【爬虫进阶】猿人学任务一之JS混淆(难度2.0)

原创 已于 2022-09-15 17:30:45 修改 · 696 阅读 · 8 ·
CC 4.0 BY-SA版权
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
文章标签：

#javascript #爬虫 #前端

于 2022-09-15 17:29:24 首次发布
本文讲述了如何逆向分析并解开JavaScript混淆代码，通过逐步排查，发现并修复atob未定义问题，最终成功获取加密后的M参数。涉及MD5加密和代码美化过程。

目录

简介

你问我Js逆向是什么？请看：👇👇👇

分析

网站：aHR0cHM6Ly9tYXRjaC55dWFucmVueHVlLmNvbS9tYXRjaC8x（base64解密）

  1. 打开调式，发现弹出无限Debug，有几种跳过方法就不过多说明，我这里采用最简单的方法直接在debug行号下右键，点击不在此处暂停，就能跳过debug
    在这里插入图片描述

  2. 跳过之后刷新一下页面，找到数据接口，有一个m参数，毫无疑问，我们需要逆向的就是它了
    在这里插入图片描述

  3. 全局搜索m，可惜找不到，从题目标题大概可以确定代码都混淆过了

  4. 我们直接在启动堆栈里面找调用的js，前两个都是jquery，所以我们直接从第三个开始入手
    在这里插入图片描述

  5. 确实是混淆，我们在控制台打印一下_0x2268f9，看看这是个啥玩意
    在这里插入图片描述

  6. 打开控制台，又一个debug，老样子行号右键，一律跳过！
    在这里插入图片描述

  7. 跳过之后，继续打印，结果是一个时间戳
    在这里插入图片描述

  8. 再往下看_0x57feae，里面调用了oo0O0函数，点进去看看
    在这里插入图片描述

  9. 找到oo0O0函数，代码无法格式化，利用格式化工具美化一下
    在这里插入图片描述

  10. 继续往下看，打印所有参数，发现_0x5d83a3[‘\x6d’]和M参数很接近，会不会就是要破解的M呢？
    在这里插入图片描述

扣代码(心态崩)

激动的心颤抖的手，看到代码就全身发抖
接下来就是最最最关键的扣代码环节，也是很关键的部分，要是扣不好，前面白费功夫

  1. 上面已经找到oo0O0函数，经过美化，我们得到：

    function oo0O0(mw) {
	window.b = '';
	for (var i = 0,
	len = window.a.length; i < len; i++) {
		console.log(window.a[i]);
		window.b += String[document.e + document.g](window.a[i][document.f + document.h]() - i - window.c)
	}
	var U = ['W5r5W6VdIHZcT8kU', 'WQ8CWRaxWQirAW=='];
	var J = function(o, E) {
		o = o - 0x0;
		var N = U[o];
		if (J['bSSGte'] === undefined) {
			var Y = function(w) {
				var m = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789+/=',
				T = String(w)['replace'](/=+$/, '');
				var A = '';
				for (var C = 0x0,
				b, W, l = 0x0; W = T['charAt'](l++);~W && (b = C % 0x4 ? b * 0x40 + W: W, C++%0x4) ? A += String['fromCharCode'](0xff & b >> ( - 0x2 * C & 0x6)) : 0x0) {
					W = m['indexOf'](W)
				}
				return A
			};
			var t = function(w, m) {
				var T = [],
				A = 0x0,
				C,
				b = '',
				W = '';
				w = Y(w);
				for (var R = 0x0,
				v = w['length']; R < v; R++) {
					W += '%' + ('00' + w['charCodeAt'](R)['toString'](0x10))['slice']( - 0x2)
				}
				w = decodeURIComponent(W);
				var l;
				for (l = 0x0; l < 0x100; l++) {
					T[l] = l
				}
				for (l = 0x0; l < 0x100; l++) {
					A = (A + T[l] + m['charCodeAt'](l % m['length'])) % 0x100,
					C = T[l],
					T[l] = T[A],
					T[A] = C
				}
				l = 0x0,
				A = 0x0;
				for (var L = 0x0; L < w['length']; L++) {
					l = (l + 0x1) % 0x100,
					A = (A + T[l]) % 0x100,
					C = T[l],
					T[l] = T[A],
					T[A] = C,
					b += String['fromCharCode'](w['charCodeAt'](L) ^ T[(T[l] + T[A]) % 0x100])
				}
				return b
			};
			J['luAabU'] = t,
			J['qlVPZg'] = {},
			J['bSSGte'] = !![]
		}
		var H = J['qlVPZg'][o];
		return H === undefined ? (J['TUDBIJ'] === undefined && (J['TUDBIJ'] = ![外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-Fq8jfiHN-1663230232374)(N, E)], J['qlVPZg'][o] = N) : N = H,
		N
	};
	eval(atob(window['b'])[J('0x0', ']dQW')](J('0x1', 'GTu!'), '\x27' + mw + '\x27'));
	return ''
}

  2. 执行报错，atob未定义，控制台打印一下

    在这里插入图片描述

  3. 确定是MD5加密，到这步就简单了，美化一下代码

    var hexcase = 0;
var b64pad = "";
var chrsz = 16;
function hex_md5(a) {
	return binl2hex(core_md5(str2binl(a), a.length * chrsz))
}
function b64_md5(a) {
	return binl2b64(core_md5(str2binl(a), a.length * chrsz))
}
function str_md5(a) {
	return binl2str(core_md5(str2binl(a), a.length * chrsz))
}
function hex_hmac_md5(a, b) {
	return binl2hex(core_hmac_md5(a, b))
}
function b64_hmac_md5(a, b) {
	return binl2b64(core_hmac_md5(a, b))
}
function str_hmac_md5(a, b) {
	return binl2str(core_hmac_md5(a, b))
}
function md5_vm_test() {
	return hex_md5("abc") == "900150983cd24fb0d6963f7d28e17f72"
}
function core_md5(p, k) {
	p[k >> 5] |= 128 << ((k) % 32);
	p[(((k + 64) >>> 9) << 4) + 14] = k;
	var o = 1732584193;
	var n = -271733879;
	var m = -1732584194;
	var l = 271733878;
	for (var g = 0; g < p.length; g += 16) {
		var j = o;
		var h = n;
		var f = m;
		var e = l;
		o = md5_ff(o, n, m, l, p[g + 0], 7, -680976936);
		l = md5_ff(l, o, n, m, p[g + 1], 12, -389564586);
		m = md5_ff(m, l, o, n, p[g + 2], 17, 606105819);
		n = md5_ff(n, m, l, o, p[g + 3], 22, -1044525330);
		o = md5_ff(o, n, m, l, p[g + 4], 7, -176418897);
		l = md5_ff(l, o, n, m, p[g + 5], 12, 1200080426);
		m = md5_ff(m, l, o, n, p[g + 6], 17, -1473231341);
		n = md5_ff(n, m, l, o, p[g + 7], 22, -45705983);
		o = md5_ff(o, n, m, l, p[g + 8], 7, 1770035416);
		l = md5_ff(l, o, n, m, p[g + 9], 12, -1958414417);
		m = md5_ff(m, l, o, n, p[g + 10], 17, -42063);
		n = md5_ff(n, m, l, o, p[g + 11], 22, -1990404162);
		o = md5_ff(o, n, m, l, p[g + 12], 7, 1804660682);
		l = md5_ff(l, o, n, m, p[g + 13], 12, -40341101);
		m = md5_ff(m, l, o, n, p[g + 14], 17, -1502002290);
		n = md5_ff(n, m, l, o, p[g + 15], 22, 1236535329);
		o = md5_gg(o, n, m, l, p[g + 1], 5, -165796510);
		l = md5_gg(l, o, n, m, p[g + 6], 9, -1069501632);
		m = md5_gg(m, l, o, n, p[g + 11], 14, 643717713);
		n = md5_gg(n, m, l, o, p[g + 0], 20, -373897302);
		o = md5_gg(o, n, m, l, p[g + 5], 5, -701558691);
		l = md5_gg(l, o, n, m, p[g + 10], 9, 38016083);
		m = md5_gg(m, l, o, n, p[g + 15], 14, -660478335);
		n = md5_gg(n, m, l, o, p[g + 4], 20, -405537848);
		o = md5_gg(o, n, m, l, p[g + 9], 5, 568446438);
		l = md5_gg(l, o, n, m, p[g + 14], 9, -1019803690);
		m = md5_gg(m, l, o, n, p[g + 3], 14, -187363961);
		n = md5_gg(n, m, l, o, p[g + 8], 20, 1163531501);
		o = md5_gg(o, n, m, l, p[g + 13], 5, -1444681467);
		l = md5_gg(l, o, n, m, p[g + 2], 9, -51403784);
		m = md5_gg(m, l, o, n, p[g + 7], 14, 1735328473);
		n = md5_gg(n, m, l, o, p[g + 12], 20, -1921207734);
		o = md5_hh(o, n, m, l, p[g + 5], 4, -378558);
		l = md5_hh(l, o, n, m, p[g + 8], 11, -2022574463);
		m = md5_hh(m, l, o, n, p[g + 11], 16, 1839030562);
		n = md5_hh(n, m, l, o, p[g + 14], 23, -35309556);
		o = md5_hh(o, n, m, l, p[g + 1], 4, -1530992060);
		l = md5_hh(l, o, n, m, p[g + 4], 11, 1272893353);
		m = md5_hh(m, l, o, n, p[g + 7], 16, -155497632);
		n = md5_hh(n, m, l, o, p[g + 10], 23, -1094730640);
		o = md5_hh(o, n, m, l, p[g + 13], 4, 681279174);
		l = md5_hh(l, o, n, m, p[g + 0], 11, -358537222);
		m = md5_hh(m, l, o, n, p[g + 3], 16, -722881979);
		n = md5_hh(n, m, l, o, p[g + 6], 23, 76029189);
		o = md5_hh(o, n, m, l, p[g + 9], 4, -640364487);
		l = md5_hh(l, o, n, m, p[g + 12], 11, -421815835);
		m = md5_hh(m, l, o, n, p[g + 15], 16, 530742520);
		n = md5_hh(n, m, l, o, p[g + 2], 23, -995338651);
		o = md5_ii(o, n, m, l, p[g + 0], 6, -198630844);
		l = md5_ii(l, o, n, m, p[g + 7], 10, 11261161415);
		m = md5_ii(m, l, o, n, p[g + 14], 15, -1416354905);
		n = md5_ii(n, m, l, o, p[g + 5], 21, -57434055);
		o = md5_ii(o, n, m, l, p[g + 12], 6, 1700485571);
		l = md5_ii(l, o, n, m, p[g + 3], 10, -1894446606);
		m = md5_ii(m, l, o, n, p[g + 10], 15, -1051523);
		n = md5_ii(n, m, l, o, p[g + 1], 21, -2054922799);
		o = md5_ii(o, n, m, l, p[g + 8], 6, 1873313359);
		l = md5_ii(l, o, n, m, p[g + 15], 10, -30611744);
		m = md5_ii(m, l, o, n, p[g + 6], 15, -1560198380);
		n = md5_ii(n, m, l, o, p[g + 13], 21, 1309151649);
		o = md5_ii(o, n, m, l, p[g + 4], 6, -145523070);
		l = md5_ii(l, o, n, m, p[g + 11], 10, -1120210379);
		m = md5_ii(m, l, o, n, p[g + 2], 15, 718787259);
		n = md5_ii(n, m, l, o, p[g + 9], 21, -343485551);
		o = safe_add(o, j);
		n = safe_add(n, h);
		m = safe_add(m, f);
		l = safe_add(l, e)
	}
	return Array(o, n, m, l)
}
function md5_cmn(h, e, d, c, g, f) {
	return safe_add(bit_rol(safe_add(safe_add(e, h), safe_add(c, f)), g), d)
}
function md5_ff(g, f, k, j, e, i, h) {
	return md5_cmn((f & k) | ((~f) & j), g, f, e, i, h)
}
function md5_gg(g, f, k, j, e, i, h) {
	return md5_cmn((f & j) | (k & (~j)), g, f, e, i, h)
}
function md5_hh(g, f, k, j, e, i, h) {
	return md5_cmn(f ^ k ^ j, g, f, e, i, h)
}
function md5_ii(g, f, k, j, e, i, h) {
	return md5_cmn(k ^ (f | (~j)), g, f, e, i, h)
}
function core_hmac_md5(c, f) {
	var e = str2binl(c);
	if (e.length > 16) {
		e = core_md5(e, c.length * chrsz)
	}
	var a = Array(16),
	d = Array(16);
	for (var b = 0; b < 16; b++) {
		a[b] = e[b] ^ 909522486;
		d[b] = e[b] ^ 1549556828
	}
	var g = core_md5(a.concat(str2binl(f)), 512 + f.length * chrsz);
	return core_md5(d.concat(g), 512 + 128)
}
function safe_add(a, d) {
	var c = (a & 65535) + (d & 65535);
	var b = (a >> 16) + (d >> 16) + (c >> 16);
	return (b << 16) | (c & 65535)
}
function bit_rol(a, b) {
	return (a << b) | (a >>> (32 - b))
}
function str2binl(d) {
	var c = Array();
	var a = (1 << chrsz) - 1;
	for (var b = 0; b < d.length * chrsz; b += chrsz) {
		c[b >> 5] |= (d.charCodeAt(b / chrsz) & a) << (b % 32)
	}
	return c
}
function binl2str(c) {
	var d = "";
	var a = (1 << chrsz) - 1;
	for (var b = 0; b < c.length * 32; b += chrsz) {
		d += String.fromCharCode((c[b >> 5] >>> (b % 32)) & a)
	}
	return d
}
function binl2hex(c) {
	var b = hexcase ? "0123456789ABCDEF": "0123456789abcdef";
	var d = "";
	for (var a = 0; a < c.length * 4; a++) {
		d += b.charAt((c[a >> 2] >> ((a % 4) * 8 + 4)) & 15) + b.charAt((c[a >> 2] >> ((a % 4) * 8)) & 15)
	}
	return d
}
function binl2b64(d) {
	var c = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
	var f = "";
	for (var b = 0; b < d.length * 4; b += 3) {
		var e = (((d[b >> 2] >> 8 * (b % 4)) & 255) << 16) | (((d[b + 1 >> 2] >> 8 * ((b + 1) % 4)) & 255) << 8) | ((d[b + 2 >> 2] >> 8 * ((b + 2) % 4)) & 255);
		for (var a = 0; a < 4; a++) {
			if (b * 8 + a * 6 > d.length * 32) {
				f += b64pad
			} else {
				f += c.charAt((e >> 6 * (3 - a)) & 63)
			}
		}
	}
	return f
};
window.f = hex_md5(mwqqppz)

  4. 很容易理解，这里就是把 mwqqppz 替换成了 mw, 通过eval执行hex_md5(mw), 最后赋值给 window.f

  5. 我们将window.f 稍微改一下，就能得到m了

    function get_param(ts){
    var timestamp = parseInt(ts)
    var mwqqppz = timestamp + 100000000
    var m = hex_md5(mwqqppz.toString()) + '丨' + mwqqppz / 1000;
    return m
}

成果

  1. 成功获取m参数，对比网页一致

    在这里插入图片描述

  2. py中导入execjs运行Js文件

    pip install execjs

    import requests
import time
import execjs

def get_param():
    ts = str(int(time.time())) + "000"
    with open('jm.js','r',encoding='utf8') as f:
        js = f.read()
    param = execjs.compile(js).call('get_param',ts)
    # response = requests.get(url=self.jm_url, params=params)
    # param = response.text
    print(param)
    return param

  3. 请求接口，获取数据

    def get_data(page, param):
  headers = {
      "User-Agent": "yuanrenxue.project",
  }
  params = {
      "page": page,
      "m": param,
  }
  response = requests.get(url=self.base_url, params=params, headers=headers).json()
  if response["status"] == "1":
      data = response["data"]
      values = [i["value"] for i in data]
      print(values)
      return values

  4. 计算结果，得到平均数

    import numpy as np #导入numpy计算 mean

def mean():
   value = []
    for i in range(1, 6):
        param = get_param()
        value = get_data(page=i, param=param)
        value.append(value)
        
    result = np.mean(total_value)
    print(result)

    在这里插入图片描述

点关注不迷路，本文若对你有帮助，烦请三连支持一下 ❤️❤️❤️
各位的支持和认可就是我最大的动力❤️❤️❤️

在这里插入图片描述

评论 8
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值