首页 > 代码库 > url下载网页的三种方法

url下载网页的三种方法

# -*- coding: utf-8 -*-
import cookielib
import urllib2

url = "http://www.baidu.com"
print "第一种方法"
response1 = urllib2.urlopen(url)
print response1.getcode()
print len(response1.read())

print "第二种方法"
res = urllib2.Request(url)
res.add_header("user-agent","Mozilla-5.0")
response2 = urllib2.urlopen(res)
print response2.getcode()
print len(response2.read())

print "第三种方法"
cj = cookielib.CookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor)
urllib2.install_opener(opener)
response3 = urllib2.urlopen(url)
print response3.getcode()
print cj
#print response3.read()

 

url下载网页的三种方法