GeezerVison

Welcome to s3pathlib Documentation

Note

You may not be viewing the full document, FULL DOCUMENT IS HERE

Quick Start

Note

COMPREHENSIVE DOCUMENT guide / features / best practice can be found at HERE

# import
>>> from s3pathlib import S3Path

# construct from string, auto join parts
>>> p = S3Path("bucket", "folder", "file.txt")
# construct from S3 URI works too
>>> p = S3Path("s3://bucket/folder/file.txt")
# construct from S3 ARN works too
>>> p = S3Path("arn:aws:s3:::bucket/folder/file.txt")
>>> p.bucket
'bucket'
>>> p.key
'folder/file.txt'
>>> p.uri
's3://bucket/folder/file.txt'
>>> p.console_url # click to preview it in AWS console
'https://s3.console.aws.amazon.com/s3/object/bucket?prefix=folder/file.txt'
>>> p.arn
'arn:aws:s3:::bucket/folder/file.txt'

# s3pathlib maintains a "context" object that holds the AWS authentication information
# you just need to build your own boto session object and attach to it
>>> import boto3
>>> from s3pathlib import context
>>> context.attach_boto_session(
...     boto3.session.Session(
...         region_name="us-east-1",
...         profile_name="my_aws_profile",
...     )
... )

>>> p = S3Path("bucket", "folder", "file.txt")
>>> p.write_text("a lot of data ...")
>>> p.etag
'3e20b77868d1a39a587e280b99cec4a8'
>>> p.size
56789000
>>> p.size_for_human
'51.16 MB'

# folder works too, you just need to use a tailing "/" to identify that
>>> p = S3Path("bucket", "datalake/")
>>> p.count_objects()
7164 # number of files under this prefix
>>> p.calculate_total_size()
(7164, 236483701963) # 7164 objects, 220.24 GB
>>> p.calculate_total_size(for_human=True)
(7164, '220.24 GB') # 7164 objects, 220.24 GB

# create a S3 folder
>>> p = S3Path("bucket", "github", "repos", "my-repo/")

# upload all python file from /my-github-repo to s3://bucket/github/repos/my-repo/
>>> p.upload_dir("/my-repo", pattern="**/*.py", overwrite=False)

# copy entire s3 folder to another s3 folder
>>> p2 = S3Path("bucket", "github", "repos", "another-repo/")
>>> p1.copy_to(p2, overwrite=True)

# delete all objects in the folder, recursively, to clean up your test bucket
>>> p.delete()
>>> p2.delete()

>>> s3bkt = S3Path("bucket") # assume you have a lots of files in this bucket
>>> iterproxy = s3bkt.iter_objects().filter(
...     S3Path.size >= 10_000_000, S3Path.ext == ".csv" # add filter
... )

>>> iterproxy.one() # fetch one
S3Path('s3://bucket/larger-than-10MB-1.csv')

>>> iterproxy.many(3) # fetch three
[
    S3Path('s3://bucket/larger-than-10MB-1.csv'),
    S3Path('s3://bucket/larger-than-10MB-2.csv'),
    S3Path('s3://bucket/larger-than-10MB-3.csv'),
]

>>> for p in iterproxy: # iter the rest
...     print(p)

# Stream big file by line
>>> p = S3Path("bucket", "log.txt")
>>> with p.open("r") as f:
...     for line in f:
...         do what every you want

# JSON io
>>> import json
>>> p = S3Path("bucket", "config.json")
>>> with p.open("w") as f:
...     json.dump({"password": "mypass"}, f)

# pandas IO
>>> import pandas as pd
>>> p = S3Path("bucket", "dataset.csv")
>>> df = pd.DataFrame(...)
>>> with p.open("w") as f:
...     df.to_csv(f)

Getting Help

Contributing

Copyright