crawlab_feader/FworkSpider/crawl_func/PYCCS_cookies.py

# -*- coding: utf-8 -*-
"""
Created on 2023-09-08 
---------
@summary: 进入前检查浏览器 PYCCS
---------
@author: Lzz
"""
import re

import execjs
import requests


def get_ck_by_js(*args):
    ex_js = '''
        function get_ck(a,b,c) {
            var x08c924 = parseInt(a);
            x08c924 = x08c924 * parseInt(b);
            x08c924 = x08c924 + parseInt(c);
            x08c924 = (x08c924 * 0x3 + 0x7);
            if (x08c924 < 0x7b)
                x08c924 = x08c924 + 0x929;
            if (x08c924 > 0x929)
                x08c924 = Math['floor'](x08c924 / 0x7b);
            return x08c924
        }
    '''
    a, b, c = args
    ctx = execjs.compile(ex_js)
    return ctx.call('get_ck', a, b, c)


def get_ck_by_py(*args):
    a, b, c = args

    # 将输入转换为整数
    x08c924 = int(a)
    x08c924 *= int(b)
    x08c924 += int(c)

    # 执行运算
    x08c924 = x08c924 * 0x3 + 0x7  # 0x3是十六进制的3，0x7是十六进制的7

    # 条件判断
    if x08c924 < 0x7b:  # 0x7b是十六进制的123
        x08c924 += 0x929  # 0x929是十六进制的2345

    if x08c924 > 0x929:
        x08c924 = x08c924 // 0x7b  # 使用整数除法模拟Math.floor

    return x08c924


def get_ck(*args, platform='py'):
    if platform == 'js':
        return get_ck_by_js(*args)
    else:
        return get_ck_by_py(*args)


def find_pyccs(url, headers, proxies=None, platform=None):
    cookies = {}
    exception = None

    request_params = dict(headers=headers, timeout=60, verify=False)
    for i in range(3):
        with requests.Session() as session:
            session.proxies = proxies
            try:
                res = session.get(url, **request_params)
                pm_data = "".join(re.findall('\|function\|(.*?)\|version\|',res.text,re.S)).split('|')
                answer = get_ck(pm_data[1], pm_data[3], pm_data[-1], platform=platform)
                data = {"answer": f"{answer}"}

                url2 = url.split('?')[0]
                resp = session.post(url2, data=data, **request_params)
                cookies = session.cookies.get_dict()
                if re.findall('\|function\|(.*?)\|version\|', resp.text, re.S):
                    print(f"请求解析异常！重试 {i + 1} 次")
                else:
                    return cookies
            except Exception as e:
                print("cookies_PYCCS 获取失败！")
                exception = e
                break

    return cookies


get_PYCCS_ck = find_pyccs


if __name__ == "__main__":
    assert get_ck_by_py(1, 2, 3) == get_ck_by_js(1, 2, 3)