OWASP HTML Sanitizer 是一个简单快捷的java类库,主要用于放置XSS
优点如下:
1.使用简单。不需要繁琐的xml配置,只用在代码中少量的编码
2.由Mike Samuel(谷歌工程师)维护
3.通过了AntiSamy超过95%的UT覆盖
4.高性能,低内存消耗
5.是 AntiSamy DOM性能的4倍
1.POM中增加
<!--html标签过滤-->
<dependency>
<groupId>com.googlecode.owasp-java-html-sanitizer</groupId>
<artifactId>owasp-java-html-sanitizer</artifactId>
<version>r136</version>
</dependency>
2.工具类
import org.owasp.html.ElementPolicy;
import org.owasp.html.HtmlPolicyBuilder;
import org.owasp.html.PolicyFactory; import java.util.List; /**
* @author : RandySun
* @date : 2018-10-08 10:32
* Comment :
*/
public class HtmlUtils { //允许的标签
private static final String[] allowedTags = {"h1", "h2", "h3", "h4", "h5", "h6",
"span", "strong",
"img", "video", "source",
"blockquote", "p", "div",
"ul", "ol", "li",
"table", "thead", "caption", "tbody", "tr", "th", "td", "br",
"a"
}; //需要转化的标签
private static final String[] needTransformTags = {"article", "aside", "command","datalist","details","figcaption", "figure",
"footer","header", "hgroup","section","summary"}; //带有超链接的标签
private static final String[] linkTags = {"img","video","source","a"};
public static String sanitizeHtml(String htmlContent){
PolicyFactory policy = new HtmlPolicyBuilder()
//所有允许的标签
.allowElements(allowedTags)
//内容标签转化为div
.allowElements( new ElementPolicy() {
@Override
public String apply(String elementName, List<String> attributes){
return "div";
}
},needTransformTags)
.allowAttributes("src","href","target").onElements(linkTags)
//校验链接中的是否为http
.allowUrlProtocols("https")
.toFactory();
String safeHTML = policy.sanitize(htmlContent);
return safeHTML;
} public static void main(String[] args){
String inputHtml = "<img src=\"https://a.jpb\"/>";
System.out.println(sanitizeHtml(inputHtml));
}
}
其中.allowElements(allowedTags)是添加所有允许的html标签,
以下是需要转化的标签,把needTransformTags中的内容全部转化为div
//内容标签转化为div
.allowElements( new ElementPolicy() {
@Override
public String apply(String elementName, List<String> attributes){
return "div";
}
},needTransformTags)
.allowAttributes("src","href","target").onElements(linkTags)是在特定的标签上允许的属性
.allowUrlProtocols("https")表示href或者src链接中只允许https协议