某网站Web端爬虫攻防大赛第一题详细题解
### **实战地址**```javascript
http://match.yuanrenxue.com/match/1
```
### **抓包分析**
**
打开上面的地址并按下F12，有个debug，选中debug这一行，
右键 **never pause here**，直接就过了。
再点击 第二页，接口有个m参数:
!(https://upload-images.jianshu.io/upload_images/23580295-3a728040032f023c.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
|后面有点像时间戳，查看页面源代码，发现这里:
!(https://upload-images.jianshu.io/upload_images/23580295-fc5d8b31d9aa89b0.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
有好几个** script **标签，关键代码扣出来后整理一波:
```javascript
var timestamp = Date.parse(new Date());
var m = oo0O0(timestamp.toString()) + window.f;
var list = {
"page": window.page,
"m": m + '丨' + timestamp / 1000
};
```
由 | 字符拼接，后面是时间戳，那不是这里还是哪里？
那就看** oo0O0** 这个函数，抠出来:
```javascript
function oo0O0(mw) {
window.b = '';
for (var i = 0, len = window.a.length; i < len; i++) {
console.log(window.a);
window.b += String(window.a() - i - window.c)
}
var U = ['W5r5W6VdIHZcT8kU', 'WQ8CWRaxWQirAW=='];
var J = function(o, E) {
o = o - 0x0;
var N = U;
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
}
for (l = 0x0; l < 0x100; l++) {
A = (A + T + m['charCodeAt'](l % m['length'])) % 0x100,
C = T,
T = T,
T = C
}
l = 0x0,
A = 0x0;
for (var L = 0x0; L < w['length']; L++) {
l = (l + 0x1) % 0x100,
A = (A + T) % 0x100,
C = T,
T = T,
T = C,
b += String['fromCharCode'](w['charCodeAt'](L) ^ T[(T + T) % 0x100])
}
return b
};
J['luAabU'] = t,
J['qlVPZg'] = {},
J['bSSGte'] = !![]
}
var H = J['qlVPZg'];
return H === undefined ? (J['TUDBIJ'] === undefined && (J['TUDBIJ'] = !![]),
N = J['luAabU'](N, E),
J['qlVPZg'] = N) : N = H,
N
};
eval(atob(window['b'])dQW')](J('0x1', 'GTu!'), '\x27' + mw + '\x27'));
return ''
}
```
注意返回值是一个空字符串，所以这行代码:
```javascript
var m = oo0O0(timestamp.toString()) + window.f;
```
m的值就是 window.f,函数里面有个eval，看看是干嘛的，控制台输入:
```javascript
atob(window['b'])
```
base64解码后是一段代码:
```javascript
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 |= 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, 7, -680976936);
l = md5_ff(l, o, n, m, p, 12, -389564586);
m = md5_ff(m, l, o, n, p, 17, 606105819);
n = md5_ff(n, m, l, o, p, 22, -1044525330);
o = md5_ff(o, n, m, l, p, 7, -176418897);
l = md5_ff(l, o, n, m, p, 12, 1200080426);
m = md5_ff(m, l, o, n, p, 17, -1473231341);
n = md5_ff(n, m, l, o, p, 22, -45705983);
o = md5_ff(o, n, m, l, p, 7, 1770035416);
l = md5_ff(l, o, n, m, p, 12, -1958414417);
m = md5_ff(m, l, o, n, p, 17, -42063);
n = md5_ff(n, m, l, o, p, 22, -1990404162);
o = md5_ff(o, n, m, l, p, 7, 1804660682);
l = md5_ff(l, o, n, m, p, 12, -40341101);
m = md5_ff(m, l, o, n, p, 17, -1502002290);
n = md5_ff(n, m, l, o, p, 22, 1236535329);
o = md5_gg(o, n, m, l, p, 5, -165796510);
l = md5_gg(l, o, n, m, p, 9, -1069501632);
m = md5_gg(m, l, o, n, p, 14, 643717713);
n = md5_gg(n, m, l, o, p, 20, -373897302);
o = md5_gg(o, n, m, l, p, 5, -701558691);
l = md5_gg(l, o, n, m, p, 9, 38016083);
m = md5_gg(m, l, o, n, p, 14, -660478335);
n = md5_gg(n, m, l, o, p, 20, -405537848);
o = md5_gg(o, n, m, l, p, 5, 568446438);
l = md5_gg(l, o, n, m, p, 9, -1019803690);
m = md5_gg(m, l, o, n, p, 14, -187363961);
n = md5_gg(n, m, l, o, p, 20, 1163531501);
o = md5_gg(o, n, m, l, p, 5, -1444681467);
l = md5_gg(l, o, n, m, p, 9, -51403784);
m = md5_gg(m, l, o, n, p, 14, 1735328473);
n = md5_gg(n, m, l, o, p, 20, -1921207734);
o = md5_hh(o, n, m, l, p, 4, -378558);
l = md5_hh(l, o, n, m, p, 11, -2022574463);
m = md5_hh(m, l, o, n, p, 16, 1839030562);
n = md5_hh(n, m, l, o, p, 23, -35309556);
o = md5_hh(o, n, m, l, p, 4, -1530992060);
l = md5_hh(l, o, n, m, p, 11, 1272893353);
m = md5_hh(m, l, o, n, p, 16, -155497632);
n = md5_hh(n, m, l, o, p, 23, -1094730640);
o = md5_hh(o, n, m, l, p, 4, 681279174);
l = md5_hh(l, o, n, m, p, 11, -358537222);
m = md5_hh(m, l, o, n, p, 16, -722881979);
n = md5_hh(n, m, l, o, p, 23, 76029189);
o = md5_hh(o, n, m, l, p, 4, -640364487);
l = md5_hh(l, o, n, m, p, 11, -421815835);
m = md5_hh(m, l, o, n, p, 16, 530742520);
n = md5_hh(n, m, l, o, p, 23, -995338651);
o = md5_ii(o, n, m, l, p, 6, -198630844);
l = md5_ii(l, o, n, m, p, 10, 11261161415);
m = md5_ii(m, l, o, n, p, 15, -1416354905);
n = md5_ii(n, m, l, o, p, 21, -57434055);
o = md5_ii(o, n, m, l, p, 6, 1700485571);
l = md5_ii(l, o, n, m, p, 10, -1894446606);
m = md5_ii(m, l, o, n, p, 15, -1051523);
n = md5_ii(n, m, l, o, p, 21, -2054922799);
o = md5_ii(o, n, m, l, p, 6, 1873313359);
l = md5_ii(l, o, n, m, p, 10, -30611744);
m = md5_ii(m, l, o, n, p, 15, -1560198380);
n = md5_ii(n, m, l, o, p, 21, 1309151649);
o = md5_ii(o, n, m, l, p, 6, -145523070);
l = md5_ii(l, o, n, m, p, 10, -1120210379);
m = md5_ii(m, l, o, n, p, 15, 718787259);
n = md5_ii(n, m, l, o, p, 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 = e ^ 909522486;
d = e ^ 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 |= (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 % 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 % 4) * 8 + 4)) & 15) + b.charAt((c >> ((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 >> 8 * (b % 4)) & 255) << 16) | (((d >> 8 * ((b + 1) % 4)) & 255) << 8) | ((d >> 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)
```
噢，window.f 原来在这里赋值的。把变量U和J分别在控制台运行下，再看下面的两个值:
!(https://upload-images.jianshu.io/upload_images/23580295-f703b0775353150c.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
原来就是把 **hex_md5 **的参数替换成 **oo0O0** 函数的参数。
逻辑清晰了，就是改造代码了。
### **改造代码，运行结果**
将上面的代码最后一行:
```javascript
;window.f = hex_md5(mwqqppz)
```
变成:
```javascript
var timestamp=Date.parse(new Date());
f = hex_md5(timestamp.toString()) + "|" + timestamp/1000;;
console.log(f)
```
保存为js文件，运行，得到结果:
!(https://upload-images.jianshu.io/upload_images/23580295-547df715d669c237.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
基本没啥难度吧。 图片挂了 mark，学习 图片挂了 过来向蔡老板学习 膜拜大佬！
页:
[1]