lot1-kickoff/airflow/dags/S3_delete.py

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

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))),
}


@dag(
    start_date=pendulum.datetime(2021, 1, 1, tz="UTC"),
    schedule=None,
    catchup=False,
    default_args=default_args,
    params={
        "prefix": "Key prefix of files to delete",
        "bucket": "bucket containing files to delete",
    },
    tags=["s3"],
)
def s3_delete():
    @task
    def delete(**context):
        hook = S3Hook(S3_CONN_ID, transfer_config_args={'use_threads': False})
        keys = hook.list_keys(bucket_name=context["params"]["bucket"], prefix=context["params"]["prefix"])
        hook.delete_objects(bucket=context["params"]["bucket"], keys=keys)
        for key in keys:
            print(f"{key} deleted!")

    delete()


s3_delete()