Python模拟浏览器发送http请求

1.使用 urllib2 实现

#! /usr/bin/env python
# -*- coding=utf-8 -*- 

import urllib2
url="https://www.baidu.com"
req_header = {"User-Agent":"Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
"Accept":"text/html;q=0.9,*/*;q=0.8",
"Accept-Charset":"ISO-8859-1,utf-8;q=0.7,*;q=0.3",
"Accept-Encoding":"gzip",
"Connection":"close",
"Referer":None #注意如果依然不能抓取的话，这里可以设置抓取网站的host
}
req_timeout = 5
req = urllib2.Request(url,None,req_header)
resp = urllib2.urlopen(req,None,req_timeout)
html = resp.read()
print(html)

2.使用 requests 模块

（1）.get请求

#-*- coding:utf-8 -*-
import requests

url = "https://www.baidu.com"
payload = {"key1": "value1", "key2": "value2"}
r = requests.get(url, params=payload)
print r.text

（2）.post请求

#-*- coding:utf-8 -*-
import requests
url1 = "http://www.exanple.com/login"#登陆地址
url2 = "http://www.example.com/main"#需要登陆才能访问的地址
data={"user":"user","password":"pass"}
headers = { "Accept":"text/html,application/xhtml+xml,application/xml;",
            "Accept-Encoding":"gzip",
            "Accept-Language":"zh-CN,zh;q=0.8",
            "Referer":"http://www.example.com/",
            "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36"
            }
res1 = requests.post(url1, data=data, headers=headers)
res2 = requests.get(url2, cookies=res1.cookies, headers=headers)

print res2.content#获得二进制响应内容
print res2.raw#获得原始响应内容,需要stream=True
print res2.raw.read(50)
print type(res2.text)#返回解码成unicode的内容
print res2.url
print res2.history#追踪重定向
print res2.cookies
print res2.cookies["example_cookie_name"]
print res2.headers
print res2.headers["Content-Type"]
print res2.headers.get("content-type")
print res2.json#讲返回内容编码为json
print res2.encoding#返回内容编码
print res2.status_code#返回http状态码
print res2.raise_for_status()#返回错误状态码

（3）.使用session对象的写法

#-*- coding:utf-8 -*-
import requests
s = requests.Session()
url1 = "http://www.exanple.com/login"#登陆地址
url2 = "http://www.example.com/main"#需要登陆才能访问的地址
data={"user":"user","password":"pass"}
headers = { "Accept":"text/html,application/xhtml+xml,application/xml;",
            "Accept-Encoding":"gzip",
            "Accept-Language":"zh-CN,zh;q=0.8",
            "Referer":"http://www.example.com/",
            "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36"
            }

prepped1 = requests.Request("POST", url1,
    data=data,
    headers=headers
).prepare()
s.send(prepped1)


"""
也可以这样写
res = requests.Request("POST", url1,
data=data,
headers=headers
)
prepared = s.prepare_request(res)
# do something with prepped.body
# do something with prepped.headers
s.send(prepared)
"""

prepare2 = requests.Request("POST", url2,
    headers=headers
).prepare()
res2 = s.send(prepare2)

print res2.content


"""另一种写法"""
#-*- coding:utf-8 -*-
import requests
s = requests.Session()
url1 = "http://www.exanple.com/login"#登陆地址
url2 = "http://www.example.com/main"#需要登陆才能访问的页面地址
data={"user":"user","password":"pass"}
headers = { "Accept":"text/html,application/xhtml+xml,application/xml;",
            "Accept-Encoding":"gzip",
            "Accept-Language":"zh-CN,zh;q=0.8",
            "Referer":"http://www.example.com/",
            "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36"
            }
res1 = s.post(url1, data=data)
res2 = s.post(url2)
print(resp2.content)

3.其他的一些请求方式

>>> r = requests.put("http://httpbin.org/put")
>>> r = requests.delete("http://httpbin.org/delete")
>>> r = requests.head("http://httpbin.org/get")
>>> r = requests.options("http://httpbin.org/get")

Tags: http http请求 python 发送模拟

本文实例讲述了Python实现模拟浏览器请求及会话保持操作。分享给大家供大家参考，具体如下：

python下读取一个页面的数据可以通过urllib2轻松实现请求

1 2	`import` `urllib2` `print` `urllib2.urlopen('http://www.baidu.com').read()`

涉及到页面的POST请求操作的话需要提供头信息，提交的post数据和请求页面。

其中的post数据需要urllib.encode()一下，其实就是将字典转换成“data1=value1&data2=value2”的格式。

import urllib
import urllib2
HEADER = {
 'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:31.0) Gecko/20100101 Firefox/31.0',
 'Referer' : 'http://202.206.1.163/logout.do'
}
POSTDATA = {
 'data1': 'value1',
 'data2': 'value2'
}
HOSTURL = 'http://xxx.com'
enpostdata = urllib.urlencode(POSTDATA)
urlrequest = urllib2.Request(hosturl,enpostdata,HEADER)
urlresponse = urllib2.urlopen(urlrequest)
print urlresponse.read()

请求之后浏览器会有一个会话保持的过程，会话都是保存在一个cookie里面的，下一次页面的请求会把cookie放到请求头，如果cookie丢失会话也就断开了。

在python下面需要设置一下cookie的保持

# cookie set
# 用来保持会话
cj = cookielib.LWPCookieJar()
cookie_support = urllib2.HTTPCookieProcessor(cj)
opener = urllib2.build_opener(cookie_support, urllib2.HTTPHandler)
urllib2.install_opener(opener)

下面是将以上知识点汇总写的一个库文件，方便使用：

# filename: analogop.py
#!/usr/bin/python
# -*-coding:UTF-8 -*-
# author: 初行
# qq: 121866673
# mail: zxbd1016@163.com
# message: I need a python job
# time: 2014/10/5
import urllib
import urllib2
import cookielib
# cookie set
# 用来保持会话
cj = cookielib.LWPCookieJar()
cookie_support = urllib2.HTTPCookieProcessor(cj)
opener = urllib2.build_opener(cookie_support, urllib2.HTTPHandler)
urllib2.install_opener(opener)
# default header
HEADER = {
 'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:31.0) Gecko/20100101 Firefox/31.0',
 'Referer' : 'http://202.206.1.163/logout.do'
}
# operate method
def geturlopen(hosturl, postdata = {}, headers = HEADER):
 # encode postdata
 enpostdata = urllib.urlencode(postdata)
 # request url
 urlrequest = urllib2.Request(hosturl, enpostdata, headers)
 # open url
 urlresponse = urllib2.urlopen(urlrequest)
 # return url
 return urlresponse

这个是测试文件，因为读者没有测试环境，需要自己搭建或者找个网站测试：

#filename: test.py
from analogop import geturlopen
postd = {
 'usernum': '2011411111',
 'upw': '124569',
 'userip': '192.168.10.1',
 'token': 'xxx'
}
urlread = geturlopen('http://127.0.0.1:8000/login/', postd)
print urlread.read().decode('utf-8')
urlread = geturlopen('http://127.0.0.1:8000/chafen/', {})
print urlread.read().decode('utf-8')

更多关于Python相关内容可查看本站专题：《Python Socket编程技巧总结》、《Python数据结构与算法教程》、《Python函数使用技巧总结》、《Python字符串操作技巧汇总》、《Python入门与进阶经典教程》及《Python文件与目录操作技巧汇总》

Python模拟浏览器发送http请求

Python模拟浏览器发送http请求

Python实现模拟浏览器请求及会话保持操作示例