爬虫逆向实战（六）--猿人学第四题

一、数据接口分析

主页地址：猿人学第四题

1、抓包

通过抓包可以发现数据接口是api/match/4

2、判断是否有加密参数

1. 请求参数是否加密？
   无
2. 请求头是否加密？
   无
3. 响应是否加密？
   响应数据无加密，但是返回的却是html代码
4. cookie是否加密？
   无

二、处理位置定位

1、看启动器

查看启动器发现有一个request调用堆栈，点进去查看
可以发现此处是ajax请求，对响应的处理就在下方成功的回调函数中，通过分析可以得出，对响应内容的处理是根据响应中的key和value进行处理生成一个j_key，然后将响应中class属性为j_key的图片隐藏，将剩下的其他图片进行展示。

三、获取数据

将定位到的j_key生成代码扣出来，然后缺啥补啥，将代码补全。
源代码：

var hexcase = 0;
var b64pad = "";
var chrsz = 8;


function safe_add(x, y) {
    var lsw = (x & 0xFFFF) + (y & 0xFFFF);
    var msw = (x >> 16) + (y >> 16) + (lsw >> 16);
    return (msw << 16) | (lsw & 0xFFFF)
}

function bit_rol(num, cnt) {
    return (num << cnt) | (num >>> (32 - cnt))
}

function md5_cmn(q, a, b, x, s, t) {
    return safe_add(bit_rol(safe_add(safe_add(a, q), safe_add(x, t)), s), b)
}

function md5_ff(a, b, c, d, x, s, t) {
    return md5_cmn((b & c) | ((~b) & d), a, b, x, s, t)
}

function md5_gg(a, b, c, d, x, s, t) {
    return md5_cmn((b & d) | (c & (~d)), a, b, x, s, t)
}

function md5_hh(a, b, c, d, x, s, t) {
    return md5_cmn(b ^ c ^ d, a, b, x, s, t)
}

function md5_ii(a, b, c, d, x, s, t) {
    return md5_cmn(c ^ (b | (~d)), a, b, x, s, t)
}

function str2binl(str) {
    var bin = Array();
    var mask = (1 << chrsz) - 1;
    for (var i = 0; i < str.length * chrsz; i += chrsz)
        bin[i >> 5] |= (str.charCodeAt(i / chrsz) & mask) << (i % 32);
    return bin
}

function core_md5(x, len) {
    x[len >> 5] |= 0x80 << ((len) % 32);
    x[(((len + 64) >>> 9) << 4) + 14] = len;
    var a = 1732584193;
    var b = -271733879;
    var c = -1732584194;
    var d = 271733878;
    for (var i = 0; i < x.length; i += 16) {
        var olda = a;
        var oldb = b;
        var oldc = c;
        var oldd = d;
        a = md5_ff(a, b, c, d, x[i + 0], 7, -680876936);
        d = md5_ff(d, a, b, c, x[i + 1], 12, -389564586);
        c = md5_ff(c, d, a, b, x[i + 2], 17, 606105819);
        b = md5_ff(b, c, d, a, x[i + 3], 22, -1044525330);
        a = md5_ff(a, b, c, d, x[i + 4], 7, -176418897);
        d = md5_ff(d, a, b, c, x[i + 5], 12, 1200080426);
        c = md5_ff(c, d, a, b, x[i + 6], 17, -1473231341);
        b = md5_ff(b, c, d, a, x[i + 7], 22, -45705983);
        a = md5_ff(a, b, c, d, x[i + 8], 7, 1770035416);
        d = md5_ff(d, a, b, c, x[i + 9], 12, -1958414417);
        c = md5_ff(c, d, a, b, x[i + 10], 17, -42063);
        b = md5_ff(b, c, d, a, x[i + 11], 22, -1990404162);
        a = md5_ff(a, b, c, d, x[i + 12], 7, 1804603682);
        d = md5_ff(d, a, b, c, x[i + 13], 12, -40341101);
        c = md5_ff(c, d, a, b, x[i + 14], 17, -1502002290);
        b = md5_ff(b, c, d, a, x[i + 15], 22, 1236535329);
        a = md5_gg(a, b, c, d, x[i + 1], 5, -165796510);
        d = md5_gg(d, a, b, c, x[i + 6], 9, -1069501632);
        c = md5_gg(c, d, a, b, x[i + 11], 14, 643717713);
        b = md5_gg(b, c, d, a, x[i + 0], 20, -373897302);
        a = md5_gg(a, b, c, d, x[i + 5], 5, -701558691);
        d = md5_gg(d, a, b, c, x[i + 10], 9, 38016083);
        c = md5_gg(c, d, a, b, x[i + 15], 14, -660478335);
        b = md5_gg(b, c, d, a, x[i + 4], 20, -405537848);
        a = md5_gg(a, b, c, d, x[i + 9], 5, 568446438);
        d = md5_gg(d, a, b, c, x[i + 14], 9, -1019803690);
        c = md5_gg(c, d, a, b, x[i + 3], 14, -187363961);
        b = md5_gg(b, c, d, a, x[i + 8], 20, 1163531501);
        a = md5_gg(a, b, c, d, x[i + 13], 5, -1444681467);
        d = md5_gg(d, a, b, c, x[i + 2], 9, -51403784);
        c = md5_gg(c, d, a, b, x[i + 7], 14, 1735328473);
        b = md5_gg(b, c, d, a, x[i + 12], 20, -1926607734);
        a = md5_hh(a, b, c, d, x[i + 5], 4, -378558);
        d = md5_hh(d, a, b, c, x[i + 8], 11, -2022574463);
        c = md5_hh(c, d, a, b, x[i + 11], 16, 1839030562);
        b = md5_hh(b, c, d, a, x[i + 14], 23, -35309556);
        a = md5_hh(a, b, c, d, x[i + 1], 4, -1530992060);
        d = md5_hh(d, a, b, c, x[i + 4], 11, 1272893353);
        c = md5_hh(c, d, a, b, x[i + 7], 16, -155497632);
        b = md5_hh(b, c, d, a, x[i + 10], 23, -1094730640);
        a = md5_hh(a, b, c, d, x[i + 13], 4, 681279174);
        d = md5_hh(d, a, b, c, x[i + 0], 11, -358537222);
        c = md5_hh(c, d, a, b, x[i + 3], 16, -722521979);
        b = md5_hh(b, c, d, a, x[i + 6], 23, 76029189);
        a = md5_hh(a, b, c, d, x[i + 9], 4, -640364487);
        d = md5_hh(d, a, b, c, x[i + 12], 11, -421815835);
        c = md5_hh(c, d, a, b, x[i + 15], 16, 530742520);
        b = md5_hh(b, c, d, a, x[i + 2], 23, -995338651);
        a = md5_ii(a, b, c, d, x[i + 0], 6, -198630844);
        d = md5_ii(d, a, b, c, x[i + 7], 10, 1126891415);
        c = md5_ii(c, d, a, b, x[i + 14], 15, -1416354905);
        b = md5_ii(b, c, d, a, x[i + 5], 21, -57434055);
        a = md5_ii(a, b, c, d, x[i + 12], 6, 1700485571);
        d = md5_ii(d, a, b, c, x[i + 3], 10, -1894986606);
        c = md5_ii(c, d, a, b, x[i + 10], 15, -1051523);
        b = md5_ii(b, c, d, a, x[i + 1], 21, -2054922799);
        a = md5_ii(a, b, c, d, x[i + 8], 6, 1873313359);
        d = md5_ii(d, a, b, c, x[i + 15], 10, -30611744);
        c = md5_ii(c, d, a, b, x[i + 6], 15, -1560198380);
        b = md5_ii(b, c, d, a, x[i + 13], 21, 1309151649);
        a = md5_ii(a, b, c, d, x[i + 4], 6, -145523070);
        d = md5_ii(d, a, b, c, x[i + 11], 10, -1120210379);
        c = md5_ii(c, d, a, b, x[i + 2], 15, 718787259);
        b = md5_ii(b, c, d, a, x[i + 9], 21, -343485551);
        a = safe_add(a, olda);
        b = safe_add(b, oldb);
        c = safe_add(c, oldc);
        d = safe_add(d, oldd)
    }
    return Array(a, b, c, d)
}

function binl2hex(binarray) {
    var hex_tab = hexcase ? "0123456789ABCDEF" : "0123456789abcdef";
    var str = "";
    for (var i = 0; i < binarray.length * 4; i++) {
        str += hex_tab.charAt((binarray[i >> 2] >> ((i % 4) * 8 + 4)) & 0xF) + hex_tab.charAt((binarray[i >> 2] >> ((i % 4) * 8)) & 0xF)
    }
    return str
}


function hex_md5(s) {
    return binl2hex(core_md5(str2binl(s), s.length * chrsz))
}

function get_key(key, value) {
    var j_key = hex_md5(btoa(key + value).replace(/=/g, ''))
    return j_key
}

此时，虽然我们已经可以生成j_key了，但是还有一个难题，就是数据是图片，如何才能获取到图片拼接的数字。
原本我是准备将base64转成图片，然后识别图片中的数字进行拼接然后相加，但是有一个问题就是响应返回的图片中会使用style="left:11.5px"重新排序，我没有想到很好的办法去处理。最后我就只能是将响应的内容写入到html文件中进行展示，然后自己再去计算展示出的所有数字的和。如果有大佬有好的办法，可以私信或者评论教我一下。
python源代码：

"""
Email：[email protected]
Date: 2023/8/1 11:08
"""
import execjs
import lxml.etree
from lxml.html import tostring
import requests


headers = {
    "authority": "match.yuanrenxue.cn",
    "referer": "https://match.yuanrenxue.cn/match/4",
    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36",
}
url = "https://match.yuanrenxue.cn/api/match/4"

with open('get_key.js', 'r', encoding='utf-8') as f:
    js_obj = execjs.compile(f.read())


for page in range(1, 6):
    params = {
        "page": str(page)
    }
    if page >= 4:
        headers['user-agent'] = 'yuanrenxue.project'
    response = requests.get(url, headers=headers, params=params)

    data = response.json()
    key = js_obj.call('get_key', data['key'], data['value'])

    html_obj = lxml.etree.HTML(data['info'])

    td_list = html_obj.xpath('//td')
    with open('img.html', 'a') as f:
        f.write('')
        for td_index, td in enumerate(td_list):
            f.write('')
            img_list = td.xpath('./img')
            for img_index, img in enumerate(img_list):
                if key in img.xpath('./@class')[0]:
                    continue
                img_str = tostring(img, encoding="utf-8").decode("utf-8")
                f.write(img_str)
            f.write('')
        f.write('')