본문 바로가기
Cloud/AWS Cloud Computing

[AWS] Boto3 사용하기 1. S3 다루기

by 스파이디웹 2023. 4. 12.
728x90

 

 

1. 사전 준비

 

Client

  • low-level 인터페이스
  • service description에 의해 만들어짐
  • botocore 수준의 client를 공개(botocore는 AWS CLI와 boto3의 기초가 되는 라이브러리)
  • AWS API와 1:1 매핑됨
  • 메소드가 스네이크 케이스로 정의되어 있음

 

Resource

  • high-level, 객체지향적 인터페이스
  • resource description에 의해 만들어짐
  • 식별자(identifier)와 속성(attribute)을 사용
  • 자원에 대한 조작 위주

2. 버킷 생성

import logging
import boto3
from botocore.exceptions import ClientError

class AWSBoto3():
    def __init__(self):
        self.access_key = 'accesskey'
        self.secret_access_key = 'secret_key'

    def create_bucket(self, bucket_name, region=None):
        """Create an S3 bucket in a specified region

        If a region is not specified, the bucket is created in the S3 default
        region (us-east-1).

        :param bucket_name: Bucket to create
        :param region: String region to create bucket in, e.g., 'us-west-2'
        :return: True if bucket created, else False
        """

        # Create bucket
        try:
            if region is None:
                s3_client = boto3.client('s3', aws_access_key_id=self.access_key, aws_secret_access_key=self.secret_access_key)
                s3_client.create_bucket(Bucket=bucket_name)
            else:
                s3_client = boto3.client('s3', region_name=region, aws_access_key_id=self.access_key, aws_secret_access_key=self.secret_access_key)
                #location = {'LocationConstraint': region}# when the region is configured to us-east-1, default bucket is created in us-east-1 region
                s3_client.create_bucket(Bucket=bucket_name)#,CreateBucketConfiguration=location) 한국 리전은 추가되어야 작동함
        except ClientError as e:
            logging.error(e)
            return False
        return True


if __name__=="__main__":
    AWSboto3 = AWSBoto3()
    AWSboto3.create_bucket(bucket_name='bucket-createdby-boto3',region='us-east-1')

여러개의 버킷을 루프(반복문)으로 만들고 싶다면 다음과 같이 사용

if __name__=="__main__":
    AWSboto3 = AWSBoto3()
    for i in range(3):
        AWSboto3.create_bucket(bucket_name=f'bucket{i}-createdby-boto3',region='us-east-1')


3. 버킷 내 폴더 생성

import logging
import boto3
from botocore.exceptions import ClientError

class AWSBoto3():
    def __init__(self):
        self.access_key = 'access_key'
        self.secret_access_key = 'secret_key'
        
    def create_folder(self, bucket_name, folder_name, region=None):
        """Create an S3 bucket in a specified region

        If a region is not specified, the bucket is created in the S3 default
        region (us-east-1).

        :param bucket_name: Bucket to create
        :param region: String region to create bucket in, e.g., 'us-west-2'
        :return: True if bucket created, else False
        """

        # Create bucket
        try:
            if region is None:
                s3_client = boto3.client('s3', aws_access_key_id=self.access_key, aws_secret_access_key=self.secret_access_key)
                s3_client.put_object(Bucket=bucket_name, Key=(folder_name+'/'))
            else:
                s3_client = boto3.client('s3', region_name=region, aws_access_key_id=self.access_key, aws_secret_access_key=self.secret_access_key)
                #location = {'LocationConstraint': region}# when the region is configured to us-east-1, default bucket is created in us-east-1 region
                s3_client.put_object(Bucket=bucket_name, Key=(folder_name+'/'))#,CreateBucketConfiguration=location)
        except ClientError as e:
            logging.error(e)
            return False
        return True
  
if __name__=="__main__":
    AWSboto3 = AWSBoto3()
    AWSboto3.create_folder('bucket-createdby-boto3','folder_lv1/folder_lv2/folder_lv3','us-east-1')


4. 존재하는 버킷 출력(List)

import logging
import boto3
from botocore.exceptions import ClientError

class AWSBoto3():
    def __init__(self):
        self.access_key = 'access_key'
        self.secret_access_key = 'secret_key'

    def list_bucket(self, region):

        # List bucket
        try:
            if region is None:
                s3_client = boto3.client('s3', aws_access_key_id=self.access_key, aws_secret_access_key=self.secret_access_key)
                response = s3_client.list_buckets()
                print('Existing buckets:')
                print('----------------------')
                for bucket in response['Buckets']:
                    print(f'{bucket["Name"]}')
                print('----------------------')
            else:
                s3_client = boto3.client('s3', region_name=region, aws_access_key_id=self.access_key, aws_secret_access_key=self.secret_access_key)
                #location = {'LocationConstraint': region}# when the region is configured to us-east-1, default bucket is created in us-east-1 region
                response = s3_client.list_buckets()#,CreateBucketConfiguration=location)
                print('Existing buckets:')
                print('----------------------')
                for bucket in response['Buckets']:
                    print(f'{bucket["Name"]}')
                print('----------------------')
        except ClientError as e:
            logging.error(e)
            return False
        return True

if __name__=="__main__":
    AWSboto3 = AWSBoto3()
    AWSboto3.list_bucket('us-east-1')

bucket list 출력


5. 파일 업로드

import logging
import boto3
from botocore.exceptions import ClientError
import os

class AWSBoto3():
    def __init__(self):
        self.access_key = 'access_key'
        self.secret_access_key = 'secret_key'
        
    def upload_file_to_s3(self, file_name, bucket, object_name=None):
        """Upload a file to an S3 bucket

        :param file_name: File to upload
        :param bucket: Bucket to upload to
        :param object_name: S3 object name. If not specified then file_name is used
        :return: True if file was uploaded, else False
        """

        # If S3 object_name was not specified, use file_name
        if object_name is None:
            object_name = os.path.basename(file_name)

        # Upload the file
        s3_client = boto3.client('s3')
        try:
            response = s3_client.upload_file(file_name, bucket, object_name)
        except ClientError as e:
            logging.error(e)
            return False
        return True

if __name__=="__main__":
    AWSboto3 = AWSBoto3()
    AWSboto3.upload_file_to_s3('파일경로/motor_ny.csv','bucket-createdby-boto3-korea','folder_lv1/folder_lv2/folder_lv3/motor_ny.csv')


6. 파일 다운로드

import logging
import boto3
from botocore.exceptions import ClientError
import os

class AWSBoto3():
    def __init__(self):
        self.access_key = 'access_key'
        self.secret_access_key = 'secret_key'
        
     def download_file_from_s3(self, bucket, object_name, file_name):
        s3_client = boto3.client('s3')
        try:
            s3_client.download_file(bucket, object_name, file_name)
        except ClientError as e:
            logging.error(e)
            return False
        return True


if __name__=="__main__":
    AWSboto3 = AWSBoto3()
    AWSboto3.download_file_from_s3('bucket-createdby-boto3-korea','folder_lv1/folder_lv2/folder_lv3/motor_ny.csv','C:/Users/JIHO PARK/Downloads/download_from_s3.csv')


7. 파일 이동 설정값

1) Multipart transfer

import boto3
from boto3.s3.transfer import TransferConfig

# Set the desired multipart threshold value (5GB)
GB = 1024 ** 3
config = TransferConfig(multipart_threshold=5*GB)

# Perform the transfer
s3 = boto3.client('s3')
s3.upload_file('FILE_NAME', 'BUCKET_NAME', 'OBJECT_NAME', Config=config)

 

Multipart
웹 클라이언트가 요청을 보낼 때, http 프로토콜의 바디 부분에 데이터를 여러 부분으로 나눠서 보내는 것

2) Concurrent transfewr operations

  • 최대 병렬처리 개수 지정
  • 기본값은 10으로 지정
# To consume less downstream bandwidth, decrease the maximum concurrency
config = TransferConfig(max_concurrency=5)

# Download an S3 object
s3 = boto3.client('s3')
s3.download_file('BUCKET_NAME', 'OBJECT_NAME', 'FILE_NAME', Config=config)

3) Threads

  • 병렬성을 실행시키기 위해 threads를 사용함
  • use_threads = False로 설정하면 threads 사용 안하는 것이고, 병렬수행은 이뤄지지 않음(max_concurrency 속성은 무시 됨)
# Disable thread use/transfer concurrency
config = TransferConfig(use_threads=False)

s3 = boto3.client('s3')
s3.download_file('BUCKET_NAME', 'OBJECT_NAME', 'FILE_NAME', Config=config)

사용된 최종 코드

import logging
import boto3
from botocore.exceptions import ClientError
import os

class AWSBoto3():
    def __init__(self):
        self.access_key = 'access_key'
        self.secret_access_key = 'secret_key'

    def create_bucket(self, bucket_name, region=None):
        """Create an S3 bucket in a specified region

        If a region is not specified, the bucket is created in the S3 default
        region (us-east-1).

        :param bucket_name: Bucket to create
        :param region: String region to create bucket in, e.g., 'us-west-2'
        :return: True if bucket created, else False
        """

        # Create bucket
        try:
            if region is None:
                s3_client = boto3.client('s3', aws_access_key_id=self.access_key, aws_secret_access_key=self.secret_access_key)
                s3_client.create_bucket(Bucket=bucket_name)
            else:
                s3_client = boto3.client('s3', region_name=region, aws_access_key_id=self.access_key, aws_secret_access_key=self.secret_access_key)
                location = {'LocationConstraint': region}# when the region is configured to us-east-1, default bucket is created in us-east-1 region
                s3_client.create_bucket(Bucket=bucket_name, CreateBucketConfiguration=location)#,CreateBucketConfiguration=location)
        except ClientError as e:
            logging.error(e)
            return False
        return True

    def create_folder(self, bucket_name, folder_name, region=None):
        """Create an S3 bucket in a specified region

        If a region is not specified, the bucket is created in the S3 default
        region (us-east-1).

        :param bucket_name: Bucket to create
        :param region: String region to create bucket in, e.g., 'us-west-2'
        :return: True if bucket created, else False
        """

        # Create folder
        try:
            if region is None:
                s3_client = boto3.client('s3', aws_access_key_id=self.access_key, aws_secret_access_key=self.secret_access_key)
                s3_client.put_object(Bucket=bucket_name, Key=(folder_name+'/'))
            else:
                s3_client = boto3.client('s3', region_name=region, aws_access_key_id=self.access_key, aws_secret_access_key=self.secret_access_key)
                #location = {'LocationConstraint': region}# when the region is configured to us-east-1, default bucket is created in us-east-1 region
                s3_client.put_object(Bucket=bucket_name, Key=(folder_name+'/'))#,CreateBucketConfiguration=location)
        except ClientError as e:
            logging.error(e)
            return False
        return True

    def list_bucket(self, region):
        # List bucket
        try:
            if region is None:
                s3_client = boto3.client('s3', aws_access_key_id=self.access_key, aws_secret_access_key=self.secret_access_key)
                response = s3_client.list_buckets()
                print('Existing buckets:')
                print('----------------------')
                for bucket in response['Buckets']:
                    print(f'{bucket["Name"]}')
                print('----------------------')
            else:
                s3_client = boto3.client('s3', region_name=region, aws_access_key_id=self.access_key, aws_secret_access_key=self.secret_access_key)
                #location = {'LocationConstraint': region}# when the region is configured to us-east-1, default bucket is created in us-east-1 region
                response = s3_client.list_buckets()#,CreateBucketConfiguration=location)
                print('Existing buckets:')
                print('----------------------')
                for bucket in response['Buckets']:
                    print(f'{bucket["Name"]}')
                print('----------------------')
        except ClientError as e:
            logging.error(e)
            return False
        return True

    def upload_file_to_s3(self, file_name, bucket, object_name=None):
        """Upload a file to an S3 bucket

        :param file_name: File to upload
        :param bucket: Bucket to upload to
        :param object_name: S3 object name. If not specified then file_name is used
        :return: True if file was uploaded, else False
        """

        # If S3 object_name was not specified, use file_name
        if object_name is None:
            object_name = os.path.basename(file_name)

        # Upload the file
        s3_client = boto3.client('s3')
        try:
            response = s3_client.upload_file(file_name, bucket, object_name)
        except ClientError as e:
            logging.error(e)
            return False
        return True

    def download_file_from_s3(self, bucket, object_name, file_name):
        """Upload a file to an S3 bucket

        :param file_name: file name and a path to download
        :param bucket: Bucket name which contains objects to download
        :param object_name: S3 object name. If not specified then file_name is used
        :return: True if file was uploaded, else False
        """
        s3_client = boto3.client('s3')
        try:
            s3_client.download_file(bucket, object_name, file_name)
        except ClientError as e:
            logging.error(e)
            return False 
        return True


if __name__=="__main__":
    AWSboto3 = AWSBoto3()

 

 

 

참조:

https://planbs.tistory.com/entry/boto3resource%EC%99%80-boto3client%EC%9D%98-%EC%B0%A8%EC%9D%B4

728x90

댓글