爬虫反爬:JS逆向实战2

1. 简介

学习某度翻译的JS参数逆向,我们可以来看看某道翻译的,用作一个练手项目即可,这一次我们要新增一个学习内容就是用Python将其复现出来获取到我们需要的数据,主要的还是JS逆向过程中的方法的学习。

2. 实战信息

网址:
aHR0cHM6Ly9mYW55aS55b3VkYW8uY29tLw==
接口:
aHR0cHM6Ly9mYW55aS55b3VkYW8uY29tL3RyYW5zbGF0ZV9vP3NtYXJ0cmVzdWx0PWRpY3Qmc21hcnRyZXN1bHQ9cnVsZQ==
逆向参数:

  • salt: 16574297023827

  • sign:ce2ff90e8f7715308bc304fa261942ea

  • lts:1657429702382

  • bv:c66136bfe956af5cdec6ce6da806f86e

3. 实战流程

第一步是永远不变的抓包找接口,有了上一个项目的实战经验,我们可以直接找到我们需要的接口,并且设置一个XHR断点,在接口可以被断住的情况下,XHR断点是迅速找到调用方法位置的断点方式,先看看需要逆向的参数。
在这里插入图片描述
salt、sign、lts、bv都像是需要逆向的参数,然后设置"/translate_o"XHR断点开始调试。
在这里插入图片描述
在这里插入图片描述

通过作用域快速找到n是传入的对象,往上一级调用栈中去寻找n参数传入位置,最后在此处发现这个对象,下断后重新开启一个调试。

在这里插入图片描述
可以看到四个需要逆向的加密参数均是r对象产生r在上文中是v.generateSaltSign(n)产生所以这个即为加密的方法,先测试数据。
在这里插入图片描述
确定之后,进入生成加密数据的方法generateSaltSign()
在这里插入图片描述
可以看到bv是由n.md5()方法对navigator.version处理后得到,navigator.version在一个网站中是不会变的等会抠代码的时候直接替换就好了,ts是一个时间戳,salt是时间戳加一个随机数,sign是拼接后的二次加密。

首先通过三方测试一下是否经过魔改的md5,如果没有魔改的话,可以直接调用Node中的方法实现或者用python单独实现,当然也是可以抠的,先测试一下。


"5.0 (Windows NT 6.3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.54 Safari/537.36 Edg/101.0.1210.39"

直接进入MD5方法,抠下来改写成一个方法即可,目前是一个对象里的属性方法。
在这里插入图片描述

function md5(e) {
    var t, n, i, o, a, s, m, g, v, y = Array();
    for (e = h(e),
        y = f(e),
        s = 1732584193,
        m = 4023233417,
        g = 2562383102,
        v = 271733878,
        t = 0; t < y.length; t += 16)
        n = s,
            i = m,
            o = g,
            a = v,
            s = l(s, m, g, v, y[t + 0], 7, 3614090360),
            v = l(v, s, m, g, y[t + 1], 12, 3905402710),
            g = l(g, v, s, m, y[t + 2], 17, 606105819),
            m = l(m, g, v, s, y[t + 3], 22, 3250441966),
            s = l(s, m, g, v, y[t + 4], 7, 4118548399),
            v = l(v, s, m, g, y[t + 5], 12, 1200080426),
            g = l(g, v, s, m, y[t + 6], 17, 2821735955),
            m = l(m, g, v, s, y[t + 7], 22, 4249261313),
            s = l(s, m, g, v, y[t + 8], 7, 1770035416),
            v = l(v, s, m, g, y[t + 9], 12, 2336552879),
            g = l(g, v, s, m, y[t + 10], 17, 4294925233),
            m = l(m, g, v, s, y[t + 11], 22, 2304563134),
            s = l(s, m, g, v, y[t + 12], 7, 1804603682),
            v = l(v, s, m, g, y[t + 13], 12, 4254626195),
            g = l(g, v, s, m, y[t + 14], 17, 2792965006),
            m = l(m, g, v, s, y[t + 15], 22, 1236535329),
            s = c(s, m, g, v, y[t + 1], 5, 4129170786),
            v = c(v, s, m, g, y[t + 6], 9, 3225465664),
            g = c(g, v, s, m, y[t + 11], 14, 643717713),
            m = c(m, g, v, s, y[t + 0], 20, 3921069994),
            s = c(s, m, g, v, y[t + 5], 5, 3593408605),
            v = c(v, s, m, g, y[t + 10], 9, 38016083),
            g = c(g, v, s, m, y[t + 15], 14, 3634488961),
            m = c(m, g, v, s, y[t + 4], 20, 3889429448),
            s = c(s, m, g, v, y[t + 9], 5, 568446438),
            v = c(v, s, m, g, y[t + 14], 9, 3275163606),
            g = c(g, v, s, m, y[t + 3], 14, 4107603335),
            m = c(m, g, v, s, y[t + 8], 20, 1163531501),
            s = c(s, m, g, v, y[t + 13], 5, 2850285829),
            v = c(v, s, m, g, y[t + 2], 9, 4243563512),
            g = c(g, v, s, m, y[t + 7], 14, 1735328473),
            m = c(m, g, v, s, y[t + 12], 20, 2368359562),
            s = u(s, m, g, v, y[t + 5], 4, 4294588738),
            v = u(v, s, m, g, y[t + 8], 11, 2272392833),
            g = u(g, v, s, m, y[t + 11], 16, 1839030562),
            m = u(m, g, v, s, y[t + 14], 23, 4259657740),
            s = u(s, m, g, v, y[t + 1], 4, 2763975236),
            v = u(v, s, m, g, y[t + 4], 11, 1272893353),
            g = u(g, v, s, m, y[t + 7], 16, 4139469664),
            m = u(m, g, v, s, y[t + 10], 23, 3200236656),
            s = u(s, m, g, v, y[t + 13], 4, 681279174),
            v = u(v, s, m, g, y[t + 0], 11, 3936430074),
            g = u(g, v, s, m, y[t + 3], 16, 3572445317),
            m = u(m, g, v, s, y[t + 6], 23, 76029189),
            s = u(s, m, g, v, y[t + 9], 4, 3654602809),
            v = u(v, s, m, g, y[t + 12], 11, 3873151461),
            g = u(g, v, s, m, y[t + 15], 16, 530742520),
            m = u(m, g, v, s, y[t + 2], 23, 3299628645),
            s = d(s, m, g, v, y[t + 0], 6, 4096336452),
            v = d(v, s, m, g, y[t + 7], 10, 1126891415),
            g = d(g, v, s, m, y[t + 14], 15, 2878612391),
            m = d(m, g, v, s, y[t + 5], 21, 4237533241),
            s = d(s, m, g, v, y[t + 12], 6, 1700485571),
            v = d(v, s, m, g, y[t + 3], 10, 2399980690),
            g = d(g, v, s, m, y[t + 10], 15, 4293915773),
            m = d(m, g, v, s, y[t + 1], 21, 2240044497),
            s = d(s, m, g, v, y[t + 8], 6, 1873313359),
            v = d(v, s, m, g, y[t + 15], 10, 4264355552),
            g = d(g, v, s, m, y[t + 6], 15, 2734768916),
            m = d(m, g, v, s, y[t + 13], 21, 1309151649),
            s = d(s, m, g, v, y[t + 4], 6, 4149444226),
            v = d(v, s, m, g, y[t + 11], 10, 3174756917),
            g = d(g, v, s, m, y[t + 2], 15, 718787259),
            m = d(m, g, v, s, y[t + 9], 21, 3951481745),
            s = r(s, n),
            m = r(m, i),
            g = r(g, o),
            v = r(v, a);
    return (p(s) + p(m) + p(g) + p(v)).toLowerCase()
}

然后把方法调用扣下来,可是方法里面依赖套依赖所以要抠全,所以从md5方法调用上方找到的依赖方法全抠,不用分析。
在这里插入图片描述
直接扒下来的完整代码测试bv的结果为:
在这里插入图片描述
对比一致即为成功。
在这里插入图片描述
自行构造一个变量导出即可Node的方法要求module.exports


var bv = md5("5.0 (Windows NT 6.3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.54 Safari/537.36 Edg/101.0.1210.39")
var ts = "" + (new Date).getTime()
var salt = ts + parseInt(10 * Math.random(), 10)
function getBv(){
    return bv
}
function getTs(){
    return ts
}
function getSalt(){
    return salt
}
function getSign(e){
    return md5("fanyideskweb" + e + salt + "Ygy_4c=r#e#4EX^NUGUc5")
}
module.exports = {
    getBv,
    getSalt,
    getSign,
    getTs
}

即可成功复现。

4. JS完整代码

// md5依赖
var n = function (e, t) {
    return e << t | e >>> 32 - t
}, r = function (e, t) {
    var n, r, i, o, a;
    return i = 2147483648 & e,
        o = 2147483648 & t,
        n = 1073741824 & e,
        r = 1073741824 & t,
        a = (1073741823 & e) + (1073741823 & t),
        n & r ? 2147483648 ^ a ^ i ^ o : n | r ? 1073741824 & a ? 3221225472 ^ a ^ i ^ o : 1073741824 ^ a ^ i ^ o : a ^ i ^ o
}, i = function (e, t, n) {
    return e & t | ~e & n
}, o = function (e, t, n) {
    return e & n | t & ~n
}, a = function (e, t, n) {
    return e ^ t ^ n
}, s = function (e, t, n) {
    return t ^ (e | ~n)
}, l = function (e, t, o, a, s, l, c) {
    return e = r(e, r(r(i(t, o, a), s), c)),
        r(n(e, l), t)
}, c = function (e, t, i, a, s, l, c) {
    return e = r(e, r(r(o(t, i, a), s), c)),
        r(n(e, l), t)
}, u = function (e, t, i, o, s, l, c) {
    return e = r(e, r(r(a(t, i, o), s), c)),
        r(n(e, l), t)
}, d = function (e, t, i, o, a, l, c) {
    return e = r(e, r(r(s(t, i, o), a), c)),
        r(n(e, l), t)
}, f = function (e) {
    for (var t, n = e.length, r = n + 8, i = 16 * ((r - r % 64) / 64 + 1), o = Array(i - 1), a = 0, s = 0; s < n;)
        a = s % 4 * 8,
            o[t = (s - s % 4) / 4] = o[t] | e.charCodeAt(s) << a,
            s++;
    return t = (s - s % 4) / 4,
        a = s % 4 * 8,
        o[t] = o[t] | 128 << a,
        o[i - 2] = n << 3,
        o[i - 1] = n >>> 29,
        o
}, p = function (e) {
    var t, n = "", r = "";
    for (t = 0; t <= 3; t++)
        n += (r = "0" + (e >>> 8 * t & 255).toString(16)).substr(r.length - 2, 2);
    return n
}, h = function (e) {
    e = e.replace(/\x0d\x0a/g, "\n");
    for (var t = "", n = 0; n < e.length; n++) {
        var r = e.charCodeAt(n);
        if (r < 128)
            t += String.fromCharCode(r);
        else if (r > 127 && r < 2048)
            t += String.fromCharCode(r >> 6 | 192),
                t += String.fromCharCode(63 & r | 128);
        else if (r >= 55296 && r <= 56319) {
            if (n + 1 < e.length) {
                var i = e.charCodeAt(n + 1);
                if (i >= 56320 && i <= 57343) {
                    var o = 1024 * (r - 55296) + (i - 56320) + 65536;
                    t += String.fromCharCode(240 | o >> 18 & 7),
                        t += String.fromCharCode(128 | o >> 12 & 63),
                        t += String.fromCharCode(128 | o >> 6 & 63),
                        t += String.fromCharCode(128 | 63 & o),
                        n++
                }
            }
        } else
            t += String.fromCharCode(r >> 12 | 224),
                t += String.fromCharCode(r >> 6 & 63 | 128),
                t += String.fromCharCode(63 & r | 128)
    }
    return t
}
// md5加密
function md5(e) {
    var t, n, i, o, a, s, m, g, v, y = Array();
    for (e = h(e),
        y = f(e),
        s = 1732584193,
        m = 4023233417,
        g = 2562383102,
        v = 271733878,
        t = 0; t < y.length; t += 16)
        n = s,
            i = m,
            o = g,
            a = v,
            s = l(s, m, g, v, y[t + 0], 7, 3614090360),
            v = l(v, s, m, g, y[t + 1], 12, 3905402710),
            g = l(g, v, s, m, y[t + 2], 17, 606105819),
            m = l(m, g, v, s, y[t + 3], 22, 3250441966),
            s = l(s, m, g, v, y[t + 4], 7, 4118548399),
            v = l(v, s, m, g, y[t + 5], 12, 1200080426),
            g = l(g, v, s, m, y[t + 6], 17, 2821735955),
            m = l(m, g, v, s, y[t + 7], 22, 4249261313),
            s = l(s, m, g, v, y[t + 8], 7, 1770035416),
            v = l(v, s, m, g, y[t + 9], 12, 2336552879),
            g = l(g, v, s, m, y[t + 10], 17, 4294925233),
            m = l(m, g, v, s, y[t + 11], 22, 2304563134),
            s = l(s, m, g, v, y[t + 12], 7, 1804603682),
            v = l(v, s, m, g, y[t + 13], 12, 4254626195),
            g = l(g, v, s, m, y[t + 14], 17, 2792965006),
            m = l(m, g, v, s, y[t + 15], 22, 1236535329),
            s = c(s, m, g, v, y[t + 1], 5, 4129170786),
            v = c(v, s, m, g, y[t + 6], 9, 3225465664),
            g = c(g, v, s, m, y[t + 11], 14, 643717713),
            m = c(m, g, v, s, y[t + 0], 20, 3921069994),
            s = c(s, m, g, v, y[t + 5], 5, 3593408605),
            v = c(v, s, m, g, y[t + 10], 9, 38016083),
            g = c(g, v, s, m, y[t + 15], 14, 3634488961),
            m = c(m, g, v, s, y[t + 4], 20, 3889429448),
            s = c(s, m, g, v, y[t + 9], 5, 568446438),
            v = c(v, s, m, g, y[t + 14], 9, 3275163606),
            g = c(g, v, s, m, y[t + 3], 14, 4107603335),
            m = c(m, g, v, s, y[t + 8], 20, 1163531501),
            s = c(s, m, g, v, y[t + 13], 5, 2850285829),
            v = c(v, s, m, g, y[t + 2], 9, 4243563512),
            g = c(g, v, s, m, y[t + 7], 14, 1735328473),
            m = c(m, g, v, s, y[t + 12], 20, 2368359562),
            s = u(s, m, g, v, y[t + 5], 4, 4294588738),
            v = u(v, s, m, g, y[t + 8], 11, 2272392833),
            g = u(g, v, s, m, y[t + 11], 16, 1839030562),
            m = u(m, g, v, s, y[t + 14], 23, 4259657740),
            s = u(s, m, g, v, y[t + 1], 4, 2763975236),
            v = u(v, s, m, g, y[t + 4], 11, 1272893353),
            g = u(g, v, s, m, y[t + 7], 16, 4139469664),
            m = u(m, g, v, s, y[t + 10], 23, 3200236656),
            s = u(s, m, g, v, y[t + 13], 4, 681279174),
            v = u(v, s, m, g, y[t + 0], 11, 3936430074),
            g = u(g, v, s, m, y[t + 3], 16, 3572445317),
            m = u(m, g, v, s, y[t + 6], 23, 76029189),
            s = u(s, m, g, v, y[t + 9], 4, 3654602809),
            v = u(v, s, m, g, y[t + 12], 11, 3873151461),
            g = u(g, v, s, m, y[t + 15], 16, 530742520),
            m = u(m, g, v, s, y[t + 2], 23, 3299628645),
            s = d(s, m, g, v, y[t + 0], 6, 4096336452),
            v = d(v, s, m, g, y[t + 7], 10, 1126891415),
            g = d(g, v, s, m, y[t + 14], 15, 2878612391),
            m = d(m, g, v, s, y[t + 5], 21, 4237533241),
            s = d(s, m, g, v, y[t + 12], 6, 1700485571),
            v = d(v, s, m, g, y[t + 3], 10, 2399980690),
            g = d(g, v, s, m, y[t + 10], 15, 4293915773),
            m = d(m, g, v, s, y[t + 1], 21, 2240044497),
            s = d(s, m, g, v, y[t + 8], 6, 1873313359),
            v = d(v, s, m, g, y[t + 15], 10, 4264355552),
            g = d(g, v, s, m, y[t + 6], 15, 2734768916),
            m = d(m, g, v, s, y[t + 13], 21, 1309151649),
            s = d(s, m, g, v, y[t + 4], 6, 4149444226),
            v = d(v, s, m, g, y[t + 11], 10, 3174756917),
            g = d(g, v, s, m, y[t + 2], 15, 718787259),
            m = d(m, g, v, s, y[t + 9], 21, 3951481745),
            s = r(s, n),
            m = r(m, i),
            g = r(g, o),
            v = r(v, a);
    return (p(s) + p(m) + p(g) + p(v)).toLowerCase()
}
var bv = md5("5.0 (Windows NT 6.3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.54 Safari/537.36 Edg/101.0.1210.39")
var ts = "" + (new Date).getTime()
var salt = ts + parseInt(10 * Math.random(), 10)
function getBv(){
    return bv
}
function getTs(){
    return ts
}
function getSalt(){
    return salt
}
function getSign(e){
    return md5("fanyideskweb" + e + salt + "Ygy_4c=r#e#4EX^NUGUc5")
}
module.exports = {
    getBv,
    getSalt,
    getSign,
    getTs
}

5. Python实现

第一步要将写好的js代码放在我们创建的python目录下方便Python调用,这里写Python的工具是Pycharm功能集成多、比较便捷 。
在这里插入图片描述
在这里插入图片描述
如此即可,然后去请求页查看需要的参数。
在这里插入图片描述
分析出URL和请求方式是POST,可以知道Python的调用方式是:

requests.post()

再分析请求头:

在这里插入图片描述
有Host、Origin、Referer、User-Agent是必须的,Cookie不知道是否需要暂时未定,所以请求头可以知道:


headers = {
  'Host': 'fanyi.youdao.com',
  'Origin': 'https://fanyi.youdao.com',
  'Referer': 'https://fanyi.youdao.com/?keyfrom=fanyi-new.logo',
  'User-Agent': 'Mozilla/5.0 (Windows NT 6.3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.54 Safari/537.36 Edg/101.0.1210.39',
  # 'Cookie': ''
}

可以开始写我们的爬虫了,先获取加密的key


def getKey(msg):
    key = {}
    with open('./有道翻译.js', encoding='utf-8') as f:
        jsDoc = execjs.compile(f.read())
        sign = jsDoc.call('getSign', msg)
        bv = jsDoc.call('getBv')
        ts = jsDoc.call('getTs')
        salt = jsDoc.call('getSalt')
        key['sign'] = sign
        key['bv'] = bv
        key['ts'] = ts
        key['salt'] = salt
    return key

测试结果:

{'sign': '9ab4b934da623ff9b34c316067858291', 'bv': 'c66136bfe956af5cdec6ce6da806f86e', 'ts': '1657438219479', 'salt': '16574382195304'}

然后开始模拟请求。


url = 'https://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'
headers = {
    'Host': 'fanyi.youdao.com',
    'Origin': 'https://fanyi.youdao.com',
    'Referer': 'https://fanyi.youdao.com/?keyfrom=fanyi-new.logo',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36X-Requested-With: XMLHttpRequest',
    'Cookie': 'OUTFOX_SEARCH_USER_ID=-1702917702@10.110.96.153; OUTFOX_SEARCH_USER_ID_NCOO=1118915067.3883293; fanyi-ad-id=307888; fanyi-ad-closed=1; ___rl__test__cookies=1657436432367'
}
def getResponse(msg):
    # 获取加密的key
    key = getKey(msg)
    data = {
        'i': msg,
        'from': 'AUTO',
        'to': 'AUTO',
        'smartresult': 'dict',
        'client': 'fanyideskweb',
        'salt': key['salt'],
        'sign': key['sign'],
        'lts': key['ts'],
        'bv': key['bv'],
        'doctype': 'json',
        'version': '2.1',
        'keyfrom': 'fanyi.web',
        'action': 'FY_BY_REALTlME'
    }
    response = requests.post(url=url, headers=headers, data=data)
    print(response.content)

运行结果:
在这里插入图片描述

6. Python完整代码

import requests
import execjs

url = 'https://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'
headers = {
    'Host': 'fanyi.youdao.com',
    'Origin': 'https://fanyi.youdao.com',
    'Referer': 'https://fanyi.youdao.com/?keyfrom=fanyi-new.logo',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36X-Requested-With: XMLHttpRequest',
    'Cookie': 'OUTFOX_SEARCH_USER_ID=-1702917702@10.110.96.153; OUTFOX_SEARCH_USER_ID_NCOO=1118915067.3883293; fanyi-ad-id=307888; fanyi-ad-closed=1; ___rl__test__cookies=1657436432367'
}
def getResponse(msg):
    # 获取加密的key
    key = getKey(msg)
    data = {
        'i': msg,
        'from': 'AUTO',
        'to': 'AUTO',
        'smartresult': 'dict',
        'client': 'fanyideskweb',
        'salt': key['salt'],
        'sign': key['sign'],
        'lts': key['ts'],
        'bv': key['bv'],
        'doctype': 'json',
        'version': '2.1',
        'keyfrom': 'fanyi.web',
        'action': 'FY_BY_REALTlME'
    }
    response = requests.post(url=url, headers=headers, data=data)
    print(response.content)
def getKey(msg):
    with open('./有道翻译.js', encoding='utf-8') as f:
        jsDoc = execjs.compile(f.read())
        res = jsDoc.call('getRes', msg)
        return res

if __name__ == '__main__':
    getResponse("你好")

看看评论区学习更多哦

  • 1
    点赞
  • 4
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 1
    评论
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
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

打赏作者

阿呆攻防

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
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