java富文本转换为纯文本

import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.Reader;

import javax.swing.text.html.HTMLEditorKit;
import javax.swing.text.html.parser.ParserDelegator;

public class Html2Text extends HTMLEditorKit.ParserCallback {

    private static Html2Text html2Text = new Html2Text();

    StringBuffer s;

    public Html2Text() {
    }

    public void parse(String str) throws IOException {

        InputStream iin = new ByteArrayInputStream(str.getBytes());
        Reader in = new InputStreamReader(iin);
        s = new StringBuffer();
        ParserDelegator delegator = new ParserDelegator();
        // the third parameter is TRUE to ignore charset directive
        delegator.parse(in, this, Boolean.TRUE);
        iin.close();
        in.close();
    }

    public void handleText(char[] text, int pos) {
        s.append(text);
    }

    public String getText() {
        return s.toString();
    }

    public static String getContent(String str) {
        try {
            html2Text.parse(str);
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
        return html2Text.getText();
    }
}

也就是把富文本里的格式和标签去掉

 

调用方式：
String text = Html2Text.getContent("你的富文本字符串");