import fitz  # PyMuPDF
import os
from PIL import Image
import io

def extract_images_from_pdf(pdf_path, output_folder):
    # 打开PDF文件
    document = fitz.open(pdf_path)
    # 确保输出文件夹存在
    os.makedirs(output_folder, exist_ok=True)

    # 遍历每一页
    for page_number in range(len(document)):
        page = document.load_page(page_number)
        # 获取页面中的图片
        images = page.get_images(full=True)

        for image_index, img in enumerate(images):
            xref = img[0]
            # 提取图片
            base_image = document.extract_image(xref)
            image_bytes = base_image["image"]
            image_ext = base_image["ext"]

            # 使用Pillow处理图片
            image = Image.open(io.BytesIO(image_bytes))
            # 构建图片文件名
            image_filename = f"page_{page_number + 1}_img_{image_index + 1}.{image_ext}"
            image_path = os.path.join(output_folder, image_filename)
            # 保存图片
            image.save(image_path)
            print(f"保存图片: {image_path}")

    # 关闭文档
    document.close()

# 使用示例
pdf_path = "/Users/xiangyu/Documents/余氏宗谱（新洲区等支族）/第一册/（5）余氏彩页    P17-40.pdf"  # 替换为你的PDF文件路径
output_folder = "extracted_images"  # 替换为你想要保存图片的文件夹
extract_images_from_pdf(pdf_path, output_folder)