Java對html標簽的過濾和清洗

OWASP HTML Sanitizer 是一個簡單快捷的java類庫，主要用於放置XSS

優點如下：

　　1.使用簡單。不需要繁瑣的xml配置，只用在代碼中少量的編碼

　　2.由Mike Samuel（谷歌工程師）維護

　　3.通過了AntiSamy超過95%的UT覆蓋

　　4.高性能，低內存消耗

　　5.是 AntiSamy DOM性能的4倍

 

1.POM中增加

        <!--html標簽過濾-->
        <dependency>
            <groupId>com.googlecode.owasp-java-html-sanitizer</groupId>
            <artifactId>owasp-java-html-sanitizer</artifactId>
            <version>r136</version>
        </dependency>

2.工具類

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 {

    //允許的標簽
    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"
    };

    //需要轉化的標簽
    private static final String[] needTransformTags = {"article", "aside", "command","datalist","details","figcaption", "figure",
            "footer","header", "hgroup","section","summary"};

    //帶有超鏈接的標簽
    private static final String[] linkTags = {"img","video","source","a"};
    public static String sanitizeHtml(String htmlContent){
        PolicyFactory policy = new HtmlPolicyBuilder()
                //所有允許的標簽
                .allowElements(allowedTags)
                //內容標簽轉化為div
                .allowElements( new ElementPolicy() {
                    @Override
                    public String apply(String elementName, List<String> attributes){
                        return "div";
                    }
                },needTransformTags)
                .allowAttributes("src","href","target").onElements(linkTags)
                //校驗鏈接中的是否為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)是添加所有允許的html標簽，

以下是需要轉化的標簽，把needTransformTags中的內容全部轉化為div

//內容標簽轉化為div
.allowElements( new ElementPolicy() {
    @Override
    public String apply(String elementName, List<String> attributes){
        return "div";
    }
},needTransformTags)

 

.allowAttributes("src","href","target").onElements(linkTags)是在特定的標簽上允許的屬性

.allowUrlProtocols("https")表示href或者src鏈接中只允許https協議