Feed.java

/**
 *
 */
package com.nugporn.xxx;

import java.io.IOException;
import java.util.ArrayList;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathExpression;
import javax.xml.xpath.XPathExpressionException;
import javax.xml.xpath.XPathFactory;

import org.w3c.dom.Document;
import org.w3c.dom.NodeList;
import org.xml.sax.SAXException;

/**
 * @author beppu
 *
 */
public class Feed {
	private ArrayList<Item> items;

	/**
	 * @return
	 */
	public ArrayList<Item> getItems() {
		return items;
	}

	/**
	 * @param item
	 */
	public void addItem(Item item) {
		this.items.add(item);
	}

	/**
	 * @param doc
	 * @throws XPathExpressionException
	 */
	Feed(Document doc) throws XPathExpressionException {
		this.items = new ArrayList<Item>();
		XPath xpath = XPathFactory.newInstance().newXPath();
		XPathExpression xx = xpath.compile("//channel/item");
		NodeList nodes = (NodeList) xx.evaluate(doc, XPathConstants.NODESET);

		for (int i = 0; i < nodes.getLength(); i++) {
			Item item = new Item(nodes.item(i));
			this.addItem(item);
		}
	}

	/**
	 * @param filename
	 * @return
	 * @throws ParserConfigurationException
	 * @throws SAXException
	 * @throws IOException
	 * @throws XPathExpressionException
	 */
	public static Feed loadFromFile(String filename) throws ParserConfigurationException, SAXException, IOException, XPathExpressionException {

		// load document into doc
		DocumentBuilderFactory domFactory = DocumentBuilderFactory.newInstance();
		domFactory.setNamespaceAware(true);
		DocumentBuilder builder = domFactory.newDocumentBuilder();
		Document doc = builder.parse(filename);

		Feed f = new Feed(doc);
		return f;
	}

	/* (non-Javadoc)
	 * @see java.lang.Object#toString()
	 */
	@Override
	public String toString() {
		StringBuffer b = new StringBuffer();
		String __ = "    ";
		for (Item i: items) {
			b.append(i.getTitle()                      + "\n");
			b.append(__ + i.getPubDate().toString()    + "\n");
			b.append(__ + i.getLink().toString()       + "\n");
			b.append(__ + i.getComments().toString()   + "\n");
			b.append(__ + i.getCreator()               + "\n");
			b.append(__ + i.getCategories().toString() + "\n");
			b.append("\n");
		}
		return b.toString();
	}
}

Item.java

package com.nugporn.xxx;

import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.Iterator;

import javax.xml.XMLConstants;
import javax.xml.namespace.NamespaceContext;
import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathExpression;
import javax.xml.xpath.XPathExpressionException;
import javax.xml.xpath.XPathFactory;

import org.w3c.dom.Node;
import org.w3c.dom.NodeList;

/**
 * @author beppu
 *
 */
public class Item {

	// item attributes from the feed
	private String title;
	private URL link;
	private URL comments;
	private String pubDate;
	private String creator;
	private String description;
	private String content;
	private ArrayList<String> categories;

	// objects for internal use
	private Node itemNode;
	private XPath xpath;

	/**
	 * @param node
	 * @throws XPathExpressionException
	 */
	public Item(Node node) throws XPathExpressionException {
		this.itemNode = node;
		this.xpath = XPathFactory.newInstance().newXPath();

		// http://www.ibm.com/developerworks/xml/library/x-nmspccontext/index.html?ca=drs-
		// It's so unfortunately retarded that I have to do this.
		this.xpath.setNamespaceContext(new NamespaceContext() {
			public String getNamespaceURI(String prefix) {
				if (prefix == null) {
					throw new IllegalArgumentException("No prefix provided");
				} else if ("dc".equals(prefix)) {
					return "http://purl.org/dc/elements/1.1/";
				} else {
					return XMLConstants.XML_NS_URI;
				}
			}

			@Override
			public String getPrefix(String namespaceURI) {
				return null;
			}

			@Override
			public Iterator<String> getPrefixes(String namespaceURI) {
				return null;
			}
		});

		try {
			this.link = new URL(x("link"));
		} catch (MalformedURLException e) {
			e.printStackTrace();
		}
		try {
			this.comments = new URL(x("comments"));
		} catch (MalformedURLException e) {
			e.printStackTrace();
		}

		this.title       =  x("title");
		this.pubDate     =  x("pubDate");
		this.creator     =  x("dc:creator");
		this.description =  x("description");
		this.content     =  x("content:encoded");
		this.categories  = xx("category");
	}

	/**
	 * @return the title
	 */
	public String getTitle() {
		return title;
	}

	/**
	 * @return the link
	 */
	public URL getLink() {
		return link;
	}

	/**
	 * @return the comments
	 */
	public URL getComments() {
		return comments;
	}

	/**
	 * @return the pubDate
	 */
	public String getPubDate() {
		return pubDate;
	}

	/**
	 * @return the creator
	 */
	public String getCreator() {
		return creator;
	}

	/**
	 * @return the description
	 */
	public String getDescription() {
		return description;
	}

	/**
	 * @return the content
	 */
	public String getContent() {
		return content;
	}

	/**
	 * @return the categories
	 */
	public ArrayList<String> getCategories() {
		return categories;
	}

	/**
	 * @param path
	 * @return
	 * @throws XPathExpressionException
	 */
	private String x(String path) throws XPathExpressionException {
		XPathExpression expr = this.xpath.compile(path);
		NodeList nodes = (NodeList) expr.evaluate(this.itemNode, XPathConstants.NODE);
		if (nodes == null) {
			return "";
		}
		Node n1 = nodes.item(0);
		if (n1 != null) {
			return n1.getNodeValue();
		} else {
			return "";
		}
	}

	/**
	 * @param path
	 * @return
	 * @throws XPathExpressionException
	 */
	private ArrayList<String> xx(String path) throws XPathExpressionException {
		// System.out.println(path);
		ArrayList<String> strings = new ArrayList<String>();
		XPathExpression expr = this.xpath.compile(path);
		NodeList nodes = (NodeList) expr.evaluate(this.itemNode, XPathConstants.NODESET);
		if (nodes == null) {
			return strings;
		}
		for (int i = 0; i < nodes.getLength(); i++) {
			strings.add(nodes.item(i).getTextContent());
		}
		return strings;
	}

}

NugFeed.java

/**
 *
 */
package com.nugporn.xxx;

import java.io.IOException;

import javax.xml.parsers.ParserConfigurationException;
import javax.xml.xpath.XPathExpressionException;

import org.xml.sax.SAXException;

/**
 * @author beppu
 *
 */
public class NugFeed {

	/**
	 *
	 */
	public NugFeed() {
	}

	/**
	 * @param args
	 */
	public static void main(String[] args) {
		Feed f = null;
		if (args.length == 0) {
			System.out.println("Usage: nugporn <FILE>\n");
		}
		try {
			f = Feed.loadFromFile(args[0]);
		} catch (ParserConfigurationException e) {
			e.printStackTrace();
		} catch (SAXException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		} catch (XPathExpressionException e) {
			e.printStackTrace();
		}
		if (f != null) {
			System.out.println(f.toString());
		} else {
			System.out.println("Could not load feed: " + args[0] + "\n");
		}
	}

}