ica_missing_files.py

import csv
import os

OLD_ICA_PATH = "/Users/jorge/Desktop/SLE_adm2_Dec2016"
NEW_ICA_PATH = "/Users/jorge/OneDrive - World Food Programme/SLE_new/2016/Admin_2/"
OUTPUT_FILE = "/Users/jorge/Desktop/test.csv"


def read_files(path):
    files = [
        [{"path": dir_path, "name": f} for f in files]
        for dir_path, _, files in os.walk(path)
    ]

    files = [item for sublist in files for item in sublist]

    # Filter .DS_Store files.
    files = [f for f in files if f != ".DS_Store"]

    return files


def main():
    old_ica_files = read_files(OLD_ICA_PATH)
    new_ica_files = read_files(NEW_ICA_PATH)

    rows = []
    for ica_file in old_ica_files:
        file_name = ica_file.get("name")
        old_path = ica_file.get("path")

        # Loop to find where the file has been moved.
        new_ica_file = next((f for f in new_ica_files if f.get("name") == file_name), None)
        if new_ica_file is None:
            new_path = ""
        else:
            new_path = new_ica_file.get("path")

        row = {"name": file_name, "old_path": old_path, "new_path": new_path}
        rows.append(row)

    sorted_rows = sorted(rows, key=lambda x: x["new_path"])

    keys = sorted_rows[0].keys()
    with open(OUTPUT_FILE, "w", newline="") as output_file:
        dict_writer = csv.DictWriter(output_file, keys)
        dict_writer.writeheader()
        dict_writer.writerows(sorted_rows)


if __name__ == "__main__":
    main()