用Jsoup对用户输入内容的HTML安全过滤_html/css_WEB-ITnose

官方API地址： http://jsoup.org/apidocs/org/jsoup/safety/Whitelist.html

发现来源：

http://www.oschina.net/question/12_10232 ， 据此自己写了个自定义的帮助类：

package com.cssor.safety; import org.jsoup.Jsoup;import org.jsoup.helper.StringUtil;import org.jsoup.safety.Whitelist; public class ContentSafeFilter {	private final static Whitelist user_content_filter = Whitelist.relaxed();	static {		//增加可信标签到白名单		user_content_filter.addTags("embed","object","param","span","div");		//增加可信属性	user_content_filter.addAttributes(":all", "style", "class", "id", "name");		user_content_filter.addAttributes("object", "width", "height","classid","codebase");		user_content_filter.addAttributes("param", "name", "value");		user_content_filter.addAttributes("embed", "src","quality","width","height","allowFullScreen","allowScriptAccess","flashvars","name","type","pluginspage");	} 	/**	 * 对用户输入内容进行过滤	 * @param html	 * @return	 */	public static String filter(String html) {		if(StringUtil.isBlank(html)) return "";		return Jsoup.clean(html, user_content_filter);		//return filterScriptAndStyle(html);	} 	/**	 * 比较宽松的过滤，但是会过滤掉object，script， span,div等标签，适用于富文本编辑器内容或其他html内容	 * @param html	 * @return	 */	public static String relaxed(String html) {		return Jsoup.clean(html, Whitelist.relaxed());	} 	/**	 * 去掉所有标签，返回纯文字.适用于textarea，input	 * @param html	 * @return	 */	public static String pureText(String html) {		return Jsoup.clean(html, Whitelist.none());	} 	/**	 * @param args	 */	public static void main(String[] args) {		String unsafe = "
1
" +	"" +				"
Link" +				"" +				"

Jsoup不支持相对路径图片的过滤，比如会被去掉src属性，想了个简单的方法避免：

/** * 自定义对用户输入内容进行过滤的标签 * @param html * @return */public static String filter(String html) {    if(StringUtil.isBlank(html)) return "";    String baseUri = "http://baseuri";    return Jsoup.clean(html, baseUri, user_content_filter).replaceAll("src=\"http://baseuri", "src=\"");}

http://cssor.com/jsoup-whitelist-clean-html-for-user-content.html