RemoveComments.java

// example solution to remove comments from HTML.
// re: http://groups.google.com/group/jsoup/browse_thread/thread/419b5ac4be88b086

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Node;

public class RemoveComments {
    public static void main(String... args) {
        String h = "<div><!-- no --><p>Hello<!-- gone --></div>";
        Document doc = Jsoup.parse(h);        
        
        removeComments(doc);        
        print(doc.html());
    }
    
    private static void removeComments(Node node) {
        // as we are removing child nodes while iterating, we cannot use a normal foreach over children,
        // or will get a concurrent list modification error.
        int i = 0;
        while (i < node.childNodes().size()) {
            Node child = node.childNode(i);
            if (child.nodeName().equals("#comment"))
                child.remove();
            else {
                removeComments(child);
                i++;
            }
        }
    }
    
    private static void print(String msg) {
        System.out.println(msg);
    }
}