需要登录的网站爬虫详解

概述

介绍一下请求状态原理
分析需要登录的网站请求特点
分析登陆前后请求差异
如何从接口分析一步步构建一个合理的登录爬虫
巧方法解决登录

案例分析

案例一

https://login2.scrape.center/
默认重定向导致无法获取到重定向前的cookie

案例二爬虫源码

javascript 复制代码

# coding=utf-8


import requests

headers = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
    'Cache-Control': 'no-cache',
    'Connection': 'keep-alive',
    'Content-Type': 'application/x-www-form-urlencoded',
    'Origin': 'https://login2.scrape.center',
    'Pragma': 'no-cache',
    'Referer': 'https://login2.scrape.center/login',
    'Sec-Fetch-Dest': 'document',
    'Sec-Fetch-Mode': 'navigate',
    'Sec-Fetch-Site': 'same-origin',
    'Sec-Fetch-User': '?1',
    'Upgrade-Insecure-Requests': '1',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
    'sec-ch-ua': '"Not_A Brand";v="8", "Chromium";v="120", "Google Chrome";v="120"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': '"Windows"',
}

data = {
    'username': 'admin',
    'password': 'admin',
}

response = requests.post('https://login2.scrape.center/login', headers=headers, data=data, allow_redirects=False)
status = response.status_code
################### 直接获取响应的cookie字段 ################
logined_cookies = response.cookies
print(status)
print(logined_cookies)
# 将cookies输出为字典
print(dict(logined_cookies))  # {'sessionid': 'h1d41qkv8qzrlhk0ykfzx54g3ph0od6j'}

################# 从响应头内获取cookie ###################
headers_resp = dict(response.headers)
cookies = headers_resp.get('Set-Cookie')  # 获取到cookie字符串
print(cookies)  # sessionid=h1d41qkv8qzrlhk0ykfzx54g3ph0od6j; expires=Wed, 24 Jan 2024 23:40:31 GMT; HttpOnly; Max-Age=1209600; Path=/; SameSite=Lax

案例二

https://login3.scrape.center/login

案例三

法信爬虫

登录脚本

javascript 复制代码

# coding=utf-8
import time

import requests

cookies = {
    'ASP.NET_SessionId': 'at0wmkahm3o1yf2uzdcyo24z',
    'insert_cookie': '89314150',
    'showUpdate': '2024-01-05',
    'Hm_lvt_a317640b4aeca83b20c90d410335b70f': '1704930439',
    'clx': 'n',
    'sid': 'at0wmkahm3o1yf2uzdcyo24z',
    'isAutoLogin': 'off',
    'Hm_lpvt_a317640b4aeca83b20c90d410335b70f': str(int(time.time())),
}

headers = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
    'Cache-Control': 'no-cache',
    'Connection': 'keep-alive',
    'Content-Type': 'application/x-www-form-urlencoded',
    # 'Cookie': 'ASP.NET_SessionId=at0wmkahm3o1yf2uzdcyo24z; insert_cookie=89314150; showUpdate=2024-01-05; Hm_lvt_a317640b4aeca83b20c90d410335b70f=1704930439; clx=n; sid=at0wmkahm3o1yf2uzdcyo24z; isAutoLogin=off; Hm_lpvt_a317640b4aeca83b20c90d410335b70f=1704930535',
    'Origin': 'https://www.faxin.cn',
    'Pragma': 'no-cache',
    'Referer': 'https://www.faxin.cn/login.aspx?url=/lib/zyfl/zyflcontent.aspx%3Fgid=A341404%26libid=010101',
    'Sec-Fetch-Dest': 'document',
    'Sec-Fetch-Mode': 'navigate',
    'Sec-Fetch-Site': 'same-origin',
    'Sec-Fetch-User': '?1',
    'Upgrade-Insecure-Requests': '1',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
    'sec-ch-ua': '"Not_A Brand";v="8", "Chromium";v="120", "Google Chrome";v="120"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': '"Windows"',
}

data = {
    '__VIEWSTATE': '/wEPDwUJNzUzMzc2OTcyZBgBBR5fX0NvbnRyb2xzUmVxdWlyZVBvc3RCYWNrS2V5X18WAgUKaXNSZW1lbWJlcgULaXNBdXRvTG9naW7CqpQN/iu5+xaD2O1P5o5lGgo7gA==',
    '__VIEWSTATEGENERATOR': 'C2EE9ABB',
    'WebUCHead_Special1$hiddIsLogin': '0',
    'WebUCSearchNoAdvSearch1$lib': '',
    'keyword': '',
    'user_name': '',# 你的用户名
    'user_password': '', # 你的密码
    'isLogout': '0',
}

response = requests.post(
    'https://www.faxin.cn/login.aspx?url=%2flib%2fzyfl%2fzyflcontent.aspx%3fgid%3dA341404%26libid%3d010101',
    cookies=cookies,
    headers=headers,
    data=data,
    allow_redirects=False
)

status = response.status_code
################### 直接获取响应的cookie字段 ################
logined_cookies = response.cookies
print(status)
print(logined_cookies)
# 将cookies输出为字典
print(dict(logined_cookies))