求救：如何使用dom读取xml文档中的数据

Question

http://www.csdn.net/develop/Read_Article.asp?Id=19171

Answer 1

http://www.csdn.net/develop/Read_Article.asp?Id=19171

Answer 2

public class TestGetPart
{
    public TestGetPart()
    {
    }    public static void println(String message)
    {
        System.out.println(message);
    }    private static org.w3c.dom.Document getParsedXmlDoc(java.io.InputStream
        XmlInput)
    {
        org.w3c.dom.Document indoc = null;
        javax.xml.parsers.DocumentBuilderFactory factory;
        javax.xml.parsers.DocumentBuilder builder;
        try
        {
            factory = javax.xml.parsers.DocumentBuilderFactory.newInstance();
            factory.setValidating(false);
            builder = factory.newDocumentBuilder();
            indoc = builder.parse(XmlInput);
            indoc.normalize();
        }
        catch (Exception e)
        {
            println("解析文件错，XML文件格式不对。堆栈信息如下");
        }
        return indoc;
    }    public static int spaceStep, spaceCount;
    public static void printDomTree(org.w3c.dom.Node node)
    {
        spaceStep = 4;
        spaceCount = 0;
        try
        {
            saveDoc(node);
        }
        catch (Exception e)
        {
            println(e.toString());
        }
    }    private static String addSpace(String line, int totalSpace)
    {
        String sp = "";
        for (int i = 0; i < (totalSpace - line.length()) / 2; i++)
        {
            sp += "-";
        }
        if (line.length() % 2 != 0)
        {
            line += "-";
        }
        return sp + line + sp;
    }    protected static String getSpace()
    {
        String str = "";
        for (int i = 0; i < spaceCount; i++)
        {
            str = str + " ";
        }
        return str;
    }    public static void print(String message)
    {
        System.out.print(message);
    }    private static void print(String str, boolean space) throws java.io.
        IOException
    {
        if (space)
        {
            str = getSpace() + str;
        }
        print(str);
    }    private static void println(String str, boolean space) throws java.io.
        IOException
    {
        if (space)
        {
            str = getSpace() + str;
        }
        str += "\r\n";
        print(str);
    }    private static void saveDoc(org.w3c.dom.Node node) throws java.io.
        IOException
    {
        if (node == null)
        {
            print("", false);
        }
        else if (node.getNodeName().indexOf("#") >= 0)
        {
            String name = node.getNodeName().trim();
            String value = node.getNodeValue().trim();
            if (name.equals("#text") && value.equals(""))
            {
                return;
            }
            println(value, true);
//            println( "[name]:\""+node.getNodeName().trim()+"\"[value]:\""+node.getNodeValue().trim()+"\"" ,true );
            return;
        }
        else if (node.getFirstChild() == null)
        {
            print("<" + node.getNodeName(), true);
            for (int i = 0; i < (node.getAttributes()).getLength(); i++)
            {
                org.w3c.dom.Node attrNode = node.getAttributes().item(i);
                print(" " + attrNode.getNodeName() + "=\"" +
                      attrNode.getNodeValue() + "\"", false);
            }
            println("/>", false);
        }
        else
        {
            print("<" + node.getNodeName(), true);
            for (int i = 0; i < (node.getAttributes()).getLength(); i++)
            {
                org.w3c.dom.Node attrNode = node.getAttributes().item(i);
                print(" " + attrNode.getNodeName() + "=\"" +
                      attrNode.getNodeValue() + "\"", false);
            }
            println(">", false);
            spaceCount += spaceStep;
            for (int i = 0; i < node.getChildNodes().getLength(); i++)
            {
                saveDoc(node.getChildNodes().item(i));
            }
            spaceCount -= spaceStep;
            println("</" + node.getNodeName() + ">", true);
        }
    }    public static void printTextAsXml(String text)
    {
        try
        {
            java.io.ByteArrayInputStream sbi = new java.io.ByteArrayInputStream(
                text.getBytes());
            org.w3c.dom.Document indoc = getParsedXmlDoc(sbi);
            if (indoc != null)
            {
                printDomTree(indoc.getLastChild());
            }
        }
        catch (Throwable t)
        {
            println(t.toString());
            println("Error happened while parsing xml,Original text is:\r\n" +
                    text);        }
    }    public static void main(String[] args)
    {
        String text = "<speech>"
            + "<speaker>catesby</speaker>"
            + "<line>The princes both make high account of you;</line>"
            + "<stagedir>aside</stagedir>"
            + "<line>For they account his head upon the bridge.</line>"
            + "</speech>";
        printTextAsXml(text);
    }
}

Answer 3

JDOM在更新xml方面比较方便，
其他的，与JDK1.4方面相比，优势不是很明显。

Answer 4

利用DOM读取XML文件的程序：
import javax.xml.parsers.*;
import org.w3c.dom.*;
import java.io.*;/**
 *使用DOM提取XML内容的例子
 */
class BookParser{
public static void main(String[] args){
try{
//获取一个XML解析器
DocumentBuilderFactory factory=DocumentBuilderFactory.newInstance();
DocumentBuilder builder=factory.newDocumentBuilder();
//解析XML文件
Document document=builder.parse(new File("books.xml"));
//去掉XML文档中空白部分
document.normalize();
//获取根节点并打印根节点的名称
Element root=document.getDocumentElement();
System.out.println("根原始的名称:"+root.getTagName());
//获取所有的"book"标记，它是一个NodeList对象
NodeList books=root.getElementsByTagName("book");
//遍历NodeList
System.out.println("书本列表");
for(int i=0;i<books.getLength();i++){
//获取books中的每一个元素
Element book=(Element)books.item(i);
//获取每个"book"标记的"id"属性
String book_id=book.getAttribute("id");//或book.getAttributeNode("id").getValue();
System.out.println("序号:"+book_id);
//获取"book"标记下的每个元素
System.out.print("作者:");
System.out.println(book.getElementsByTagName("author").item(0).getFirstChild().getNodeValue());
System.out.print("标题:");
System.out.println(book.getElementsByTagName("title").item(0).getFirstChild().getNodeValue());
//获取"publish_date"元素
Element publishDate=(Element)book.getElementsByTagName("publish_date").item(0);
//获取"publish_date"元素下的每个子元素
String year=publishDate.getElementsByTagName("year").item(0).getFirstChild().getNodeValue();
String month=publishDate.getElementsByTagName("month").item(0).getFirstChild().getNodeValue();
String day=publishDate.getElementsByTagName("day").item(0).getFirstChild().getNodeValue();
System.out.println("出版日期:"+year+"年"+month+"月"+day+"日");
System.out.print("描述:");
System.out.println(book.getElementsByTagName("description").item(0).getFirstChild().getNodeValue());
System.out.println("--------------------");
}
}
catch(Exception e2){}
}
}相应的XML文件:
<?xml version="1.0" encoding="UTF-8"?>
<catalog>
<book id="bk101">
<author>Gambardella, Matthew</author>
<title>XML Developer's Guide</title>
<publish_date>
  <year>2000</year>
  <month>10</month>
  <day>1</day>
</publish_date>
<description>An in-depth look at creating applications with XML.</description>
</book>
<book id="bk102">
<author>Ralls, Kim</author>
<title>Midnight Rain</title>
<publish_date>
  <year>2000</year>
  <month>12</month>
  <day>16</day>
</publish_date>
<description>A former architect battles corporate zombies.</description>
</book>
<book id="bk103">
<author>Corets, Eva</author>
<title>Maeve Ascendant</title>
<publish_date>
  <year>2000</year>
  <month>11</month>
  <day>17</day>
</publish_date>
<description>After the collapse of a nanotechnology society in England.</description>
</book>
<book id="bk104">
<author>leony</author>
<title>Maeve Ascendant</title>
<publish_date>
  <year>2000</year>
  <month>11</month>
  <day>17</day>
</publish_date>
<description>XML</description>
</book>
</catalog>
把两个文件copy在同一目录下，编译运行即可