The purpose is to compare two list of files (A and B) and get a list of files does not exist in list A, and viceversa. This can be helpful for example when we want to make sure files were downloaded/reloaded succesfuly to avoid missing data.

comparetwofilelist.py

import os
from pathlib import PureWindowsPath

def print_diff_files():
    '''
    Compare the content of two files
    '''
    _local_dir = os.path.dirname(os.path.abspath(__file__))
    files_to_extract = PureWindowsPath(_local_dir + '\\' + 'files_to_find.txt')
    downloaded_files = PureWindowsPath(_local_dir + '\\' + 'filelist.txt')
    not_found_files = PureWindowsPath(_local_dir + '\\' + 'files_not_found.txt')
    extra_files = PureWindowsPath(_local_dir + '\\' + 'extra_files_found.txt')

    with open(files_to_find, 'r') as file1:

        with open(downloaded_files, 'r') as file2:
            diff = set(file1) - set(file2)
            extras = set(file2) - set(file1)

    with open(not_found_files, 'w') as file_out:
        for line in diff:
            file_out.write(line)

    with open(extra_files, 'w') as file_out:
        for line in extras:
            file_out.write(line)

if __name__ == '__main__':
    print_diff_files()