【python】爬虫2——下载亦舒博客首页所有文章

#! /usr/bin/env python
#coding=utf-8
from urllib import urlopen
import time
url = ['']*40
i = 0
arti = urlopen('http://blog.sina.com.cn/s/articlelist_1227636382_0_1.html').read()
title = arti.find(r'<a title=')
href = arti.find(r'href=',title)
html = arti.find(r'.html',href)
url[0] = arti[href+6:html+5]
print url

while title != -1 and href != -1 and html != -1 and i<40:
    url[i] = arti[href+6:html+5]
    print url[i]
    title = arti.find(r'<a title=',html)
    href = arti.find(r'href=',title)
    html = arti.find(r'.html',href)
    i = i + 1

else:
    print 'find end'
    
j=0
while j<50:
    content = urlopen(url[j]).read()
    filename = url[j][-26:]
    print filename
    open(r'yishu/'+url[j][-26:],'w+').write(content)
    print 'downloading',url[j]
    j = j+1
    time.sleep(1)
else:
    print 'download article finished'