pdf ファイルから画像を抽出する

pip install fitz
pip install PyMuPDF

import fitz
import os

filename = 'aaa.pdf'
dir_name = os.path.splitext(filename)[0]
img_dir = os.path.join(os.getcwd(), dir_name)

if not os.path.exists(img_dir):
    os.makedirs(img_dir)

doc = fitz.open(filename)

for page_index in range(len(doc)):
    page = doc[page_index]
    images = page.get_images(full=True)

    for img_index, img in enumerate(images):
        xref = img[0]
        base_image = doc.extract_image(xref)
        image_bytes = base_image["image"]
        ext = base_image["ext"]

        img_name = os.path.join(img_dir, f'image{page_index+1}_{img_index}.{ext}')
        with open(img_name, 'wb') as f:
            f.write(image_bytes)
        print(f"Saved: {img_name}")