python中使用urllib2伪造HTTP报头的2个方法

在采集网页信息的时候，经常需要伪造报头来实现采集脚本的有效执行

下面，我们将使用urllib2的header部分伪造报头来实现采集信息

方法1、

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

import urllib2
import sys

#抓取网页内容-发送报头-1
url= "https://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)
r = urllib2.urlopen(req)

html = r.read()        #返回网页内容
receive_header = r.info()     #返回的报头信息

# sys.getfilesystemencoding()
html = html.decode('utf-8','replace').encode(sys.getfilesystemencoding()) #转码:避免输出出现乱码

print receive_header
# print '####################################'
print html

方法2、

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

import urllib2
import sys

url = 'https://www.jb51.net'

req = urllib2.Request(url)
req.add_header('Referer','https://www.jb51.net/')
req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.2; rv:16.0) Gecko/20100101 Firefox/16.0')
r = urllib2.urlopen(req)

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

html = html.decode('utf-8').encode(sys.getfilesystemencoding())

print receive_header
print '#####################################'
print html