adlfs_azure_blob_storage_list_files_and_read_pandas_dataframe.py

1import adlfs
2import pandas as pd
3
4# Initialize the filesystem
5# Replace with your storage account name and key (or use connection_string/SAS token)
6fs = adlfs.AzureBlobFileSystem(account_name="myaccount", account_key="mykey")
7
8# List files in a container
9files = fs.ls("mycontainer/data-folder")
10print(f"Files found: {files}")
11
12# Read a CSV file directly from Azure Blob Storage into a pandas DataFrame
13# adlfs integrates with fsspec, allowing pandas to use 'abfs://' protocol
14storage_options = {'account_name': "myaccount", 'account_key': "mykey"}
15df = pd.read_csv("abfs://mycontainer/data-folder/dataset.csv", storage_options=storage_options)
16
17print(df.head())