JavaWeb实现XSS过滤器

自定一个请求处理类继承HttpServletRequestWrapper类，重写各个请求参数的获取方法，在方法里面使用正则匹配过滤掉特殊的符号:

public class XSSHttpServletRequestWrapper extends HttpServletRequestWrapper {
    /**
     * Constructs a request object wrapping the given request.
     *
     * @param request The request to wrap
     * @throws IllegalArgumentException if the request is null
     */
    public XSSHttpServletRequestWrapper(HttpServletRequest request) {
        super(request);
    }

    /**
     * 对数组参数进行特殊字符过滤
     */
    @Override
    public String[] getParameterValues(String name) {
        String[] values = super.getParameterValues(name);
        if (values == null) {
            return null;
        }
        int count = values.length;
        String[] encodedValues = new String[count];
        for (int i = 0; i < count; i++) {
            encodedValues[i] = cleanXSS(values[i]);
        }
        return encodedValues;
    }

    /**
     * 对参数中特殊字符进行过滤
     */
    @Override
    public String getParameter(String name) {
        String value = super.getParameter(name);
        if (value == null) {
            return null;
        }
        return cleanXSS(value);
    }

    /**
     * 获取attribute,特殊字符过滤
     */
    @Override
    public Object getAttribute(String name) {
        Object value = super.getAttribute(name);
        if (value != null && value instanceof String) {
            cleanXSS((String) value);
        }
        return value;
    }

    /**
     * 对请求头部进行特殊字符过滤
     */
    @Override
    public String getHeader(String name) {
        String value = super.getHeader(name);
        if (value == null) {
            return null;
        }
        return cleanXSS(value);
    }

    private String cleanXSS(String value) {
        if (value != null) {
            //推荐使用ESAPI库来避免脚本攻击,value = ESAPI.encoder().canonicalize(value);
            // 避免空字符串
            value = value.replaceAll(" ", "");
            // 避免script 标签
            Pattern scriptPattern = Pattern.compile("<script>(.*?)</script>", Pattern.CASE_INSENSITIVE);
            value = scriptPattern.matcher(value).replaceAll("");
            // 避免src形式的表达式
            scriptPattern = Pattern.compile("src[\r\n]*=[\r\n]*\\\'(.*?)\\\'",
                    Pattern.CASE_INSENSITIVE | Pattern.MULTILINE | Pattern.DOTALL);
            value = scriptPattern.matcher(value).replaceAll("");
            scriptPattern = Pattern.compile("src[\r\n]*=[\r\n]*\\\"(.*?)\\\"",
                    Pattern.CASE_INSENSITIVE | Pattern.MULTILINE | Pattern.DOTALL);
            value = scriptPattern.matcher(value).replaceAll("");
            // 删除单个的 </script> 标签
            scriptPattern = Pattern.compile("</script>", Pattern.CASE_INSENSITIVE);
            value = scriptPattern.matcher(value).replaceAll("");
            // 删除单个的<script ...> 标签
            scriptPattern = Pattern.compile("<script(.*?)>",
                    Pattern.CASE_INSENSITIVE | Pattern.MULTILINE | Pattern.DOTALL);
            value = scriptPattern.matcher(value).replaceAll("");
            // 避免 eval(...) 形式表达式
            scriptPattern = Pattern.compile("eval\\((.*?)\\)",
                    Pattern.CASE_INSENSITIVE | Pattern.MULTILINE | Pattern.DOTALL);
            value = scriptPattern.matcher(value).replaceAll("");
            // 避免 e­xpression(...) 表达式
            scriptPattern = Pattern.compile("e­xpression\\((.*?)\\)",
                    Pattern.CASE_INSENSITIVE | Pattern.MULTILINE | Pattern.DOTALL);
            value = scriptPattern.matcher(value).replaceAll("");
            // 避免 javascript: 表达式
            scriptPattern = Pattern.compile("javascript:", Pattern.CASE_INSENSITIVE);
            value = scriptPattern.matcher(value).replaceAll("");
            // 避免 vbscript:表达式
            scriptPattern = Pattern.compile("vbscript:", Pattern.CASE_INSENSITIVE);
            value = scriptPattern.matcher(value).replaceAll("");
            // 避免 οnlοad= 表达式
            scriptPattern = Pattern.compile("onload(.*?)=",
                    Pattern.CASE_INSENSITIVE | Pattern.MULTILINE | Pattern.DOTALL);
            value = scriptPattern.matcher(value).replaceAll("");
        }
        return value;
    }
}

定义过滤器：

public class XSSHttpServletRequestFilter implements Filter {
    private final Logger logger = LoggerFactory.getLogger(getClass());

    @Override
    public void init(FilterConfig filterConfig) throws ServletException {
        logger.info("##init XSSFilter");
    }

    @Override
    public void doFilter(ServletRequest request, ServletResponse response, FilterChain chain) throws IOException, ServletException {
        try {
            //将请求转换为 自定义的请求包装类
            chain.doFilter(new XSSHttpServletRequestWrapper((HttpServletRequest) request), response);
        } catch (Exception e) {
            throw e;
        }
    }

    @Override
    public void destroy() {
        logger.info("##destroy XSSFilter");
    }
}

将过滤器注册到spring的bean容器中:

@Bean
public FilterRegistrationBean xSSHttpServletRequestFilterRegistrationBean() {
    FilterRegistrationBean filterRegistrationBean = new FilterRegistrationBean();
    filterRegistrationBean.setFilter(new XSSHttpServletRequestFilter());
    filterRegistrationBean.setName("xSSHttpServletRequestFilter");
    filterRegistrationBean.setUrlPatterns(Arrays.asList("/xxx"));
    filterRegistrationBean.setOrder(1);
    return filterRegistrationBean;
}

这里使用的springboot，如果是spring，相当于在web.xml中加入一下配置：

<filter>
   <filter-name>xSSHttpServletRequestFilter</filter-name>
   <filter-class>com.xxx.xxx.xxxx.XSSHttpServletRequestFilter</filter-class>
</filter>
<filter-mapping>
   <filter-name>xSSHttpServletRequestFilter</filter-name>
   <url-pattern>/xxx</url-pattern>
</filter-mapping>

来源：oschina

链接：https://my.oschina.net/zerzer/blog/4264692