nekohtml的2个小例子

//获取网页里面的keywords和description
	public static void main(String[] argv) throws Exception {

		BufferedReader in = new BufferedReader(new FileReader("d:/163.html"));
		DOMParser parser = new DOMParser();
		 parser.setProperty(
			     "http://cyberneko.org/html/properties/default-encoding",
			     "gb2312");
		parser.parse(new InputSource(in));

		Document doc = parser.getDocument();
		NodeList list = doc.getElementsByTagName("META");
		for(int i = 0, n = list.getLength(); i < n ; i++){
			Element e = (Element) list.item(i);
			if(e.getAttribute("name").equalsIgnoreCase("keywords")){
				String keywords = e.getAttribute("content");
				System.out.println("keywords: " + keywords);
			}
			if(e.getAttribute("name").equalsIgnoreCase("description")){
				String description = e.getAttribute("content");
				System.out.println(description);
			}
		}
	} 

==========================================================================
//2、test使用DOMFragmentParser，提取所有正文，由于没有过滤一些没用的标签，所以会有没用的信息打印，这个可以再事先过滤一下。

	public static void main(String[] argv) throws Exception {
		DOMFragmentParser parser = new DOMFragmentParser();
		HTMLDocument document = new HTMLDocumentImpl();
		DocumentFragment fragment = document.createDocumentFragment();
		parser.parse("http://sports.sina.com.cn/f1/2009-09-21/20104599271.shtml", fragment);
		print(fragment, "");
	} 

	/** Prints a node's class name. */
	public static void print(Node node, String indent) {

//		System.out.println(indent + node.getClass().getName());
//		System.out.println(node.getNodeType());

		if (node.getNodeType() == Node.TEXT_NODE) {
			System.out.println(indent + node.getNodeValue());
		}
		Node child = node.getFirstChild();
		while (child != null) {
			print(child, indent + " ");
			child = child.getNextSibling();
		}
	} 

}