網頁抓取

### -*- coding: cp936 -*-
###<a href="http://home.51cto.com" target="_blank">家園</a>
##import urllib
##str0='<a href="http://home.51cto.com" target="_blank">家園</a>'
##href=str0.find('<a href')
##print href
##com=str0.find('.com"')
##print com
##url=str0[href+9:com+4]
##print url
##content=urllib.urlopen(url).read()
###print content
##filename=url[-9:]
##print filename
##open(filename,'w').write(content)
####_________________________________
import urllib
url = ['']*50
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('href=',title)
html = con.find('.html',href)

while title !=-1 and href != -1 and html != -1 and i < 50 :
  url[i] = con[href + 6:html + 5]
  print url[i]
  title = con.find('<a title=',html)
  href = con.find('href=',title)
  html = con.find('.html',href)
  i = i + 1
else:
    print 'find end!'
j = 0
while j < 50:
    content = urllib.urlopen(url[j]).read()
    open('hanhan/'+url[j][-26:],'w').write(content)
    j = j + 1
else:
    print "over"

##
##--------------------------------------------