【python】爬虫3——抓取亦舒博客所有文章

<span style="font-family: Arial, Helvetica, sans-serif;">#! /usr/bin/env python</span>

#coding=utf-8
from urllib import urlopen
import time
url = ['']*350
page = 1
link = 1#链接变量

while page<= 4:
    arti = urlopen('http://blog.sina.com.cn/s/articlelist_1227636382_0_'+str(page)+'.html').read()
    i = 0
    title = arti.find(r'<a title=')
    href = arti.find(r'href=',title)
    html = arti.find(r'.html',href)
    while title != -1 and href != -1 and html != -1 and i<40:
        url[i] = arti[href+6:html+5]
        print link,' ',url[i]
        title = arti.find(r'<a title=',html)
        href = arti.find(r'href=',title)
        html = arti.find(r'.html',href)
        
        content = urlopen(url[i]).read()  
        filename = url[i][-26:]  
        print ' ',filename  
        open(r'yishu/'+url[i][-26:],'w+').write(content)  
        print 'downloading',url[i]  
        
        i = i + 1
        link = link+1#发现了多少链接地
        time.sleep(1)  
       
    else:
        print page,'find end'
    page=page+1
    
else:
    print'all find'