Boto3 to download all files from a S3 Bucket

Solution 1:

I have the same needs and created the following function that download recursively the files.

The directories are created locally only if they contain files.

import boto3
import os

def download_dir(client, resource, dist, local='/tmp', bucket='your_bucket'):
    paginator = client.get_paginator('list_objects')
    for result in paginator.paginate(Bucket=bucket, Delimiter='/', Prefix=dist):
        if result.get('CommonPrefixes') is not None:
            for subdir in result.get('CommonPrefixes'):
                download_dir(client, resource, subdir.get('Prefix'), local, bucket)
        for file in result.get('Contents', []):
            dest_pathname = os.path.join(local, file.get('Key'))
            if not os.path.exists(os.path.dirname(dest_pathname)):
                os.makedirs(os.path.dirname(dest_pathname))
            if not file.get('Key').endswith('/'):
                resource.meta.client.download_file(bucket, file.get('Key'), dest_pathname)

The function is called that way:

def _start():
    client = boto3.client('s3')
    resource = boto3.resource('s3')
    download_dir(client, resource, 'clientconf/', '/tmp', bucket='my-bucket')

Solution 2:

When working with buckets that have 1000+ objects its necessary to implement a solution that uses the NextContinuationToken on sequential sets of, at most, 1000 keys. This solution first compiles a list of objects then iteratively creates the specified directories and downloads the existing objects.

import boto3
import os

s3_client = boto3.client('s3')

def download_dir(prefix, local, bucket, client=s3_client):
    """
    params:
    - prefix: pattern to match in s3
    - local: local path to folder in which to place files
    - bucket: s3 bucket with target contents
    - client: initialized s3 client object
    """
    keys = []
    dirs = []
    next_token = ''
    base_kwargs = {
        'Bucket':bucket,
        'Prefix':prefix,
    }
    while next_token is not None:
        kwargs = base_kwargs.copy()
        if next_token != '':
            kwargs.update({'ContinuationToken': next_token})
        results = client.list_objects_v2(**kwargs)
        contents = results.get('Contents')
        for i in contents:
            k = i.get('Key')
            if k[-1] != '/':
                keys.append(k)
            else:
                dirs.append(k)
        next_token = results.get('NextContinuationToken')
    for d in dirs:
        dest_pathname = os.path.join(local, d)
        if not os.path.exists(os.path.dirname(dest_pathname)):
            os.makedirs(os.path.dirname(dest_pathname))
    for k in keys:
        dest_pathname = os.path.join(local, k)
        if not os.path.exists(os.path.dirname(dest_pathname)):
            os.makedirs(os.path.dirname(dest_pathname))
        client.download_file(bucket, k, dest_pathname)