目录
该代码简易实现了获取URL地址后对文档进行关键字统计的功能。具体的自己看吧
1.实现URL文档的拷贝
import java.util.Scanner;
import java.util.regex.Pattern;
import java.net.*;
import java.io.*;
import javax.swing.*;
import javax.swing.UIManager;
import java.awt.*;
import javax.swing.plaf.FontUIResource;
public class TestURL {
static String getUserKeyWords=null; //获取用户选择的关键词
public static void main(String[] args) {
File copyfile=new File("D:/newTest.txt");
InputStream in=null;
BufferedReader br=null; //字符流写入
BufferedWriter out=null; //字符流写出
String urladdress=null; //获取用户输入的URL地址
try
{
UIManager.put("JOptionPane.messageFont",new FontUIResource(new Font("宋体",Font.BOLD,20)));
String getUserURL=JOptionPane.showInputDialog(null,"URL地址：\n","输入URL地址",JOptionPane.PLAIN_MESSAGE);
String urlAddr=getUserURL.substring(getUserURL.lastIndexOf("/"));
copyfile=new File("D:/"+urlAddr);
getUserKeyWords=JOptionPane.showInputDialog(null,"关键字查询：\n","关键字",JOptionPane.PLAIN_MESSAGE);
//URL url=new URL("http://news.cctv.com/2019/06/19/ARTIhqziOpWz2COTyHFW063b190619.shtml"); //获取URL地址
URL url=new URL(getUserURL); //获取URL地址
HttpURLConnection urlC=(HttpURLConnection)url.openConnection(); //由URL获取URLConnection对象
in=urlC.getInputStream(); //获取urlC的输入流
br=new BufferedReader(new InputStreamReader(in,"UTF-8")); //将url默认的字节流转成字符流,并以UTF-8的格式写入文档
out=new BufferedWriter(new FileWriter(copyfile)); //将获取的信息写入到TestURL文档中
String length=null;
while ((length=br.readLine())!=null)
{
out.write(Html2Text(length));
out.newLine();
}
}
catch (Exception e)
{
e.getMessage();
}finally{
System.out.println("拷贝完成！");
try{
if (in!=null){in.close();}
if (out!=null){out.close();}
if (br!=null){br.close();}
}catch(Exception ee){
ee.getMessage();
}
}
TextFileSearch search = new TextFileSearch();
search.SearchKeyword(copyfile, getUserKeyWords);
} //程序到这就结束了 ，下面是不同方法实现对html的剔除功能，可以忽略
//从html中提取纯文本 ，这部分其实没什么用，最开始想截取html中的字符串，后面检查也没啥用，就没删除，保留着
public static String Html2Text(String inputString) {
String htmlStr = inputString; // 含html标签的字符串
String textStr = "";
java.util.regex.Pattern p_script;
java.util.regex.Matcher m_script;
java.util.regex.Pattern p_style;
java.util.regex.Matcher m_style;
java.util.regex.Pattern p_html;
java.util.regex.Matcher m_html;
try {
String regEx_script = "<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\s]*?>"; // 定义script的正则表达式{或<script[^>]*?>[\\s\\S]*?<\\/script>
String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>"; // 定义style的正则表达式{或<style[^>]*?>[\\s\\S]*?<\\/style>
String regEx_html = "<[^>]+>"; // 定义HTML标签的正则表达式
p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
m_script = p_script.matcher(htmlStr);
htmlStr = m_script.replaceAll(""); // 过滤script标签
p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
m_style = p_style.matcher(htmlStr);
htmlStr = m_style.replaceAll(""); // 过滤style标签
p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
m_html = p_html.matcher(htmlStr);
htmlStr = m_html.replaceAll(""); // 过滤html标签
textStr = htmlStr;
} catch (Exception e) {System.err.println("Html2Text: " + e.getMessage()); }
//剔除空格行
textStr=textStr.replaceAll("[ ]+", " ");
textStr=textStr.replaceAll("(?m)^\\s*$(\\n|\\r\\n)", "");
return textStr;// 返回文本字符串
}
/*//从html中提取纯文本，这个部分是简易实现html剔除，只能部分筛选
public static String stripHT(String strHtml){
String txtcontent = strHtml.replaceAll("</?[^>]+>", ""); //剔出<html>的标签
txtcontent = txtcontent.replaceAll("<a>\\s*|\t|\r|\n</a>", "");//去除字符串中的空格,回车,换行符,制表符
return txtcontent;
}*/
/* //这个是利用java自带的类实现html剔除功能，基本上没怎么用，这部分可以忽略
import java.io.*;
import javax.swing.text.html.*;
import javax.swing.text.html.parser.*;
public class Html2Text extends HTMLEditorKit.ParserCallback {
StringBuffer s;
public Html2Text() {}
public void parse(Reader in) throws IOException {
s = new StringBuffer();
ParserDelegator delegator = new ParserDelegator();
// the third parameter is TRUE to ignore charset directive
delegator.parse(in, this, Boolean.TRUE);
}
public void handleText(char[] text, int pos) {
s.append(text);
}
public String getText() {
return s.toString();
}
public static void main (String[] args) {
try {
// the HTML to convert
//Reader in=new StringReader("string");
FileReader in = new FileReader("java-new.html");
Html2Text parser = new Html2Text();
parser.parse(in);
in.close();
System.out.println(parser.getText());
}
catch (Exception e) {
e.printStackTrace();
}
}
}*/
}
2.实现关键词在文档的查询功能
import java.io.Closeable;
import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.io.LineNumberReader;
import javax.swing.UIManager;
import javax.swing.*;
import java.awt.*;
import javax.swing.plaf.FontUIResource;
/**
* 对文本文件的关键词进行搜索
*/
public class TextFileSearch {
TestURL tt;
public void SearchKeyword(File file,String keyword) {
//参数校验
verifyParam(file, keyword);
//行读取
LineNumberReader lineReader = null;
try {
lineReader = new LineNumberReader(new FileReader(file));
String readLine = null;
int times = 0;//出现的次数
while((readLine =lineReader.readLine()) != null){
//判断每一行中,出现关键词的次数
int index = 0; //获得readLine的对象值
int next = 0; //定义开始查找关键字的序列号
//int times = 0;//出现的次数
//判断次数
while((index = readLine.indexOf(keyword,next)) != -1) { //从每行的第0个索引开始遍历关键字
next = index + keyword.length(); //下一次的遍历序号为序列号+关键字长度
times++;//次数加1
}
/*if(times > 0) {
//System.out.println("第"+ lineReader.getLineNumber() +"行" + "出现 "+keyword+" 次数: "+times);
}*/
}
if (times>0)
{
UIManager.put("JOptionPane.messageFont",new FontUIResource(new Font("宋体",Font.BOLD,20)));
JOptionPane.showMessageDialog(null,"关键字"+"@"+tt.getUserKeyWords+"@"+"共有"+times+"个");
}
} catch (IOException e) {
e.printStackTrace();
} finally {
//关闭流
close(lineReader);
}
}
/**
* 参数校验
*/
private void verifyParam(File file, String keyword) {
//对参数进行校验证
if(file == null ){
throw new NullPointerException("the file is null");
}
if(keyword == null || keyword.trim().equals("")){
throw new NullPointerException("the keyword is null or \"\" ");
}
if(!file.exists()) {
throw new RuntimeException("the file is not exists");
}
//非目录
if(file.isDirectory()){
throw new RuntimeException("the file is a directory,not a file");
}
//可读取
if(!file.canRead()) {
throw new RuntimeException("the file can't read");
}
}
/**
* 关闭流
*/
private void close(Closeable able){
if(able != null){
try {
able.close();
} catch (IOException e) {
e.printStackTrace();
able = null;
}
}
}
}
3.显示效果
URL地址获取效果图
关键字查询界面
查询后效果图
