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
|
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
xpath_element,
xpath_text,
xpath_with_ns,
int_or_none,
ExtractorError
)
from ..compat import compat_urllib_parse_unquote
class XiamiBaseIE(InfoExtractor):
_XML_BASE_URL = 'http://www.xiami.com/song/playlist/id'
_NS_MAP = {'xm': 'http://xspf.org/ns/0/'}
def _extract_track(self, track):
artist = xpath_text(track, xpath_with_ns('xm:artist', self._NS_MAP), default='')
artist = artist.split(';')
ret = {
'id': xpath_text(track, xpath_with_ns('xm:song_id', self._NS_MAP)),
'title': xpath_text(track, xpath_with_ns('xm:title', self._NS_MAP)),
'album': xpath_text(track, xpath_with_ns('xm:album_name', self._NS_MAP)),
'artist': ';'.join(artist) if artist else None,
'creator': artist[0] if artist else None,
'url': self._decrypt(xpath_text(track, xpath_with_ns('xm:location', self._NS_MAP))),
'thumbnail': xpath_text(track, xpath_with_ns('xm:pic', self._NS_MAP), default=None),
'duration': int_or_none(xpath_text(track, xpath_with_ns('xm:length', self._NS_MAP))),
}
lyrics_url = xpath_text(track, xpath_with_ns('xm:lyric', self._NS_MAP))
if lyrics_url and lyrics_url.endswith('.lrc'):
ret['description'] = self._download_webpage(lyrics_url, ret['id'])
return ret
def _extract_xml(self, _id, typ=''):
playlist = self._download_xml('%s/%s%s' % (self._XML_BASE_URL, _id, typ), _id)
tracklist = xpath_element(playlist, xpath_with_ns('./xm:trackList', self._NS_MAP))
if not len(tracklist):
raise ExtractorError('No track found')
return [self._extract_track(track) for track in 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 XiamiIE(XiamiBaseIE):
IE_NAME = 'xiami:song'
IE_DESC = '虾米音乐'
_VALID_URL = r'http://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',
'creator': 'HONNE',
'album': 'Woman',
'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
'description': 'md5:052ec7de41ca19f67e7fd70a1bfc4e0b',
}
},
{
'url': 'http://www.xiami.com/song/1775256504',
'md5': '932a3abd45c6aa2b1fdbe028fcb4c4fc',
'info_dict': {
'id': '1775256504',
'ext': 'mp3',
'title': '悟空',
'creator': '戴荃',
'album': '悟空',
'description': 'md5:206e67e84f9bed1d473d04196a00b990',
}
},
]
def _real_extract(self, url):
_id = self._match_id(url)
return self._extract_xml(_id)[0]
class XiamiAlbumIE(XiamiBaseIE):
IE_NAME = 'xiami:album'
IE_DESC = '虾米音乐 - 专辑'
_VALID_URL = r'http://www\.xiami\.com/album/(?P<id>[0-9]+)'
_TESTS = [
{
'url': 'http://www.xiami.com/album/2100300444',
'info_dict': {
'id': '2100300444',
},
'playlist_count': 10,
},
{
'url': 'http://www.xiami.com/album/512288?spm=a1z1s.6843761.1110925389.6.hhE9p9',
'only_matching': True,
}
]
def _real_extract(self, url):
_id = self._match_id(url)
return self.playlist_result(self._extract_xml(_id, '/type/1'), _id)
class XiamiArtistIE(XiamiBaseIE):
IE_NAME = 'xiami:artist'
IE_DESC = '虾米音乐 - 歌手'
_VALID_URL = r'http://www\.xiami\.com/artist/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.xiami.com/artist/2132?spm=0.0.0.0.dKaScp',
'info_dict': {
'id': '2132',
},
'playlist_count': 20,
}
def _real_extract(self, url):
_id = self._match_id(url)
return self.playlist_result(self._extract_xml(_id, '/type/2'), _id)
class XiamiCollectionIE(XiamiBaseIE):
IE_NAME = 'xiami:collection'
IE_DESC = '虾米音乐 - 精选集'
_VALID_URL = r'http://www\.xiami\.com/collect/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.xiami.com/collect/156527391?spm=a1z1s.2943601.6856193.12.4jpBnr',
'info_dict': {
'id': '156527391',
},
'playlist_count': 26,
}
def _real_extract(self, url):
_id = self._match_id(url)
return self.playlist_result(self._extract_xml(_id, '/type/3'), _id)
|
