Extract JPEG images from a PDF and create a zip. Name of images is based on PDF.

extract_jpgs_from_pdf.py

import fitz  # PyMuPDF
import sys
import os
import zipfile

def extract_jpg_images_from_pdf(pdf_path):
    doc = fitz.open(pdf_path)
    images = []
    for page_number in range(len(doc)):
        page = doc[page_number]
        for img in page.get_images(full=True):
            xref = img[0]
            base_image = doc.extract_image(xref)
            img_bytes = base_image["image"]
            img_ext = base_image["ext"]
            if img_ext.lower() == "jpg" or img_ext.lower() == "jpeg":
                images.append((img_bytes, img_ext))
    return images

def save_images_and_zip(images, pdf_path):
    base = os.path.splitext(os.path.basename(pdf_path))[0]
    temp_dir = f"{base}_extracted_jpgs"
    os.makedirs(temp_dir, exist_ok=True)

    img_paths = []
    for i, (img_bytes, img_ext) in enumerate(images):
        img_filename = f"{base}_{i+1}.{img_ext}"
        img_path = os.path.join(temp_dir, img_filename)
        with open(img_path, "wb") as img_file:
            img_file.write(img_bytes)
        img_paths.append(img_path)

    zip_filename = f"{base}.zip"
    with zipfile.ZipFile(zip_filename, "w", zipfile.ZIP_DEFLATED) as zipf:
        for img_path in img_paths:
            zipf.write(img_path, arcname=os.path.basename(img_path))

    # Cleanup extracted files
    for img_path in img_paths:
        os.remove(img_path)
    os.rmdir(temp_dir)

    print(f"ZIP created: {zip_filename}")

def main():
    if len(sys.argv) != 2:
        print("Usage: python extract_jpgs_from_pdf.py <file.pdf>")
        sys.exit(1)

    pdf_path = sys.argv[1]
    images = extract_jpg_images_from_pdf(pdf_path)
    if not images:
        print("No JPG images found in PDF.")
        sys.exit(0)
    save_images_and_zip(images, pdf_path)

if __name__ == "__main__":
    main()