DOM4J可以处理html文件吗? 怎么处理

DOM4J可以处理html文件吗? 怎么处理

可以，以字符串的形式解析。。。
package com.mty95190.test;
//先加入dom4j.jar包
import java.util.HashMap;
import java.util.Iterator;
import java.util.Map;

import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.DocumentHelper;
import org.dom4j.Element;


public class aa {

public void readStringXml(String xml) {
Document doc = null;
try {

// 读取并解析XML文档
// SAXReader就是一个管道，用一个流的方式，把xml文件读出来
//
// SAXReader reader = new SAXReader(); //User.hbm.xml表示你要解析的xml文档
// Document document = reader.read(new File("User.hbm.xml"));
// 下面的是通过解析xml字符串的
doc = DocumentHelper.parseText(xml); // 将字符串转为XML

Element rootElt = doc.getRootElement(); // 获取根节点
System.out.println("根节点：" + rootElt.getName()); // 拿到根节点的名称

Iterator iter = rootElt.elementIterator("head"); // 获取根节点下的子节点head

// 遍历head节点
while (iter.hasNext()) {

Element recordEle = (Element) iter.next();
String title = recordEle.elementTextTrim("title"); // 拿到head节点下的子节点title值
System.out.println("title:" + title);

Iterator iters = recordEle.elementIterator("script"); // 获取子节点head下的子节点script

// 遍历Header节点下的Response节点
while (iters.hasNext()) {

Element itemEle = (Element) iters.next();

String username = itemEle.elementTextTrim("username"); // 拿到head下的子节点script下的字节点username的值
String password = itemEle.elementTextTrim("password");

System.out.println("username:" + username);
System.out.println("password:" + password);
}
}
Iterator iterss = rootElt.elementIterator("body"); ///获取根节点下的子节点body
// 遍历body节点
while (iterss.hasNext()) {

Element recordEless = (Element) iterss.next();
String result = recordEless.elementTextTrim("result"); // 拿到body节点下的子节点result值
System.out.println("result:" + result);

Iterator itersElIterator = recordEless.elementIterator("form"); // 获取子节点body下的子节点form
// 遍历Header节点下的Response节点
while (itersElIterator.hasNext()) {

Element itemEle = (Element) itersElIterator.next();

String banlce = itemEle.elementTextTrim("banlce"); // 拿到body下的子节点form下的字节点banlce的值
String subID = itemEle.elementTextTrim("subID");

System.out.println("banlce:" + banlce);
System.out.println("subID:" + subID);
}
}
} catch (DocumentException e) {
e.printStackTrace();

} catch (Exception e) {
e.printStackTrace();

}
}


public static Map readStringXmlOut(String xml) {
Map map = new HashMap();
Document doc = null;
try {
doc = DocumentHelper.parseText(xml); // 将字符串转为XML
Element rootElt = doc.getRootElement(); // 获取根节点
System.out.println("根节点：" + rootElt.getName()); // 拿到根节点的名称

Iterator iter = rootElt.elementIterator("head"); // 获取根节点下的子节点head
// 遍历head节点
while (iter.hasNext()) {

Element recordEle = (Element) iter.next();
String title = recordEle.elementTextTrim("title"); // 拿到head节点下的子节点title值
System.out.println("title:" + title);
map.put("title", title);

Iterator iters = recordEle.elementIterator("script"); // 获取子节点head下的子节点script

// 遍历Header节点下的Response节点
while (iters.hasNext()) {

Element itemEle = (Element) iters.next();

String username = itemEle.elementTextTrim("username"); // 拿到head下的子节点script下的字节点username的值
String password = itemEle.elementTextTrim("password");

System.out.println("username:" + username);
System.out.println("password:" + password);
map.put("username", username);
map.put("password", password);

}
}

Iterator iterss = rootElt.elementIterator("body"); ///获取根节点下的子节点body
// 遍历body节点
while (iterss.hasNext()) {
Element recordEless = (Element) iterss.next();
String result = recordEless.elementTextTrim("result"); // 拿到body节点下的子节点result值
System.out.println("result:" + result);

Iterator itersElIterator = recordEless.elementIterator("form"); // 获取子节点body下的子节点form
// 遍历Header节点下的Response节点
while (itersElIterator.hasNext()) {

Element itemEle = (Element) itersElIterator.next();

String banlce = itemEle.elementTextTrim("banlce"); // 拿到body下的子节点form下的字节点banlce的值
String subID = itemEle.elementTextTrim("subID");

System.out.println("banlce:" + banlce);
System.out.println("subID:" + subID);
map.put("result", result);
map.put("banlce", banlce);
map.put("subID", subID);
}
}
} catch (DocumentException e) {
e.printStackTrace();
} catch (Exception e) {
e.printStackTrace();
}
return map;
}

public static void main(String[] args) {

// 下面是需要解析的xml字符串例子
String xmlString = "" + "" + ""
+ "" + ""
+ "" + "0" + "" + "" + "";


Map map = readStringXmlOut(xmlString);
Iterator iters = map.keySet().iterator();
while (iters.hasNext()) {
String key = iters.next().toString(); // 拿到键
String val = map.get(key).toString(); // 拿到值
System.out.println(key + "=" + val);
}
}

}

如以上回答内容为低俗、色情、不良、暴力、侵权、涉及违法等信息，可以点下面链接进行举报！

点此我要举报以上问答信息