java 常用操作工具

Java中，操作文件（讀寫內容）工具、讀寫properties文件工具、序列化工具、正則提取工具、網頁抓取和解析工具。

package com.shao.utils;
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.FileWriter;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
publicclass FileUtil {
/**
 * 從文件中讀取數據,將內容放置到List容器中
 * @param fileStr
 * @return
 */
publicstatic List<String> getDataFromFile(String fileStr){
 List<String> data = null;
if(fileStr!=null && fileStr.length()>0){
try {
 File file=new File(fileStr);
if(!file.exists()||file.isDirectory()){
thrownew FileNotFoundException();
 }else{
 BufferedReader br = new BufferedReader(new FileReader(file));
 data = new ArrayList<String>();
 String temp = br.readLine();
while(temp!=null){
 data.add(temp);
 temp = br.readLine();
 }
 }
 } catch (FileNotFoundException e) {
 e.printStackTrace();
 } catch (IOException e) {
 e.printStackTrace();
 }
 }
return data;
 }
/**
 * 將List容器中的數據寫入到文件中
 * @param fileStr
 */
publicstaticvoid writeDataToFile(String fileStr,List<String> data){
if(data==null || data.size()==0){
return;
 }
try {
 FileWriter writer = new FileWriter(fileStr);
 BufferedWriter bw = new BufferedWriter(writer);
for (Iterator<String> iterator = data.iterator(); iterator.hasNext();) {
 String temp = (String) iterator.next();
 bw.write(temp+"\n");
 }
 bw.close();
 writer.close();
 } catch (IOException e) {
 e.printStackTrace();
 }
 }
/**
 * 從文件中讀取數據, 返回文件內容
 * @param fileStr
 * @return
 */
publicstatic String getContentFromFile(String fileStr){
 StringBuffer sb = new StringBuffer();
if(fileStr!=null && fileStr.length()>0){
try {
 File file=new File(fileStr);
if(!file.exists()||file.isDirectory()){
thrownew FileNotFoundException();
 }else{
 BufferedReader br = new BufferedReader(new FileReader(file));
 String temp = br.readLine();
while(temp!=null){
 sb.append(temp+"\n");
 temp = br.readLine();
 }
 }
 } catch (FileNotFoundException e) {
 e.printStackTrace();
 } catch (IOException e) {
 e.printStackTrace();
 }
 }
return sb.toString();
 }
/**
 * 將數據內容寫入到文件中
 * @param fileStr
 */
publicstaticvoid writeContentToFile(String fileStr,String content){
try {
 FileWriter writer = new FileWriter(fileStr);
 BufferedWriter bw = new BufferedWriter(writer);
 bw.write(content);
 bw.close();
 writer.close();
 } catch (IOException e) {
 e.printStackTrace();
 }
 }
/**
 * 從給定的目錄中讀取所有的文件內容
 * @param dir
 * @return
 */
publicstatic List<String> getContentsFromDir(File file){
 List<String> cons = null;
if(file.isDirectory()){
 cons = new ArrayList<String>();
 File[] files = file.listFiles();
for (int i = 0; i < files.length; i++) {
 File f = files[i];
if(f.isDirectory()){
 List<String> temp = getContentsFromDir(f);
for (Iterator iterator = temp.iterator(); iterator
 .hasNext();) {
 String c = (String) iterator.next();
 cons.add(c);
 }
 }else{
 String con = getContentFromFile(f.getAbsolutePath());
 cons.add(con);
 }
 }
 }
return cons;
 }
}

package com.shao.utils;
import java.io.BufferedInputStream;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.Properties;
/**
 * properties文件處理工具
 * @author heshaopeng
 * @date 2012-11-23
 */
publicclass PropertiesUtil {
/**
 * 讀取配置文件
 * @param file
 * @return
 */
publicstatic Properties readPropertiesFile(String file){
 Properties prop=null;
try {
 BufferedInputStream is=new BufferedInputStream(new FileInputStream(file));
 prop=new Properties();
 prop.load(is);
 } catch (FileNotFoundException e) {
 System.out.println("File Not Found!");
 e.printStackTrace();
 } catch (IOException e) {
 e.printStackTrace();
 }
return prop;
 }
/*
 * 寫資源文件
 * @param filename
 * @param p
 */
publicstaticvoid writePropertiesFile(String filename,Properties p)
 {
try
 {
 OutputStream outputStream = new FileOutputStream(filename);
 p.store(outputStream,"");
 outputStream.close();
 }
catch (IOException e)
 {
 e.printStackTrace();
 }
 }
}

package com.shao.utils;
import java.io.BufferedInputStream;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.Properties;
/**
 * properties文件處理工具
 * @author heshaopeng
 * @date 2012-11-23
 */
publicclass PropertiesUtil {
/**
 * 讀取配置文件
 * @param file
 * @return
 */
publicstatic Properties readPropertiesFile(String file){
 Properties prop=null;
try {
 BufferedInputStream is=new BufferedInputStream(new FileInputStream(file));
 prop=new Properties();
 prop.load(is);
 } catch (FileNotFoundException e) {
 System.out.println("File Not Found!");
 e.printStackTrace();
 } catch (IOException e) {
 e.printStackTrace();
 }
return prop;
 }
/*
 * 寫資源文件
 * @param filename
 * @param p
 */
publicstaticvoid writePropertiesFile(String filename,Properties p)
 {
try
 {
 OutputStream outputStream = new FileOutputStream(filename);
 p.store(outputStream,"");
 outputStream.close();
 }
catch (IOException e)
 {
 e.printStackTrace();
 }
 }
}

package com.shao.utils;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
 * 正則表達式使用
 * @author Administrator
 *
 */
publicclass RegxUtil {
/**
 * 利用正則表達式解析網頁內容
 * @param s 全部網頁內容
 * @param regex 正則表達式
 * @return
 */
public List<String> parseContent(String content,String regex) {
//regex = "(((?<=(<a))[\\s\\S]*?(?=(</a>))))";
 List<String> list = new ArrayList<String>();
 Pattern pa = Pattern.compile(regex);
 Matcher ma = pa.matcher(content);
while (ma.find()) {
 String ss = ma.group();
 list.add(ss);
 }
return list;
 }
}

package com.shao.utils;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.io.ObjectInputStream;
import java.io.ObjectOutputStream;
/**
 * 序列化工具
 * @author heshaopeng
 * @date 2012-11-23
 */
publicclass SerializationUtil {
privatefinalstatic String SERIALIZATION_PATH = "file2uuid.map";
/**
 * 將對象序列化到磁盤文件中
 * @param o
 * @throwsException
 */
publicstaticvoid writeObject(Object o,String path) throws Exception{
 File f=new File(path);
if(f.exists()){
 f.delete();
 }
 FileOutputStream os=new FileOutputStream(f);
 ObjectOutputStream oos=new ObjectOutputStream(os);
 oos.writeObject(o);
 oos.close();
 os.close();
 }
/**
 *反序列化,將磁盤文件轉化爲對象
 *@return Object
 *@throwsException
 */
publicstatic Object readObject(String path) throws Exception{
 File f=new File(path);
if(!f.exists()){
returnnull;
 }else{
 InputStream is=new FileInputStream(f);
 ObjectInputStream ois=new ObjectInputStream(is);
return ois.readObject();
 }
 }
}

package com.shao.spider;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import com.shao.utils.FileUtil;
/**
 * 抓取網頁
 * @author Administrator
 *
 */
publicclass WebSpider {
/**
 * 讀取一個網頁全部內容
 */
public String getOneHtml(String htmlurl) throws IOException {
 URL url;
 String temp;
 StringBuffer sb = new StringBuffer();
try {
//1.根據網址，創建一個URL對象
 url = new URL(htmlurl);
//2.讀取網頁全部內容，採用utf-8編碼方式來讀取
//url.openStream()獲取輸入流，並用BufferedReader進行封裝
 BufferedReader in = new BufferedReader(new InputStreamReader(url.openStream(), "utf-8"));
while ((temp = in.readLine()) != null) {
if(temp.trim().length()>0){
 sb.append(temp+"\n");
 }
 }
 in.close();
 } catch (MalformedURLException me) {
 System.out.println("你輸入的URL格式有問題！請仔細輸入");
 me.getMessage();
throw me;
 } catch (IOException e) {
 e.printStackTrace();
throw e;
 }
return sb.toString();
 }
/**
 * 抓取網頁，並保存爲html文件
 * @param htmlURL
 */
publicvoid getHtmlFileFromURL(String filename,String htmlURL){
try {
 String content = getOneHtml(htmlURL);
 List<String> data = new ArrayList<String>();
 data.add(content);
 FileUtil.writeDataToFile(filename, data);
 } catch (IOException e) {
 e.printStackTrace();
 }
 }
/**
 * 將網頁內容寫入到文件,按照網頁標題保存文件
 * @param htmlURL
 */
publicvoid writeHtmlToFile(String path,String content){
 String filename = path+getTitle(content)+".html";
 FileUtil.writeContentToFile(filename, content);
 }
/**
 *
 * @param s
 * @return 獲得網頁標題
 */
public String getTitle(String s) {
 String regex;
 String title = "";
 List<String> list = new ArrayList<String>();
 regex = "<title>.*?</title>";
 list = parseContent(s,regex);
for (int i = 0; i < list.size(); i++) {
 title = title + list.get(i);
 }
return outTag(title);
 }
/**
 *
 * @param s
 * @return 去掉標記
 */
public String outTag(final String s) {
return s.replaceAll("<.*?>", "");
 }
/**
 * 利用正則表達式解析網頁內容
 * @param s 全部網頁內容
 * @param regex 正則表達式
 * @return
 */
public List<String> parseContent(String content,String regex) {
//regex = "(((?<=(<a))[\\s\\S]*?(?=(</a>))))";
 List<String> list = new ArrayList<String>();
 Pattern pa = Pattern.compile(regex);
 Matcher ma = pa.matcher(content);
while (ma.find()) {
 String ss = ma.group();
 list.add(ss);
 }
return list;
 }
publicstaticvoid main(String[] args) throws IOException {
 WebSpider wc = new WebSpider();
 String urlhtml = "http://bus.mapbar.com/shenzhen/station_list/A.shtml";
/*//抓取這個網頁 的內容
 String con = wc.getOneHtml(urlhtml);
 System.out.println(con);*/
/*//將抓取的頁面保存爲html頁面
 wc.getHtmlFileFromURL("A.html", urlhtml);*/
/*//按照抓物的網頁的標題保存網頁文件
 String con = wc.getOneHtml(urlhtml);
 wc.writeHtmlToFile("",con);*/
//============測試批量抓取網頁,並保存爲文件========================
/*String urlhtml2 = "http://bus.mapbar.com/shenzhen/station_list/%%.shtml";
 String[] ss = {"A","B","C","D","E","F","G",
 "H","I","J","K","L","M","N",
 "O","P","Q","R","S","T",
 "U","V","W","X","Y","Z",
 "1","2","3","4","5","6","7","8","9"};
 List<String> htmlContent = new ArrayList<String>();
 for (int i = 0; i < ss.length; i++) {
 String temp = urlhtml2.replace("%%", ss[i]);
 String con = wc.getOneHtml(temp);
 wc.writeHtmlToFile("", con);
 }*/
/*//從抓取後的網頁文件中讀取網頁內容
 String path = "深圳公交站點查詢列表-- A字頭-- Mapbar深圳公交.html";
 String content = FileUtil.getContentFromFile(path);
 System.out.println(content);*/
// File file = new File("test.txt");
// String path = file.getAbsolutePath();
// System.out.println(path);
//============測試批量抓取網頁,並保存爲文件,到特定目錄下========================
/*String urlhtml2 = "http://bus.mapbar.com/shenzhen/station_list/%%.shtml";
 String[] ss = {"A","B","C","D","E","F","G",};
 List<String> htmlContent = new ArrayList<String>();
 for (int i = 0; i < ss.length; i++) {
 String temp = urlhtml2.replace("%%", ss[i]);
 String con = wc.getOneHtml(temp);
 wc.writeHtmlToFile("G:/test/", con);
 }*/
//============從特定目錄下，讀取所有抓取下來的文件內容========================
/*File file = new File("G:/test/");
 List<String> cons = FileUtil.getContentsFromDir(file);
 System.out.println(cons.size());*/
 }
}

package com.shao.spider;
import java.awt.image.BufferedImage;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStream;
import java.net.MalformedURLException;
import java.net.URL;
import javax.imageio.ImageIO;
/**
 * 抓取所有文本、媒體等資源
 * @author Administrator
 *
 */
publicclass AllSpider {
/**
 * 抓取圖片,採用輸入流的方式
 */
publicvoid getImageFromWeb(String htmlurl) throws IOException {
 URL url;
try {
// 1.根據網址，創建一個URL對象
 url = new URL(htmlurl);
 String imageName = htmlurl.substring(htmlurl.lastIndexOf("/") + 1);
 String path = "G:/test/" + imageName;
 File file = new File(path);
// 2.讀取網頁全部內容，採用utf-8編碼方式來讀取
// url.openStream()獲取輸入流，並用BufferedReader進行封裝
 InputStream is = url.openStream();
 OutputStream os = null;
 os = new FileOutputStream(file);
int b = is.read();
while (b != -1) {
 os.write(b);
 b = is.read();
 }
 is.close();
 os.close();
 } catch (MalformedURLException me) {
 System.out.println("你輸入的URL格式有問題！請仔細輸入");
 me.getMessage();
throw me;
 } catch (IOException e) {
 e.printStackTrace();
throw e;
 }
 }
publicstaticvoid main(String[] args) throws IOException {
 AllSpider as = new AllSpider();
//最普通的方式
 String imaurl = "http://a.hiphotos.baidu.com/album/s%3D680%3Bq%3D90/sign=22cf18d6f3d3572c62e29fd4ba28121a/48540923dd54564eba46ab06b2de9c82d1584fe9.jpg";
 as.getImageFromWeb(imaurl);
//採用第二種方式，抓取音頻文件
 String mp3url = "http://mc.djkk.com/mix/2012/2012-09/2012-09-20/2012092020483953.wma";
 as.getImageFromWeb(mp3url);
 }
}