#!/usr/bin/python
# -*- coding: utf-8 -*-
#encoding=utf-8
#Filename:urllib2-header.py
 
import urllib2
import sys
 
#抓取網(wǎng)頁內(nèi)容-發(fā)送報頭-1
url= "http://www.dbjr.com.cn"
send_headers = {
 'Host':'www.dbjr.com.cn',
 '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()        #返回網(wǎng)頁內(nèi)容
receive_header = r.info()     #返回的報頭信息
 
# sys.getfilesystemencoding() 
html = html.decode('utf-8','replace').encode(sys.getfilesystemencoding()) #轉(zhuǎn)碼:避免輸出出現(xiàn)亂碼 
 
print receive_header
# print '####################################'
print html

#!/usr/bin/python
# -*- coding: utf-8 -*-
#encoding=utf-8
#Filename:urllib2-header.py
 
import urllib2
import sys
 
url = 'http://www.dbjr.com.cn'
 
req = urllib2.Request(url)
req.add_header('Referer','http://www.dbjr.com.cn/')
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