handtruck 0.2.0

Async S3 client using httpx & anyio

handtruck

The simple module for putting and getting object from Amazon S3 compatible endpoints.

Installation

pip install handtruck

Usage

from http import HTTPStatus

from httpx import AsyncClient
from handtruck import S3Client


client = S3Client(
    url="http://s3-url",
    client=AsyncClient(),
    access_key_id="key-id",
    secret_access_key="hackme",
    region="us-east-1"
)

# Upload str object to bucket "bucket" and key "str"
resp = await client.put("bucket/str", "hello, world")
assert resp.status_code == HTTPStatus.OK

# Upload bytes object to bucket "bucket" and key "bytes"
resp = await client.put("bucket/bytes", b"hello, world")
assert resp.status_code == HTTPStatus.OK

# Upload AsyncIterable to bucket "bucket" and key "iterable"
async def gen():
    yield b'some bytes'

resp = await client.put("bucket/file", gen())
assert resp.status_code == HTTPStatus.OK

# Upload file to bucket "bucket" and key "file"
resp = await client.put_file("bucket/file", "/path_to_file" )
assert resp.status_code == HTTPStatus.OK

# Check object exists using bucket+key
resp = await client.head("bucket/key")
assert resp.status_code == HTTPStatus.OK

# Get object by bucket+key
resp = await client.get("bucket/key")
data = resp.content

# Delete object using bucket+key
resp = await client.delete("bucket/key")
assert resp == HTTPStatus.NO_CONTENT

# List objects by prefix
async for result in client.list_objects_v2("bucket/", prefix="prefix"):
    # Each result is a list of metadata objects representing an object
    # stored in the bucket.
    do_work(result)

Bucket may be specified as subdomain or in object name:

import httpx
from handtruck import S3Client


client = S3Client(url="http://bucket.your-s3-host",
                  client=httpx.AsyncClient())
resp = await client.put("key", gen())
...

client = S3Client(url="http://your-s3-host",
                  client=httpx.AsyncClient())
resp = await client.put("bucket/key", gen())
...

client = S3Client(url="http://your-s3-host/bucket",
                  client=httpx.AsyncClient())
resp = await client.put("key", gen())
...

Auth may be specified with keywords or in URL:

import httpx
from handtruck import S3Client

client_credentials_as_kw = S3Client(
    url="http://your-s3-host",
    access_key_id="key_id",
    secret_access_key="access_key",
    client=httpx.AsyncClient(),
)

client_credentials_in_url = S3Client(
    url="http://key_id:access_key@your-s3-host",
    client=httpx.AsyncClient(),
)

Credentials

By default S3Client trying to collect all available credentials from keyword arguments like access_key_id= and secret_access_key=, after that from the username and password from passed url argument, so the nex step is environment variables parsing and the last source for collection is the config file.

You can pass credentials explicitly using the handtruck.credentials module.

Parallel Transfer

Parallel transfer is fully supported, either with multipart uploading or the Range header.

import httpx
from handtruck import S3Client


client = S3Client(url="http://your-s3-host", client=httpx.AsyncClient())

await client.put_file_multipart(
    "test/bigfile.csv",
    headers={
        "Content-Type": "text/csv",
    },
    workers_count=8,
)

await client.get_file_parallel(
    "dump/bigfile.csv",
    "/home/user/bigfile.csv",
    workers_count=8,
)