dump-files-puppet-catalog.py

import os
import re
import sys

import requests

TIMEOUT=10

def fetch_catalog(url):
    r = requests.get(url, timeout=TIMEOUT)
    return r.json()


def main(catalog_url, path_regex=None):
    regex = re.compile(path_regex)
    print('[*] Fetching catalog...')
    catalog = fetch_catalog(catalog_url)
    print('[*] Dumping files...')
    for resource in catalog['resources']:
        if resource['type'] != 'File':
            continue
        if regex.match(resource['title']) is None:
            continue
        if 'content' not in resource['parameters']:
            continue
        path = resource['title'].lstrip('/')
        os.makedirs(os.path.dirname(path), exist_ok=True)
        with open(path, 'wb') as f:
            f.write(resource['parameters']['content'].encode('utf-8'))


if __name__ == '__main__':
    if len(sys.argv) != 3:
        print("Usage: {} catalog_URL path_regex".format(sys.argv[0]))
        sys.exit(1)

    main(sys.argv[1], sys.argv[2])