Java去除HTML标签

去除所有标签

package com.alibaba.xiaomi.externalservice.provider.iocevent;


import java.io.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * @Author 楚璃轩
 * @Date 2021/12/29  17:35
 * @Description
 */

public class ceshi{
    public static void main(String[] args) throws IOException {

        String content="<p>受理范围<br/> <a href='ssssss'>gggggggg</a>要求提交身份证明。<br/></p><a href='ssssss'>fffff</a>";
       
        //定义html的正则表达式
        String pattern="<[^>]+>";
        //控制正则表达式的匹配行为的参数。让表达式忽略大小写进行匹配
        Pattern compile = Pattern.compile(pattern, Pattern.CASE_INSENSITIVE);
        //创建一个匹配器，该匹配器将根据此模式匹配给定的输入
        Matcher matcher = compile.matcher(content);
        //替换
        content = matcher.replaceAll("");
        System.out.println(content);	//受理范围 gggggggg要求提交身份证明。fffff

    }

}

去除某个标签

package com.alibaba.xiaomi.externalservice.provider.iocevent;


import java.io.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * @Author 楚璃轩
 * @Date 2021/12/29  17:35
 * @Description
 */

public class ceshi{
    public static void main(String[] args) throws IOException {

        String content="<p>受理范围<br/> <a href='ssssss'>gggggggg</a>要求提交身份证明。<br/></p><a href='ssssss'>fffff</a>";

        //去除<a>
        Pattern pattern1 = Pattern.compile("<a[^<]*?>");
        Matcher matcher1 = pattern1.matcher(content);
        content=matcher1.replaceAll("");
        Pattern pattern2 = Pattern.compile("</a>");
        Matcher matcher2 = pattern2.matcher(content);
        content= matcher2.replaceAll("");
        去除<p>
        Pattern pattern3 = Pattern.compile("<p[^<]*?>");
        Matcher matcher3 = pattern3.matcher(content);
        content=matcher3.replaceAll("");
        Pattern pattern4 = Pattern.compile("</p>");
        Matcher matcher4 = pattern4.matcher(content);
        content= matcher4.replaceAll("");

        System.out.println(content);	//受理范围<br/> gggggggg要求提交身份证明。<br/>fffff


    }


}