java+dom4j.jar提取xml文档内容

<?xml version="1.0" encoding="UTF-8"?> 
 
-
 
 
-
 

 
 
 
 
 
 
 
 


 
 
-
 

 

 
 
-
 
ATOMIC WEAPONS 
NUCLEAR TESTS 
TESTS AND TESTING 
EDITORIALS 
CLINTON, BILL (PRES) 
Editorial 
Top/Opinion 
Top/Opinion/Opinion 
Top/Opinion/Opinion/Editorials 
Nuclear Tests 
Atomic Weapons 
Tests and Testing 
Armament, Defense and Military Forces
 
 
 

 

 
 
-
 
 
-
 
 
-
 
An End to Nuclear Testing
 
 

 
 
-
 
 
-
 
For nearly half a century, test explosions in the Nevada desert were a reverberating reminder of cold war insecurity. Now the biggest worry is nuclear proliferation, not the Soviet threat. That's why President Clinton has quietly decided to extend the moratorium on tests of nuclear arms for at least 15 months.
 
To persuade nuclear have-nots to stay out of the bomb-making business, it makes more sense to halt testing and try to get others to do likewise than to conduct more demonstrations of America's deterrent power.
 

 
 
-
 
For nearly half a century, test explosions in the Nevada desert were a reverberating reminder of cold war insecurity. Now the biggest worry is nuclear proliferation, not the Soviet threat. That's why President Clinton has quietly decided to extend the moratorium on tests of nuclear arms for at least 15 months.
To persuade nuclear have-nots to stay out of the bomb-making business, it makes more sense to halt testing and try to get others to do likewise than to conduct more demonstrations of America's deterrent power.
 
Not that nuclear wannabes will necessarily follow America's lead. Nor will an end to all testing assure an end to bomb-making; states like Pakistan have developed nuclear devices without testing them first.
But calling a halt to U.S. nuclear testing makes it easier for leaders in Russia and France to extend the moratoriums they are now observing and improve the atmosphere for prompt negotiation of a treaty to ban all tests.
That test ban in turn should shore up international support for the 1968 Nonproliferation Treaty, linchpin of efforts to stop the spread of nuclear arms, when it comes up for review in 1995. It will also bolster the backing for tighter controls on exports used in bomb-making.
Mr. Clinton has taken three helpful steps. He has extended the Congressionally mandated moratorium on U.S. tests that was due to expire last week. He has declared that the U.S. will not test unless another nation does so first. And he wants to negotiate a total ban on testing.
But the President also wants the nuclear labs to be prepared for a prompt resumption of warhead safety and reliability tests. This could cost millions of dollars and doesn't make much sense, since in Mr. Clinton's own words, "After a thorough review, my Administration has determined that the nuclear weapons in the United States' arsenal are safe and reliable."
Moreover, preparations for testing can take on a life of their own: 30 years after the Limited Test Ban Treaty put an end to above-ground tests, the U.S. still spends $20 million a year on Safeguard C, a program to keep test sites ready.
American security no longer rests on that sort of eternal nuclear vigilance. Mr. Clinton's moratorium may make America safer than all the tests and preparations for tests that the nuclear labs can dream up.
 

 

 

 

package com.njupt.ymh;
 
import java.io.File;
import java.util.ArrayList;
import java.util.List;
 
import edu.princeton.cs.algs4.In;
 
/**
 * 返回文件名列表
 * @author 11860
 *
 */
public class SearchFile {
 
 public static List getAllFile(String directoryPath,boolean isAddDirectory) {
  List list = new ArrayList(); // 存放文件路径
  File baseFile = new File(directoryPath); // 当前路径
  
  if (baseFile.isFile() || !baseFile.exists()) 
   return list;
  
  File[] files = baseFile.listFiles(); // 子文件
  for (File file : files) {
   if (file.isDirectory()) 
   { 
    if(isAddDirectory) // isAddDirectory 是否将子文件夹的路径也添加到list集合中
     list.add(file.getAbsolutePath()); // 全路径
    
    list.addAll(getAllFile(file.getAbsolutePath(),isAddDirectory));
   } 
   else 
   {
    list.add(file.getAbsolutePath());
   }
  }
  return list;
 }
 public static void main(String[] args) {
 
 //SearchFile sFile = new SearchFile();
 List listFile = SearchFile.getAllFile("E:\\huadai", false);
 System.out.println(listFile.size());
 File file = new File(listFile.get(3));
 In in = new In(listFile.get(4));
 while (in.hasNextLine()) {
 String readLine = in.readLine().trim(); // 读取当前行
 System.out.println(readLine);
 
 }
 System.out.println(file.length());
 
 }
 
}

package com.njupt.ymh;
 
import java.io.File;
import java.util.Iterator;
import java.util.List;
 
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.Node;
import org.dom4j.io.SAXReader;
 
public class NewsPaper {
 int doc_id; // 文章id
 String doc_title; // 文章标题
 String lead_paragraph ; // 文章首段
 String full_text; // 文章内容
 String date; // 文章日期
 public NewsPaper(String xml) {
 doc_id = -1; // 文章id
 doc_title = null; // 文章标题
 lead_paragraph = null; // 文章首段
 full_text = null; // 文章内容
 date = null; // 文章日期
 searchValue(xml);
 }
 
 /**
 * 加载Document文件
 * @param fileName
 * @return Document
 */
 private Document load(String fileName) {
 Document document = null; // 文档
 SAXReader saxReader = new SAXReader(); // 读取文件流
 
 try {
 document = saxReader.read(new File(fileName));
 } catch (DocumentException e) {
 e.printStackTrace();
 }
 
 return document;
 }
 
 /**
 * 获取Document的根节点
 * @param args
 */
 private Element getRootNode(Document document) {
 return document.getRootElement();
 }
 
 /**
 * 获取所需节点值
 * @param xml
 */
 private void searchValue(String xml) {
 Document document = load(xml);
  Element root = getRootNode(document); // 根节点 
  
  // 文章日期
  date = xml.substring(10, 20);
  // 文章标题
  doc_title = root.valueOf("//head/title");
  
  // 文章-id
  List list_doc_id = document.selectNodes("//doc-id/@id-string"); 
  for(Node ele:list_doc_id){
   doc_id = Integer.parseInt(ele.getText());
  }
  
  // 文章内容
  for (Iterator i = root.elementIterator(); i.hasNext();) { 
   Element el = (Element) i.next(); // head、body
   
   // 对body节点进行操作
   if (el.getName() == "body") { // body
    for (Iterator body = el.elementIterator(); body.hasNext();) {
  Element elbody = body.next();
  
  if (elbody.getName() == "body.content") { //body.content
  for (Iterator block = elbody.elementIterator(); block.hasNext();) {
  Element block_class = (Element) block.next();
  
  if (block_class.attributeValue("class").equals("full_text") ) { // full_text
  List list_text = block_class.selectNodes("p");
  for (Node text : list_text) 
   if (full_text == null) 
   full_text = text.getStringValue();
   else 
   full_text = full_text +" " + text.getStringValue();
  }
  
  else { // lead_paragraph
  List list_lead = block_class.selectNodes("p");
  for (Node lead : list_lead) 
   if (lead_paragraph == null)
   lead_paragraph = lead.getStringValue();
   else 
   lead_paragraph = lead_paragraph +" "+ lead.getStringValue();
  }
  }
  }
 }
   }
  } 
 }
 
 /**
 * 获取文章标题
 * @param args
 */
 public String getTitle() {
 return doc_title;
 }
 
 /**
 * 获取文章id
 * @param args
 */
 public int getID() {
 return doc_id;
 }
 
 /**
 * 获取文章简介
 * @param args
 */
 public String getLead() {
 if (getID() < 394070 && lead_paragraph != null && lead_paragraph.length() > 6)  //1990-10-22之前
 return lead_paragraph.substring(6);
 else       //1990-10-22之后
 return lead_paragraph;
 }
 
 /**
 * 获取文章正文
 * @param args
 */
 public String getfull() {
 if (getID() < 394070 && full_text != null && full_text.length() > 6)   //1990-10-22之前
 return full_text.substring(6);
 else
 return full_text;
 }
 
 /**
 * 获取文章日期
 * @param args
 */
 public String getDate() {
 return date;
 }
 
 /**
 * 判断获取的信息是否有用
 * @return
 */
 public boolean isUseful() {
 if (getID() == -1)
 return false;
 if (getDate() == null ) 
 return false;
 if (getTitle() == null || getTitle().length() >= 255) 
 return false;
 if (getLead() == null || getLead().length() >= 65535 ) 
 return false;
 if (getfull() == null || getfull().length() >= 65535) 
 return false;
 
 return !isnum();
 }
 
 /**
 * 挑出具有特殊开头的数字内容文章
 * @return
 */
 private boolean isnum() {
 if (getfull() != null && getfull().length() > 24) {
 if (getfull().substring(0, 20).contains("*3*** COMPANY REPORT") ) { // 剔除数字文章 
 return true;
 }
 }
 return false;
 }
 
 
 public static void main(String[] args) {
 List listFile = SearchFile.getAllFile("E:\\huadai\\1989\\10", false); // 文件列表
 //String date; // 日期
 int count = 0;
 int i = 0;
 for (String string : listFile) {
 NewsPaper newsPaper = new NewsPaper(string);
 count++;
 if (!newsPaper.isUseful()) {
 i++;
 System.out.println(newsPaper.getLead());
 } 
 }
 
 System.out.println(i + " "+ count);
 
 }
}