Scrapy模拟登录小记

Scrapy登录方式

• 方式一：直接携带cookie
• 方式二：找到发送post请求的URL地址，带上信息，发送请求

人人练习

创建爬虫项目

scrapy startproject renren

renrenlogin.py

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

from ..settings import DEFAULT_REQUEST_HEADERS

class RenrenloginSpider(scrapy.Spider):
    name = 'renrenlogin'
    allowed_domains = ['renren.com']
    start_urls = ['http://www.renren.com/269782969/profile']

    #重写父类的方法
    def start_requests(self):

        str_cookies = '{}'.format(cookies字符串)

        cookies = {}
        for i in str_cookies.split(';'):
            # print(i)
            # print(i.split('=')[0])
            # print(i.split('=')[1])
            cookies[i.split('=')[0]] = i.split('=')[1]
        #print(DEFAULT_REQUEST_HEADERS)
        #print(self.start_urls[0])
        print(cookies)
        yield scrapy.Request(
            url=self.start_urls[0],
            headers=DEFAULT_REQUEST_HEADERS,
            cookies = cookies,
            callback=self.parse
        )

    def parse(self, response):

        #print(response.text)
        with open('renren.html', 'w', encoding='utf-8') as f:
            f.write(response.body.decode())