Dom4j,解析Xml 简单列子

xml结构

 

<?xml version="1.0" encoding="UTF-8"?>

<sites>

 <site host="sina.com.cn" name="新浪网" charset="utf-8">
  <news>
   <collectionUid>2</collectionUid>
   <mediaType>新闻门户</mediaType>
  </news>
  <blog>
  <collectionUid>63</collectionUid>
   <mediaType>博客</mediaType>
   </blog>
 </site>
 
 <site host="qq.com" name="腾讯" charset="gb2312">
  <news>
   <collectionUid>1</collectionUid>
   <mediaType>新闻</mediaType>
    </news>
  <blog>
  </blog>
 </site> 

</sites>

解析方法

 

public class Dom4JParserXml {
	

	@SuppressWarnings("unchecked")
	public static void parseXml()
			throws FileNotFoundException, DocumentException {

		Document doc = new SAXReader().read(Dom4JParserXml.class.getResourceAsStream("/sites-config.xml"));
		List itemList = doc.selectNodes("/sites/site");
		
		Iterator it = itemList.iterator();
		while (it.hasNext()) {
			Element element = (Element) it.next();
			parseEle(element);
		}
	}

	private static void parseEle(Element el) {
		try {
			
			String name = el.attributeValue("name");
			System.out.println("------->>"+name);
		
			Element elNew = el.element("news");
			Element elblog = el.element("blog");
			if(elNew != null  && elNew.elements().size() > 0) {
				String collectionUid = elNew.elementText("collectionUid");
				String mediaType = elNew.elementText("mediaType");
				
				System.out.println("-------new:collectionUid>>"+collectionUid);
				System.out.println("-------new:mediaType>>"+mediaType);
			}
			if(elblog != null && elblog.elements().size() > 0) {
				String collectionUid = elblog.elementText("collectionUid");
				String mediaType = elblog.elementText("mediaType");
				
				System.out.println("-------blog:collectionUid>>"+collectionUid);
				System.out.println("-------blog:mediaType>>"+mediaType);
				
			}

		} catch (Exception e) {
			e.printStackTrace();
		}
	}
	
	public static void main(String [] args) {
		try {
			parseXml();
		} catch (FileNotFoundException e) {
			e.printStackTrace();
		} catch (DocumentException e) {
			e.printStackTrace();
		}
	}
}

解析结果：控制台输出

 

------->>新浪网
-------new:collectionUid>>2
-------new:mediaType>>新闻门户
-------blog:collectionUid>>63
-------blog:mediaType>>博客
------->>腾讯
-------new:collectionUid>>1
-------new:mediaType>>新闻
------->>网易
-------new:collectionUid>>3
-------new:mediaType>>新闻
------->>搜狐
-------new:collectionUid>>4
-------new:mediaType>>新闻