DOM、SAX和StAX只是解析方式,没有API。
JAXP是SUN提供的一套XML解析API。 JAXP(Java API for XMLProcessing,意为XML处理的Java API)
JAXP很好的支持DOM和SAX解析。
JAXP开发包是JAVASE的一部分,它由java.xml、org.w3c.dom、org.xml.sax包及其子包组成
products.mxl
<?xml version="1.0" encoding="UTF-8"?> <!DOCTYPE products[ <!ELEMENT products (product+)> <!ELEMENT product (name,price)> <!ELEMENT name (#PCDATA)> <!ELEMENT price (#PCDATA)> <!ATTLIST product id ID #REQUIRED> ]> <products> <product id="p001"> <name>往事并不如烟</name> <price>49.9元</price> </product> <product id="p002"> <name>围城</name> <price>59.9元</price> </product> </products>
package com.rk.xml.d_jaxp_dom; import javax.xml.parsers.DocumentBuilderFactory; import javax.xml.parsers.DocumentBuilder; import org.w3c.dom.Document; import org.w3c.dom.Element; /** * 根据Id读取一个元素(Element) * 通过Document.getElementById(String elementId)方法获取一个元素(Element) * @author RK * */ public class Demo01 { public static void main(String[] args) throws Exception { //1、新拿到解析器工厂 //2、通过解析器工厂拿到解析器对象 //3、通过解析器对象解析XML文档,并返回Document对象 //4、通过Document对象去获取节点Node //1、新拿到解析器工厂 DocumentBuilderFactory builderFactory = DocumentBuilderFactory.newInstance(); //2、通过解析器工厂拿到解析器对象 DocumentBuilder builder = builderFactory.newDocumentBuilder(); //3、通过解析器对象解析XML文档,并返回Document对象 Document doc = builder.parse("./src/products.xml"); //4、通过Document对象去获取节点Node Element elem = doc.getElementById("p001");//必须使用DTD声明ID属性 System.out.println(elem);//[product: null] System.out.println(elem.getNodeType());//1 元素(Element)类型的节点用1表示 System.out.println(elem.getNodeName());//product System.out.println(elem.getNodeValue());//null System.out.println(elem.getTextContent());//往事并不如烟49.9元 } }
package com.rk.xml.d_jaxp_dom; import javax.xml.parsers.DocumentBuilderFactory; import javax.xml.parsers.DocumentBuilder; import org.w3c.dom.Document; import org.w3c.dom.NodeList; import org.w3c.dom.Node; /** * 读取一系列节点(NodeList) * 通过Document.getElementsByTagName(String tagname)获取一系列节点。 * @author RK * */ public class Demo02 { public static void main(String[] args) throws Exception { //1、新拿到解析器工厂 //2、通过解析器工厂拿到解析器对象 //3、通过解析器对象解析XML文档,并返回Document对象 //4、通过Document对象去获取节点Node //1、新拿到解析器工厂 DocumentBuilderFactory builderFactory = DocumentBuilderFactory.newInstance(); //2、通过解析器工厂拿到解析器对象 DocumentBuilder builder = builderFactory.newDocumentBuilder(); //3、通过解析器对象解析XML文档,并返回Document对象 Document doc = builder.parse("./src/products.xml"); //4、通过Document对象去获取节点Node NodeList list = doc.getElementsByTagName("product"); System.out.println("找到"+list.getLength()+"个");//找到多少个节点 for(int i=0;i<list.getLength();i++) { Node node = list.item(i); System.out.println(node);//将各个节点进行打印 } } }
package com.rk.xml.d_jaxp_dom; import javax.xml.parsers.DocumentBuilderFactory; import javax.xml.parsers.DocumentBuilder; import org.w3c.dom.Document; import org.w3c.dom.Node; import org.w3c.dom.NodeList; import org.w3c.dom.NamedNodeMap; /** * 读取一个属性(Attribute) * @author RK * */ public class Demo03 { public static void main(String[] args) throws Exception { DocumentBuilderFactory builderFactory = DocumentBuilderFactory.newInstance(); DocumentBuilder builder = builderFactory.newDocumentBuilder(); Document doc = builder.parse("./src/products.xml"); NodeList list = doc.getElementsByTagName("product"); Node node = list.item(0); NamedNodeMap map = node.getAttributes();//获取到所有属性类型的节点 Node attrNode = map.getNamedItem("id");//获取到属性为“id”的节点 System.out.println(attrNode.getNodeType());//2 属性(Attribute)类型的节点用2表示 System.out.println(attrNode.getNodeName());//id System.out.println(attrNode.getNodeValue());//p001 System.out.println(attrNode.getTextContent());//p001 } }
package com.rk.xml.d_jaxp_dom; import javax.xml.parsers.DocumentBuilderFactory; import javax.xml.parsers.DocumentBuilder; import org.w3c.dom.Document; import org.w3c.dom.NodeList; import org.w3c.dom.Node; /** * 读取一个元素的文本(Text) * @author RK * */ public class Demo04 { public static void main(String[] args) throws Exception { DocumentBuilderFactory builderFactory = DocumentBuilderFactory.newInstance(); DocumentBuilder builder = builderFactory.newDocumentBuilder(); Document doc = builder.parse("./src/products.xml"); NodeList list = doc.getElementsByTagName("name"); Node node = list.item(0); System.out.println(node.getTextContent());//往事并不如烟 } }
package com.rk.xml.d_jaxp_dom; import javax.xml.parsers.DocumentBuilderFactory; import javax.xml.parsers.DocumentBuilder; import org.w3c.dom.Document; import org.w3c.dom.NodeList; import org.w3c.dom.Node; import org.w3c.dom.NamedNodeMap; /** * 遍历所有节点 * @author RK * */ public class Demo05 { public static void main(String[] args) throws Exception { DocumentBuilderFactory builderFactory = DocumentBuilderFactory.newInstance(); DocumentBuilder builder = builderFactory.newDocumentBuilder(); Document doc = builder.parse("./src/products.xml"); StringBuilder sb = new StringBuilder(); NodeList childNodes = doc.getChildNodes(); for(int i=0;i<childNodes.getLength();i++) { Node node = childNodes.item(i); System.out.println(node.getNodeType() + "===" + node.getNodeName()+ "===" + node.getNodeValue()); } /* 输出结果: 10===products===null DOCUMENT_TYPE_NODE = 10 1===products===null ELEMENT_NODE = 1 */ traverseDocument(doc.getLastChild(),sb); System.out.println(sb.toString()); /* 输出结果: <products > <product id="p001" > <name >往事并不如烟</name> <price >49.9元</price> </product> <product id="p002" > <name >围城</name> <price >59.9元</price> </product> </products> */ } private static void traverseDocument(Node node, StringBuilder sb) { //1、当前元素开始 sb.append("<" + node.getNodeName() + " "); //2、获取属性 if(node.hasAttributes()) { NamedNodeMap nodeMap = node.getAttributes(); for(int i=0;i<nodeMap.getLength();i++) { Node attrNode = nodeMap.item(i); sb.append(attrNode.getNodeName() + "=\"" + attrNode.getNodeValue() + "\" "); } } sb.append(">"); //3、获取子节点 NodeList childNodes = node.getChildNodes(); for(int i=0;i<childNodes.getLength();i++) { Node subNode = childNodes.item(i); short type = subNode.getNodeType(); if(type == 1)//当前节点是Element节点 { traverseDocument(subNode, sb); } else if(type == 3)//当前节点是Text节点 { sb.append(subNode.getTextContent()); } else { //其它情况,不做处理 } } //4、当前元素结束 sb.append("</" + node.getNodeName() + ">"); } }
XML系列:(4)XML解析-JAXP的DOM解析方式读取XML
原文地址:http://lsieun.blog.51cto.com/9210464/1773164