将扫描的PDF或tessaract可搜索的PDF转换为docx/doc，并使用python维护所有格式和布局

import fitz  # PyMuPDF
from docx import Document
from docx.shared import Pt

def pdf_to_docx(pdf_path, docx_path):
    # 打开PDF文件
    pdf_document = fitz.open(pdf_path)
    doc = Document()

    for page_num in range(len(pdf_document)):
        page = pdf_document.load_page(page_num)
        text_instances = page.getText("dict")["blocks"]

        for inst in text_instances:
            if inst["type"] == 0:  # 文本块
                for line in inst["lines"]:
                    for span in line["spans"]:
                        # 创建段落并设置字体大小
                        p = doc.add_paragraph()
                        run = p.add_run(span["text"])
                        font = run.font
                        font.size = Pt(span["size"])

    # 保存为docx文件
    doc.save(docx_path)

# 使用示例
pdf_to_docx("example.pdf", "output.docx")