comput_md5.py

import pandas as pd
import argparse
import hashlib
import re
import os


def read_args():
    parser = argparse.ArgumentParser()
    parser.add_argument("target_dir",
            help="Directory containing files to compute md5 of.")
    args = parser.parse_args()
    return(args)


def get_files(target_dir):
    all_files = pd.DataFrame(columns = ["path", "basename"])
    for root, dirs, files in os.walk(target_dir):
        for f in files:
            row = pd.DataFrame({"path": [os.path.join(root, f)],
                                "basename": [f]})
            all_files = all_files.append(row, ignore_index = True)
    return all_files


def md5sum(filename, blocksize=65536):
    hash = hashlib.md5()
    with open(filename, "rb") as f:
        for block in iter(lambda: f.read(blocksize), b""):
            hash.update(block)
    return hash.hexdigest()


def compute_md5(all_files):
    md5s = all_files.path.apply(md5sum)
    return md5s


def main():
    args = read_args()
    output_file_name = re.sub(r"/", "_", args.target_dir)
    all_files = get_files(args.target_dir)
    md5s = compute_md5(all_files)
    all_files['md5'] = md5s
    all_files.to_csv(output_file_name + "_md5.csv", index = False)


if __name__ == "__main__":
    main()