Python 爬虫，scrapy，携带cookie请求登录

谁借莪１个温暖的怀抱￠ 2022-03-25 08:40 265阅读 0赞

**项目名/spiders/爬虫名.py（爬虫，携带cookie登录）：**

# -*- coding: utf-8 -*-
    import scrapy
    import re
    
    
    class RenrenSpider(scrapy.Spider):
        name = '爬虫名'
        allowed_domains = ['renren.com']
        start_urls = ['http://www.renren.com/327550029/profile']  # 需要登陆后才能正常访问的url
    
        # start_urls都是默认交给start_requests函数处理的，可以重写该方法添加请求头、cookie等。
        def start_requests(self):
            # 该cookie是登陆后获取的cookie字符串。
            cookies = "anonymid=jcokuqturos8ql; depovince=GW; jebecookies=f90c9e96-78d7-4f74-b1c8-b6448492995b|||||; _r01_=1; JSESSIONID=abcx4tkKLbB1-hVwvcyew; ick_login=ff436c18-ec61-4d65-8c56-a7962af397f4; _de=BF09EE3A28DED52E6B65F6A4705D973F1383380866D39FF5; p=90dea4bfc79ef80402417810c0de60989; first_login_flag=1; ln_uact=mr_mao_hacker@163.com; ln_hurl=http://hdn.xnimg.cn/photos/hdn421/20171230/1635/main_JQzq_ae7b0000a8791986.jpg; t=24ee96e2e2301bf2c350d7102956540a9; societyguester=24ee96e2e2301bf2c350d7102956540a9; id=327550029; xnsid=e7f66e0b; loginfrom=syshome; ch_id=10016"
            # 转换成字典
            cookies = {i.split("=")[0]:i.split("=")[1] for i in cookies.split("; ")}
            # headers = {"Cookie":cookies}  # cookie放到headers中无效
            yield scrapy.Request(
                self.start_urls[0],
                callback=self.parse,
                cookies=cookies   # 携带cookie进行请求
                # headers = headers  # cookie放到headers中无效
            )
    
        def parse(self, response):
            print(re.findall("张三",response.body.decode()))
            # 后续的请求会自动携带之前的cookie (setting.py配置文件中不要禁用cookie)
            yield scrapy.Request(
                "http://www.renren.com/327550029/profile?v=info_timeline",
                callback=self.parse_detial
            )
    
        def parse_detial(self,response):
            print(re.findall("张三",response.body.decode()))

**项目名/settings.py（配置文件，不要禁用cookie）：**

# 。。。
    
    # 禁用cookie (默认开启cookie)
    # COOKIES_ENABLED = False
    COOKIES_DEBUG = True  # 开启cookie的调试信息
    
    # 。。。