您现在的位置是：网站首页> 学习笔记> 爬虫爬虫

国家税务总局A级纳税人采集爬虫

2021-01-30 [JS逆向] 3894人已围观

网址：http://hd.chinatax.gov.cn/nszx/InitCredit.html 主要是学习为主，没有做大量爬取,大量爬取应该得上代理池。用无痕模式多刷新几次，可以发现主要是cookie中的C3VK值在变，用fiddler抓包，第一次请求返回了一堆JS代码：

拷出来格式化看一下：

代码比较简单稍微改一下放浏览器看一下eval中的代码是什么：

可以看出这里设置了cookie中的C3VK，且C3VK的值等于B4MJ（这个动态的，每次都不一样），把多余的代码删掉：

function P9TR(jc9) {
    var B4MJ = "000000";
    w1Oh5 = 0x6a9a, MZyt3 = 0x6ab9;
    B4MJ += (jc9 ^ w1Oh5).toString(16);
    B4MJ = B4MJ.slice(-6);
    return B4MJ;
}
P9TR("0xb70d1a");

然后就是试着模拟一下请求过程：

import requests
import cchardet
import re
import execjs
import json


class Chinatax(object):
    def __init__(self):
        # 第一次请求的页面
        self.url_first = "http://hd.chinatax.gov.cn/nszx/InitCredit.html"
        # 数据请求页面地址
        self.url_data = "http://hd.chinatax.gov.cn/service/findCredit.do"

        # 第一次请求的headers
        self.headers_first = {
            'Host': 'hd.chinatax.gov.cn',
            'Connection': 'keep-alive',
            'Upgrade-Insecure-Requests': '1',
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36',
            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
            'Accept-Encoding': 'gzip, deflate',
            'Accept-Language': 'zh-CN,zh;q=0.9'
        }

        # 数据请求页面的headers
        self.headers_data = {
            'Host': 'hd.chinatax.gov.cn',
            'Connection': 'keep-alive',
            'Accept': 'application/json, text/javascript, */*; q=0.01',
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36',
            'X-Requested-With': 'XMLHttpRequest',
            'Referer': 'http://hd.chinatax.gov.cn/nszx/InitCredit.html',
            'Accept-Encoding': 'gzip, deflate',
            'Accept-Language': 'zh-CN,zh;q=0.9'
        }

        self.cookies = {
            'yfx_c_g_u_id_10003701': 'ck21013011582214923037283811800',
            'yfx_f_l_v_t_10003701': 'f_t_1611979102489__r_t_1611979102489__v_t_1611979102489__r_c_0',
            'JSESSIONID': '52B2AD0DC6E943B7BFD1E25A5E6B9907',
            '_Jo0OQK': '595C840C56C2736D27D1688C38C71781A0257625D274062322959B6DD768A3F621B6327A4A63E8038C69151C3B0C3FD7925A2F5E8639C032F51AC15E028DC9C2A671B918CCA8FE3BB9470EE0D297309F84070EE0D297309F8403E79D27820DC97D0B5F5E5E09BAC0B2AGJ1Z1Vw==',
        }

        self.payload = {
            'page': '100',
            'location=': '110000',
            'code': '',
            'name': '',
            'evalyear': '2019',
            'cPage': ''
        }

        self.session = requests.session()
        self.session.headers.clear()
        self.session.headers.update(self.headers_first)
        self.session.cookies.update(self.cookies)

    def get_cookie_c3vk(self, response):
        # 生成C3VK
        args1 = ''
        c3vk = ''
        try:
            args1 = re.search(r',"(\w.*?)"\)</script', response.text).group(1)
            print('args1: ', args1)
        except:
            c3vk = re.search('cookie="C3VK=(\w.*?);', response.text).group(1)

        if args1:
            js_text = '''
                    function get_c3vk(jc9) {
                        var B4MJ = "000000";
                        w1Oh5 = 0x6a9a, MZyt3 = 0x6ab9;
                        B4MJ += (jc9 ^ w1Oh5).toString(16);
                        B4MJ = B4MJ.slice(-6);
                        return B4MJ;
                    }
                '''
            c3vk = execjs.compile(js_text).call('get_c3vk', args1)
        print('c3vk: ', c3vk)
        return c3vk

    def run(self):
        res = self.session.get(self.url_first)
        print(res.text)

        cookies = requests.utils.dict_from_cookiejar(self.session.cookies)
        cookies['C3VK'] = self.get_cookie_c3vk(res)

        self.session.cookies.update(cookies)
        self.session.headers.update(self.headers_data)

        for page in range(1, 5):
            self.payload['page'] = page

            response = self.session.post(self.url_data, data=self.payload)

            # print(response.text)
            if isinstance(response.content, bytes):
                encoding = cchardet.detect(response.content)['encoding']

                html = response.content.decode(encoding, 'ignore')
                print(html)


if __name__ == '__main__':
    tax = Chinatax()
    tax.run()