Last active
March 15, 2022 15:25
-
-
Save laughingman7743/4e0d609c765553b600c6 to your computer and use it in GitHub Desktop.
redshift merge unload file
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
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
import argparse | |
import gzip | |
import json | |
import os | |
from boto.s3.connection import S3Connection | |
from boto.s3.key import Key | |
import cStringIO | |
def unzip_merge_file(bucket, manifest_file, out_file): | |
if os.path.exists(out_file): | |
os.remove(out_file) | |
manifest_key = Key(bucket, manifest_file) | |
manifest = json.loads(manifest_key.get_contents_as_string()) | |
with open(out_file, 'ab+') as f: | |
for url in manifest['entries']: | |
path = url['url'].replace('s3://' + bucket.name, '') | |
print path | |
key = Key(bucket, path) | |
stream = cStringIO.StringIO() | |
key.get_contents_to_file(stream) | |
stream.seek(0) | |
unzip = gzip.GzipFile(fileobj=stream) | |
f.write(unzip.read()) | |
PARSER = argparse.ArgumentParser() | |
PARSER.add_argument('-b', '--bucket', | |
dest='bucket_name', | |
type=str, | |
required=True, | |
help='Bucket name') | |
PARSER.add_argument('-m', '--manifest', | |
dest='manifest', | |
type=str, | |
required=True, | |
help='Manifest file path') | |
PARSER.add_argument('-o', '--output', | |
dest='output', | |
type=str, | |
default='output.txt', | |
help='Output file path (default: output.txt)') | |
ARGS = PARSER.parse_args() | |
if __name__ == '__main__': | |
conn = S3Connection() | |
bucket = conn.get_bucket(ARGS.bucket_name) | |
unzip_merge_file(bucket, ARGS.manifest, ARGS.output) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment