以下代码用于将word转换为jpg图片，默认为A4纸尺寸

import os
import tempfile
from PIL import Image
import comtypes.client
import fitz  # PyMuPDF库，用于PDF处理

def word_to_images(input_file, output_folder=None, dpi=300):
    """
    将Word文档转换为图片，保持原始尺寸。

    参数:
        input_file (str): Word文档路径
        output_folder (str, optional): 输出图片文件夹路径，默认为None(创建临时文件夹)
        dpi (int, optional): 图片DPI，默认为300

    返回:
        list: 生成的图片路径列表
    """
    # 创建输出文件夹
    if output_folder is None:
        output_folder = tempfile.mkdtemp()
    os.makedirs(output_folder, exist_ok=True)

    # 获取文件名(不带扩展名)
    base_name = os.path.splitext(os.path.basename(input_file))[0]

    try:
        # 第一步：将Word转换为PDF
        pdf_path = os.path.join(tempfile.gettempdir(), f"{base_name}.pdf")
        
        # 创建Word应用实例
        word = comtypes.client.CreateObject('Word.Application')
        word.Visible = False

        # 打开文档
        doc = word.Documents.Open(os.path.abspath(input_file))
        
        # 保存为PDF
        doc.SaveAs(pdf_path, FileFormat=17)  # 17代表PDF格式
        
        # 关闭文档和应用
        doc.Close()
        word.Quit()
        
        # 第二步：从PDF生成图片
        image_paths = []
        
        # 打开PDF
        pdf_document = fitz.open(pdf_path)
        
        # 处理每一页
        for page_num in range(len(pdf_document)):
            page = pdf_document.load_page(page_num)
            pix = page.get_pixmap(matrix=fitz.Matrix(dpi/72, dpi/72))  # 设置DPI
            
            # 创建图片路径
            image_path = os.path.join(output_folder, f"{base_name}_page{page_num+1}.png")
            
            # 保存图片
            pix.save(image_path)
            image_paths.append(image_path)
            print(f"已生成图片: {image_path}")
            
            # 检查图片尺寸是否为A4
            is_a4 = check_a4_size(image_path, dpi)
            size_info = "A4尺寸" if is_a4 else "非A4尺寸"
            print(f"  - 图片尺寸: {size_info}")
        
        # 关闭PDF文档
        pdf_document.close()
        
        # 删除临时PDF文件
        os.remove(pdf_path)
        
        return image_paths

    except Exception as e:
        print(f"致命错误: {str(e)}")
        # 确保清理资源
        try:
            if 'word' in locals() and word:
                word.Quit()
            if 'pdf_document' in locals() and pdf_document:
                pdf_document.close()
            # 删除可能残留的临时文件
            if os.path.exists(pdf_path):
                os.remove(pdf_path)
        except:
            pass
        return []

def check_a4_size(image_path, dpi=300, tolerance=0.02):
    """
    检查图片是否符合A4尺寸标准
    
    参数:
        image_path (str): 图片路径
        dpi (int): 图片DPI，默认为300
        tolerance (float): 容差范围，默认为0.02 (2%)
        
    返回:
        bool: 如果图片尺寸在A4标准范围内返回True，否则返回False
    """
    # A4纸的标准尺寸(mm)
    a4_width_mm = 210
    a4_height_mm = 297
    
    # 计算A4纸在指定DPI下的像素尺寸
    a4_width_px = round((a4_width_mm / 25.4) * dpi)
    a4_height_px = round((a4_height_mm / 25.4) * dpi)
    
    # 打开图片获取尺寸
    with Image.open(image_path) as img:
        width, height = img.size
    
    # 计算允许的误差范围
    width_min = a4_width_px * (1 - tolerance)
    width_max = a4_width_px * (1 + tolerance)
    height_min = a4_height_px * (1 - tolerance)
    height_max = a4_height_px * (1 + tolerance)
    
    # 检查图片尺寸是否在允许的误差范围内
    # 考虑到图片可能被旋转
    return (
        (width_min <= width <= width_max and height_min <= height <= height_max) or
        (width_min <= height <= width_max and height_min <= width <= height_max)
    )

if __name__ == "__main__":
    # 使用示例
    input_file = "Doc1.docx"  # 替换为你的Word文档路径
    output_folder = "word_images"  # 替换为你想要的输出文件夹
    dpi = 300  # 设置DPI值
    
    images = word_to_images(input_file, output_folder, dpi)
    
    if images:
        print(f"成功生成 {len(images)} 张图片")
    else:
        print("转换失败")