Compare folder files vs subfolder files - Cristian

import os

# Set the paths to the folders you want to compare
folder_a = r"c:\Folder-Oana\extracted"
folder_b = r"c:\Folder-Oana\extracted\translated"

# Define a function to get a list of all files, including subfolders
def get_all_files(folder):
    # Initialize an empty list to store the file paths
    all_files = []

    # Use the os.walk function to walk through the directory tree
    for root, dirs, files in os.walk(folder):
        # Loop through the files in the current directory
        for file in files:
            # Append the file path to the all_files list
            all_files.append(os.path.join(root, file))
        # Loop through all the subdirectories in the current directory - NEW
        for dir in dirs:
            # Get all files in each subdirectory
            subdir_files = get_all_files(os.path.join(root, dir))
            all_files = all_files + subdir_files
    # Return the list of file paths
    return all_files

if __name__ == '__main__':
    # Get the lists of all files in folder_a and folder_b
    files_in_folder_a = get_all_files(folder_a)
    files_in_folder_b = get_all_files(folder_b)

    # Convert the lists to sets for faster comparison
    set_a = set(files_in_folder_a)
    set_b = set(files_in_folder_b)

    # Find the files that are in folder_a but not in folder_b
    not_in_b = set_a - set_b
    # Print the filenames that are not in folder_b
    print("The following files are in folder A but not in folder B:\n")
    for file in not_in_b:
        print(file)