一键下载developer.android.com下的simples

本想直接在线学习，不过网速实在不给力，写了个多线程下载类，把官网下的实例全部下载下，包括图片，java文件，xml文件。并按照相应目录进行存储。总计时间大概6分钟左右下完。
先贴代码：

    
package com.multilThreadDownload;

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.FileWriter;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.Map;
import java.util.concurrent.TimeUnit;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/*
 * 此类是用来获取http://developer.android.com/resources
 * 中的例子。
 * */
public class GetFileFromWeb2 {
	public static final int times = 4;      //请求失败继续请求直到成功，最多请求4次
	public static final String[] imageType={"png","gif","jpg"};   //声明可读取的图片类型
	public static final String fileName = "index.html";		//默认文件名
	private static Map<String,String> map = new HashMap<String, String>(); //用来存储下载失败的文件及其地址信息
	private static ArrayList<MultiThread> threadList = new ArrayList<MultiThread>();
	
	public static void main(String[] args) {
	    long startTime = System.currentTimeMillis();
		String baseSavePath =  "C:/Documents and Settings/Administrator/桌面/test/";  //写到桌面
		String basePath = "http://developer.android.com/resources/samples/ApiDemos/";
	   
		try {
			oneKey2GetFile(basePath,baseSavePath);
		} catch (Exception e) {
			System.out.println("网络断开或不存在此页面："+basePath+fileName);
		}
		while (!threadList.isEmpty()) {		//确保其他线程执行完后计算时间
			System.out.println("-------");
			for(int i=0;i<threadList.size();i++){
				MultiThread temp = threadList.get(i);
				if(!temp.isAlive()){
					threadList.remove(temp);
				}
			}
			try {
				TimeUnit.SECONDS.sleep(1);
			} catch (InterruptedException e) {
				e.printStackTrace();
			}
		}
		System.out.println("下载耗时："+(System.currentTimeMillis()-startTime)+"ms");
	    System.out.println("===========保存出错列表=============");
	    for(Map.Entry<String,String> entry:map.entrySet()){
	    	String key = entry.getKey();
	    	String value = entry.getValue();
	    	System.out.println("文件名："+key+"\t所在页面："+value);
	    }
	}
	
	/*
	 * 此方法用于递归调用
	 * 一键获取此网页文件下所有文件
	 * */
	public static void oneKey2GetFile(String basePath,String baseSavePath)throws Exception{
		String dirPath = createDir(basePath,baseSavePath);	//获取当前创建的目录
		String data = null;
		
		try {
			data = new String(getData(basePath,fileName));     //获取上一层目录数据
		} catch (Exception e1) {
			throw new Exception();
		}
		
		ArrayList<String> fileNames = dataFilter(data);		//读取上一层目录数据获取文件名
		for(int i=0;i<fileNames.size();i++){		//遍历依次读取
				String name = fileNames.get(i);
				System.out.println(name);
				if(name.endsWith("/")){		//表示是目录
					String newBasePath = basePath+name;
					MultiThread multi = new MultiThread(newBasePath,dirPath);
					threadList.add(multi);
					multi.start();
				}else{					//表示是文件或图片
					try {
						byte[] files = getData(basePath,name);
						filterSave(files,name,dirPath);
					} catch (Exception e) {
						System.out.println(fileNames.get(i)+"读取出错2");
					}
				}
		}
	}
	
	
	/*
	 * 判断获取的文件名是否是图片文件
	 * */
	public static boolean containImage(String name){
		for(int i=0;i<imageType.length;i++){
			if(imageType[i].equals(name.substring(name.lastIndexOf('.')+1))){
				return true;
			}
		}
		return false;
	}
	
	/*
	 * 静态方法获取目录名称。并创建它。并返回目录名称
	 * */
	public static String createDir(String path,String baseSavePath){
		path = path.substring(0, path.length()-1);
		String dir = path.substring(path.lastIndexOf('/')+1);
		String dirPath = baseSavePath+dir;
		System.out.println("保存路径："+dirPath);
		File file = new File(dirPath);
		if(!file.exists()){			//创建目录
			file.mkdirs();
		}
		return dirPath+"/";
	}
	
	/*
	 * 返回指定网页路径返回的数据字节流
	 * */
	public static byte[] getData(String basePath,String fileName) throws Exception{
		String fileName2 = fileName;
		if(!containImage(fileName)){	
			fileName = fileName.replaceAll("\\.\\w+", "\\.html");
		}
		ByteArrayOutputStream byteArray =null;
		for (int i = 0; i < times; i++) { // 指定请求次数
			try {
				URL url = new URL(basePath + fileName);
				HttpURLConnection conn = (HttpURLConnection) url.openConnection();
				conn.setConnectTimeout(10 * 1000);
				conn.setRequestMethod("GET");
				InputStream inStream = conn.getInputStream();
				byte[] buff = new byte[1024];
				byteArray = new ByteArrayOutputStream();
				int len = 0;
				while ((len = inStream.read(buff)) != -1) {
					byteArray.write(buff, 0, len);
				}
				byteArray.flush();
				byteArray.close();
				inStream.close();
				System.out.println(conn.getResponseCode());
				if (conn.getResponseCode() == 200)
					break; // 如果请求成功则终止循环
			} catch (Exception e) {
				if(i>=times-1){
					map.put(fileName2, basePath+GetFileFromWeb2.fileName);
					throw new Exception();    //请求大于指定次数后还不成功则抛出异常
				}
			}

		}
		return byteArray.toByteArray();
	}
	
	/*
	 * 读取上一层目录数据获取文件名,
	 * 过滤文件，获取指定的文件名数组
	 * */
	public static ArrayList<String> dataFilter(String data){
		Pattern p = Pattern.compile("<a href=\".*\">\\s*(.+/|.*\\.(xml|java|png|gif|jpg))\\s*</a>");  //匹配单个文件或目录
		Matcher matcher = p.matcher(data);
		ArrayList<String> fileNames = new ArrayList<String>();
		while(matcher.find()){
			fileNames.add(matcher.group(1));  
		}
		return fileNames;
	}
	
	/*
	 * 过滤获取指定的xml或java文件。并保存文件
	 * */
	public static void filterSave(byte[] fileBytes,String fileName,String dirPath) throws Exception{
		String fileData = new String(fileBytes);
		String name = dirPath + fileName;
		if(containImage(fileName)){            //判断是否是图片
			FileOutputStream outStream = new FileOutputStream(name);
			outStream.write(fileBytes, 0, fileBytes.length); // 写入图片内容
			outStream.flush();
			outStream.close();
		}else{
			fileData = fileData.replaceAll("&lt;", "<");
			fileData = fileData.replaceAll("&gt;", ">");
			 /*由于存在大量的回车换行，
			  * 需先行替换，不然匹配不出内容，
			  * 注意有些文件可能还含有/r，也要替换
			  * */
			fileData = fileData.replaceAll("\n", "#@");    
			Pattern p = Pattern.compile("<pre>(.*)</pre>");
			Matcher matcher = p.matcher(fileData);
			while(matcher.find()){
				String str = matcher.group(1).replaceAll("#@", "\n");  //匹配到后再替换回来
				File file = new File(name);
				FileWriter writer = new FileWriter(file);
				writer.write(str, 0, str.length());
				writer.flush();
				writer.close();
			}
		}
		System.out.println(name);
	}
	
	static class MultiThread extends Thread{
		private String basePath;
		private String baseSavePath;
		
		public MultiThread(){
			
		}
		
		public MultiThread(String basePath,String baseSavePath){
			this.basePath = basePath;
			this.baseSavePath = baseSavePath;
		}
		@Override
		public void run(){
			try {
				oneKey2GetFile(basePath,baseSavePath);
			} catch (Exception e) {
				System.out.println("读取目录:"+basePath+" 出错");
			}
		}
	}
}


  

再贴图：
这是http://developer.android.com/resources/samples/ApiDemos/index.html页面下的路径格式



下面是保存下来的文件目录格式：



代码直接运行即可。

一键下载developer.android.com下的simples