java 下载zip处理（zip内容是图片或者pdf）

下面有三个方法都是获取到zip里面的图片的inputStream，因为我只需要后去

目录

1http://xxxxxxxxxxxxxxx/xxxx.zip
2.http://xxxxxxxxxxxxxx/xxxxx 下载是个文件流
3.本地文件获取

两者的区别，第一种的比较慢，第二种比较快
因为第一种的.zip可以直接使用URLConnection来获取到文件
而第二种则需要通过http请求之后获取到文件内容所以比较慢

第一种.zip的下载链接

public static void downloadFile(String urlPath) throws Exception {

       
       File file = null;
       BufferedInputStream bin = null;
       OutputStream out = null;
        HttpURLConnection httpURLConnection = null;
       try {
           // 统一资源
           URL url = new URL(urlPath);
           
           // 连接类的父类，抽象类
           URLConnection urlConnection = url.openConnection();
           // http的连接类
           httpURLConnection = (HttpURLConnection) urlConnection;
           httpURLConnection.setDoOutput(true);// http正文内，因此需要设为true, 默认情况下是false;
           httpURLConnection.setDoInput(true);
			int responseCode = httpURLConnection.getResponseCode();//查看请求状态
			System.out.println(responseCode);
//           // 设定请求的方法，默认是GET
//           httpURLConnection.setRequestMethod("GET");
           // 设置字符编码
          httpURLConnection.setRequestProperty("Charset", "UTF-8");
           // 打开到此 URL 引用的资源的通信链接（如果尚未建立这样的连接）。
           httpURLConnection.connect();

           // 文件大小
           int fileLength = httpURLConnection.getContentLength();
           System.out.println(fileLength);
           //后面参数要字符编码要设置，不然可能会读不到
           ZipInputStream zipI=new ZipInputStream(httpURLConnection.getInputStream(),Charset.forName("GBK"));
           ZipEntry entry;
           while((entry=zipI.getNextEntry())!=null) {
        	   byte[] data = getByte(zipI); // 获取当前条目的字节数组
               InputStream is = new ByteArrayInputStream(data);  //获取到zip内容的InputStream 之后就可以爱干嘛干嘛了
               FileUtil.filter(is, "pdf");
             
           }
       } catch (Exception e) {
           // TODO Auto-generated catch block
//           throw new CustomException(e.toString()+"文件下载异常，请检查下载链接$$"+urlPath);
       } finally {
           if (bin != null) 
               bin.close();          
           if (out != null) 
               out.close();           
          
       }
   }

获取当前条目的字节数组

private static byte[] getByte(ZipInputStream zipI) {
	  try {
          ByteArrayOutputStream bout = new ByteArrayOutputStream();
          byte[] temp = new byte[1024];
          byte[] buf = null;
          int length = 0;
          while ((length = zipI.read(temp, 0, 1024)) != -1) {
              bout.write(temp, 0, length);
          }
          buf = bout.toByteArray();
          bout.close();
          return buf;
      } catch (IOException e) {
          e.printStackTrace();
          return null;
      }
}

//判断文件类型

public static boolean filter(InputStream in,String type) throws IOException {
		byte[] b = new byte[3];
		try {
			in.read(b, 0, b.length);
		} catch (IOException e) {
			e.printStackTrace();
			return false;
		}
		String xxx = bytesToHexString(b);
		logger.error("文件类型++++=="+xxx);
        xxx = xxx.toUpperCase();
        if(type.equals(checkType(xxx))) {
        	return true;
        }
		return false;
	}

private static String checkType(String xxxx) {
        switch (xxxx) {
        case "FFD8FF": 
    		logger.debug("类型是：JPEG" );
    		return "photo";
    	case "89504E":
    		logger.debug("类型是：PNG");
    		return "photo";
    	case "255044": 
    		logger.debug("类型是：PDF");
    		return "pdf";
    	default: 
    		logger.debug("文件头："+xxxx);
    		return null;
        }
	}

zip内容

程序运行结果

获取到了两个InputStream 都是pdf类型的

非zip后缀的处理方法

需要使用到的是

public static void downloadFile(String urlPath) throws Exception {

       
       File file = null;
       BufferedInputStream bin = null;
       OutputStream out = null;
        HttpURLConnection httpURLConnection = null;
       try {
  long startTime=System.currentTimeMillis();
           ZipInputStream zipI=new ZipInputStream(new ByteArrayInputStream(AllRequest.GetStringtobyte(urlPath)),Charset.forName("GBK"));
         long endTime=System.currentTimeMillis(); 
         System.out.println(endTime-startTime);
           ZipEntry entry;
           while((entry=zipI.getNextEntry())!=null) {
        	   byte[] data = getByte(zipI); // 获取当前条目的字节数组
               InputStream is = new ByteArrayInputStream(data);
               FileUtil.filter(is, "pdf");
           }
           
       } catch (Exception e) {
           // TODO Auto-generated catch block
//           throw new CustomException(e.toString()+"文件下载异常，请检查下载链接$$"+urlPath);
       } finally {
           if (bin != null) 
               bin.close();          
           if (out != null) 
               out.close();           
          
       }
   }

请求获取到byte

	public static byte[] GetStringtobyte(String url) {
		try {
			CloseableHttpClient httpClient = HttpClients.createDefault();
			HttpGet httpGet = new HttpGet(url);
			httpGet.setHeader("content-type", "application/json");
			CloseableHttpResponse response = httpClient.execute(httpGet);
			HttpEntity httpEntity = response.getEntity();
			byte[] back = EntityUtils.toByteArray(httpEntity);
			return back;
		} catch (Exception e) {
			e.printStackTrace();
			return null;
		}
	}

107s

还有一种是本地文件读取使用FileZip

 public static void main(String[] args) throws IOException {
	ZipInputStream zi=new ZipInputStream(InputStream());
	ZipFile zipFile = new ZipFile("D:\\AAAAA.zip",Charset.forName("GBK"));
    Enumeration<? extends ZipEntry> entries = zipFile.entries();
    while(entries.hasMoreElements()){
        ZipEntry entry = entries.nextElement();
	    InputStream stream = zipFile.getInputStream(entry);
        FileUtil.filter(stream, "pdf");    
    }
}