优志愿

说明

# URL
https://youzy.cn/tzy/search/colleges/collegeList

# 接口
https://uwf7de983aad7a717eb.youzy.cn/youzy.dms.basiclib.api.college.query

此案例含有requests请求json数据的坑，需谨慎处理

代码实现 - 1

enc.js

const CryptoJS = require("crypto-js")

function get_sign(t) {
    e = '/youzy.dms.basiclib.api.college.query'
    var r, i = "9SASji5OWnG41iRKiSvTJHlXHmRySRp1", o = "", a = t || {}, s = (e = e || "").split("?");
    if (s.length > 0 && (r = s[1]),
        r) {
        var u = r.split("&")
            , c = "";
        u.forEach((function (e) {
                var t = e.split("=");
                c += "".concat(t[0], "=").concat(encodeURI(t[1]), "&")
            }
        )),
            o = "".concat(_.trimEnd(c, "&"), "&").concat(i)
    } else
        o = Object.keys(a).length > 0 ? "".concat(JSON.stringify(a), "&").concat(i) : "&".concat(i);
    return o = o.toLowerCase(),
        // n(o)
        CryptoJS.MD5(CryptoJS.enc.Utf8.parse(o)).toString()
}

spider.py

import execjs
import json
import requests

headers = {
    'Accept': '*/*',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Cache-Control': 'no-cache',
    'Connection': 'keep-alive',
    'Content-Type': 'application/json',
    'Origin': 'https://pv4y-pc.youzy.cn',
    'Pragma': 'no-cache',
    'Referer': 'https://pv4y-pc.youzy.cn/',
    'Sec-Fetch-Dest': 'empty',
    'Sec-Fetch-Mode': 'cors',
    'Sec-Fetch-Site': 'same-site',
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36',
    'sec-ch-ua': '"Not(A:Brand";v="99", "Google Chrome";v="133", "Chromium";v="133"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': '"macOS"',
    # 'u-sign': '643ff9499febb3ee34c95ffe0bb29cb0',
    'u-token': '',
}

json_data = {
    'keyword': '',
    'provinceNames': [],
    'natureTypes': [],
    'eduLevel': '',
    'categories': [],
    'features': [],
    'pageIndex': 1,
    'pageSize': 20,
    'sort': 11,
}

data = json.dumps(json_data, separators=(',', ':'))
# 处理json_data，序列化使之字符串中不含空格
# 若不进行此部处理且在requests中使用json=jsona_data，则requests中的json会自动序列化使字符串中含有空格
# 造成与网站程序所需字符串不一致，从而导致失败
# 处理后则在requests中不使用json=json_data，转而使用data = data
# print(data)
# {"keyword":"","provinceNames":[],"natureTypes":[],"eduLevel":"","categories":[],"features":[],"pageIndex":1,"pageSize":20,"sort":11}


js_compile = execjs.compile(open('day15-04.js', 'r', encoding='utf-8').read())
sign = js_compile.call("get_sign", json_data)
print(sign)

headers['u-sign'] = sign

response = requests.post(
    'https://uwf7de983aad7a717eb.youzy.cn/youzy.dms.basiclib.api.college.query',
    headers=headers,
    data=data
)
print(response.json())

代码实现 - 2

enc.js

const CryptoJS = require("crypto-js")

function get_sign(t) {
    e = '/youzy.dms.basiclib.api.college.query'
    var r, i = "9SASji5OWnG41iRKiSvTJHlXHmRySRp1", o = "", a = t || {}, s = (e = e || "").split("?");
    if (s.length > 0 && (r = s[1]),
        r) {
        var u = r.split("&")
            , c = "";
        u.forEach((function (e) {
                var t = e.split("=");
                c += "".concat(t[0], "=").concat(encodeURI(t[1]), "&")
            }
        )),
            o = "".concat(_.trimEnd(c, "&"), "&").concat(i)
    } else
        o = Object.keys(a).length > 0 ? "".concat(JSON.stringify(a), "&").concat(i) : "&".concat(i);
    return o = o.toLowerCase(),
        // n(o)
        CryptoJS.MD5(CryptoJS.enc.Utf8.parse(o)).toString()
}

spieder.py

import execjs
# 使用此requests可以简单绕过指纹识别，下方配合参数（impersonate="chrome119"）
from curl_cffi import requests

headers = {
    'Accept': '*/*',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Cache-Control': 'no-cache',
    'Connection': 'keep-alive',
    'Content-Type': 'application/json',
    'Origin': 'https://pv4y-pc.youzy.cn',
    'Pragma': 'no-cache',
    'Referer': 'https://pv4y-pc.youzy.cn/',
    'Sec-Fetch-Dest': 'empty',
    'Sec-Fetch-Mode': 'cors',
    'Sec-Fetch-Site': 'same-site',
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36',
    'sec-ch-ua': '"Not(A:Brand";v="99", "Google Chrome";v="133", "Chromium";v="133"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': '"macOS"',
    # 'u-sign': '643ff9499febb3ee34c95ffe0bb29cb0',
    'u-token': '',
}

json_data = {
    'keyword': '',
    'provinceNames': [],
    'natureTypes': [],
    'eduLevel': '',
    'categories': [],
    'features': [],
    'pageIndex': 1,
    'pageSize': 20,
    'sort': 11,
}

js_compile = execjs.compile(open('enc.js', 'r', encoding='utf-8').read())
sign = js_compile.call("get_sign", json_data)
print(sign)

headers['u-sign'] = sign

response = requests.post(
    'https://uwf7de983aad7a717eb.youzy.cn/youzy.dms.basiclib.api.college.query',
    headers=headers,
    json=json_data,
    impersonate="chrome119"
)
print(response.json())