这篇文章主要介绍了python中使用urllib2伪造http报头的2个方法,即伪造http头信息,需要的朋友可以参考下
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= http://www.xxx.net
send_headers = {
'host':'www.xxx.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 = 'http://www.xxx.net'
req = urllib2.request(url)
req.add_header('referer','http://www.xxx.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