public static String getPlainHtml(Element element) { FormattingVisitor formatter = new FormattingVisitor(); NodeTraversor traversor = new NodeTraversor(formatter); traversor.traverse(element); // walk the DOM, and call .head() and .tail() for each node return formatter.toString(); }
/** * @param htmlText * @return */ public static String htmlToPlainText(String htmlText) { // replace the blanks in previous htmlText = htmlText.replaceAll(" ", ""); Document doc = Jsoup.parse(htmlText); FormattingVisitor formatter = new FormattingVisitor(); NodeTraversor traversor = new NodeTraversor(formatter); traversor.traverse(doc); return formatter.toString().trim(); }