python网页抓取代码

用python抓取韩寒的新浪博客的代码：

#<a title="地震思考录" target="_blank" href="http://blog.sina.com.cn/s/blog_4701280b0102egl0.html">地震思考录</a>
#coding:utf-8
import urllib
import time
url=['']*6
con=urllib.urlopen('http://blog.sina.com.cn/s/articlelist_1191258123_0_1.html').read()
i=0
title=con.find(r'<a title=')
href=con.find(r'href=',title)
html=con.find(r'.html',href)
while title!=-1 and href!=-1 and html!=-1 and i<6:
    url[i]=con[href+6:html+5]
    print url[i]
    title=con.find(r'<a title=',html)
    href=con.find(r'href=',title)
    html=con.find(r'.html',href)
    i=i+1
else:
    print 'end of find!'
j=0
while j<6:
    content=urllib.urlopen(url[j]).read()
    open(r'hanhan/'+url[j][-26:],'w+').write(content)
    print'downloading',url[j]
    j=j+1
    time.sleep(15)
else:
    print 'download finished'