quick and dirty tool to scan an ansible archive and return a complete list of modules used throughout the archive.

scan-ansible-archive for modules.py

import argparse
import collections
import os
import yaml


MODULES = collections.defaultdict(int)
POP_ITEMS = ['always',
    'args',
    'assert',
    'async',
    'async_status',
    'authorized_key',
    'become',
    'become_user',
    'delay',
    'delegate_to',
    'environment',
    'failed_when',
    'group',
    'ignore_errors',
    'loop',
    'loop_control',
    'name',
    'no_log',
    'notify',
    'poll',
    'register',
    'rescue',
    'retires',
    'run_once',
    'sefcontext',
    'state',
    'tags',
    'until',
    'user',
    'vars',
    'when'
]



def parse_opts():
    """Parse options."""

    parser = argparse.ArgumentParser(
        description="Scan an ansible archive and return all used modules."
    )
    parser.add_argument(
        "path", help="ansible archive to scan"
    )

    return parser.parse_args()


def parse_task(task):
    for i in POP_ITEMS:
        task.pop(i, None)

    for k in task.keys():
        if k.startswith("with_"):
            continue

        if k == "block":
            for b in task[k]:
                parse_task(task=b)

        MODULES[k] += 1



def main():
    opts = parse_opts()
    for root, dirs, files in os.walk(opts.path):
        for f in files:
            file_path = os.path.join(root, f)
            if f.endswith(('yml', 'yaml')) and os.path.exists(file_path):
                with open(file_path) as y:
                    content = yaml.safe_load(y)
                    if isinstance(content, list):
                        for item in content:
                            if 'hosts' in item:
                                for task_key in ["pre_tasks", "tasks", "post_tasks"]:
                                    task_values = item.get(task_key)
                                    if task_values:
                                        for task_value in task_values:
                                            parse_task(task=task_value)
                            else:
                                parse_task(task=item)

    print(yaml.safe_dump(dict(MODULES), default_flow_style=False))

if __name__ == "__main__":
    main()