sousou搜索 用python抓取

def sousousearch(request,url):
    import re
    from urllib import FancyURLopener
    from random import choice

   #模拟随即浏览器
    user_agents = [
        'Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11',
        'Opera/9.25 (Windows NT 5.1; U; en)',
        'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)',
        'Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)',
        'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12',
        'Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9'
    ]
    class MyOpener(FancyURLopener, object):
        version = choice(user_agents)
    def MyFunc(url):    
        myopener = MyOpener()
        s = myopener.open(url).read()
        body=findbiaoqian(s,'<div id="result"','div')
        foot=buquan(findbiaoqian(s,'<div id="pager">','div').replace('/q?','/vip/search/'))
        print body
        print foot
        a=[]
        a.append(body.decode('gbk'))
        a.append(foot.decode('gbk'))    
        return a
    def buquan(string):
        split_s=string.split('"')
        for i in split_s:
            if i.find('vip')!=-1:
                split_s[split_s.index(i)]=i+'/'
        return '"'.join(split_s)

	#捡取自己喜欢的部分，如<div id="pager"和对应的</div>之间

    def findbiaoqian(string,biaoqian,tebie):
        begin=string.find(biaoqian)
        i=1
        tlen=len(tebie)
        temp=string[begin+tlen:].find(tebie)+begin+tlen
        while i>0:        
            print temp
            if string[temp-1]=='/':
                i-=1
                print '/'+str(i)
            else:
                i+=1
                print i
            temp=string[temp+tlen:].find(tebie)+temp+tlen
        return string[begin:temp-1]
    a=MyFunc('http://www.soso.com/q?'+url)
    return render_to_response('vip/search.html', {'body': a[0],'foot':a[1],})

用的django模版，