pdf2jpeg.py

#!/usr/bin/env python3

import fitz  # PyMuPDF
import os
import argparse

def pdf_to_images(pdf_path, output_folder):
    """
    Converts each page of a PDF into a JPEG image.

    Args:
        pdf_path (str): Path to the PDF file.
        output_folder (str): Folder where the images will be saved.
    """
    # Ensure output folder exists
    os.makedirs(output_folder, exist_ok=True)

    # Check if the input file is a PDF
    if not pdf_path.lower().endswith('.pdf'):
        raise ValueError("The input file must be a PDF.")

    # Open the PDF file
    pdf_document = fitz.open(pdf_path)

    for page_number in range(len(pdf_document)):
        # Select the page
        page = pdf_document.load_page(page_number)

        # Render the page as a pixmap (image)
        pix = page.get_pixmap()

        # Define output image path
        output_path = os.path.join(output_folder, f"page_{page_number + 1}.jpeg")

        # Save the image in JPEG format
        pix.save(output_path)

        print(f"Saved page {page_number + 1} as {output_path}")

    # Close the PDF document
    pdf_document.close()

def main():
    # Argument parser setup
    parser = argparse.ArgumentParser(description="Convert PDF pages to JPEG images.")
    parser.add_argument('-i', '--input', required=True, help="Path to the input PDF file.")
    parser.add_argument('-o', '--output', required=True, help="Path to the output folder for JPEG images.")

    # Parse arguments
    args = parser.parse_args()

    pdf_path = args.input
    output_folder = args.output

    # Check if the output folder is valid
    if not os.path.isdir(output_folder):
        os.makedirs(output_folder, exist_ok=True)

    try:
        pdf_to_images(pdf_path, output_folder)
        print("All pages have been converted to images.")
    except Exception as e:
        print(f"Error: {e}")

if __name__ == "__main__":
    main()