1.猿人学web爬虫攻防第一题 js混淆源码乱码
题目链接：http://match.yuanrenxue.com/match/1
1.首先我们打开F12开发者工具,点击.....
我们可以看到在请求中有m的加密参数！
2.根据题目js混淆，我们寻找m参数的js方法。
-
这里我搜索的是|的符号，因为这种符号一般很少出现在js代码中。当然还有其他的方法，因人而异。
Ok,我们可以看到搜索结果已经出现，我们的js代码找到了。
将js代码复制，格式化找到我们需要的。
- 可以看到m参数是由oo0O0函数+ window.f;生成。
- 继续寻找oo0O0函数。
可以看到oo0O0函数也是在这个js当中，我们将该函数复制下来。
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'] = !![]), N = J['luAabU'](N, E), J['qlVPZg'][o] = N) : N = H,
N
};
eval(atob(window['b'])[J('0x0', ']dQW')](J('0x1', 'GTu!'), '\x27' + mw + '\x27'));
return ''
}
有点奇怪的是这里return '',所以m的值完全取决于 window.f;
我们看oo0O0函数的最后部分。
eval(atob(window['b'])[J('0x0', ']dQW')](J('0x1', 'GTu!'), '\x27' + mw + '\x27'));
return ''
JS中的 eval() 函数可计算某个字符串，并执行其中的的 JavaScript 代码
而eval()里面还调用了一个函数atob()
atob() 方法用于解码使用 base-64 编码的字符串
我们将 【atob(window['b'])】复制下来,在调试工具的Console运行一下,可以得到了下列代码
将其复制，进行，格式化，得到。
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)
查看js代码，看到window.f = hex_md5(mwqqppz)
window.f是由hex_md5方法进行处理，而mwqqppz是什么？继续分析
eval函数里面除了atob(window['b'],还有：
- J('0x0', ']dQW')
- J('0x1', 'GTu!')
- 'x27' + mw + 'x27'
继续尝试：
我们发现J 不存在，将js代码中的J 复制出来 执行。
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'] = !![]), N = J['luAabU'](N, E), J['qlVPZg'][o] = N) : N = H,
N
};
再次尝试，发现可以了。
再次尝试J('0x1', 'GTu!')
再次尝试'\x27' + mw + '\x27';
mw没有找到 ！这是因为[ mw ]是oo0O0()函数的一个形参
Ok,这样看 就非常清晰思路。
3.翻译eval()
eval(atob(window['b'])[J('0x0', ']dQW')](J('0x1', 'GTu!'), '\x27' + mw + '\x27'));
翻译后：
eval(atob(window['b'])["replace"]("mwqqppz",'mw'));
'\x27'，其实就是‘。
这个函数的意思实际上就是将【atob(window['b'])】里面的【mwqqppz】替换成【mw】
而mw实际上就是时间戳字符串。
// 我们一步步分析下来也就是
var timestamp = Date.parse(new Date()) + 100000000;
var m = oo0O0(timestamp.toString()) + window.f;
var m = window.f;
var m = hex_md5(mwqqppz);
var m = hex_md5(timestamp);
4.结果
function get_m() {
//var timestamp = Date.parse(new Date()) + 100000000;
var timestamp = '1612253498000';
var m = hex_md5(timestamp);
return m;
}
5.最后的爬虫和解出答案
在Python代码中可以通过第三方库execjs,执行这个JS文件,得到密文
# -*- coding: utf-8 -*-
'''
@Time : 2021/2/1 11:24
@Author : 水一RAR
'''
import requests
import execjs
import time
def get_md5_value():
# 导入JS,读取需要的js文件
with open(r'./js代码/01.js',encoding='utf-8',mode='r') as f:
JsData = f.read()
# 加载js文件,使用call()函数执行,传入需要执行函数即可获取返回值
psd = execjs.compile(JsData).call('get_m')
psd = psd.replace('丨','%E4%B8%A8')
return psd
def get_data(page_num,md5):
url = f'http://match.yuanrenxue.com/api/match/1?page={page_num}&m={md5}'
headers = {
'Host':'match.yuanrenxue.com',
'Referer':'http://match.yuanrenxue.com/match/1',
'User-Agent':'yuanrenxue.project',
}
response = requests.get(url,headers=headers)
return response.json()
if __name__ == '__main__':
sum_num = 0
index_num = 0
for page_num in range(1,6):
info = get_data(page_num,get_md5_value())
price_list = [i['value'] for i in info['data']]
print(f'第{page_num}页的价格列表{price_list}')
sum_num += sum(price_list)
index_num += len(price_list)
time.sleep(1)
average_price = sum_num / index_num
print(f'机票价格的平均值:{average_price}')
6.结果：
