以下是如何使用java客户端。

<dependency>
    <groupId>com.amazonaws</groupId>
    <artifactId>aws-java-sdk-s3</artifactId>
    <version>1.11.519</version>
</dependency>

import com.amazonaws.ClientConfiguration;
import com.amazonaws.Protocol;
import com.amazonaws.auth.AWSStaticCredentialsProvider;
import com.amazonaws.auth.BasicAWSCredentials;
import com.amazonaws.services.s3.AmazonS3;
import com.amazonaws.services.s3.AmazonS3ClientBuilder;
import com.amazonaws.services.s3.model.ObjectListing;

public class AmazonS3Service {

    private static final String S3_ACCESS_KEY_ID = "ACCESS_KEY";
    private static final String S3_SECRET_KEY = "SECRET_KEY";
    private static final String S3_ENDPOINT = "S3_URL";

    private AmazonS3 amazonS3;

    public AmazonS3Service() {
        ClientConfiguration clientConfiguration = new ClientConfiguration();
        clientConfiguration.setProtocol(Protocol.HTTPS);
        clientConfiguration.setSignerOverride("S3SignerType");
        BasicAWSCredentials credentials = new BasicAWSCredentials(S3_ACCESS_KEY_ID, S3_SECRET_KEY);
        AWSStaticCredentialsProvider credentialsProvider = new AWSStaticCredentialsProvider(credentials);
        AmazonS3ClientBuilder.EndpointConfiguration endpointConfiguration = new AmazonS3ClientBuilder.EndpointConfiguration(S3_ENDPOINT, null);
        amazonS3 = AmazonS3ClientBuilder.standard().withCredentials(credentialsProvider).withClientConfiguration(clientConfiguration)
                .withPathStyleAccessEnabled(true).withEndpointConfiguration(endpointConfiguration).build();
    }

    public int countObjects(String bucketName) {
        int count = 0;
        ObjectListing objectListing = amazonS3.listObjects(bucketName);
        int currentBatchCount = objectListing.getObjectSummaries().size();
        while (currentBatchCount != 0) {
            count += currentBatchCount;
            objectListing = amazonS3.listNextBatchOfObjects(objectListing);
            currentBatchCount = objectListing.getObjectSummaries().size();
        }
        return count;
    }
}

如果你正在寻找特定的文件，比如.jpg图像，你可以执行以下操作:

aws s3 ls s3://your_bucket | grep jpg | wc -l

您可以只执行这个cli命令来获取桶或特定文件夹中的总文件计数

扫描整个桶

aws s3api list-objects-v2 --bucket testbucket | grep "Key" | wc -l
aws s3api list-objects-v2 --bucket BUCKET_NAME | grep "Key" | wc -l

可以使用该命令获取详细信息

aws s3api list-objects-v2 --bucket BUCKET_NAME

扫描特定文件夹

aws s3api list-objects-v2 --bucket testbucket --prefix testfolder --start-after testfolder/ | grep "Key" | wc -l

aws s3api list-objects-v2 --bucket BUCKET_NAME --prefix FOLDER_NAME --start-after FOLDER_NAME/ | grep "Key" | wc -l

我使用来自scalablelogic.com的python脚本(添加计数日志记录)。伟大的工作。

#!/usr/local/bin/python

import sys

from boto.s3.connection import S3Connection

s3bucket = S3Connection().get_bucket(sys.argv[1])
size = 0
totalCount = 0

for key in s3bucket.list():
    totalCount += 1
    size += key.size

print 'total size:'
print "%.3f GB" % (size*1.0/1024/1024/1024)
print 'total count:'
print totalCount

现在S3 API有一个简单的解决方案(在AWS cli中可用):

aws s3api list-objects --bucket BUCKETNAME --output json --query "[length(Contents[])]"

或针对特定文件夹:

aws s3api list-objects --bucket BUCKETNAME --prefix "folder/subfolder/" --output json --query "[length(Contents[])]"

也可以用gsutil du(是的，一个谷歌云工具)

gsutil du s3://mybucket/ | wc -l