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
http://box.zhangmen.baidu.com/x"htmlcode">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"htmlcode">http://zhangmenshiting.baidu.com/data2/music/12762845/YmRqamdua21fn6NndK6ap5WXcJlrmG1xlJhobWibmGpjk5ZtmWiZcWRjZ5lqbGyelGKWlZtubGljZ5lka2uanWSXY1qin5t1YWBmZW5ocGlhaWdnbGtqbzE$12762845.mp3"htmlcode">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"+b+"$$"+a+"$$$$ " the_file.write(song_url+'\n') page = urllib2.urlopen(song_url).read() print page theid = 0 lrcid = re.compile('<lrcid>(.*"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。。。只能说明还是学艺不精呢
原文：逝去日子的博客 » 使用python扫描本地音乐并下载歌词