pdf2img python編

import fitz  # pip install PyMuPDF
import os
import shutil
from pathlib import Path

def extract_images_from_pdf(pdf_path, save_folder):
    doc = fitz.open(pdf_path)
    print(pdf_path)
    save_prefix = "_".join(element[:10] for element in pdf_path.split("\\"))
    #save_prefix = pdf_path.replace("\\", "-")[0:20]
    print(save_prefix)

    img_index =0
    for page_number in range(doc.page_count):
        page = doc[page_number]
        images = page.get_images(full=True)
        #print("found images "+len(images))


        for img_info in images:
            img_index += 1
            image_index = img_info[0]
            #print(img_index,image_index)
            base_image = doc.extract_image(image_index)

            image_bytes = base_image["image"]
            image_filename = f"{save_folder}/{save_prefix}_{img_index}.jpg"

            with open(image_filename, "wb") as image_file:
                image_file.write(image_bytes)
    print("extracted images = "+str(img_index)+"\n")
    doc.close()
    
    
def extract_images_from_pdfs(pdf_folder, save_folder):
    files = [f for f in os.listdir(pdf_folder) if os.path.isfile(os.path.join(pdf_folder, f))]
    for file in files:
        #print(file)
        if file.lower().endswith(('.pdf')):
            filepath = os.path.join(pdf_folder, file)
            extract_images_from_pdf(filepath, save_folder)
    print("Done!")
            
extract_images_from_pdfs('Session 5 - Interfaces for the Body and Beyond','extracted_images')