Convert old Microsoft .doc files to PDFs

README.md

Convert DOC files to PDF using AppleScript

1. Use ScriptEditor.app to create the final file ConvertDOCtoPDF.scpt
2. Save the ConvertDOCtoPDF.scpt script and set the final path in the Python script
3. Set the source and output folders in the Python script
4. Enjoy!

convert_doc_pdf_applescript.py

import os
import subprocess

def convert_doc_to_pdf_applescript(input_file, output_file):
    script_path = '/path/to/applescript/ConvertDOCtoPDF.scpt'
    subprocess.call(['osascript', script_path, input_file, output_file])

def convert_all_docs_to_pdfs(source_dir, target_dir):
    if not os.path.exists(target_dir):
        os.makedirs(target_dir)

    convert_batch = 5
    i = 0
    for file_name in os.listdir(source_dir):
        if file_name.endswith('.doc'):
            # check if the pdf is not already created
            if os.path.exists(os.path.join(target_dir, os.path.splitext(file_name)[0] + '.pdf')):
                print(f'PDF already exists: {file_name}')
                continue
            input_file = os.path.join(source_dir, file_name)
            output_file = os.path.join(target_dir, os.path.splitext(file_name)[0] + '.pdf')
            convert_doc_to_pdf_applescript(input_file, output_file)
            print(f'Converted: {file_name} to PDF')
            i = i + 1
            if i >= convert_batch:
                print(f'Converted {convert_batch} files, stopping')
                break

if __name__ == '__main__':
    source_dir = '/folder/with/doc/files'  # Path to the source directory containing .doc files
    target_dir = '/folder/with/pdfs'  # Path to the target directory for .pdf files
    convert_all_docs_to_pdfs(source_dir, target_dir)

ConvertDOCtoPDF.scpt.source

on run {input_file, output_file}
	try
		-- Ensure input and output paths are POSIX paths (macOS paths)
		set input_path to POSIX file input_file
		set output_path to POSIX file output_file
		
		tell application "Microsoft Word"
			-- Start Microsoft Word if not already running
			if not application "Microsoft Word" is running then
				launch
				delay 2
			end if
			
			open input_path
			set theDoc to the front document
			save as theDoc file format format PDF file name output_path
			close theDoc
		end tell
		return "Success"
	on error errMsg number errNum
		return "Error: " & errMsg & " (" & errNum & ")"
	end try
end run