Last active
September 21, 2023 16:06
-
-
Save GabrielSGoncalves/eaa6fb06ed93a2d333771e99bc9ad8df to your computer and use it in GitHub Desktop.
Read private files from a Google Drive
This file contains hidden or 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
from typing import Union, Dict | |
from io import BytesIO, StringIO | |
import json | |
import pandas as pd | |
import requests | |
from pydrive2.auth import GoogleAuth | |
from pydrive2.drive import GoogleDrive | |
def read_private_file_from_gdrive( | |
file_url: str, file_format: str, google_auth: GoogleAuth, **kwargs | |
) -> Union[pd.DataFrame, Dict, str]: | |
"""Read private files from Google Drive. | |
Parameters | |
---------- | |
file_url : str | |
URL adress to file in Google Drive. | |
file_format : str | |
File format can be 'csv', 'xlsx', 'parquet', 'json' or 'txt'. | |
google_auth: GoogleAuth | |
Google Authentication object with access to target account. For more | |
information on how to login using Auth2, please check the link below: | |
https://docs.iterative.ai/PyDrive2/quickstart/#authentication | |
Returns | |
------- | |
Union[pd.DataFrame, Dict, str]. | |
The specified object generate from target file. | |
""" | |
drive = GoogleDrive(google_auth) | |
# Parsing file URL | |
file_id = file_url.split("/")[-2] | |
file = drive.CreateFile({"id": file_id}) | |
content_io_buffer = file.GetContentIOBuffer() | |
if file_format == "csv": | |
return pd.read_csv( | |
StringIO(content_io_buffer.read().decode()), **kwargs | |
) | |
elif file_format == "xlsx": | |
return pd.read_excel(content_io_buffer.read(), **kwargs) | |
elif file_format == "parquet": | |
byte_stream = content_io_buffer.read() | |
return pd.read_parquet(BytesIO(byte_stream), **kwargs) | |
elif file_format == "json": | |
return json.load(StringIO(content_io_buffer.read().decode())) | |
elif file_format == "txt": | |
byte_stream = content_io_buffer.read() | |
return byte_stream.decode("utf-8", **kwargs) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
thanks for this snipet !
Quick tip: You could replace
from: StringIO(file.GetContentIOBuffer().read().decode())
to: StringIO(file.GetContentString())
no need to follow the route: GetContentIOBuffer > read > decode
because the getcontentstring method of 'GoogleDriveFile object' already delivers the string