Hipnosis183 · November 21, 2024 22:52
diff --git a/s3-downloader.py b/s3-downloader.py
 # Requires Boto3 package.
 # pip install boto3
 import boto3
 import botocore
 import os
 import sys

 # Initialize S3 client without credentials.
 s3 = boto3.client('s3', config=boto3.session.Config(signature_version=botocore.UNSIGNED))

 # Download all files in a given bucket.
 def files_download(bucket):
    try:
        files_path = f'{os.getcwd()}/{bucket}'

        # Bucket cursor pagination loop.
        token = None
        while True:
            # Get list of objects in the bucket.
            params = {'Bucket': bucket}
            if token:
                params['ContinuationToken'] = token
            response = s3.list_objects_v2(**params)

            # Check if the bucket is empty.
            if 'Contents' not in response:
                print(f'Bucket {bucket} has no files.')
                return

            # Download all files in the current bucket list.
            for object in response['Contents']:
                file_key = object['Key']
                file_path = os.path.join(files_path, file_key)
                print(f'- {file_key}')

                # Ensure the file path exists.
                if not os.path.exists(os.path.dirname(file_path)):
                    os.makedirs(os.path.dirname(file_path))

                # Download the file.
                print(f'Downloading {file_key} to {file_path}...')
                s3.download_file(bucket, file_key, file_path)
                print(f'Downloaded {file_key} successfully.')

            # Check if there are more files.
            if response.get('IsTruncated'):
                token = response.get('NextContinuationToken')
            else:
                break

    except Exception as e:
        print(f'An error occurred: {e}')

 def main():
    # Define bucket name.
    bucket = sys.argv[1] if len(sys.argv) > 1 else 'mbrown-dq-mdl'

    # Start bucket files download.
    print(f'Downloading files from bucket \'{bucket}\'...')
    files_download(bucket)

 # Run script.
 main()
diff --git a/s3-fileslist.py b/s3-fileslist.py
 # Requires Boto3 package.
 # pip install boto3
 import boto3
 import botocore
 import sys

 # Convert size in bytes to a human-readable format.
 def size_format(bytes):
    if bytes >= 1024 ** 3:
        return f'{bytes / (1024 ** 3):.2f} GB'
    elif bytes >= 1024**2:
        return f'{bytes / (1024 ** 2):.2f} MB'
    else:
        return f'{bytes / 1024:.2f} KB'

 # Initialize S3 client without credentials.
 s3 = boto3.client('s3', config=boto3.session.Config(signature_version=botocore.UNSIGNED))

 # Get list of files for a given bucket.
 def files_list(bucket):
    files = []
    size = 0

    # Setup pagination to overcome the 1000 files limit.
    paginator = s3.get_paginator('list_objects_v2')
    pages = paginator.paginate(Bucket=bucket)

    # Iterate through the pages and get file keys and sizes.
    for page in pages:
        if 'Contents' in page:
            for item in page['Contents']:
                size += item['Size']
                files.append({
                    'file_key': item['Key'],
                    'size': size_format(item['Size'])
                })

    return files, size

 # Create index page from the files list.
 def html_create(bucket, files, size):
    files_total = len(files)
    size_total = size_format(size)

    html = f'''
    <html>
    <head>
        <title>Files in Bucket: {bucket}</title>
        <style>
            body {{
                font-family: Arial, sans-serif;
            }}
            table {{
                width: 100%;
                border-collapse: collapse;
            }}
            th, td {{
                border: 1px solid #ddd;
                padding: 8px;
                text-align: left;
            }}
            th {{
                background-color: #f2f2f2;
            }}
            a {{
                color: #2a65b1;
            }}
        </style>
    </head>
    <body>
        <h1>Files in Bucket: {bucket}</h1>
        <p><strong>Total Files:</strong> {files_total} | <strong>Total Size:</strong> {size_total}</p>
        <table>
            <thead>
                <tr>
                    <th>Name</th>
                    <th>Size</th>
                    <th>Link</th>
                </tr>
            </thead>
            <tbody>
    '''

    for file in files:
        html += f'''
            <tr>
                <td>{file['file_key']}</td>
                <td>{file['size']}</td>
                <td><a href="https://{bucket}.s3.amazonaws.com/{file['file_key']}" target="_blank">Download</a></td>
            </tr>
        '''

    html += '''
            </tbody>
        </table>
    </body>
    </html>
    '''

    return html

 # Save index page to a file.
 def html_save(html, filename):
    with open(filename, 'w') as file:
        file.write(html)

 def main():
    # Define bucket name.
    bucket = sys.argv[1] if len(sys.argv) > 1 else 'mbrown-dq-mdl'

    # List all files in the bucket.
    print(f'Fetching files from bucket \'{bucket}\'...')
    files, size = files_list(bucket)

    # Generate the HTML content.
    print('Generating HTML file...')
    html = html_create(bucket, files, size)

    # Save the HTML content to a file.
    html_save(html, f'{bucket}.html')
    print(f'Saved HTML file as \'{bucket}.html\'.')

 # Run script.
 main()
	# Requires Boto3 package.
	# pip install boto3
	import boto3
	import botocore
	import os
	import sys

	# Initialize S3 client without credentials.
	s3 = boto3.client('s3', config=boto3.session.Config(signature_version=botocore.UNSIGNED))

	# Download all files in a given bucket.
	def files_download(bucket):
	try:
	files_path = f'{os.getcwd()}/{bucket}'

	# Bucket cursor pagination loop.
	token = None
	while True:
	# Get list of objects in the bucket.
	params = {'Bucket': bucket}
	if token:
	params['ContinuationToken'] = token
	response = s3.list_objects_v2(**params)

	# Check if the bucket is empty.
	if 'Contents' not in response:
	print(f'Bucket {bucket} has no files.')
	return

	# Download all files in the current bucket list.
	for object in response['Contents']:
	file_key = object['Key']
	file_path = os.path.join(files_path, file_key)
	print(f'- {file_key}')

	# Ensure the file path exists.
	if not os.path.exists(os.path.dirname(file_path)):
	os.makedirs(os.path.dirname(file_path))

	# Download the file.
	print(f'Downloading {file_key} to {file_path}...')
	s3.download_file(bucket, file_key, file_path)
	print(f'Downloaded {file_key} successfully.')

	# Check if there are more files.
	if response.get('IsTruncated'):
	token = response.get('NextContinuationToken')
	else:
	break

	except Exception as e:
	print(f'An error occurred: {e}')

	def main():
	# Define bucket name.
	bucket = sys.argv[1] if len(sys.argv) > 1 else 'mbrown-dq-mdl'

	# Start bucket files download.
	print(f'Downloading files from bucket \'{bucket}\'...')
	files_download(bucket)

	# Run script.
	main()