Created
September 22, 2017 14:42
-
-
Save vsx-gh/fc0a1f347f1e704da0af5e025ad65c8d to your computer and use it in GitHub Desktop.
Remove completely S3 objects that have delete markers
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
#!/usr/bin/env python3 | |
''' | |
Program: s3_full_delete.py | |
Author: https://github.com/vsx-gh | |
Created: 20170920 | |
Program finds S3 objects with delete markers and deletes all versions | |
of those objects. | |
Be very careful running this code! | |
''' | |
import boto3 | |
from collections import defaultdict | |
working_bucket = '<your_bucket_name>' | |
id_list = defaultdict() # Holds delete markers | |
del_obj_list = defaultdict(list) # Holds all version IDs for objects w/delete markers | |
s3_client = boto3.client('s3') | |
bucket = boto3.resource('s3').Bucket(working_bucket) | |
resp = s3_client.list_object_versions(Bucket=working_bucket) | |
# All delete markers that are latest version, i.e., should be deleted | |
del_markers = {item['Key']: item['VersionId'] for item in resp['DeleteMarkers'] if item['IsLatest'] == True} | |
# Get all version IDs for all objects that have eligible delete markers | |
for item in resp['Versions']: | |
if item['Key'] in del_markers.keys(): | |
del_obj_list[item['Key']].append(item['VersionId']) | |
# Remove old versions of object by VersionId | |
for del_item in del_obj_list: | |
print('Deleting {}....'.format(del_item)) | |
rm_obj = bucket.Object(del_item) | |
for del_id in del_obj_list[del_item]: | |
rm_obj.delete(VersionId=del_id) | |
# Remove delete marker | |
rm_obj.delete(VersionId=del_markers[del_item]) | |
print('-----\n') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment