JSL（加速乐）反爬跳过

套路：

加速乐产品分析：会发起3次请求

第一次请求：设置cookie : __jsluid_h

返回一段js，执行js可以获取到第一个__jsl_clearance

状态：400

第二次请求：设置cookie : __jsluid_h 和 第一个__jsl_clearance

返回一段ob混淆过的js代码，代码中go函数入参包含一种随机生成的算法类型（md5/sha1/sha256）,执行js中对应的加密方法，可以获取到第二个__jsl_clearance

状态：521

第三次请求：设置cookie : __jsluid_h 和 第二个__jsl_clearance

返回正确的网页html文本数据

状态：200

下面以这个网址 http://www.scio.gov.cn/xwfb/gwyxwbgsxwfbh/fbh/ 为例

代码：

这里提供Java和python两种方案代码：

Java代码：

import com.gargoylesoftware.htmlunit.*;
import com.gargoylesoftware.htmlunit.util.Cookie;
import org.json.JSONObject;

import javax.script.ScriptEngine;
import javax.script.ScriptEngineManager;
import java.io.IOException;
import java.nio.charset.StandardCharsets;
import java.security.MessageDigest;
import java.security.NoSuchAlgorithmException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class SetJslCookie {
    private static final String USER_AGENT = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36";

    public static void main(String[] args) throws Exception {
        String url = "http://www.scio.gov.cn/xwfb/gwyxwbgsxwfbh/fbh/";
        WebClient webClient = new WebClient(BrowserVersion.CHROME);
        webClient.getOptions().setJavaScriptEnabled(true);
        webClient.getOptions().setThrowExceptionOnScriptError(false);
        webClient.getOptions().setCssEnabled(false);
        webClient.getOptions().setRedirectEnabled(true);
        webClient.getOptions().setUseInsecureSSL(true);
        webClient.addRequestHeader("User-Agent", USER_AGENT);

        setFirstCookie(webClient, url);
        setSecondCookie(webClient, url);

        WebRequest request = new WebRequest(new java.net.URL(url), HttpMethod.GET);
        WebResponse response = webClient.loadWebResponse(request);
        String content = response.getContentAsString();
        System.out.println(content);

        webClient.close();
    }

    private static void setFirstCookie(WebClient webClient, String url) throws IOException {
        WebRequest request = new WebRequest(new java.net.URL(url), HttpMethod.GET);
        WebResponse response = webClient.loadWebResponse(request);
        String content = response.getContentAsString();
        Pattern pattern = Pattern.compile("cookie=(.*?);location");
        Matcher matcher = pattern.matcher(content);
        if (matcher.find()) {
            String cookieValue = matcher.group(1);
            String[] parts = executeJavaScript(cookieValue).split(";")[0].split("=");
            Cookie cookie = new Cookie(getDomain(url), parts[0], parts[1]);
            webClient.getCookieManager().addCookie(cookie);
        }
    }

    private static void setSecondCookie(WebClient webClient, String url) throws IOException {
        WebRequest request = new WebRequest(new java.net.URL(url), HttpMethod.GET);
        request.setAdditionalHeader("Referer", url);
        WebResponse response = webClient.loadWebResponse(request);
        String content = response.getContentAsString();

        Pattern pattern = Pattern.compile("go\\(\\{(.*?)\\}\\)");
        Matcher matcher = pattern.matcher(content);
        if (matcher.find()) {
            String jsonString = "{" + matcher.group(1) + "}";
            JSONObject jsonObject = new JSONObject(jsonString);
            String cookieName = jsonObject.getString("tn");
            String cookieValue = setJslClearanceS(jsonObject);
            Cookie cookie = new Cookie(getDomain(url), cookieName, cookieValue);
            webClient.getCookieManager().addCookie(cookie);
        }
    }

    private static String setJslClearanceS(JSONObject jsonObject) {
        String bts0 = jsonObject.getJSONArray("bts").getString(0);
        String bts1 = jsonObject.getJSONArray("bts").getString(1);
        String ha = jsonObject.getString("ha");
        String ct = jsonObject.getString("ct");
        String chars = jsonObject.getString("chars");

        for (int e = 0; e < chars.length(); e++) {
            for (int r = 0; r < chars.length(); r++) {
                String text = bts0 + chars.charAt(e) + chars.charAt(r) + bts1;
                if (getHash(text, ha).equals(ct)) {
                    return text;
                }
            }
        }
        return null;
    }

    private static String getHash(String string, String mode) {
        try {
            MessageDigest digest = MessageDigest.getInstance(mode.toUpperCase());
            byte[] hashBytes = digest.digest(string.getBytes(StandardCharsets.UTF_8));
            return toHexString(hashBytes);
        } catch (NoSuchAlgorithmException e) {
            throw new RuntimeException("Error getting hash: " + e.getMessage());
        }
    }

    private static String toHexString(byte[] bytes) {
        StringBuilder hexString = new StringBuilder();
        for (byte b : bytes) {
            String hex = Integer.toHexString(0xff & b);
            if (hex.length() == 1) {
                hexString.append('0');
            }
            hexString.append(hex);
        }
        return hexString.toString();
    }

    private static String executeJavaScript(String script) {
        try {
            ScriptEngineManager manager = new ScriptEngineManager();
            ScriptEngine engine = manager.getEngineByName("JavaScript");
            return engine.eval(script).toString();
        } catch (ScriptException e) {
            throw new RuntimeException("Error executing JavaScript: " + e.getMessage());
        } catch (javax.script.ScriptException e) {
            throw new RuntimeException(e);
        }
    }

    private static String getDomain(String url) {
        String domainRegex = "^(?:https?://)?([a-zA-Z0-9-]+(?:\\.[a-zA-Z0-9-]+)+)(?::\\d+)?(?:/.*)?$";
        Pattern pattern = Pattern.compile(domainRegex);
        Matcher matcher = pattern.matcher(url);
        if (matcher.find()) {
            return matcher.group(1);
        } else {
            throw new RuntimeException("无效的url,解析域名失败");
        }
    }
}

python代码：

import re
import hashlib
import json
import execjs
import requests

headers = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
    'Accept-Language': 'zh,zh-CN;q=0.9',
    'Cache-Control': 'no-cache',
    'Connection': 'keep-alive',
    'Pragma': 'no-cache',
    'Upgrade-Insecure-Requests': '1',
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36',
}

class Set_Jsl_Coolie(object):
    def __init__(self, url):
        self.url = url
        self.headers = headers
        self.session = requests.session()
        self.set_first_cookie()
        self.set_second_cookie()


    def set_first_cookie(self):
        first_response = self.session.get(self.url, headers=self.headers)
        content_first = re.findall('cookie=(.*?);location', first_response.text)[0]
        jsl_clearance_s = execjs.eval(content_first).split(';')[0].split('=')
        self.session.cookies[jsl_clearance_s[0]] = jsl_clearance_s[1]

    def set_second_cookie(self):
        self.headers['Referer'] = self.url
        def set_jsl_clearance_s(data):
            def get_hash(string, mode):
                mode = mode.lower()
                if mode == 'sha1':
                    return hashlib.sha1(string.encode('utf-8')).hexdigest()
                elif mode == 'sha256':
                    return hashlib.sha256(string.encode('utf-8')).hexdigest()
                else:
                    return hashlib.md5(string.encode('utf-8')).hexdigest()
            for e in range(len(data["chars"])):
                for r in range(len(data["chars"])):
                    text = data["bts"][0] + data['chars'][e:e + 1] + data['chars'][r:r+1] + data["bts"][1]
                    if get_hash(text, data['ha']) == data['ct']:
                        return text
        second_response = self.session.get(self.url, headers=self.headers)
        content_second = json.loads("{" + re.findall("go\({(.*?)}\)", second_response.text) [0] + "}")
        self.session.cookies[content_second["tn"]] = set_jsl_clearance_s(content_second)

    def get_session(self):
        return self.session


url = 'http://www.scio.gov.cn/xwfb/gwyxwbgsxwfbh/fbh/'
Set_Jsl_Coolie(url)
session = a.get_session()
response = session.get(url, headers=headers)
response.encoding = 'utf-8'print(response.text)