使用Python统计PDF中的图像数量

import io
from PyPDF2 import PdfFileReader
from pdfminer.high_level import extract_images

def count_images_in_pdf(pdf_path):
    # 打开PDF文件
    with open(pdf_path, 'rb') as file:
        reader = PdfFileReader(file)
        image_count = 0

        # 遍历PDF页面
        for page_num in range(reader.numPages):
            page = reader.getPage(page_num)

            # 提取页面中的图像
            images = extract_images(io.BytesIO(page.extractText().encode('utf-8')))

            # 统计图像数量
            image_count += len(images)

        return image_count

# 使用示例
pdf_path = 'your_pdf_file.pdf'
image_count = count_images_in_pdf(pdf_path)
print(f'The PDF contains {image_count} images.')