Created
September 5, 2021 21:09
-
-
Save ari-vedant-jain/3ab00e625e93fca20b6897734a6023b9 to your computer and use it in GitHub Desktop.
Uncompress Zip files in S3 using 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 boto3 | |
| import zipfile | |
| from datetime import * | |
| from io import BytesIO | |
| import json | |
| import re | |
| def unzip_file(): | |
| session = boto3.Session() | |
| dev_client = session.client('s3') | |
| dev_resource=boto3.resource('s3') | |
| S3_ZIP_FOLDER = '<sourceFolder/>' | |
| S3_UNZIPPED_FOLDER = '<destinationFolder/>' | |
| S3_BUCKET = '<bucketname>' | |
| ZIP_FILE='<zipfile.zip>' | |
| bucket_dev = dev_resource.Bucket(S3_BUCKET) | |
| zip_obj = dev_resource.Object(bucket_name=S3_BUCKET, key=f"{S3_ZIP_FOLDER}{ZIP_FILE}") | |
| print("zip_obj=",zip_obj) | |
| buffer = BytesIO(zip_obj.get()["Body"].read()) | |
| z = zipfile.ZipFile(buffer) | |
| # | |
| # for each file within the zip | |
| for filename in z.namelist(): | |
| file_info = z.getinfo(filename) | |
| # Now copy the files to the 'unzipped' S3 folder | |
| print(f"Copying file {filename} to {S3_BUCKET}/{S3_UNZIPPED_FOLDER}{filename}") | |
| response = dev_client.put_object( | |
| Body=z.open(filename).read() , | |
| # might need to replace above line with the one | |
| # below for windows files | |
| # | |
| # Body=z.open(filename).read().decode("iso-8859-1").encode(encoding='UTF-8'), | |
| Bucket=S3_BUCKET, | |
| Key=f'{S3_UNZIPPED_FOLDER}{filename}' | |
| ) | |
| print(f"Done Unzipping {ZIP_FILE}") | |
| unzip_file() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment