wordXML解析

使用DOM方式去解析word内容

 

@Override
	public String exportPath(ZjclSj sj) {
		String filepath = "/temp/" + sj.getSjmc() + ".xml";
		//调用 DocumentBuilderFactory.newInstance() 方法得到创建 DOM 解析器的工厂  
		DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
		try {
			 //调用工厂对象的 newDocumentBuilder方法得到 DOM 解析器对象  
			DocumentBuilder builder = factory.newDocumentBuilder();
			//1、通过文件的方式获取Document对象  
			String path = ResourceManager.getRealPath() + "/temp/sjmb.xml";
			Document document = builder.parse(new File(path));

			//根据标签名称获取该名称的所有节点对象  
//		    NodeList nodelist = document.getElementsByTagName("wx:sect");
//		    //遍历  
//		    for (int i = 0; i < nodelist.getLength(); i++) {  
//		        //得到具体的某个节点对象  
//		        Node node = nodelist.item(i);  
//		        System.out.println(node.getNodeName());
//		        listNodes(node);
//		    }  
			//Node sectNode = document.getElementById("sectId"); 
			Node sectNode = document.getElementsByTagName("wx:sect").item(0);
			System.out.println("----------"+sectNode.getNodeName());
			
//			 <w:p>
//		        <w:r>
//		         <w:t>Hello, World.</w:t>
//		        </w:r>
//		       </w:p>
			
			//创建元素节点  
		    Element wp = document.createElement("w:p");  
		    Node wr = document.createElement("w:r");  
		    Node wt = document.createElement("w:t");  
		    wt.appendChild(document.createTextNode("Hello, World."));  
		    wr.appendChild(wt);  
		    wp.appendChild(wr);  
		    sectNode.appendChild(wp); 
			
		    String path2 = ResourceManager.getRealPath() + "/temp/" + sj.getSjmc() + ".doc";;
		    System.out.println("path2:"+path2);
			saveXml(path2, document);
		} catch (Exception e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		return filepath;
	}

	
	public static void saveXml(String fileName, Document doc) {// 将Document输出到文件
		TransformerFactory transFactory = TransformerFactory.newInstance();
		try {
			Transformer transformer = transFactory.newTransformer();
			transformer.setOutputProperty("indent", "yes");
			DOMSource source = new DOMSource();
			source.setNode(doc);
			StreamResult result = new StreamResult();
			result.setOutputStream(new FileOutputStream(fileName));
			transformer.transform(source, result);
		} catch (TransformerConfigurationException e) {
			e.printStackTrace();
		} catch (TransformerException e) {
			e.printStackTrace();
		} catch (FileNotFoundException e) {
			e.printStackTrace();
		}
	}
	
	/** 
     * 遍历根据节点对象下面的所有的节点对象 
     * @param node 
     */  
    public void listNodes(Node node) {  
        // 节点是什么类型的节点  
        if (node.getNodeType() == Node.ELEMENT_NODE) {// 判断是否是元素节点  
            Element element = (Element) node;  
            //判断此元素节点是否有属性  
            if(element.hasAttributes()){  
                //获取属性节点的集合  
                NamedNodeMap namenm = element.getAttributes();//Node  
                //遍历属性节点的集合  
                for(int k=0;k<namenm.getLength();k++){  
                    //获取具体的某个属性节点  
                    Attr attr = (Attr) namenm.item(k);  
                    System.out.println("attr:"+attr.getNodeName()+" value:"  
                                     +attr.getNodeValue()+"  type:"+attr.getNodeType());  
                }  
            }  
            //获取元素节点的所有孩子节点  
            NodeList listnode = element.getChildNodes();  
            //遍历  
            for (int j = 0; j < listnode.getLength(); j++) {  
                //得到某个具体的节点对象  
                Node nd = listnode.item(j);  
                System.out.println("nd:" + nd.getNodeName() + "  value:"  
                        + nd.getNodeValue() + "  type:" + nd.getNodeType());  
                //重新调用遍历节点的操作的方法  
                listNodes(nd);  
            }  
  
        }  
    }  

 --摘自 试卷考试系统、手动组卷导出