xercesxmlextractor.java

《lucene+nutch搜索引擎开发》源代码

package chapter9;

import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.*;
import java.io.*;
import org.w3c.dom.Document; 
import org.w3c.dom.NodeList;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.xml.sax.SAXException ;

public class XercesXMLExtractor {
	   public static void main(String[] args) {
		   getXmlNodeText("D:\\workshop\\docs\\tree.xml");
	    }
	   public static void getXmlNodeText(String filename) {
	            // 获取DOM对象树的生成器
	        DocumentBuilderFactory builderfactory = DocumentBuilderFactory.newInstance();
	        try {
	            // 获取 DocumentBuilder实例
	            DocumentBuilder builder = builderfactory.newDocumentBuilder();
	            File file = new File(filename);
	            ////从 XML 文档获取 DOM 文档实例
	            Document document = builder.parse(file);
	            //获取某节点的集合
	            NodeList nodelist = document.getElementsByTagName("item");
	            // 获取节点列表的总长度
	            int listnum = nodelist.getLength();
	            System.out.println("--------节点数量："+listnum + "--------");
	            for (int i = 0; i < listnum; i++) {
	            	// 获取节点
	                Element eltItem = (Element) nodelist.item(i);
	                // 获取节点的各项属性
	                Node eltTitle = eltItem.getElementsByTagName("title").item(0);
	                Node eltLink  = eltItem.getElementsByTagName("addr").item(0);
	                Node eltDescription  = eltItem.getElementsByTagName("description").item(0);
	                String title = "";
	                if( eltTitle!= null) {
	                	title = eltTitle.getFirstChild().getNodeValue();
	                }
	                String link = "";
	                if( eltLink!= null) {
	                	link = eltLink.getFirstChild().getNodeValue();
	                }
	                String description = "";
	                if( eltDescription!= null) {
	                	description = eltDescription.getFirstChild().getNodeValue();
	                }	                
	                // 输出结果
	                System.out.print("标题：");
	                System.out.println(title);
	                System.out.print("链接：");
	                System.out.println(link);
	                System.out.print("描述：");
	                System.out.println(description);
	                System.out.println("----------------------------\n");
	            }
	        } catch (ParserConfigurationException e) {
	            e.printStackTrace();
	        } catch (SAXException e) {
	            e.printStackTrace();
	        } catch (IOException e) {
	            e.printStackTrace();
	        }		   
	   }
}