Scrapy 知乎验证码

Posted 2020-10-14 WANGLC

# -*- coding: utf-8 -*-
#scrapy genspider zhihu www.zhihu.com

import scrapy
import time
import json
import re
from scrapy.http import Request, FormRequest
try:
    from PIL import Image
except:
    pass


class ZhihuSpider(scrapy.Spider):
    name = ‘zhihu‘
    allowed_domains = [‘www.zhihu.com‘]
    start_urls = [‘http://www.zhihu.com/‘]
    agent = ‘Mozilla/5.0 (Linux; android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/56.0.2924.87 Mobile Safari/537.36‘
    headers = {
        "Host": "www.zhihu.com",
        "Referer": "https://www.zhihu.com/",
        ‘User-Agent‘: agent
    }

    def parse(self, response):
        pass

    def start_requests(self):
        #首先要完成登录 因此要重写scrapy的start_requests
        t = str(int(time.time() * 1000))
        captcha_url = ‘https://www.zhihu.com/captcha.gif?r=‘ + t + ‘&type=login‘
        return [Request(captcha_url, callback=self.parser_captcha, headers=self.headers)]

    def parser_captcha(self, response):
        with open(‘captcha.jpg‘, ‘wb‘) as f:
            f.write(response.body)
            f.close()
        im = Image.open(‘captcha.jpg‘)
        im.show()
        im.close()
        captcha = input("输入验证码：\n>")
        return Request(url=‘https://www.zhihu.com/‘, callback=self.login, meta={‘captcha‘: captcha},headers=self.headers)

    def login(self, response):
        match_obj = re.match(‘.*name="_xsrf" value="(.*?)"‘, response.text, re.DOTALL)
        xsrf = ‘‘
        if match_obj:
            xsrf = match_obj.group(1)
        print(‘xsrf:‘ + xsrf)
        print(response.meta[‘captcha‘])
        return [FormRequest(‘https://www.zhihu.com/login/phone_num‘,
                            method=‘POST‘,
                            formdata={
                                ‘phone_num‘: ‘1303922‘,
                                ‘password‘: ‘123456‘,
                                ‘_xsrf‘: xsrf,
                                ‘captcha_type‘: ‘en‘,
                                ‘captcha‘: response.meta[‘captcha‘],
                            },

                            callback=self.after_login,
                            headers=self.headers
                            )]

    def after_login(self, response):
        json_file = json.loads(response.text)
        if json_file[‘r‘] == 0:
            print(‘success........登录成功‘)
        else:
            print(‘登录失败！‘)

scrapy shell 环境下：

　　scrapy shell https://www.zhihu.com/question/52117226/answer/257823105

　　response   <500 https://www.zhihu.com/question/52117226/answer/257823105>

出现状态码500错误就是没有加上header问题导致

解决方法：

　　>scrapy shell -s USER_AGENT="Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Mobile Safari/537.36 " https://www.zhihu.com/question/52117226/answer/257823105

　　状态变为：response   <200 https://www.zhihu.com/question/52117226/answer/257823105>