java读取解析xml文件实例
程序员文章站
2024-03-02 15:24:52
读取本地的xml文件，通过dom进行解析，dom解析的特点就是把整个xml文件装载入内存中，形成一颗dom树形结构，树结构是方便遍历和和操纵。
dom解析的特性就是读取x...
读取本地的xml文件，通过dom进行解析，dom解析的特点就是把整个xml文件装载入内存中，形成一颗dom树形结构，树结构是方便遍历和和操纵。
dom解析的特性就是读取xml文件转换为 dom树形结构，通过节点进行遍历。
这是w3c关于节点的概念
如果xml中包含有大量的数据，由于dom一次性把xml装入内存中的特性，所以dom不适合于包含大量数据的xml解析。当包含有大量xml的时候，用sax进行解析比较节省内存。
下面是一个运用dom进行解析xml文件的例子：
xml文件结构如下：
<?xml version="1.0" encoding="iso-8859-1"?> <bookstore> <book category="cooking"> <title lang="en">everyday italian</title> <author>giada de laurentiis</author> <year>2005</year> <price>30.00</price> </book> <book category="children"> <title lang="en">harry potter</title> <author>j k. rowling</author> <year>2005</year> <price>29.99</price> </book> <book category="web"> <title lang="en">xquery kick start</title> <author>james mcgovern</author> <year>2003</year> <price>49.99</price> </book> <book category="web" cover="paperback"> <title lang="en">learning xml</title> <author>erik t. ray</author> <year>2003</year> <price>39.95</price> </book> </bookstore>
创建解析xml的类如下：
package xml.dom;
import java.io.file;
import javax.xml.parsers.documentbuilder;
import javax.xml.parsers.documentbuilderfactory;
import org.w3c.dom.document;
import org.w3c.dom.element;
import org.w3c.dom.node;
import org.w3c.dom.nodelist;
public class readxmlfile {
public static void main(string[] args) {
try{
file xmlfile = new file("src/resource/book.xml");
documentbuilderfactory builderfactory = documentbuilderfactory.newinstance();
documentbuilder builder = builderfactory.newdocumentbuilder();
document doc = builder.parse(xmlfile);
doc.getdocumentelement().normalize();
system.out.println("root element: "+doc.getdocumentelement().getnodename());
nodelist nlist = doc.getelementsbytagname("book");
for(int i = 0 ; i<nlist.getlength();i++){
node node = nlist.item(i);
system.out.println("node name: "+ node.getnodename());
element ele = (element)node;
system.out.println("----------------------------");
if(node.getnodetype() == element.element_node){
system.out.println("book category: "+ ele.getattribute("category"));
system.out.println("title name: "+ ele.getelementsbytagname("title").item(0).gettextcontent());
system.out.println("author name: "+ele.getelementsbytagname("author").item(0).gettextcontent());
system.out.println("year :"+ele.getelementsbytagname("year").item(0).gettextcontent());
system.out.println("price : "+ele.getelementsbytagname("price").item(0).gettextcontent());
system.out.println("-------------------------");
}
}
解析结果：
root element: bookstore node name: book ---------------------------- book category: cooking title name: everyday italian author name: giada de laurentiis year :2005 price : 30.00 ------------------------- node name: book ---------------------------- book category: children title name: harry potter author name: j k. rowling year :2005 price : 29.99 ------------------------- node name: book ---------------------------- book category: web title name: xquery kick start author name: james mcgovern year :2003 price : 49.99 ------------------------- node name: book ---------------------------- book category: web title name: learning xml author name: erik t. ray year :2003 price : 39.95 -------------------------
以上是通过name获得对应的值，
下面利用循环节点的方式输出：
循环节点输出方式的代码如下：
package xml.dom;
import java.io.file;
import javax.xml.parsers.documentbuilder;
import javax.xml.parsers.documentbuilderfactory;
import org.w3c.dom.document;
import org.w3c.dom.namednodemap;
import org.w3c.dom.node;
import org.w3c.dom.nodelist;
public class readxmlfile2 {
public static void main(string[] args) {
try{
file xmlfile = new file("src/resource/book.xml");
documentbuilderfactory builderfactory = documentbuilderfactory.newinstance();
documentbuilder builder = builderfactory.newdocumentbuilder();
document doc = builder.parse(xmlfile);
doc.getdocumentelement().normalize();
system.out.println("root element: "+doc.getdocumentelement().getnodename());
if(doc.haschildnodes()){
printnode(doc.getchildnodes());
}
}catch(exception e){
e.printstacktrace();
}
}
public static void printnode(nodelist nodelist){
system.out.println("------------------------");
// system.out.println(nodelist.getlength());
for(int i = 0; i<nodelist.getlength(); i++){
node node = (node)nodelist.item(i);
if(node.getnodetype() == node.element_node){
system.out.println("node name: "+node.getnodename());
system.out.println("node value: "+node.gettextcontent());
if(node.hasattributes()){
namednodemap nodemap = node.getattributes();
for(int j = 0; j < nodemap.getlength() ; j++){
node nodenew = nodemap.item(j);
system.out.println("node name "+nodenew.getnodename());
system.out.println("node value "+nodenew.getnodevalue());
}
}
if(node.haschildnodes()){
printnode(node.getchildnodes());
}
}
}
}
}
输出结果如下：
root element: bookstore ------------------------ node name: bookstore node value: everyday italian giada de laurentiis 2005 30.00 harry potter j k. rowling 2005 29.99 xquery kick start james mcgovern 2003 49.99 learning xml erik t. ray 2003 39.95 ------------------------ node name: book node value: everyday italian giada de laurentiis 2005 30.00 node name category node value cooking ------------------------ node name: title node value: everyday italian node name lang node value en ------------------------ node name: author node value: giada de laurentiis ------------------------ node name: year node value: 2005 ------------------------ node name: price node value: 30.00 ------------------------ node name: book node value: harry potter j k. rowling 2005 29.99 node name category node value children ------------------------ node name: title node value: harry potter node name lang node value en ------------------------ node name: author node value: j k. rowling ------------------------ node name: year node value: 2005 ------------------------ node name: price node value: 29.99 ------------------------ node name: book node value: xquery kick start james mcgovern 2003 49.99 node name category node value web ------------------------ node name: title node value: xquery kick start node name lang node value en ------------------------ node name: author node value: james mcgovern ------------------------ node name: year node value: 2003 ------------------------ node name: price node value: 49.99 ------------------------ node name: book node value: learning xml erik t. ray 2003 39.95 node name category node value web node name cover node value paperback ------------------------ node name: title node value: learning xml node name lang node value en ------------------------ node name: author node value: erik t. ray ------------------------ node name: year node value: 2003 ------------------------ node name: price node value: 39.95 ------------------------
关于节点的问题：
<book category="cooking"> <title lang="en">everyday italian</title> <author>giada de laurentiis</author> <year>2005</year> <price>30.00</price> </book>
对于 book应用：doc.getchildnodes() 得到一个nodelist其中nodelist的长度为9
9个节点分别如下：
title节点
lang节点
everyday节点
author节点
giada de laurentiis节点
year节点
2005节点
price节点
30.00节点
ps：这里再为大家提供几款关于xml操作的在线工具供大家参考使用：
在线xml/json互相转换工具：
在线格式化xml/在线压缩xml：
xml在线压缩/格式化工具：