使用python扫描本地音乐并下载歌词
这次这个真的是干货哦,昨晚弄了半晚上,,,,从8点吃完饭就开始写,一直到了快12点才弄好,,,新手,伤不起呀。。。。
先简单的说下吧,百度提供了一个音乐搜索的api,你想百度请求类似于
1
|
http://box.zhangmen.baidu.com/x?op=12&count=1&title=最佳损友$$陈奕迅$$$$ |
的地址,百度会给你返回一段xml,如下所示
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
|
This XML file does not appear to have any style information associated with it. The document tree is shown below. < result > < count >1</ count > < url > < encode > <![CDATA[ http://zhangmenshiting.baidu.com/data2/music/12762845/YmRqamdua21fn6NndK6ap5WXcJlrmG1xlJhobWibmGpjk5ZtmWiZcWRjZ5lqbGyelGKWlZtubGljZ5lka2uanWSXY1qin5t1YWBmZW5ocGlhaWdnbGtqbzE$ ]]> </ encode > < decode > <![CDATA[ 12762845.mp3?xcode=e6b69cf593ea22ac9d2b9314e565fc0caf85125f065ce3e0&mid=0.31929107437537 ]]> </ decode > < type >8</ type > < lrcid >2829</ lrcid > < flag >1</ flag > </ url > < durl > < encode > <![CDATA[ http://zhangmenshiting2.baidu.com/data2/music/7345405/aGVnaWlmbGaeomZzrZmmnJZvmGqXbHCbl2dsZ5qXaWqSlWpsmmdrb2mXamxpbXCclGNsmW2ba25mYmxtapmZcWqTWaGemnRoX2VkbWdvaGhoZmZramluOA$$ ]]> </ encode > < decode > <![CDATA[ 7345405.mp3?xcode=e6b69cf593ea22ac78e1478e78479dc19e8e4650995cb99a&mid=0.31929107437537 ]]> </ decode > < type >8</ type > < lrcid >2829</ lrcid > < flag >1</ flag > </ durl > < p2p > < hash >f98b6772aa97966550ec80617879becee0233bf4</ hash > < url > <![CDATA[ ]]> </ url > < type >mp3</ type > < size >3778335</ size > < bitrate >128</ bitrate > </ p2p > </ result > |
简单的说明下,由于我们要做的只是获取到歌曲的lrc歌词地址,所以有用的只有2829这个标签。
而encode和decode里面的拼接起来就是mp3的下载地址,如本例的
1
|
http://zhangmenshiting.baidu.com/data2/music/12762845/YmRqamdua21fn6NndK6ap5WXcJlrmG1xlJhobWibmGpjk5ZtmWiZcWRjZ5lqbGyelGKWlZtubGljZ5lka2uanWSXY1qin5t1YWBmZW5ocGlhaWdnbGtqbzE$12762845.mp3?xcode=e6b69cf593ea22ac9d2b9314e565fc0caf85125f065ce3e0&mid=0.31929107437537 |
就是下载地址,不过音质太差,有时间在研究下这个。
继续说歌词,注意lrcid标签里面的2829
http://box.zhangmen.baidu.com/bdlrc/ 这个是百度lrc歌词存放地址,
然后本例的歌词地址是http://box.zhangmen.baidu.com/bdlrc/28/2829.lrc
看到了吧,歌词地址后面的两个数字的计算方法是在lrcid除以100所获得的整数,就是第一个数字,然后第二个数字就是lrcid,然后后面加上后缀.lrc就搞定了
获得lrc地址之后就简单了,只要请求该地址,然后将获取到的内容写入文件就ok了。
好了,大概就是这样,下面是代码
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
|
import os import os.path import re import eyed3 import urllib2 import urllib from urllib import urlencode import sys import os reload (sys) sys.setdefaultencoding( 'utf8' ) music_path = r "E:\music" lrc_path = r "e:\lrc" os.remove( 'nolrc.txt' ) os.remove( 'lrcxml.txt' ) the_file = open ( 'lrcxml.txt' , 'a' ) nolrc_file = open ( 'nolrc.txt' , 'a' ) for root,dirs,files in os.walk(music_path): for filepath in files: the_path = os.path.join(root,filepath) if (the_path.find( "mp3" ) ! = - 1 ): print the_path the_music = eyed3.load(the_path) the_teg = the_music.tag._getAlbum() the_artist = the_music.tag._getArtist() the_title = the_music.tag._getTitle() # print the_teg # print the_title # print the_artist b = the_title.replace( ' ' , '+' ) # print b a = the_artist.replace( ' ' , '+' ) #print urlencode(str(b)) if isinstance (a, unicode ): a = a.encode( 'utf8' ) song_url = "http://box.zhangmen.baidu.com/x?op=12&count=1&title=" + b + "$$" + a + "$$$$ " the_file.write(song_url + '\n' ) page = urllib2.urlopen(song_url).read() print page theid = 0 lrcid = re. compile ( '<lrcid>(.*?)</lrcid>' ,re.S).findall(page) have_lrc = True if lrcid ! = []: theid = lrcid[ 0 ] else : nolrc_file.write(the_title + '\n' ) have_lrc = False print theid if have_lrc: firstid = int (theid) / 100 lrcurl = "http://box.zhangmen.baidu.com/bdlrc/" + str (firstid) + "/" + theid + ".lrc" print lrcurl lrc = urllib2.urlopen(lrcurl).read() if (lrc.find( 'html' ) = = - 1 ): lrcfile = open (lrc_path + "\\"+the_title+" .lrc", 'w' ) lrcfile.writelines(lrc) lrcfile.close() else : nolrc_file.write(the_title + '\n' ) the_file.close() nolrc_file.close() print "end!" |
有用第一步请求所获取到底是xml格式的,所以本来想着解析xml来获取lrcid,但是在实现过程中遇到了各种问题,别的还容易,就在这一块儿浪费的时间最长,纠结未果之后,只能改用正则表达式来获取了。。。
使用python将歌词嵌入歌曲中
以前一直用的是Google Play Music来作为手机的音乐播放器,可是现在谷歌被墙的这么厉害的,从PC上传到Google Play的音乐在手机上面同步下来的话特麻烦,索性放弃之买了大名鼎鼎的Poweramp播放器,开始使用之后瞬间就被Poweramp强大的功能所吸引住了,不愧是安卓端的音乐播放器的王者!唯美的锁屏界面,强大的均衡器功能等等。唯一美中不足的就是歌词.如果要显示歌词的话必须安装第三方软件,或者是把歌词嵌入到音乐中。所以昨天下班之后就开始研究,所幸最后终于搞定了,先上下效果图
可以看到,效果还是很不错的呢。
好了,废话不多说,下面上程序
首先,必须安装eyed3模块,还有,我所有的歌词都在E:\lrc这个路径中的
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
|
import threading import time import datetime import re import os import eyed3 import sys reload (sys) sys.setdefaultencoding( 'utf8' ) def getstr(i): if i < 10 : return "0" + str (i) else : return str (i) musicpath = r 'I:\music' lrcpath = r 'E:\lrc' def deallrc( str ): mystr = re.sub(r '\[\d\d:\d\d.\d\d\]' ,'', str ) mystr.replace( '\n' ,'') return mystr def checklrcfile(path,timespan): file = open (path, 'r' ) mylrcstr = '' #print timespan for line in file .readlines( 100 ): #errorlog(line) if line.find(timespan)> 0 : return deallrc(line) else : continue return '' def getlrcstr(lrc): mylrcstr = '' #print lrc for i in range ( 00 , 05 ): for j in range ( 00 , 59 ): for k in range ( 00 , 99 ): timespan = getstr(i) + ":" + getstr(j) + "." + getstr(k) mylrcstr + = checklrcfile(lrc, timespan) #print timespan return mylrcstr def getlrc(musicname): musicname = u''.join(musicname) musicname = musicname.encode( 'gb2312' ) for root,dirs,files in os.walk(lrcpath): for filepath in files: the_path = os.path.join(root,filepath) if (the_path.find(musicname) ! = - 1 ): print the_path return the_path def errorlog(path): file = open (r 'e:\nolrc.txt' , 'a' ) if path is None : path = '' path = path + '\n' file .write(path) file .close() def writetag(themusic,lrcstr): music = eyed3.load(themusic) lrcstr = lrcstr.decode( 'utf8' ) lrcstr = u''.join(lrcstr) #lrcstr=unicode(lrcstr) music.tag.lyrics. set (lrcstr) music.tag.save() def dealmusic(path): print path the_music = eyed3.load(path) the_teg = the_music.tag._getAlbum() the_artist = the_music.tag._getArtist() the_title = the_music.tag._getTitle() #print the_title try : lrc = getlrc(the_title) lrcstr = getlrcstr(lrc) writetag(path, lrcstr) except : errorlog(path) class writelrc(threading.Thread): def __init__( self ,the_path): threading.Thread.__init__( self ) self .thepath = the_path def run( self ): dealmusic( self .thepath) if __name__ = = '__main__' : count = 0 threads = [] for root,dirs,files in os.walk(musicpath): for filepath in files: the_path = os.path.join(root,filepath) if (the_path.find( "mp3" ) ! = - 1 ): count + = 1 threads.append(writelrc(the_path)) if count % 10 = = 0 : for t in threads: t.start() for t in threads: t.join() threads = [] |
好了,大概就是这样,大家有什么问题可以直接提出来,我会尽快回复的。