Extract plain text from HTML

HtmlToText.java

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


final StringBuilder sb = new StringBuilder();
HTMLEditorKit.ParserCallback parserCallback = new HTMLEditorKit.ParserCallback() {
    public boolean readyForNewline;

    @Override public void handleText(final char[] data, final int pos) {
        String s = new String(data);
        sb.append(s.trim());
        readyForNewline = true;
    }
    @Override public void handleStartTag(final HTML.Tag t, final MutableAttributeSet a, final int pos) {
        if (readyForNewline && (t == HTML.Tag.DIV || t == HTML.Tag.BR || t == HTML.Tag.P || t == HTML.Tag.LI)) {
            sb.append("\n");
            readyForNewline = false;
        }
    }
    @Override public void handleSimpleTag(final HTML.Tag t, final MutableAttributeSet a, final int pos) {
        handleStartTag(t, a, pos);
    }
};
new ParserDelegator().parse(new StringReader(html), parserCallback, false);
String plainText = sb.toString();

Copied from http://stackoverflow.com/questions/3911385/convert-html-to-plain-text-in-java

|| t == HTML.Tag.Li needed