如何在Amazon S3中读取文件的内容

Question

我在存储桶ABCD中的Amazon S3中有一个文件。 我有3个对象("folderA/folderB/folderC/abcd.csv")是文件夹，在最终文件夹中我有.csv文件(abcd.csv) 。 我使用逻辑将其转换为JSON并将其加载回另一个文件，该文件是同一文件夹中的.txt文件("folderA/folderB/folderC/abcd.txt") 。 我必须在本地下载文件才能做到这一点。 我如何直接读取文件并将其写回文本文件。 我用来写入S3中的文件的代码如下，我需要从S3读取文件。

 InputStream inputStream = new ByteArrayInputStream(json.getBytes(StandardCharsets.UTF_16));
 ObjectMetadata metadata = new ObjectMetadata();
 metadata.setContentLength(json.length());
 PutObjectRequest request = new PutObjectRequest(bucketPut, filePut, inputStream, metadata);
 s3.putObject(request);

Answer 1

首先，你应该得到对象InputStream来满足你的需求。

S3Object object = s3Client.getObject(new GetObjectRequest(bucketName, key));
InputStream objectData = object.getObjectContent();

将InputStream ， File Name和path传递给下面的方法以下载您的流。

public void saveFile(String fileName, String path, InputStream objectData) throws Exception {
    DataOutputStream dos = null;
    OutputStream out = null;
    try {
        File newDirectory = new File(path);
        if (!newDirectory.exists()) {
            newDirectory.mkdirs();
        }

        File uploadedFile = new File(path, uploadFileName);
        out = new FileOutputStream(uploadedFile);
        byte[] fileAsBytes = new byte[inputStream.available()];
        inputStream.read(fileAsBytes);

        dos = new DataOutputStream(out);
        dos.write(fileAsBytes);
    } catch (IOException io) {
        io.printStackTrace();
    } catch (Exception e) {
        e.printStackTrace();
    } finally {
        try {
            if (out != null) {
                out.close();
            }
            if (dos != null) {
                dos.close();
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

下载对象后，读取文件并将其转换为JSON并将其写入.txt文件，之后您可以将txt文件上传到S3的所需存储桶

Answer 2

您可以使用其他java库来下载或读取文件而无需下载。 请检查代码，我希望它对您有所帮助。 PDF的这个例子。

import java.io.IOException;
import java.io.InputStream;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.List;
import javax.swing.JTextArea;
import java.io.FileWriter;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.pdfbox.text.PDFTextStripperByArea;
import org.joda.time.DateTime;
import com.amazonaws.auth.AWSCredentials;
import com.amazonaws.auth.BasicAWSCredentials;
import com.amazonaws.services.s3.AmazonS3;
import com.amazonaws.services.s3.AmazonS3Client;
import com.amazonaws.services.s3.model.AmazonS3Exception;
import com.amazonaws.services.s3.model.CopyObjectRequest;
import com.amazonaws.services.s3.model.GetObjectRequest;
import com.amazonaws.services.s3.model.ListObjectsV2Request;
import com.amazonaws.services.s3.model.ListObjectsV2Result;
import com.amazonaws.services.s3.model.S3Object;
import com.amazonaws.services.s3.model.S3ObjectSummary;
import java.io.File; 
   //..
   // in your main class 
   private static AWSCredentials credentials = null;
   private static AmazonS3 amazonS3Client = null;

   public static void intializeAmazonObjects() {
        credentials = new BasicAWSCredentials(ACCESS_KEY, SECRET_ACCESS_KEY);
        amazonS3Client = new AmazonS3Client(credentials);
    }
   public void mainMethod() throws IOException, AmazonS3Exception{
        // connect to aws
        intializeAmazonObjects();

    ListObjectsV2Request req = new ListObjectsV2Request().withBucketName(bucketName);
    ListObjectsV2Result listObjectsResult;
do {

        listObjectsResult = amazonS3Client.listObjectsV2(req);
        int count = 0;
        for (S3ObjectSummary objectSummary : listObjectsResult.getObjectSummaries()) {
            System.out.printf(" - %s (size: %d)\n", objectSummary.getKey(), objectSummary.getSize());

            // Date lastModifiedDate = objectSummary.getLastModified();

            // String bucket = objectSummary.getBucketName();
            String key = objectSummary.getKey();
            String newKey = "";
            String newBucket = "";
            String resultText = "";

            // only try to read pdf files
            if (!key.contains(".pdf")) {
                continue;
            }

            // Read the source file as text
            String pdfFileInText = readAwsFile(objectSummary.getBucketName(), objectSummary.getKey());
            if (pdfFileInText.isEmpty())
                continue;
        }//end of current bulk

        // If there are more than maxKeys(in this case 999 default) keys in the bucket,
        // get a continuation token
        // and list the next objects.
        String token = listObjectsResult.getNextContinuationToken();
        System.out.println("Next Continuation Token: " + token);
        req.setContinuationToken(token);
    } while (listObjectsResult.isTruncated());
}

public String readAwsFile(String bucketName, String keyName) {
    S3Object object;
    String pdfFileInText = "";
    try {

        // AmazonS3 s3client = getAmazonS3ClientObject();
        object = amazonS3Client.getObject(new GetObjectRequest(bucketName, keyName));
        InputStream objectData = object.getObjectContent();

        PDDocument document = PDDocument.load(objectData);
        document.getClass();

        if (!document.isEncrypted()) {

            PDFTextStripperByArea stripper = new PDFTextStripperByArea();
            stripper.setSortByPosition(true);

            PDFTextStripper tStripper = new PDFTextStripper();

            pdfFileInText = tStripper.getText(document);

        }

    } catch (Exception e) {
        e.printStackTrace();
    }
    return pdfFileInText;
}