python中使用百度音乐搜索的api下载指定歌曲的lrc歌词

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('(.*?)',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)+"//m.sbmmt.com/m/"+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