对于boto3

import boto3

s3 = boto3.resource('s3')
my_bucket = s3.Bucket('my_bucket_name')

for object_summary in my_bucket.objects.filter(Prefix="dir_name/"):
    print(object_summary.key)

默认情况下，当你在boto中执行get_bucket调用时，它会尝试通过对bucket URL执行HEAD请求来验证你是否真的拥有对该bucket的访问权限。在这种情况下，你不希望boto这样做，因为你没有访问bucket本身的权限。

bucket = conn.get_bucket('my-bucket-url', validate=False)

然后你就可以像这样列出对象：

for key in bucket.list(prefix='dir-in-bucket'): 
    <do something>

如果仍然出现403错误，请尝试在前缀末尾添加一个斜杠。

for key in bucket.list(prefix='dir-in-bucket/'): 
    <do something>

注：此答案是针对boto version 2模块编写的，该模块现已过时，目前（2020年）boto3是与AWS配合使用的标准模块，更多信息请参见此问题：What is the difference between the AWS boto and boto3

Boto3客户端：

import boto3

_BUCKET_NAME = 'mybucket'
_PREFIX = 'subfolder/'

client = boto3.client('s3', aws_access_key_id=ACCESS_KEY,
                            aws_secret_access_key=SECRET_KEY)

def ListFiles(client):
    """List files in specific S3 URL"""
    response = client.list_objects(Bucket=_BUCKET_NAME, Prefix=_PREFIX)
    for content in response.get('Contents', []):
        yield content.get('Key')

file_list = ListFiles(client)
for file in file_list:
    print 'File found: %s' % file

使用会话

from boto3.session import Session

_BUCKET_NAME = 'mybucket'
_PREFIX = 'subfolder/'

session = Session(aws_access_key_id=ACCESS_KEY,
                  aws_secret_access_key=SECRET_KEY)

client = session.client('s3')

def ListFilesV1(client, bucket, prefix=''):
    """List files in specific S3 URL"""
    paginator = client.get_paginator('list_objects')
    for result in paginator.paginate(Bucket=bucket, Prefix=prefix,
                                     Delimiter='/'):
        for content in result.get('Contents', []):
            yield content.get('Key')

file_list = ListFilesV1(client, _BUCKET_NAME, prefix=_PREFIX)
for file in file_list:
    print 'File found: %s' % file

我刚刚遇到了同样的问题，这段代码可以解决这个问题。

import boto3

s3 = boto3.resource("s3")
s3_bucket = s3.Bucket("bucket-name")
dir = "dir-in-bucket"
files_in_s3 = [f.key.split(dir + "/")[1] for f in 
s3_bucket.objects.filter(Prefix=dir).all()]

以下代码将列出S3存储桶中特定目录下的所有文件：

import boto3

s3 = boto3.client('s3')

def get_all_s3_keys(s3_path):
    """
    Get a list of all keys in an S3 bucket.

    :param s3_path: Path of S3 dir.
    """
    keys = []

    if not s3_path.startswith('s3://'):
        s3_path = 's3://' + s3_path

    bucket = s3_path.split('//')[1].split('/')[0]
    prefix = '/'.join(s3_path.split('//')[1].split('/')[1:])

    kwargs = {'Bucket': bucket, 'Prefix': prefix}
    while True:
        resp = s3.list_objects_v2(**kwargs)
        for obj in resp['Contents']:
            keys.append(obj['Key'])

        try:
            kwargs['ContinuationToken'] = resp['NextContinuationToken']
        except KeyError:
            break

    return keys

这可以通过以下方式完成：

s3_client = boto3.client('s3')
objects = s3_client.list_objects_v2(Bucket='bucket_name')
for obj in objects['Contents']:
  print(obj['Key'])

如果要列出存储桶中某个文件夹的所有对象，可以在列出时指定。

import boto
conn = boto.connect_s3(AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY)
bucket = conn.get_bucket(AWS_BUCKET_NAME)
for file in bucket.list("FOLDER_NAME/", "/"):
    <do something with required file>

在S3中列出具有特定前缀的对象的最简单方法是使用awswrangler：

import awswrangler as wr
wr.s3.list_objects("s3://bucket_name/some/prefix/")

这将返回存储在some/prefix/中的对象列表