根据接受的答案:
Removing HTML from a Java String
MyHtml2Text parser = new MyHtml2Text();
try {
parser.parse(new StringReader(myTextPane.getText()));
} catch (IOException ee) {
//handle exception
}
System.out.println(parser.getText());
在我链接的答案上找到的Html2Text类的略微修改版本
import java.io.IOException;
import javax.swing.text.html.*;
import javax.swing.text.html.parser.*;
public class MyHtml2Text extends HTMLEditorKit.ParserCallback {
StringBuffer s;
public MyHtml2Text() {}
public void parse(Reader in) throws IOException {
s = new StringBuffer();
ParserDelegator delegator = new ParserDelegator();
delegator.parse(in, this, Boolean.TRUE);
}
public void handleText(char[] text, int pos) {
s.append(text);
s.append("\n");
}
public String getText() {
return s.toString();
}
}