php 爬虫 cookies,Python3 爬虫带上 cookie

Cookie的英文原意是“点心”，它是在客户端访问Web服务器时，服务器在客户端硬盘上存放的信息，好像是服务器发送给客户的“点心”。服务器可以根据Cookie来跟踪客户状态，这对于需要区别客户的场合(如电子商务)特别有用。

当客户端首次请求访问服务器时，服务器先在客户端存放包含该客户的相关信息的Cookie，以后客户端每次请求访问服务器时，都会在HTTP请求数据中包含Cookie，服务器解析HTTP请求中的Cookie，就能由此获得关于客户的相关信息。

下面我们就来看一下python3爬虫带上cookie的方法：

1、直接将Cookie写在header头部# coding:utf-8

import requests

from bs4 import BeautifulSoup

cookie = '''cisession=19dfd70a27ec0eecf1fe3fc2e48b7f91c7c83c60;CNZZDATA1000201968=181584

6425-1478580135-https%253A%252F%252Fwww.baidu.com%252F%7C1483922031;Hm_lvt_f805f7762a9a2

37a0deac37015e9f6d9=1482722012,1483926313;Hm_lpvt_f805f7762a9a237a0deac37015e9f6d9=14839

26368'''

header = {

'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Geck

o) Chrome/53.0.2785.143 Safari/537.36',

'Connection': 'keep-alive',

'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',

'Cookie': cookie}

url = 'https://www.jb51.net/article/191947.htm'

wbdata = requests.get(url,headers=header).text

soup = BeautifulSoup(wbdata,'lxml')

print(soup)

2、使用requests插入Cookie# coding:utf-8

import requests

from bs4 import BeautifulSoup

cookie = {

"cisession":"19dfd70a27ec0eecf1fe3fc2e48b7f91c7c83c60",

"CNZZDATA100020196":"1815846425-1478580135-https%253A%252F%252Fwww.baidu.com%252F%7C1483

922031",

"Hm_lvt_f805f7762a9a237a0deac37015e9f6d9":"1482722012,1483926313",

"Hm_lpvt_f805f7762a9a237a0deac37015e9f6d9":"1483926368"

}

url = 'https://www.jb51.net/article/191947.htm'

wbdata = requests.get(url,cookies=cookie).text

soup = BeautifulSoup(wbdata,'lxml')

print(soup)

实例扩展：

使用cookie登录哈工大ACM站点

获取站点登录地址

http://acm.hit.edu.cn/hoj/system/login

查看要传送的post数据

user和password

Code:#!/usr/bin/env python

# -*- coding: utf-8 -*-

"""

__author__ = 'pi'

__email__ = 'pipisorry@126.com'

"""

import urllib.request, urllib.parse, urllib.error

import http.cookiejar

LOGIN_URL = 'http://acm.hit.edu.cn/hoj/system/login'

values = {'user': '******', 'password': '******'} # , 'submit' : 'Login'

postdata = urllib.parse.urlencode(values).encode()

user_agent = r'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36'

headers = {'User-Agent': user_agent, 'Connection': 'keep-alive'}

cookie_filename = 'cookie.txt'

cookie = http.cookiejar.MozillaCookieJar(cookie_filename)

handler = urllib.request.HTTPCookieProcessor(cookie)

opener = urllib.request.build_opener(handler)

request = urllib.request.Request(LOGIN_URL, postdata, headers)

try:

response = opener.open(request)

page = response.read().decode()

# print(page)

except urllib.error.URLError as e:

print(e.code, ':', e.reason)

cookie.save(ignore_discard=True, ignore_expires=True) # 保存cookie到cookie.txt中

print(cookie)

for item in cookie:

print('Name = ' + item.name)

print('Value = ' + item.value)

get_url = 'http://acm.hit.edu.cn/hoj/problem/solution/?problem=1' # 利用cookie请求訪问还有一个网址

get_request = urllib.request.Request(get_url, headers=headers)

get_response = opener.open(get_request)

print(get_response.read().decode())

# print('You have not solved this problem' in get_response.read().decode())