This script is useful to pull all the S3 bucket names and its relevant Tags from AWS S3 to a CSV file programmatically.

get_s3_tags.py

#!/bin/python

"""
  This script is useful to pull all the S3 bucket names and it's relevant tags from AWS S3 to a CSV file programmatically.

  Some highlights on this script:
  * One has to provide all the tags which has to be read and converted to a CSV Header
  * These tags are mentioned in TagSets class, wherein, the variables like: "OWNER", "TEAM" and all is available in S3 tags
  * Create a CSV order in which format/sequence do you want the headers using "ORDER" array in TagSets
  * Execute this script as `python get_s3_tags.py`
  * The default CSV file created in the same directory is named as: `s3_details.csv`
"""


import boto3
import csv
from botocore.exceptions import ClientError

class TagSets:
    """
      This class needs to be modified to capture the proper tags one is willing to download.
    """
    OWNER = "OWNER"
    TEAM = "TEAM"
    PRODUCT = "PRODUCT"
    ENVIRONMENT = "ENVIRONMENT"
    BUCKET = "BUCKET"
    ORDER = [BUCKET, PRODUCT, OWNER, TEAM, ENVIRONMENT]

    @classmethod
    def convert_to_order(cls, tag_set_map):
        value = []
        for item in cls.ORDER:
            value.append(tag_set_map.get(item, ""))

        return value

s3 = boto3.client('s3')
response = s3.list_buckets()['Buckets']
file_name = "s3_details.csv"
with open(file_name, 'w') as file:
    writer = csv.writer(file)
    headers = TagSets.ORDER
    writer.writerow(headers)

    for bucket in response:
        bucket_name = bucket['Name']
        tags = []
        try:
            response = s3.get_bucket_tagging(Bucket=bucket_name)
            if 'TagSet' in response:
                tag_set = response['TagSet']
                tag_set_map = dict([(item['Key'], item['Value']) for item in tag_set])
                tag_set_map[TagSets.BUCKET] = bucket_name
                values = []
                values.extend(TagSets.convert_to_order(tag_set_map))
                writer.writerow(values)
        except ClientError:
            writer.writerow([bucket_name])
            pass

print("Completed writing S3 tags to a csv file: " + file_name)