1 # -*- coding: UTF-8 -*-
2
3 # Created on 2012-11-21
4
5
6
7 #下载百度音乐
8 import urllib
9 import re
10
11 baseurl = "http://music.baidu.com"
12 url = "http://music.baidu.com/search/tag?key=经典流行"
13 html = urllib.urlopen(url).read()
14 uri = re.findall(r'/song/\d+', html, re.M)
15 #print uri
16 lst = []
17 for i in uri:
18 link = baseurl+i+"/download"
19 # print link
20 lst.insert(0, link) #构造lst列表数据
21 print lst
22 for k in lst:
23 res = urllib.urlopen(k).read()
24 #print res
25 down = re.search('http://[^ ]*xcode.[a-z0-9]*' , res, re.M).group()
26 print 'down'
27 print down
28 #res2 = r"c:\1.html"
29 #s1 = re.findall('title=".*',res, re.M)
30 s1 = re.search('title=".*',res, re.M).group()
31 print s1
32
33 s2 = re.search('>.*<.a', s1, re.M).group()
34 print s2
35 s3 = s2[1:-3]
36 print s3
37 s3=unicode(s3,"utf-8","ignore").encode("gb2312","ignore")#解决乱码
38 urllib.urlretrieve(down, s3+".mp3")
