I’m doing a fairly simple code on aiflow responsible for downloading data from github. The file is not heavy at all. However, as soon as I launch the DAG, I get this error.

Task exited with return code Negsignal.SIGSEGV

I use the basic airflow config with the SequentialExecutor.

This is my DAG

from datetime import datetime
from airflow import DAG
from airflow.operators.python import PythonOperator
from src.download_netflix import download_netflix_data



with DAG(
    dag_id='s3_dag',
    schedule='@daily',
    start_date=datetime(2022, 3, 1),
    catchup=False,
) as dag:

    task_scrap_netflix = PythonOperator(
        task_id='scrap_netflix',
        python_callable=download_netflix_data,
    )


task_scrap_netflix

and this is my downloader

import io
import os
import logging
import requests


def fetch_data_from_github(url, **kwargs):
    try:
        data_dir = os.path.join(os.path.dirname(__file__), "..", "data")
        logging.info(f"Data directory: {data_dir}")
        local_directory = os.path.join(data_dir, "netflix")
        logging.info(f"Local directory: {local_directory}")
        os.makedirs(local_directory, exist_ok=True)
        logging.info(f"Folder created or exists already: {local_directory}")
        filename = url.split("/")[-1]
        file_path = os.path.join(local_directory, filename)
        logging.info(f"File path: {file_path}")

        if os.path.exists(file_path):
            logging.info(f"File {file_path} already exists, skipping download.")
            return

        logging.info(f"Requesting URL: {url}")
        response = requests.get(url)
        response.raise_for_status()

        with open(file_path, 'wb') as file:
            file.write(response.content)

        logging.info(f"Data downloaded and saved locally to {file_path}.")

    except Exception as e:
        logging.error(f"An error occurred: {str(e)}")
        raise

def download_netflix_data():
    GITHUB_DATA_URL = 'https://raw.githubusercontent.com/garg-priya-creator/Netflix-Recommendation-System/main/app/NetflixDataset.csv'
    fetch_data_from_github(GITHUB_DATA_URL)

I tried to increase the memory, but without results.
Thank you all for your contributions!