(32)scrapy 登录

import scrapy


class LogSpider(scrapy.Spider):
    name = 'log'
    allowed_domains = ['sxt.cn']
 #   start_urls = ['http://sxt.cn/']
    def start_requests(self):
        url=''
        form_data={
            'user':     ,
            'password':     ,
        }
        yield scrapy.FormRequest(url,formdata=form_data,callback=self.parse)
    def parse(self, response):
        print(response.text)

存在错误，作为笔记保存

import scrapy
import re


class LogSpider(scrapy.Spider):
    name = 'log'
    allowed_domains = ['ganji.com']
    start_urls = ['https://passport.ganji.com/login.php']

    def parse(self, response):
        hash_code = re.findall(r'"__hash__":"(.+)"',response.text)[0]
        img_url = response.xpath('''//div/label/img[@alt='图片验证码']/@src''').extract_first()
        yield scrapy.Request(img_url, callback=self.parse_info,meta={'hash_code':hash_code})


    def parse_info(self,response):
        hash_code = response.request.meta['hash_code']
        with open('yzm.jpg','wb') as f:
            f.write(response.body)
        f.close()
        code = input('请输入验证码')
        form_data={
            'username': '15506306812',
            'password': 'L06306812',
            'setcookie': '0',
            'checkCode':code,
                'next': '/',
        'source': 'passport',
        '__hash__': hash_code
        }
        url = 'https://passport.ganji.com/login.php?next=/'
        yield scrapy.FormRequest(url, formdata = form_data, callback = self.after_login)

    def after_login(self,response):
        print(response.text)