python爬虫工具-（1）urllib

• 简单方法

importurllib2

response = urllib2.urlopen("http://www.baidu.com")

print response.read()

• 构造request

import urllib2

request = urllib2.Request("http://www.baidu.com")
response = urllib2.urlopen(request)
print response.read()

• get请求

import urllib
import urllib2

values = {}
values["username"] = "anthoy@gmail.com"
values["passwd"] = "123456"
#编码values字典，格式化
data = urllib.urlencode(values)
print data
#构建get访问地址
geturl = "http://www.baidu.com"+"?"+data
print geturl
request = urllib2.Request(geturl)
respose = urllib2.urlopen(request)

• post请求

import urllib
import urllib2

values = {}
values['username'] = "anthony@gmail.com"
values['password'] = "123456"
#编码values字典，格式化
data = urllib.urlencode(values)
print data
url = "http://passport.csdn.net/account/login?from=http://my.csdn.net/my/mycsdn"
#构建post请求
request = urllib2.Request(url, data)
print request
response = urllib2.urlopen(request)
print response.read()

参考http://cuiqingcai.com/947.html

• headers设置

import urllib
import urllib2

enable_proxy = True
#设置代理
proxy_handler = urllib2.ProxyHandler({"http": 'http://119.23.161.182:3128'})
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)
#设置头部
url = 'http://passport.csdn.net/account/login?from=http://my.csdn.net/my/mycsdn'
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
#对付反盗链
referer = 'http://www.jianshu.com/p/q81RER'
values = {'username': 'anthony', 'password': '123456'}
headers = {'User-Agent': user_agent, 'Referer': referer}
data = urllib.urlencode(values)
request = urllib2.Request(url, data, headers)
response = urllib2.urlopen(request)
page = response.read()
print page

参考http://cuiqingcai.com/954.html

• Cookielib

保存cookie到临时变量

import urllib2
import cookielib

# 保存cookie到变量
cookie = cookielib.CookieJar()
handler = urllib2.HTTPCookieProcessor(cookie)
opener = urllib2.build_opener(handler)
response = opener.open('http://www.baidu.com')
for item in cookie:
    print 'Name = ' + item.name
    print 'Value = ' + item.value

保存cookie到本地

import cookielib
import urllib2

# 保存cookie到本地文件
filename = 'cookie.txt'
cookie = cookielib.MozillaCookieJar(filename)
handler = urllib2.HTTPCookieProcessor(cookie)
opener = urllib2.build_opener(handler)
response = opener.open("http://www.baidu.com")
cookie.save(ignore_discard=True, ignore_expires=True)
for item in cookie:
    print 'Name = ' + item.name
    print 'Value = ' + item.value

读取本地cookie

import cookielib
import urllib2

#读取本地cookie
cookie = cookielib.MozillaCookieJar()
cookie.load('cookie.txt', ignore_discard=True, ignore_expires=True)
req = urllib2.Request("http://www.baidu.com")
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))
response = opener.open(req)
print response.read()
for item in cookie:
    print 'Name = ' + item.name
    print 'Value = ' + item.value

参考http://cuiqingcai.com/968.html