新版本知乎使用headers中的x-zse-86进行校验
URL :https://www.zhihu.com/api/v4/search_v3?t=general&q=怀孕失眠&correction=1&offset=0&limit=20&lc_idx=0&show_all_topics=0
这是搜索接口链接
我们来看一下Request Headers都有什么信息
我们可以看到很乱, 但是这里边的信息不是全部都有用,下面我来测试下那些有用哪写没有用
经过测试我们发先实际上有的信息就这么几个,看起来清晰多了。下面来这翻页测试看看哪些信息是变化的, 我们发现只有x-zse-86的信息是有变化的, 所以我们找到s-zse-86的生成方式就行了
全局搜索x-zse-86
![在这里插入图片描述](https://img-blog.csdnimg.cn/20200723200804547.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MDM1MjcxNQ==,size_16,color_FFFFFF,t_70
全局搜索x-zse-86
可以明显的看出x-zse-86是由Z和p做的字符串拼接,Z是写死的常量1.0, 所有p就是我们想要的,向上找可以发现p = f.signture,我们来找一下f.signture是什么
通过打点调试
我们找到signture = Y()(z()(f))
首先对这个Y()(z()(f))进行拆解 先看下找到参数f 可以看到方框上边的这行就是f的生成方式
f = [r, u, l, o, $(d) && d, i].filter(Boolean).join("+");
对这行进行打点调试可以知道r,u,l,o,d,i都是什么 然后通过join对列表进行字符串拼接使用+
结果:
"3_2.0+/api/v4/search_v3?t=general&q=%E6%80%80%E5%AD%95%E5%A4%B1%E7%9C%A0&correction=1&offset=0&limit=20&lc_idx=0&show_all_topics=0+https://www.zhihu.com/search?type=content&q=%E6%80%80%E5%AD%95%E5%A4%B1%E7%9C%A0+"AACSLMY7lBGPTo9fXdy2pmiGQ4ZVVUcqzC4=|1594785557""
其实就是请求头里的x-zse-83+url+referer+“cookie.d_c0”
然后来看z()(f), 通过断点调试出来的是个32位字符串,首先我们想到的就是md5
我们在console里测试下,发现这个z()就是做了一个md5的操作
最后一步是Y()的这个方法
可以看到Y这调用的是__g.encrypy(encodeURICOmponent®) 在console中点击是可以直接挑过去的
这的还js比较多无法通过猜来破解了, 所以直接把这块的js copy出来做一些修改直接通过execjs模块来调用, 这个封装的代码我就不自己写了,网上挺多的我直接找了一个略作修改,
如下:
创建一个g_encrypt.js的文件代码如下
const jsdom = require("jsdom");
const { JSDOM } = jsdom;
const dom = new JSDOM(`Hello world
`);
window = dom.window;
document = window.document;
XMLHttpRequest = window.XMLHttpRequest;
var exports = {}
function t(e) {
return (t = "function" == typeof Symbol && "symbol" == typeof Symbol.A ? function(e) {
return typeof e
}
: function(e) {
return e && "function" == typeof Symbol && e.constructor === Symbol && e !== Symbol.prototype ? "symbol" : typeof e
}
)(e)
}
Object.defineProperty(exports, "__esModule", {
value: !0
});
var A = "2.0"
, __g = {};
function s() {}
function i(e) {
this.t = (2048 & e) >> 11,
this.s = (1536 & e) >> 9,
this.i = 511 & e,
this.h = 511 & e
}
function h(e) {
this.s = (3072 & e) >> 10,
this.h = 1023 & e
}
function a(e) {
this.a = (3072 & e) >> 10,
this.c = (768 & e) >> 8,
this.n = (192 & e) >> 6,
this.t = 63 & e
}
function c(e) {
this.s = e >> 10 & 3,
this.i = 1023 & e
}
function n() {}
function e(e) {
this.a = (3072 & e) >> 10,
this.c = (768 & e) >> 8,
this.n = (192 & e) >> 6,
this.t = 63 & e
}
function o(e) {
this.h = (4095 & e) >> 2,
this.t = 3 & e
}
function r(e) {
this.s = e >> 10 & 3,
this.i = e >> 2 & 255,
this.t = 3 & e
}
s.prototype.e = function(e) {
e.o = !1
}
,
i.prototype.e = function(e) {
switch (this.t) {
case 0:
e.r[this.s] = this.i;
break;
case 1:
e.r[this.s] = e.k[this.h]
}
}
,
h.prototype.e = function(e) {
e.k[this.h] = e.r[this.s]
}
,
a.prototype.e = function(e) {
switch (this.t) {
case 0:
e.r[this.a] = e.r[this.c] + e.r[this.n];
break;
case 1:
e.r[this.a] = e.r[this.c] - e.r[this.n];
break;
case 2:
e.r[this.a] = e.r[this.c] * e.r[this.n];
break;
case 3:
e.r[this.a] = e.r[this.c] / e.r[this.n];
break;
case 4:
e.r[this.a] = e.r[this.c] % e.r[this.n];
break;
case 5:
e.r[this.a] = e.r[this.c] == e.r[this.n];
break;
case 6:
e.r[this.a] = e.r[this.c] >= e.r[this.n];
break;
case 7:
e.r[this.a] = e.r[this.c] || e.r[this.n];
break;
case 8:
e.r[this.a] = e.r[this.c] && e.r[this.n];
break;
case 9:
e.r[this.a] = e.r[this.c] !== e.r[this.n];
break;
case 10:
e.r[this.a] = t(e.r[this.c]);
break;
case 11:
e.r[this.a] = e.r[this.c]in e.r[this.n];
break;
case 12:
e.r[this.a] = e.r[this.c] > e.r[this.n];
break;
case 13:
e.r[this.a] = -e.r[this.c];
break;
case 14:
e.r[this.a] = e.r[this.c] < e.r[this.n];
break;
case 15:
e.r[this.a] = e.r[this.c] & e.r[this.n];
break;
case 16:
e.r[this.a] = e.r[this.c] ^ e.r[this.n];
break;
case 17:
e.r[this.a] = e.r[this.c] << e.r[this.n];
break;
case 18:
e.r[this.a] = e.r[this.c] >>> e.r[this.n];
break;
case 19:
e.r[this.a] = e.r[this.c] | e.r[this.n];
break;
case 20:
e.r[this.a] = !e.r[this.c]
}
}
,
c.prototype.e = function(e) {
e.Q.push(e.C),
e.B.push(e.k),
e.C = e.r[this.s],
e.k = [];
for (var t = 0; t < this.i; t++)
e.k.unshift(e.f.pop());
e.g.push(e.f),
e.f = []
}
,
n.prototype.e = function(e) {
e.C = e.Q.pop(),
e.k = e.B.pop(),
e.f = e.g.pop()
}
,
e.prototype.e = function(e) {
switch (this.t) {
case 0:
e.u = e.r[this.a] >= e.r[this.c];
break;
case 1:
e.u = e.r[this.a] <= e.r[this.c];
break;
case 2:
e.u = e.r[this.a] > e.r[this.c];
break;
case 3:
e.u = e.r[this.a] < e.r[this.c];
break;
case 4:
e.u = e.r[this.a] == e.r[this.c];
break;
case 5:
e.u = e.r[this.a] != e.r[this.c];
break;
case 6:
e.u = e.r[this.a];
break;
case 7:
e.u = !e.r[this.a]
}
}
,
o.prototype.e = function(e) {
switch (this.t) {
case 0:
e.C = this.h;
break;
case 1:
e.u && (e.C = this.h);
break;
case 2:
e.u || (e.C = this.h);
break;
case 3:
e.C = this.h,
e.w = null
}
e.u = !1
}
,
r.prototype.e = function(e) {
switch (this.t) {
case 0:
for (var t = [], n = 0; n < this.i; n++)
t.unshift(e.f.pop());
e.r[3] = e.r[this.s](t[0], t[1]);
break;
case 1:
for (var r = e.f.pop(), o = [], i = 0; i < this.i; i++)
o.unshift(e.f.pop());
e.r[3] = e.r[this.s][r](o[0], o[1]);
break;
case 2:
for (var a = [], c = 0; c < this.i; c++)
a.unshift(e.f.pop());
e.r[3] = new e.r[this.s](a[0],a[1])
}
}
;
var k = function(e) {
for (var t = 66, n = [], r = 0; r < e.length; r++) {
var o = 24 ^ e.charCodeAt(r) ^ t;
n.push(String.fromCharCode(o)),
t = o
}
return n.join("")
};
function Q(e) {
this.t = (4095 & e) >> 10,
this.s = (1023 & e) >> 8,
this.i = 1023 & e,
this.h = 63 & e
}
function C(e) {
this.t = (4095 & e) >> 10,
this.a = (1023 & e) >> 8,
this.c = (255 & e) >> 6
}
function B(e) {
this.s = (3072 & e) >> 10,
this.h = 1023 & e
}
function f(e) {
this.h = 4095 & e
}
function g(e) {
this.s = (3072 & e) >> 10
}
function u(e) {
this.h = 4095 & e
}
function w(e) {
this.t = (3840 & e) >> 8,
this.s = (192 & e) >> 6,
this.i = 63 & e
}
function G() {
this.r = [0, 0, 0, 0],
this.C = 0,
this.Q = [],
this.k = [],
this.B = [],
this.f = [],
this.g = [],
this.u = !1,
this.G = [],
this.b = [],
this.o = !1,
this.w = null,
this.U = null,
this.F = [],
this.R = 0,
this.J = {
0: s,
1: i,
2: h,
3: a,
4: c,
5: n,
6: e,
7: o,
8: r,
9: Q,
10: C,
11: B,
12: f,
13: g,
14: u,
15: w
}
}
Q.prototype.e = function(e) {
switch (this.t) {
case 0:
e.f.push(e.r[this.s]);
break;
case 1:
e.f.push(this.i);
break;
case 2:
e.f.push(e.k[this.h]);
break;
case 3:
e.f.push(k(e.b[this.h]))
}
}
,
C.prototype.e = function(A) {
switch (this.t) {
case 0:
var t = A.f.pop();
A.r[this.a] = A.r[this.c][t];
break;
case 1:
var s = A.f.pop()
, i = A.f.pop();
A.r[this.c][s] = i;
break;
case 2:
var h = A.f.pop();
A.r[this.a] = eval(h)
}
}
,
B.prototype.e = function(e) {
e.r[this.s] = k(e.b[this.h])
}
,
f.prototype.e = function(e) {
e.w = this.h
}
,
g.prototype.e = function(e) {
throw e.r[this.s]
}
,
u.prototype.e = function(e) {
var t = this
, n = [0];
e.k.forEach(function(e) {
n.push(e)
});
var r = function(r) {
var o = new G;
return o.k = n,
o.k[0] = r,
o.v(e.G, t.h, e.b, e.F),
o.r[3]
};
r.toString = function() {
return "() { [native code] }"
}
,
e.r[3] = r
}
,
w.prototype.e = function(e) {
switch (this.t) {
case 0:
for (var t = {}, n = 0; n < this.i; n++) {
var r = e.f.pop();
t[e.f.pop()] = r
}
e.r[this.s] = t;
break;
case 1:
for (var o = [], i = 0; i < this.i; i++)
o.unshift(e.f.pop());
e.r[this.s] = o
}
}
,
G.prototype.D = function(e) {
console.log(window.atob(e));
for (var t = window.atob(e), n = t.charCodeAt(0) << 8 | t.charCodeAt(1), r = [], o = 2; o < n + 2; o += 2)
r.push(t.charCodeAt(o) << 8 | t.charCodeAt(o + 1));
this.G = r;
for (var i = [], a = n + 2; a < t.length; ) {
var c = t.charCodeAt(a) << 8 | t.charCodeAt(a + 1)
, s = t.slice(a + 2, a + 2 + c);
i.push(s),
a += c + 2
}
this.b = i
}
,
G.prototype.v = function(e, t, n) {
for (t = t || 0,
n = n || [],
this.C = t,
"string" == typeof e ? this.D(e) : (this.G = e,
this.b = n),
this.o = !0,
this.R = Date.now(); this.o; ) {
var r = this.G[this.C++];
if ("number" != typeof r)
break;
var o = Date.now();
if (500 < o - this.R)
return;
this.R = o;
try {
this.e(r)
} catch (e) {
this.U = e,
this.w && (this.C = this.w)
}
}
}
,
G.prototype.e = function(e) {
var t = (61440 & e) >> 12;
new this.J[t](e).e(this)
}
,
(new G).v("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");
function b(e) {
console.log(e);
console.log(encodeURIComponent(e));
return __g._encrypt(encodeURIComponent(e))
};
测试zhihu_test.py 代码如下
需要安装jsdom, npm i jsdom -g 在调用的时候写路径不然会有问题
import requests
import execjs
import hashlib
url = "/api/v4/search_v3?t=general&q=%E6%80%80%E5%AD%95%E5%A4%B1%E7%9C%A0&correction=1&offset=0&limit=20&lc_idx=0&show_all_topics=0"
referer = "https://www.zhihu.com/search?type=content&q=%E6%80%80%E5%AD%95%E5%A4%B1%E7%9C%A0"
f = "+".join(["3_2.0", url, referer, '"AACSLMY7lBGPTo9fXdy2pmiGQ4ZVVUcqzC4=|1594785557"'])
fmd5 = hashlib.new('md5', f.encode()).hexdigest()
with open('g_encrypt.js', 'r') as f:
ctx1 = execjs.compile(f.read(), cwd=r'/usr/local/lib/node_modules')
encrypt_str = ctx1.call('b', fmd5)
headers = {
"referer": referer,
"user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36",
"cookie": 'd_c0="AACSLMY7lBGPTo9fXdy2pmiGQ4ZVVUcqzC4=|1594785557";',
"x-api-version": "3.0.91",
"x-zse-83": "3_2.0",
"x-zse-86": "1.0_%s" % encrypt_str,
}
print(headers)
r = requests.get("https://www.zhihu.com" + url, headers=headers)
print(r.text)