A simple gist to pull all the images from a PDF file

pdf_extract_images

#!/usr/bin/env python3
# coding=utf-8

from PIL import Image
import fitz
import os
import sys
import io

def pdf_extract_images(pdf_path, output_dir):
    # Open the PDF
    pdf = fitz.open(pdf_path)

    # Iterate over each page
    for page_number in range(pdf.page_count):
        page = pdf[page_number]
        image_list = page.get_images(full=True)
        for image_index, img in enumerate(image_list):
            xref = img[0]
            base_image = pdf.extract_image(xref)
            image_bytes = base_image["image"]
            image = Image.open(io.BytesIO(image_bytes))
            image.save(os.path.join(output_dir, f"page_{page_number}_image_{image_index}.png"))

    # Close the PDF
    pdf.close()

if __name__ == "__main__":
    pdf_path = sys.argv[1]
    output_dir = sys.argv[2] if len(sys.argv) > 2 else pdf_path.replace(".pdf", "")
    if not os.path.exists(output_dir):
        os.makedirs(output_dir, exist_ok=True)
    elif input(f"Output directory {output_dir} already exists. Continue? (y/n): ").lower() != "y":
        sys.exit(1)
    pdf_extract_images(pdf_path, output_dir)