XSS攻击全称跨站脚本攻击,是一种在web应用中的计算机安全漏洞,它允许恶意web用户将代码植入到提供给其它用户使用的页面中。
你可以自己做个简单尝试:
1. 在任何一个表单内,你输入一段简单的js代码:,将其存入数据库;
2. 在页面上一个div元素内直接展示第一步内存入的值,你会发现弹出框出现了;
以上两个示例仅仅算是恶作剧,恶意用户能做的更多,如获取用户信息,进行“网络钓鱼”攻击等。
应对XSS攻击的其中一个方式就是后端对输入内容进行过滤,输入内容里面的敏感信息直接过滤,如标签等。
Jsoup使用标签白名单的机制用来进行防止XSS攻击, 假设白名单中只允许p标签存在, 此时在一段HTML代码中, 只能存在p标签 , 其他标签将会被清除只保留被标签所包裹的内容,当然,Jsoup不仅仅可以用来过滤,还可以用来爬虫,这里先不做说明,后期会单写一篇文章进行讲解。
org.jsoup
jsoup
1.10.2
在core下创建filter
文件夹
1、创建过滤规则
package com.example.demo.core.filter;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.safety.Whitelist;
/**phubing张瑶
* @Description: xss非法标签过滤
* @date 2019/5/16 20:03
*/
public class XssFilterUtil {
/**
* 使用自带的basicWithImages 白名单
* 允许的便签有a,b,blockquote,br,cite,code,dd,dl,dt,em,i,li,ol,p,pre,q,small,span,
* strike,strong,sub,sup,u,ul,img
* 以及a标签的href,img标签的src,align,alt,height,width,title属性
*/
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);
}
}
2、重写请求参数处理函数,这是实现XSS过滤的关键,在其内重写了getParameter,getParameterValues,getHeader等方法,对http请求内的参数进行了过滤。
package com.example.demo.core.filter;
import org.apache.commons.lang3.StringUtils;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletRequestWrapper;
/**
* 重写请求参数处理函数
*/
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 = XssFilterUtil.clean(name);
String value = super.getParameter(name);
if (StringUtils.isNotBlank(value)) {
value = XssFilterUtil.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] = XssFilterUtil.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 = XssFilterUtil.clean(name);
String value = super.getHeader(name);
if (StringUtils.isNotBlank(value)) {
value = XssFilterUtil.clean(value);
}
return value;
}
/**
* 获取最原始的request
*
* @return
*/
public HttpServletRequest getOrgRequest() {
return orgRequest;
}
/**
* 获取最原始的request的静态方法
*
* @return
*/
public static HttpServletRequest getOrgRequest(HttpServletRequest req) {
if (req instanceof XssHttpServletRequestWrapper) {
return ((XssHttpServletRequestWrapper) req).getOrgRequest();
}
return req;
}
}
3、添加过滤XSS请求的入口,在这里通过XssHttpServletRequestWrapper将HttpServletRequest进行了封装,filterChain.doFilter(xssRequest, response);
保证了后续代码执行request.getParameter,request.getParameterValues,request.getHeader时调用的都是XssHttpServletRequestWrapper内重写的方法,获取到的参数是已经进行过标签过滤的内容,从而消除了敏感信息。
package com.example.demo.core.filter;
import org.apache.commons.lang3.BooleanUtils;
import org.apache.commons.lang3.StringUtils;
import javax.servlet.*;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
* @author phubing
* @Description: 拦截防止xss注入 通过Jsoup过滤请求参数内的特定字符
* @date 2019/5/16 20:04
*/
public class XssFilter implements Filter {
//是否过滤富文本内容
private static boolean IS_INCLUDE_RICH_TEXT = true;
public List excludes = new ArrayList<>();
@Override
public void doFilter(ServletRequest request, ServletResponse response, FilterChain filterChain) throws IOException, ServletException {
HttpServletRequest req = (HttpServletRequest) request;
HttpServletResponse resp = (HttpServletResponse) response;
if (handleExcludeURL(req, resp)) {
filterChain.doFilter(request, response);
return;
}
XssHttpServletRequestWrapper xssRequest = new XssHttpServletRequestWrapper((HttpServletRequest) request, IS_INCLUDE_RICH_TEXT);
filterChain.doFilter(xssRequest, response);
}
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;
}
@Override
public void init(FilterConfig filterConfig) throws ServletException {
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 destroy() {
}
}
创建core→configurer→XssFilterConfigurer
package com.example.demo.core.configurer;
import com.example.demo.core.filter.XssFilter;
import org.springframework.boot.web.servlet.FilterRegistrationBean;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
import java.util.HashMap;
import java.util.Map;
/**
* @author phubing
* @Description:xss过滤拦截器配置文件
* @time 2019/5/16 20:47
*/
@Configuration
public class XssFilterConfigurer {
/**
* xss过滤拦截器
*/
@Bean
public FilterRegistrationBean xssFilterRegistrationBean() {
FilterRegistrationBean filterRegistrationBean = new FilterRegistrationBean();
filterRegistrationBean.setFilter(new XssFilter());
filterRegistrationBean.setOrder(Integer.MAX_VALUE-1);
filterRegistrationBean.setEnabled(true);
filterRegistrationBean.addUrlPatterns("/*");
Map initParameters = new HashMap();
//excludes用于配置不需要参数过滤的请求url
initParameters.put("excludes", "/favicon.ico,/img/*,/js/*,/css/*");
//isIncludeRichText主要用于设置富文本内容是否需要过滤
initParameters.put("isIncludeRichText", "true");
filterRegistrationBean.setInitParameters(initParameters);
return filterRegistrationBean;
}
}
路径localhost:8080/userInfo/selectById
请求参数id=1ssssss
我们可以看到已经被过滤掉