Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- private String cleanHTML(String str) {
- Element element = Jsoup.parse(str);
- final StringBuilder buffer = new StringBuilder();
- new NodeTraversor(new NodeVisitor() {
- boolean isNewline = true;
- @Override
- public void head(Node node, int depth) {
- }
- @Override
- public void tail(Node node, int depth) {
- if (node instanceof TextNode) {
- TextNode textNode = (TextNode) node;
- String text = textNode.text();//.replace('\u00A0', ' ').trim();
- if(!text.isEmpty()) {
- buffer.append(text);
- isNewline = false;
- }
- } else if (node instanceof Element) {
- Element element = (Element) node;
- if (!isNewline) {
- if((element.isBlock() || element.tagName().equals("br"))) {
- buffer.append("\n");
- isNewline = true;
- }
- }
- }
- }
- }).traverse(element);
- return buffer.toString();
- }
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement