知乎改版api接口之scrapy自动登陆

Posted 2020-10-25 amchen

最近使用scrapy模拟登陆知乎，发现所有接口都发生变化了，包括验证码也发生了很大变化，通过抓包分析，记录下改版后的知乎模拟登陆,废话不多说，直接上代码，亲测有效

# -*- coding: utf-8 -*-
from PIL import Image
from scrapy.exceptions import CloseSpider
import scrapy
import json
import base64


class ZhihuSpider(scrapy.Spider):
    name = \'zhihu\'
    allowed_domains = [\'www.zhihu.com\']
    start_urls = [\'http://www.zhihu.com/\']
    handle_httpstatus_list = [401, 403]
    client_id = \'c3cef7c66a1843f8b3a9e6a1e3160e20\'    #固定不变
    signature = \'b858d0c8b1f2e86c6cb0d93d4055963bcf1121ec\'    #抓包获取
    timestamp = \'1519567594106\'       #抓包获取
    headers = {
        "HOST": "www.zhihu.com",
        "Referer": "https://www.zhihu.com/signup?next=%2F",
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/63.0.3239.132 Safari/537.36Name",
        "authorization": "oauth c3cef7c66a1843f8b3a9e6a1e3160e20",
    }

    def parse(self, response):
        pass

    def start_requests(self):
        \'\'\'
        获取登陆页面，set_cookie
        :return:
        \'\'\'
        return [scrapy.Request(url=\'https://www.zhihu.com/signup?next=%2F\',
                               headers=self.headers,
                               method="GET",
                               meta={\'cookiejar\':1},
                               callback=self.post_captchareq,
                               dont_filter=True,
                               )]

    def post_captchareq(self, response):
        \'\'\'
        发送获取验证码请求
        :param response:
        :return:
        \'\'\'
        return [scrapy.Request(
            url=\'https://www.zhihu.com/api/v3/oauth/captcha?lang=en\',
            headers=self.headers,
            meta={\'cookiejar\': response.meta[\'cookiejar\']},
            dont_filter=True,
            callback=self.deal_captchareq,
        )]

    def deal_captchareq(self, response):
        \'\'\'
        判断是否需要验证码
        :param response:
        :return:
        \'\'\'
        json_res = json.loads(response.text)
        post_data = {
            "client_id": self.client_id,
            "grant_type":"password",
            "timestamp": self.timestamp,
            "source": "com.zhihu.web",
            "signature": self.signature,
            "username": \'+86你的手机号码\',
            "password":\'密码\',
            "captcha": \'\',
            "lang":"en",
            "ref_source":"homepage",
            "utm_source":""
        }
        if json_res.get("show_captcha", None):
            return [
                scrapy.Request(
                    url=\'https://www.zhihu.com/api/v3/oauth/captcha?lang=en\',
                    headers=self.headers,
                    method=\'PUT\',
                    meta={\'cookiejar\': response.meta[\'cookiejar\'],
                            \'post_data\':post_data},
                    callback=self.get_captchaimg
                )
            ]
        return [
            scrapy.FormRequest(
                url="https://www.zhihu.com/api/v3/oauth/sign_in",
                formdata=post_data,
                method="POST",
                headers=self.headers,
                meta={\'cookiejar\': response.meta[\'cookiejar\']},
                callback=self.check_login,
                dont_filter=True,
            )
        ]

    def get_captchaimg(self, response):
        \'\'\'
        获取验证码图片流数据,手动输入验证码
        :param response:
        :return:
        \'\'\'
        post_data = response.meta[\'post_data\']
        try:
            json_img = json.loads(response.text)
            bs64_img = json_img["img_base64"]
            bs64_img = bs64_img.encode(\'utf-8\')
            img_steam = base64.b64decode(bs64_img)
            with open("zhihucaptcha.jpg", \'wb\') as f:
                f.write(img_steam)
            img = Image.open("zhihucaptcha.jpg")
            img.show()
            input_captcha = input("请输入图中验证码：").strip()
            post_data[\'captcha\'] = input_captcha
            img.close()
            post_code = {
                "input_text":input_captcha,
            }
            return [
                scrapy.FormRequest(
                    url="https://www.zhihu.com/api/v3/oauth/captcha?lang=en",
                    formdata=post_code,
                    headers=self.headers,
                    method=\'POST\',
                    meta={\'cookiejar\': response.meta[\'cookiejar\'],
                          \'post_data\':post_data},
                    callback=self.post_captcha,
                    dont_filter=True,
                )
            ]
        except Exception as e:
            raise CloseSpider(\'获取验证码发生错误:{error}\'.format(error=e))

    def post_captcha(self, response):
        \'\'\'
        发送用户认证信息登陆
        :param response:
        :return:
        \'\'\'
        post_data = response.meta.get(\'post_data\')
        if json.loads(response.text).get(\'success\'):
            return [
                scrapy.FormRequest(
                    url="https://www.zhihu.com/api/v3/oauth/sign_in",
                    formdata=post_data,
                    headers=self.headers,
                    method=\'POST\',
                    meta={\'cookiejar\': response.meta[\'cookiejar\']},
                    callback=self.check_login,
                    dont_filter=True,
                )
            ]
        else:
            raise CloseSpider(\'验证码不正确\')

    def check_login(self, response):
        #验证是否登陆成功
        print(\'==============>\',response.text)
        print(response.status)
        if response.status == 201:
            self.logger.info("登陆成功!")
        else:
            raise CloseSpider(\'登陆信息有误！\')　　

  其中，其它参数如client_id, oauth等都是固定的，signature与timestamp是随着时间戳变化的，它是用于验证合法用户的token,实质也是一段客户端的js运行生成的，这里为了方便，直接通过抓包获取某个固定时间戳对应的signature

 

 

 先在pc端输入错误账户信息，抓包获取timestamp与signature，替换对应的即可