Converts all docx files in a folder to pdf using LibreOffice CLI

bulk_docx_to_pdf.py

import os
import subprocess
import platform

def convert_docx_to_pdf(input_folder, output_folder):
    """Converts all docx files in the input folder to pdf and saves them in the output folder.

    Args:
        input_folder: The path to the folder containing the docx files.
        output_folder: The path to the folder where the converted pdf files will be saved.
    """

    # Create the output folder if it doesn't exist.
    os.makedirs(output_folder, exist_ok=True)

    # Loop through each file in the input folder.
    for filename in os.listdir(input_folder):
        # Check if the file is a docx file.
        if filename.endswith(".docx"):
            # Construct the full path to the input file.
            input_path = os.path.join(input_folder, filename)
            # Construct the full path to the output file.
            output_path = os.path.join(output_folder, filename[:-5] + ".pdf")  # Replace .docx with .pdf

            # Use LibreOffice to convert the docx file to pdf.
            subprocess.run([
                'libreoffice',
                '--headless',  # Run LibreOffice in headless mode (no GUI).
                '--convert-to', 'pdf',  # Specify the output format as pdf.
                '--outdir', output_folder,  # Specify the output folder.
                input_path  # Specify the input file path.
            ])

if __name__ == "__main__":
    # Reminder to install LibreOffice
    print("Remember to install LibreOffice if you haven't already.")
    print("Here's how to install it on different operating systems:")
    print("  - Windows/macOS: Download and install from the official website: ")
    print("  - Linux (Debian/Ubuntu): Run 'sudo apt-get install libreoffice'")
    print("  - Linux (Fedora): Run 'sudo dnf install libreoffice'")
    print("  - Other Linux distributions: Refer to your distribution's package manager.")
    print("Make sure LibreOffice is added to your system's PATH environment variable.")

    # Define the input and output folders.
    input_folder = "docx_files"  # Folder containing docx files.
    output_folder = "pdf_files" # Folder to store converted pdf files.

    # Call the function to convert the files.
    convert_docx_to_pdf(input_folder, output folder)