引入Maven依赖

pom.xml文件中引入jsoup依赖

 <!--jsoup-->
 <dependency>
     <groupId>org.jsoup</groupId>
     <artifactId>jsoup</artifactId>
     <version>1.13.1</version>
 </dependency>

编写Jsoup工具类

创建一个JsoupUtil工具类

import java.io.FileNotFoundException;
import java.io.IOException;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.safety.Whitelist;

/**
 * xss过滤检查工具
 */
public class JsoupUtil {
    private static final Whitelist whitelist = Whitelist.basicWithImages();

    /*
    * 配置过滤化参数,不对代码进行格式化
    */
    private static final Document.OutputSettings outputSettings = new Document.OutputSettings().prettyPrint(false);
    static {
        /*
         * 富文本编辑时一些样式是使用style来进行实现的 比如红色字体 style="color:red;" 所以需要给所有标签添加style属性
         */
        whitelist.addAttributes(":all", "style");
    }

    public static String clean(String content) {
        return Jsoup.clean(content, "", whitelist, outputSettings);
    }
}

这里采用的白名单为basicWithImages，Jsoup内置了几种常见的白名单供我们选择，如下表所示：

| 白名单

| 标签

| 描述

| | —- | —- | —- | | none | | 只保留标签内的文本内容

| | simpleText | b,em,i,strong,u | 简单的文本标签 | | basic | a,b,blockquote,br,cite,code,dd,
dl,dt,em,i,li,ol,p,pre,q,small,span,
strike,strong,sub,sup,u,ul | 基本使用的标签 | | basicWithImages | basic 的基础上添加了 img 标签
及 img 标签的 src,align,alt,height,width,title 属性 | 基本使用的加上 img 标签 | | relaxed | a,b,blockquote,br,caption,cite,
code,col,colgroup,dd,div,dl,dt,
em,h1,h2,h3,h4,h5,h6,i,img,li,
ol,p,pre,q,small,span,strike,strong,
sub,sup,table,tbody,td,tfoot,th,thead,tr,u,ul | 在basicWithImages 的基础上又增加了一部分部分标签 |

编写Request包装类

创建一个XssHttpServletRequestWrapper类同过重写
- getParameter()
- getParameterValues()
- getHeader()
方法来过滤HTTP请求中参数包含的恶意字符：

import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletRequestWrapper;

import org.apache.commons.lang.StringUtils;

import cc.mrbird.common.util.JsoupUtil;

/**
 * 过滤http请求，防止Xss攻击
 */
public class XssHttpServletRequestWrapper extends HttpServletRequestWrapper {

    HttpServletRequest orgRequest = null;

    private boolean isIncludeRichText = false;

    public XssHttpServletRequestWrapper(HttpServletRequest request, boolean isIncludeRichText) {
        super(request);
        orgRequest = request;
        this.isIncludeRichText = isIncludeRichText;
    }

    /**
    * 覆盖getParameter方法，将参数名和参数值都做xss过滤如果需要获得原始的值，则通过super.getParameterValues(name)来获取
    * getParameterNames,getParameterValues和getParameterMap也可能需要覆盖
    */
    @Override
    public String getParameter(String name) {
        if (("content".equals(name) || name.endsWith("WithHtml")) && !isIncludeRichText) {
            return super.getParameter(name);
        }
        name = JsoupUtil.clean(name);
        String value = super.getParameter(name);
        if (StringUtils.isNotBlank(value)) {
            value = JsoupUtil.clean(value);
        }
        return value;
    }

    @Override
    public String[] getParameterValues(String name) {
        String[] arr = super.getParameterValues(name);
        if (arr != null) {
            for (int i = 0; i < arr.length; i++) {
                arr[i] = JsoupUtil.clean(arr[i]);
            }
        }
        return arr;
    }

    /**
    * 覆盖getHeader方法，将参数名和参数值都做xss过滤如果需要获得原始的值，则通过super.getHeaders(name)来获取
    * getHeaderNames 也可能需要覆盖
    */
    @Override
    public String getHeader(String name) {
        name = JsoupUtil.clean(name);
        String value = super.getHeader(name);
        if (StringUtils.isNotBlank(value)) {
            value = JsoupUtil.clean(value);
        }
        return value;
    }

    /**
    * 获取原始的request
    */
    public HttpServletRequest getOrgRequest() {
        return orgRequest;
    }

    /**
    * 获取原始的request的静态方法
    */
    public static HttpServletRequest getOrgRequest(HttpServletRequest req) {
        if (req instanceof XssHttpServletRequestWrapper) {
            return ((XssHttpServletRequestWrapper) req).getOrgRequest();
        }
        return req;
    }

}

编写过滤器

创建过滤器，同过使用上面定义的XssHttpServletRequestWrapper类中的getParameter()等方法来保证参数得到了过滤：

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

import javax.servlet.Filter;
import javax.servlet.FilterChain;
import javax.servlet.FilterConfig;
import javax.servlet.ServletException;
import javax.servlet.ServletRequest;
import javax.servlet.ServletResponse;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;

import org.apache.commons.lang.BooleanUtils;
import org.apache.commons.lang.StringUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

/**
 * Xss攻击拦截器
 *
 */
public class XssFilter implements Filter {

    private static Logger logger = LoggerFactory.getLogger(XssFilter.class);
    // 是否过滤富文本内容
    private static boolean IS_INCLUDE_RICH_TEXT = false;

    public List<String> excludes = new ArrayList<String>();

    @Override
    public void init(FilterConfig filterConfig) throws ServletException {
        logger.info("------------ xss filter init ------------");
        String isIncludeRichText = filterConfig.getInitParameter("isIncludeRichText");
        if (StringUtils.isNotBlank(isIncludeRichText)) {
            IS_INCLUDE_RICH_TEXT = BooleanUtils.toBoolean(isIncludeRichText);
        }
        String temp = filterConfig.getInitParameter("excludes");
        if (temp != null) {
            String[] url = temp.split(",");
            for (int i = 0; url != null && i < url.length; i++) {
                excludes.add(url[i]);
            }
        }
    }

    @Override
    public void doFilter(ServletRequest request, ServletResponse response, FilterChain chain)
            throws IOException, ServletException {
        HttpServletRequest req = (HttpServletRequest) request;
        HttpServletResponse resp = (HttpServletResponse) response;
        if (handleExcludeURL(req, resp)) {
            chain.doFilter(request, response);
            return;
        }
        XssHttpServletRequestWrapper xssRequest = new XssHttpServletRequestWrapper((HttpServletRequest) request,
          IS_INCLUDE_RICH_TEXT);
        chain.doFilter(xssRequest, response);
    }

    @Override
    public void destroy() {

    }

    private boolean handleExcludeURL(HttpServletRequest request, HttpServletResponse response) {
        if (excludes == null || excludes.isEmpty()) {
            return false;
        }
        String url = request.getServletPath();
        for (String pattern : excludes) {
            Pattern p = Pattern.compile("^" + pattern);
            Matcher m = p.matcher(url);
            if (m.find())
            return true;
        }
        return false;
    }
}

编写配置过滤器

使用JavaConfig的方式配置

@Bean
public FilterRegistrationBean xssFilterRegistrationBean() {
    FilterRegistrationBean filterRegistrationBean = new FilterRegistrationBean();
    filterRegistrationBean.setFilter(new XssFilter());
    filterRegistrationBean.setOrder(1);
    filterRegistrationBean.setEnabled(true);
    filterRegistrationBean.addUrlPatterns("/*");
    Map<String, String> initParameters = new HashMap<String, String>();
    initParameters.put("excludes", "/favicon.ico,/img/*,/js/*,/css/*");
    initParameters.put("isIncludeRichText", "true");
    filterRegistrationBean.setInitParameters(initParameters);
    return filterRegistrationBean;
}

附录：