55 lines
1.9 KiB
Python
55 lines
1.9 KiB
Python
import os
|
|
from datetime import timedelta
|
|
|
|
import pendulum
|
|
from airflow.decorators import dag
|
|
from airflow.decorators import task
|
|
from airflow.providers.amazon.aws.hooks.s3 import S3Hook
|
|
from airflow.utils.file import TemporaryDirectory
|
|
|
|
S3_CONN_ID = os.getenv("S3_CONN_ID", "s3_conn")
|
|
EXECUTION_TIMEOUT = int(os.getenv("EXECUTION_TIMEOUT", 6))
|
|
|
|
default_args = {
|
|
"execution_timeout": timedelta(hours=EXECUTION_TIMEOUT),
|
|
"retries": int(os.getenv("DEFAULT_TASK_RETRIES", 1)),
|
|
"retry_delay": timedelta(seconds=int(os.getenv("DEFAULT_RETRY_DELAY_SECONDS", 60))),
|
|
}
|
|
|
|
def s3_dowload_unzip_upload(s3conn: str, src_key: str, src_bucket: str, dest_bucket: str):
|
|
hook = S3Hook(s3conn, transfer_config_args={'use_threads': False})
|
|
|
|
with TemporaryDirectory() as dwl_dir:
|
|
with TemporaryDirectory() as tmp_dir:
|
|
archive = f'{dwl_dir}/{src_key}'
|
|
hook.download_file(key=src_key, bucket_name=src_bucket, local_path=dwl_dir, preserve_file_name=True,
|
|
use_autogenerated_subdir=False)
|
|
with zipfile.ZipFile(archive, 'r') as zip_ref:
|
|
for info in zip_ref.infolist():
|
|
with zip_ref.open(info.filename) as file:
|
|
hook.load_file_obj(file, info.filename, dest_bucket, replace=True)
|
|
|
|
@dag(
|
|
start_date=pendulum.datetime(2021, 1, 1, tz="UTC"),
|
|
schedule=None,
|
|
catchup=False,
|
|
default_args=default_args,
|
|
params={
|
|
"zipfile": "File to unzip",
|
|
"src_bucket": "bucket containing the zip file",
|
|
"dst_bucket": "bucket that will contain unzipped files"
|
|
},
|
|
tags=["s3"],
|
|
)
|
|
def s3_unzip():
|
|
@task
|
|
def unzip(**context):
|
|
s3_dowload_unzip_upload(S3_CONN_ID,
|
|
context["params"]["zipfile"],
|
|
context["params"]["src_bucket"],
|
|
context["params"]["dst_bucket"])
|
|
|
|
unzip()
|
|
|
|
|
|
s3_unzip() |