python 網頁抓取（使用代理服務器），解析一例

#coding:utf-8
'''
Created on 2009-7-15

@author: Administrator
'''
import urllib2
import newhttplib
import lxml.html as x  

def getmusic(num,soc=None):
    s=num.split(':')
    s[0]=s[0].strip()
    s[1]=s[1].strip()
    s[2]=s[2].strip()
    h1 = newhttplib.HTTPConnection('10.0.0.172',80)
    h1.auto_open = 0
    h1.connect(soc)
    url='http://218.200.160.29/s3/i/app/search/musicResult.jsp?qd=1956&CH=12530-wap-lslb&v=1864&tplpath=/s3/i/qrc/&type=all&keyword='+urllib2.quote(s[0]+" "+s[1]) 
    h1.request("GET",url) 
    r1 = h1.getresponse()
    content=r1.read()
    doc=x.document_fromstring(content)  
    alist=doc.xpath("//a")
    print s[0],s[1]
    for a in alist:
        c1= a.text_content()
        try:
            if c1.find(s[0])>=0 and c1.find(s[1])>=0:
                print c1
                print c1.find(s[0]),c1.find(s[1])
                nexturl='http://218.200.160.29'+a.get('href') 
                h1.request("GET",nexturl) 
                r1 = h1.getresponse()
                content=r1.read()
                print content
                doc=x.document_fromstring(content)  
                blist=doc.xpath("//a")
                for b in blist:
                    bcontent=b.text_content()
                    if bcontent.find('高潮版')>=0 or bcontent.find('超長版')>=0:
                         print bcontent
                         bhref= b.get('href')
                         nnexturl='http://218.200.160.29'+bhref
                         h1.request("GET",nnexturl) 
                         r1 = h1.getresponse()
                         ccontent=r1.read()
                         #print ccontent
                         doc=x.document_fromstring(ccontent)  
                         clist=doc.xpath("//a")
                         for c in clist:
                             chref=c.get('href')
                             if chref.find('218.200.160.10')>=0:
                                 print chref
                                 sb2=s[2][11:]
                                 print sb2
                                 if chref.find(sb2)>=0:
                                     print u'找到匹配歌曲開始下載。。。'
                                     h1.request("GET",chref) 
                                     r1 = h1.getresponse()
                                     print r1.status
                                     dcontent=r1.read()
                                     f=open('./test.mp3','wb')
                                     f.write(dcontent)
                                     f.close()
        except BaseException,e:
            print e

if __name__ == '__main__':
    getmusic('相信:曾建軍:600902000005714466')