import requests import zipfile import os def download_file(url, filename): headers = {"User-Agent": "LeonardExcoffier/1.0 (excoffier.leonard@gmail.com)"} response = requests.get(url, headers=headers, stream=True) response.raise_for_status() with open(filename, "wb") as file: for chunk in response.iter_content(chunk_size=8192): file.write(chunk) def extract_zip(source_filename, destination_folder): with zipfile.ZipFile(source_filename, "r") as zip_ref: zip_ref.extractall(destination_folder) dataset_dir = "dataset" dataset_link = "https://www.sec.gov/files/dera/data/financial-statement-data-sets/2024q2.zip" dataset_zip = "2024q2.zip" os.makedirs(dataset_dir, exist_ok=True) download_file(dataset_link, dataset_zip) extract_zip(dataset_zip, dataset_dir)