' % typ if typ else ''), item_id)
43         return [
44             self._extract_track(track, item_id)
45             for track in playlist['data']['trackList']]
46
47     @staticmethod
48     def _decrypt(origin):
49         n = int(origin[0])
50         origin = origin[1:]
51         short_lenth = len(origin) // n
52         long_num = len(origin) - short_lenth * n
53         l = tuple()
54         for i in range(0, n):
55             length = short_lenth
56             if i < long_num:
57                 length += 1
58             l += (origin[0:length], )
59             origin = origin[length:]
60         ans = ''
61         for i in range(0, short_lenth + 1):
62             for j in range(0, n):
63                 if len(l[j]) > i:
64                     ans += l[j][i]
65         return compat_urllib_parse_unquote(ans).replace('^', '0')
66
67
68 class XiamiSongIE(XiamiBaseIE):
69     IE_NAME = 'xiami:song'
70     IE_DESC = '虾米音乐'
71     _VALID_URL = r'https?://(?:www\.)?xiami\.com/song/(?P<id>[0-9]+)'
72     _TESTS = [{
73         'url': 'http://www.xiami.com/song/1775610518',
74         'md5': '521dd6bea40fd5c9c69f913c232cb57e',
75         'info_dict': {
76             'id': '1775610518',
77             'ext': 'mp3',
78             'title': 'Woman',
79             'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
80             'duration': 265,
81             'creator': 'HONNE',
82             'track': 'Woman',
83             'album': 'Woman',
84             'artist': 'HONNE',
85             'subtitles': {
86                 'origin': [{
87                     'ext': 'lrc',
88                 }],
89             },
90         },
91         'skip': 'Georestricted',
92     }, {
93         'url': 'http://www.xiami.com/song/1775256504',
94         'md5': '932a3abd45c6aa2b1fdbe028fcb4c4fc',
95         'info_dict': {
96             'id': '1775256504',
97             'ext': 'mp3',
98             'title': '悟空',
99             'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
100             'duration': 200,
101             'creator': '戴荃',
102             'track': '悟空',
103             'album': '悟空',
104             'artist': '戴荃',
105             'subtitles': {
106                 'origin': [{
107                     'ext': 'lrc',
108                 }],
109             },
110         },
111         'skip': 'Georestricted',
112     }]
113
114     def _real_extract(self, url):
115         return self._extract_tracks(self._match_id(url))[0]
116
117
118 class XiamiPlaylistBaseIE(XiamiBaseIE):
119     def _real_extract(self, url):
120         item_id = self._match_id(url)
121         return self.playlist_result(self._extract_tracks(item_id, self._TYPE), item_id)
122
123
124 class XiamiAlbumIE(XiamiPlaylistBaseIE):
125     IE_NAME = 'xiami:album'
126     IE_DESC = '虾米音乐 - 专辑'
127     _VALID_URL = r'https?://(?:www\.)?xiami\.com/album/(?P<id>[0-9]+)'
128     _TYPE = '1'
129     _TESTS = [{
130         'url': 'http://www.xiami.com/album/2100300444',
131         'info_dict': {
132             'id': '2100300444',
133         },
134         'playlist_count': 10,
135         'skip': 'Georestricted',
136     }, {
137         'url': 'http://www.xiami.com/album/512288?spm=a1z1s.6843761.1110925389.6.hhE9p9',
138         'only_matching': True,
139     }]
140
141
142 class XiamiArtistIE(XiamiPlaylistBaseIE):
143     IE_NAME = 'xiami:artist'
144     IE_DESC = '虾米音乐 - 歌手'
145     _VALID_URL = r'https?://(?:www\.)?xiami\.com/artist/(?P<id>[0-9]+)'
146     _TYPE = '2'
147     _TEST = {
148         'url': 'http://www.xiami.com/artist/2132?spm=0.0.0.0.dKaScp',
149         'info_dict': {
150             'id': '2132',
151         },
152         'playlist_count': 20,
153         'skip': 'Georestricted',
154     }
155
156
157 class XiamiCollectionIE(XiamiPlaylistBaseIE):
158     IE_NAME = 'xiami:collection'
159     IE_DESC = '虾米音乐 - 精选集'
160     _VALID_URL = r'https?://(?:www\.)?xiami\.com/collect/(?P<id>[0-9]+)'
161     _TYPE = '3'
162     _TEST = {
163         'url': 'http://www.xiami.com/collect/156527391?spm=a1z1s.2943601.6856193.12.4jpBnr',
164         'info_dict': {
165             'id': '156527391',
166         },
167         'playlist_mincount': 29,
168         'skip': 'Georestricted',
169     }