JDOM based TagStripper

import org.jdom.*;
import org.jdom.output.XMLOutputter;
import org.jdom.input.SAXBuilder;
import java.io.*;
import java.util.*;


public class TagStripper extends XMLOutputter {

  public TagStripper() {
    super();
  }

  // Things we won't print at all
  protected void printDeclaration(Document doc, Writer out, String encoding) {}
  protected void printComment(Comment comment, Writer out, int indentLevel) {}
  protected void printDocType(DocType docType, Writer out) {}
  protected void printProcessingInstruction(ProcessingInstruction pi, 
   Writer out, int indentLevel) {}
  protected void printNamespace(Namespace ns, Writer out) {}
  protected void printAttributes(List attributes, Writer out) {}
  
  
  protected void printElement(Element element, Writer out, int indentLevel)
   throws IOException {
    
    List content = element.getMixedContent();
    Iterator iterator = content.iterator();
    while (iterator.hasNext()) {
      Object o = iterator.next();
      if (o instanceof String) {
        out.write((String) o);
        this.maybePrintln(out);
      }
      else if (o instanceof Element) {
        printElement((Element) o, out, indentLevel);
      }
    }
          
  }

  // Could easily have put main() method in a separate class
  public static void main(String[] args) {
     
    if (args.length == 0) {
      System.out.println(
       "Usage: java TagStripper URL1 URL2..."); 
    } 
      
    TagStripper stripper = new TagStripper();
    SAXBuilder builder   = new SAXBuilder();
    
    // start parsing... 
    for (int i = 0; i < args.length; i++) {
      
      // command line should offer URIs or file names
      try {
        Document doc = builder.build(args[i]);
        stripper.output(doc, System.out);
      }
      catch (JDOMException e) { // a well-formedness error
        System.out.println(args[i] + " is not well formed.");
        System.out.println(e.getMessage());
      }
      catch (IOException e) { // a well-formedness error
        System.out.println(e.getMessage());
      }
      
    }  
  
  }

}

Previous | Next | Top | Cafe con Leche

Copyright 2000 Elliotte Rusty Harold
elharo@metalab.unc.edu
Last Modified June 20, 2000