Created
February 12, 2016 23:02
-
-
Save myndzi/4a615b3cd820658627a0 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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(); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment