Last active
July 19, 2024 16:18
-
-
Save MaximRouiller/a0b817274a2a2fbd687acee06167f266 to your computer and use it in GitHub Desktop.
Automatically download files to Azure Blob Storage using Copy From URL API with Python
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
from azure.storage.blob import BlobServiceClient, BlobClient, ContainerClient | |
from datetime import datetime | |
from urllib.parse import urlparse | |
# Required package: azure-storage-blob | |
# API Docs: https://docs.microsoft.com/en-us/rest/api/storageservices/copy-blob-from-url | |
now = datetime.now() | |
connection_string = os.getenv('AZURE_CONNECTION_STRING') | |
files_to_process = ["http://deepyeti.ucsd.edu/jianmo/amazon/categoryFilesSmall/AMAZON_FASHION_5.json.gz", | |
"http://deepyeti.ucsd.edu/jianmo/amazon/categoryFilesSmall/AMAZON_FASHION.csv", | |
"http://deepyeti.ucsd.edu/jianmo/amazon/categoryFilesSmall/All_Beauty_5.json.gz"] | |
print(f'Copying {len(files_to_process)} Blobs from URL') | |
blob_service_client= BlobServiceClient.from_connection_string(connection_string) | |
timestamp = now.strftime("%Y%m%d%H%M%S") | |
container_name = f'data-{timestamp}' | |
container_client = blob_service_client.create_container(container_name) | |
for file_to_process in files_to_process: | |
url = urlparse(file_to_process) | |
filename = os.path.basename(url.path) | |
blob_client = container_client.get_blob_client(filename) | |
blob_client.start_copy_from_url(file_to_process, metadata=None, incremental_copy=False) | |
print("Operation started. Closing application.") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment