pdf转word(以图片形式)

import fitz  # PyMuPDF
from docx import Document
from docx.shared import Inches
import io


def pdf_to_word_screenshots(pdf_path, zoom=10):
    """
    使用PyMuPDF将PDF转换为Word中的图片

    参数:
        pdf_path: 输入的PDF文件路径
        zoom: 缩放因子(默认2，提高分辨率)
    """
    doc = Document()
    pdf_doc = fitz.open(pdf_path)

    for page_num in range(len(pdf_doc)):
        page = pdf_doc.load_page(page_num)
        mat = fitz.Matrix(zoom, zoom)  # 提高分辨率
        pix = page.get_pixmap(matrix = mat)
        img_bytes = pix.tobytes("png")

        # 将图片添加到Word
        img_io = io.BytesIO(img_bytes)
        doc.add_picture(img_io, width = Inches(6))
        doc.add_page_break()

    word_path = pdf_path + ".docx"
    doc.save(word_path)
    print(f"Word文档已保存到: {word_path}")

# 安装PyMuPDF: pip install pymupdf
pdf_to_word_screenshots(r"C:\Users\12997\Desktop\xxxPDF.pdf")

############################################################################ 一下是将pdf转为png保存

import fitz  # PyMuPDF
import os

def pdf_to_png(pdf_path, output_folder, zoom=2):
    """
    将PDF每一页保存为PNG图片

    参数:
        pdf_path: 输入的PDF文件路径
        output_folder: 输出图片的文件夹路径
        zoom: 缩放因子(默认2，提高分辨率)
    """
    # 创建输出文件夹(如果不存在)
    # os.makedirs(output_folder, exist_ok = True)

    # 打开PDF文件
    pdf_doc = fitz.open(pdf_path)

    for page_num in range(len(pdf_doc)):
        page = pdf_doc.load_page(page_num)
        mat = fitz.Matrix(zoom, zoom)  # 设置分辨率

        # 获取页面像素图
        pix = page.get_pixmap(matrix = mat)

        # 构建输出文件名
        output_path = os.path.join(output_folder, f"page_{page_num + 1}.png")

        # 保存为PNG
        pix.save(output_path)
        print(f"已保存: {output_path}")


# 使用示例
pdf_path = r"C:\Users\xxx\Desktop\PDF.pdf"
output_folder = r"C:\Users\xxx\Desktop"
pdf_to_png(pdf_path, output_folder, zoom = 4)