知乎搜索接口解密

2024-06-02 06:38| 来源: 网络整理| 查看: 265

文章目录前言传参解密分析

前言

最近接到了一个知乎搜索的采集要求，所以研究了一下知乎的搜索接口加密。

传参

在这里插入图片描述研究了一下，只有cookie、x-zse-93和x-zse-96是必传的，93是固定值，96是用的加密的方式，话不多说，直接开始解密分析。

解密分析

全局搜索。可以发现在在这里插入图片描述去source里找到对应文件，打上断点，运行一路点进去可以看到这个函数再点进去可以看到一个G.v函数基本这个就是最终加密了，使用的是将query+cookie+version拼接之后先base64转码之后再调用自己的js加密的方式，直接上代码

import execjs import sys import hashlib import urllib.parse import json import random import requests import pandas as pd from db_config import engine_zhihu from utils import iooo import time query="/api/v4/search_v3?t=general&q={}&correction=1&offset=0&limit=20&filter_fields=&lc_idx=0&show_all_topics=0&search_source=Filter&sort=created_time&time_interval=a_day" cookie_format="\"AgBQb9bVUBSPTvIsEEM6EqLhxleZUfM2F3o=|164180{}{}{}{}\"" version="101_3_2.0" with open("g_encrypt.js", 'r', encoding='utf-8') as f: # ctx1 = execjs.compile(f.read()) ctx1 = execjs.compile(f.read(), cwd="node_modules") if __name__ == '__main__': while True: try: sql_keyword="select keyword from ety_zhihu_keyword where status=0" for keyword in pd.read_sql(sql_keyword,engine_zhihu())['keyword']: keyword=urllib.parse.quote(keyword) query_now = query.format(keyword) url = "https://www.zhihu.com" + query_now cookie_now = cookie_format.format(random.randint(1, 9), random.randint(1, 9), random.randint(1, 9), random.randint(1, 9)) payload = {} str = version + "+" + query_now + "+" + cookie_now hl = hashlib.md5() hl.update(str.encode(encoding='utf-8')) fmd5 = hl.hexdigest() encrpt_str = ctx1.call('b', fmd5) headers = { 'cookie': 'd_c0={}; '.format(cookie_now), 'x-zse-93': version, 'x-zse-96': '2.0_{}'.format(encrpt_str), 'User-Agent': 'PostmanRuntime/7.28.4' } r = requests.request("GET", url, headers=headers, data=payload) r.encoding = 'utf-8' html = r.text resp = json.loads(html) list_data=[] for dict_data in resp['data']: if dict_data['type']=='relevant_query': continue data={} try: data['summary']=dict_data['highlight']['description'] except Exception: data['summary']=None data['title']=dict_data['highlight']['title'] try: data['content']=dict_data['object']['content'] except Exception: data['content']=None try: data['url']=dict_data['object']['url'] except Exception: data['url']=dict_data['object']['video_url'] try: timeArray = time.localtime(dict_data['object']['updated_time']) except Exception: timeArray = time.localtime(dict_data['object']['created_at']) data['publish_time'] =time.strftime( "%Y-%m-%d %H:%M:%S" , timeArray) try: data['author_name']=dict_data['object']['author']['name'] except Exception: data['author_name']=None list_data.append(data) insert_df=pd.DataFrame(list_data) iooo.to_sql("ety_zhihu_article",engine_zhihu(),insert_df) time.sleep(60*60*4-120) except Exception as e: print(e) time.sleep(60*5) continue

g_encrpt.js的代码如下

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 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 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 3: e.u = e.r[this.a] 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 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 console.log(window.atob(e)); for (var t = window.atob(e), n = t.charCodeAt(0) 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 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)) };

注意一开始的

const jsdom = require("jsdom"); const { JSDOM } = jsdom; const dom = new JSDOM(`

Hello world

`); window = dom.window; document = window.document; XMLHttpRequest = window.XMLHttpRequest;

这个需要通过nodejs安装jsdom，具体安装方法就不列在这里了最终运行计算出的加密函数结果如下在这里插入图片描述

【本文地址】

公司简介

联系我们