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();
}
private int copySafeNodes(Element source, Element dest) {
CleaningVisitor cleaningVisitor = new CleaningVisitor(source, dest);
NodeTraversor traversor = new NodeTraversor(cleaningVisitor);
traversor.traverse(source);
return cleaningVisitor.numDiscarded;
}
public static String getPlainText(Element element) {
PlainTextFormatter plainTextFormatter = new PlainTextFormatter();
NodeTraversor traversor = new NodeTraversor(plainTextFormatter);
traversor.traverse(element);
return plainTextFormatter.toString();
}