1. 网页下载

构造request

import urllib2
request = urllib2.Request("http://www.baidu.com")
response = urllib2.urlopen(request)
print response.read()
#urlopen(url, data, timeout)

post

import urllib
import urllib2
 
values = {"username":"1016903103@qq.com","password":"XXXX"}
data = urllib.urlencode(values) 
url = "https://passport.csdn.net/account/login?from=http://my.csdn.net/my/mycsdn"
request = urllib2.Request(url,data)
response = urllib2.urlopen(request)
print response.read()

get

import urllib
import urllib2
 
values={}
values['username'] = "1016903103@qq.com"
values['password']="XXXX"
data = urllib.urlencode(values) 
url = "http://passport.csdn.net/account/login"
geturl = url + "?"+data
request = urllib2.Request(geturl)
response = urllib2.urlopen(request)
print response.read()

模拟浏览器

import urllib  
import urllib2  
 
url = 'http://www.server.com/login'
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'  
values = {'username' : 'cqc',  'password' : 'XXXX' }  
headers = { 'User-Agent' : user_agent }  
data = urllib.urlencode(values)  
request = urllib2.Request(url, data, headers)  
response = urllib2.urlopen(request)  
page = response.read() 

设置代理服务器

import urllib2
enable_proxy = True
proxy_handler = urllib2.ProxyHandler({"http" : 'http://some-proxy.com:8080'})
null_proxy_handler = urllib2.ProxyHandler({})
if enable_proxy:
    opener = urllib2.build_opener(proxy_handler)
else:
    opener = urllib2.build_opener(null_proxy_handler)
urllib2.install_opener(opener)

2. cookie的相关操作

将cookie 保存在变量中

import urllib2
import cookielib
#声明一个CookieJar对象实例来保存cookie
cookie = cookielib.CookieJar()
#利用urllib2库的HTTPCookieProcessor对象来创建cookie处理器
handler=urllib2.HTTPCookieProcessor(cookie)
#通过handler来构建opener
opener = urllib2.build_opener(handler)
#此处的open方法同urllib2的urlopen方法，也可以传入request
response = opener.open('http://www.baidu.com')
for item in cookie:
    print 'Name = '+item.name
    print 'Value = '+item.value

从文件中导入cookie，并使用来浏览网站

import cookielib
import urllib2
 
#创建MozillaCookieJar实例对象
cookie = cookielib.MozillaCookieJar()
#从文件中读取cookie内容到变量
cookie.load('cookie.txt', ignore_discard=True, ignore_expires=True)
#创建请求的request
req = urllib2.Request("http://www.baidu.com")
#利用urllib2的build_opener方法创建一个opener
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))
response = opener.open(req)
print response.read()

利用cookie模拟网站登录

import urllib
import urllib2
import cookielib

filename = 'cookie.txt'
#声明一个MozillaCookieJar对象实例来保存cookie，之后写入文件
cookie = cookielib.MozillaCookieJar(filename)
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))
postdata = urllib.urlencode({
            'stuid':'201200131012',
            'pwd':'23342321'
        })
#登录教务系统的URL
loginUrl = 'http://jwxt.sdu.edu.cn:7890/pls/wwwbks/bks_login2.login'
#模拟登录，并把cookie保存到变量
result = opener.open(loginUrl,postdata)
#保存cookie到cookie.txt中
cookie.save(ignore_discard=True, ignore_expires=True)
#利用cookie请求访问另一个网址，此网址是成绩查询网址
gradeUrl = 'http://jwxt.sdu.edu.cn:7890/pls/wwwbks/bkscjcx.curscopre'
#请求访问成绩查询网址
result = opener.open(gradeUrl)
print result.read()