当您想要读取与默认配置不同的文件时,请mpu.aws.s3_download(s3path, destination)
直接使用或复制粘贴的代码:
def s3_download(source, destination,
exists_strategy='raise',
profile_name=None):
"""
Copy a file from an S3 source to a local destination.
Parameters
----------
source : str
Path starting with s3://, e.g. 's3://bucket-name/key/foo.bar'
destination : str
exists_strategy : {'raise', 'replace', 'abort'}
What is done when the destination already exists?
profile_name : str, optional
AWS profile
Raises
------
botocore.exceptions.NoCredentialsError
Botocore is not able to find your credentials. Either specify
profile_name or add the environment variables AWS_ACCESS_KEY_ID,
AWS_SECRET_ACCESS_KEY and AWS_SESSION_TOKEN.
See https://boto3.readthedocs.io/en/latest/guide/configuration.html
"""
exists_strategies = ['raise', 'replace', 'abort']
if exists_strategy not in exists_strategies:
raise ValueError('exists_strategy \'{}\' is not in {}'
.format(exists_strategy, exists_strategies))
session = boto3.Session(profile_name=profile_name)
s3 = session.resource('s3')
bucket_name, key = _s3_path_split(source)
if os.path.isfile(destination):
if exists_strategy is 'raise':
raise RuntimeError('File \'{}\' already exists.'
.format(destination))
elif exists_strategy is 'abort':
return
s3.Bucket(bucket_name).download_file(key, destination)
from collections import namedtuple
S3Path = namedtuple("S3Path", ["bucket_name", "key"])
def _s3_path_split(s3_path):
"""
Split an S3 path into bucket and key.
Parameters
----------
s3_path : str
Returns
-------
splitted : (str, str)
(bucket, key)
Examples
--------
>>> _s3_path_split('s3://my-bucket/foo/bar.jpg')
S3Path(bucket_name='my-bucket', key='foo/bar.jpg')
"""
if not s3_path.startswith("s3://"):
raise ValueError(
"s3_path is expected to start with 's3://', " "but was {}"
.format(s3_path)
)
bucket_key = s3_path[len("s3://"):]
bucket_name, key = bucket_key.split("/", 1)
return S3Path(bucket_name, key)