python之scrapy的FormRequest模拟POST表单自动登陆

1、FormRequest表单实现自动登陆

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

import re

class GithubSpider(scrapy.Spider):
    name = 'github'
    allowed_domains = ['github.com']
    start_urls = ['https://github.com/login']

    def parse(self, response):
        authenticity_token = response.xpath("//input[@name='authenticity_token']/@value").extract_first()
        utf8 = response.xpath("//input[@name='utf8']/@value").extract_first()
        commit = response.xpath("//input[@name='commit']/@value").extract_first()
        post_data = dict(
            login="812******[e-mail]",
            password="******",
            authenticity_token=authenticity_token,
            utf8=utf8,
            commit=commit,
        )
        #表单请求
        yield scrapy.FormRequest(
            "https://github.com/session",
            formdata=post_data,
            callback=self.after_login
        )

    def after_login(self,response):
        # with open("a.html","w",encoding="utf-8") as f:
        #     f.write(response.body.decode())
        print(re.findall("",response.body.decode()))

2、FormRequest.from_response模拟自动登陆

# -*- coding: utf-8 -*-
import scrapy
import re
class Github2Spider(scrapy.Spider):
    name = 'github2'
    allowed_domains = ['github.com']
    start_urls = ['https://github.com/login']

    def parse(self, response):
        yield scrapy.FormRequest.from_response(
            response, #自动的从response中寻找from表单
            #formdata只需要传入字典型登录名和密码，字典的健是input标签中的name属性
            formdata={"login":"****@qq.com","password":"***********"},
            callback = self.after_login
        )

    def after_login(self,response):
        print(re.findall("........",response.body.decode()))

3、笔记

　　a）FormRequest

　　

　　b) FormRequest.from_response