HtmlParser解析中関村オンラインのタイトルとキーワード

public class ZolParser
{

	public static void main(String[] args) throws Exception
	{
		/**   */
		long now = System.currentTimeMillis();

		//  
		String htmlCode = setHtmlCode();
		/**   */
		getTitle(htmlCode);
		/**   */
		getkeywords(htmlCode);

		/**   */
		long current = System.currentTimeMillis();
		//  
		System.out.println(" ：" + (current - now));
	}

	/**
	 *  HTML 
	 * 
	 * @return
	 * @throws Exception
	 */
	public static String setHtmlCode() throws Exception
	{
		/**  HttpParser HTML */
		Parser parsers = new Parser("http://www.zol.com.cn/");
		//  
		parsers.setEncoding("gb2312");
		//  
		NodeFilter filter = new TagNameFilter("html");
		//  
		NodeList nList = parsers.extractAllNodesThatMatch(filter);
		//  
		return nList.toHtml();
	}

	/**
	 *  
	 * 
	 * @param htmlCode
	 * @throws ParserException
	 */
	public static void getTitle(String htmlCode) throws ParserException
	{

		Parser parser = new Parser();
		parser.setInputHTML(htmlCode);
		/*   */
		NodeFilter filter = new NodeClassFilter(TitleTag.class);
		NodeList nodeList = parser.extractAllNodesThatMatch(filter);
		/**   */
		System.out.println(" ： "+nodeList.elementAt(0).toPlainTextString());
	}

	/**
	 *  
	 * 
	 * @param htmlCode
	 * @throws ParserException
	 */
	public static void getkeywords(String htmlCode) throws ParserException
	{
		Parser parser = new Parser();
		parser.setInputHTML(htmlCode);
		/*   */
		NodeFilter filter = new AndFilter(new NodeClassFilter(MetaTag.class), new HasAttributeFilter("name", "keywords"));
		NodeList nodeList = parser.extractAllNodesThatMatch(filter);
		/**   */
		if (nodeList.size() > 0)
		{
			System.out.println(" ： "+((TagNode) nodeList.elementAt(0)).getAttribute("content"));
		}
	}
}