python 抓一下 循环的访问也可以

#!/usr/bin/python
# -*- coding: utf-8 -*-
#encoding=utf-8
#Filename:urllib2-header.py

import urllib2
import sys

url= "http://www.jb51.net"
send_headers = {
 'Host':'www.jb51.net',
 'User-Agent':'Mozilla/5.0 (Windows NT 6.2; rv:16.0) Gecko/20100101 Firefox/16.0',
 'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
 'Connection':'keep-alive'
}

req = urllib2.Request(url,headers=send_headers)

for num in range(0,100):  

	r = urllib2.urlopen(req)

	html = r.read()
	receive_header = r.info()     

	html = html.decode('gbk','replace').encode(sys.getfilesystemencoding()) #转码:避免输出出现乱码 

	#print receive_header
	print html