textextractionutility

来自「随书的代码」· 代码 · 共 30 行

import org.w3c.dom.*;
import org.w3c.dom.traversal.*;


public class TextExtractor {

  public static String getText(Node node) {
    
    if (node == null) return "";
    
    // Set up the iterator
    Document doc = node.getOwnerDocument();
    DocumentTraversal traversable = (DocumentTraversal) doc;
    int whatToShow 
     = NodeFilter.SHOW_TEXT | NodeFilter.SHOW_CDATA_SECTION;
    NodeIterator iterator = traversable.createNodeIterator(node, 
     whatToShow, null, true);
     
    // Extract the text
    StringBuffer result = new StringBuffer();
    Node current;
    while ((current = iterator.nextNode()) != null) {
      result.append(current.getNodeValue());
    }
    return result.toString();
    
  }

}