s3_migration.py

import os
import boto3
from multiprocessing import Pool, cpu_count

# Configuration
LOCAL_FOLDER = 'PRT'  # The local folder with files
BUCKET_NAME = 'your-s3-bucket-name'  # Your S3 bucket name
REGION = 'your-region'  # Your AWS region, e.g., 'us-east-1'

# Initialize S3 client
s3_client = boto3.client('s3', region_name=REGION)

def upload_file(file_path):
    """
    Upload a file to S3.
    :param file_path: Path of the file to upload
    """
    try:
        # Define the key for the file in S3 (optional: you can keep the same name or change it)
        s3_key = os.path.relpath(file_path, LOCAL_FOLDER)
        print(f"Uploading {file_path} to s3://{BUCKET_NAME}/{s3_key}")
        s3_client.upload_file(file_path, BUCKET_NAME, s3_key)
        print(f"Upload of {file_path} completed successfully.")
    except Exception as e:
        print(f"Error uploading {file_path}: {e}")

def main():
    # Get all files in the LOCAL_FOLDER
    files_to_upload = [
        os.path.join(LOCAL_FOLDER, f) for f in os.listdir(LOCAL_FOLDER)
        if os.path.isfile(os.path.join(LOCAL_FOLDER, f))
    ]
    
    # Determine the number of processes to use
    num_processes = min(cpu_count(), len(files_to_upload))

    # Use multiprocessing Pool to upload files in parallel
    with Pool(processes=num_processes) as pool:
        pool.map(upload_file, files_to_upload)

if __name__ == "__main__":
    main()
















import boto3
import multiprocessing
import os

def upload_file_to_s3(file_path, s3_bucket, s3_key):
    s3 = boto3.client('s3')
    s3.upload_file(file_path, s3_bucket, s3_key)

def migrate_files_to_s3(folder_path, s3_bucket, s3_folder, num_processes):
    files = [os.path.join(folder_path, file) for file in os.listdir(folder_path)]

    def worker(files):
        for file in files:
            s3_key = os.path.join(s3_folder, os.path.basename(file))
            upload_file_to_s3(file, s3_bucket, s3_key)

    with multiprocessing.Pool(processes=num_processes) as pool:
        chunk_size = len(files) // num_processes
        for i in range(0, len(files), chunk_size):
            chunk = files[i:i+chunk_size]
            pool.apply_async(worker, args=(chunk,))
        pool.close()
        pool.join()

if __name__ == '__main__':
    folder_path = 'PRT'
    s3_bucket = 'MPT-2'
    s3_folder = 'Ortus'
    num_processes = 4  # Adjust the number of processes as needed

    migrate_files_to_s3(folder_path, s3_bucket, s3_folder, num_processes)



import boto3

s3 = boto3.client('s3')
response = s3.list_objects_v2(Bucket='your-bucket-name', Prefix='')

for obj in response['Contents']:
    if obj['Key'].endswith('/'):
        print(obj['Key'])