Using LibreOffice, convert all WordPerfect files inside a directory (recursively) into Docx format.

convert_wpd.py

import os
import subprocess

def is_wordperfect_file(filepath):
    with open(filepath, 'rb') as file:
        header = file.read(4)
    return header == bytes([0xFF, 0x57, 0x50, 0x43])

def convert_files(source_directory, target_directory):
    # Traverse the directory
    for root, dirs, files in os.walk(source_directory):
        for file in files:
            file_path = os.path.join(root, file)
            if is_wordperfect_file(file_path):
                # Construct target file paths
                docx_file_path = file_path + ".docx"
                
                # Calculate relative path from source directory and create corresponding path in target directory
                relative_path = os.path.relpath(root, source_directory)
                target_subdir = os.path.join(target_directory, relative_path)
                os.makedirs(target_subdir, exist_ok=True)
                
                # Adjust the output path for the DOCX file to be in the target directory
                target_docx_path = os.path.join(target_subdir, os.path.basename(docx_file_path))
                
                # Construct the LibreOffice convert command
                command = [
                    "C:\Program Files\LibreOffice\program\soffice.exe", "--headless", "--convert-to", "docx",
                    "--outdir", target_subdir, file_path
                ]
                
                # Execute the command
                subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
                print(f"Converted: {file_path} to {target_docx_path}")

# Specify the source and target directories
source_directory = "./source"
target_directory = "./dest"
convert_files(source_directory, target_directory)