pip install python-markdown python-docx beautifulsoup4

import markdown
from docx import Document
from docx.shared import Pt, Inches
from docx.enum.text import WD_ALIGN_PARAGRAPH, WD_PARAGRAPH_ALIGNMENT
from docx.oxml.ns import qn
from bs4 import BeautifulSoup
import os

def markdown_to_word(md_file_path, docx_file_path=None):
    """
    Markdown文件轉(zhuǎn)Word文檔核心函數(shù)
    :param md_file_path: 源Markdown文件路徑（必填，如：./test.md）
    :param docx_file_path: 輸出Word文件路徑（可選，默認(rèn)同目錄同名.docx）
    """
    # 1. 校驗(yàn)源文件是否存在
    if not os.path.exists(md_file_path):
        print(f"錯(cuò)誤：源文件 {md_file_path} 不存在！")
        return
    
    # 2. 默認(rèn)輸出路徑（同目錄、同名，后綴替換為.docx）
    if docx_file_path is None:
        docx_file_path = os.path.splitext(md_file_path)[0] + ".docx"
    
    # 3. 讀取Markdown文件內(nèi)容（指定UTF-8編碼，避免中文亂碼）
    with open(md_file_path, "r", encoding="utf-8") as f:
        md_content = f.read()
    
    # 4. Markdown → HTML（啟用擴(kuò)展，支持更完整語(yǔ)法）
    html_content = markdown.markdown(
        md_content,
        extensions=[
            'extra',        # 支持表格、代碼塊、腳注等擴(kuò)展語(yǔ)法
            'sane_lists',   # 優(yōu)化列表解析規(guī)則
            'nl2br'         # 換行符\n轉(zhuǎn)為HTML的<br>標(biāo)簽
        ],
        extension_configs={}
    )
    
    # 5. 初始化Word文檔對(duì)象
    doc = Document()
    
    # 6. 全局樣式配置（統(tǒng)一字體、避免中文宋體異常）
    doc.styles['Normal'].font.name = '宋體'
    doc.styles['Normal']._element.rPr.rFonts.set(qn('w:eastAsia'), '宋體')
    doc.styles['Normal'].font.size = Pt(12)  # 正文字號(hào)12號(hào)
    
    # 7. 解析HTML并渲染到Word
    soup = BeautifulSoup(html_content, "html.parser")
    parse_html_node(soup, doc)
    
    # 8. 保存Word文檔
    doc.save(docx_file_path)
    print(f"轉(zhuǎn)換成功！Word文件已保存至：{docx_file_path}")

def parse_html_node(node, doc):
    """遞歸解析HTML節(jié)點(diǎn)，映射為Word對(duì)應(yīng)樣式"""
    # 處理標(biāo)題（h1-h6）
    if node.name in [f'h{i}' for i in range(1,7)]:
        level = int(node.name[1])
        p = doc.add_paragraph()
        run = p.add_run(node.get_text(strip=True))
        # 標(biāo)題樣式：字號(hào)隨級(jí)別遞減，加粗
        run.font.size = Pt(20 - level * 2)
        run.font.bold = True
        run.font.name = '黑體'
        run._element.rPr.rFonts.set(qn('w:eastAsia'), '黑體')
        p.alignment = WD_ALIGN_PARAGRAPH.LEFT
    
    # 處理段落
    elif node.name == 'p':
        p = doc.add_paragraph()
        parse_inline_content(node, p)
    
    # 處理無(wú)序列表
    elif node.name == 'ul':
        for li in node.find_all('li', recursive=False):
            p = doc.add_paragraph(style='List Bullet')
            parse_inline_content(li, p)
    
    # 處理有序列表
    elif node.name == 'ol':
        for li in node.find_all('li', recursive=False):
            p = doc.add_paragraph(style='List Number')
            parse_inline_content(li, p)
    
    # 處理?yè)Q行
    elif node.name == 'br':
        doc.add_paragraph()
    
    # 遞歸處理子節(jié)點(diǎn)（兼容嵌套結(jié)構(gòu)）
    for child in node.children:
        if child.name:
            parse_html_node(child, doc)

def parse_inline_content(node, paragraph):
    """解析行內(nèi)元素（加粗、斜體、超鏈接等），添加到指定段落"""
    for content in node.contents:
        if isinstance(content, str):
            # 純文本內(nèi)容
            run = paragraph.add_run(content)
            run.font.name = '宋體'
            run._element.rPr.rFonts.set(qn('w:eastAsia'), '宋體')
            run.font.size = Pt(12)
        elif content.name == 'strong':
            # 加粗文本（MD：**內(nèi)容**）
            run = paragraph.add_run(content.get_text())
            run.font.bold = True
            run.font.name = '宋體'
            run._element.rPr.rFonts.set(qn('w:eastAsia'), '宋體')
        elif content.name == 'em':
            # 斜體文本（MD：*內(nèi)容*）
            run = paragraph.add_run(content.get_text())
            run.font.italic = True
            run.font.name = '宋體'
            run._element.rPr.rFonts.set(qn('w:eastAsia'), '宋體')
        elif content.name == 'a':
            # 超鏈接（MD：[文本](鏈接)）
            text = content.get_text()
            link = content.get('href', '')
            run = paragraph.add_run(f"{text}({link})")
            run.font.color.rgb = None  # 可自定義鏈接顏色
            run.font.name = '宋體'
            run._element.rPr.rFonts.set(qn('w:eastAsia'), '宋體')

# ------------------- 調(diào)用示例 -------------------
if __name__ == "__main__":
    # 替換為你的Markdown文件路徑（相對(duì)路徑/絕對(duì)路徑均可）
    INPUT_MD_FILE = "./test.md"
    # 可選：指定輸出Word路徑，如 "./轉(zhuǎn)換結(jié)果.docx"
    OUTPUT_DOCX_FILE = None
    
    markdown_to_word(INPUT_MD_FILE, OUTPUT_DOCX_FILE)

import markdown
from docx import Document
from docx.shared import Pt, Inches, RGBColor
from docx.enum.text import WD_ALIGN_PARAGRAPH
from docx.enum.table import WD_TABLE_ALIGNMENT, WD_ALIGN_VERTICAL
from docx.oxml.ns import qn
from bs4 import BeautifulSoup
import os

def markdown_to_word(md_file_path, docx_file_path=None):
    if not os.path.exists(md_file_path):
        print(f"錯(cuò)誤：源文件 {md_file_path} 不存在！")
        return
    if docx_file_path is None:
        docx_file_path = os.path.splitext(md_file_path)[0] + ".docx"

    with open(md_file_path, "r", encoding="utf-8") as f:
        md_content = f.read()

    # 啟用表格、代碼塊擴(kuò)展
    html_content = markdown.markdown(
        md_content,
        extensions=['extra', 'sane_lists', 'nl2br', 'codehilite'],
        extension_configs={}
    )

    doc = Document()
    doc.styles['Normal'].font.name = '宋體'
    doc.styles['Normal']._element.rPr.rFonts.set(qn('w:eastAsia'), '宋體')
    doc.styles['Normal'].font.size = Pt(12)

    soup = BeautifulSoup(html_content, "html.parser")
    parse_html_node(soup, doc)
    doc.save(docx_file_path)
    print(f"轉(zhuǎn)換成功！Word文件已保存至：{docx_file_path}")

def parse_html_node(node, doc):
    # 基礎(chǔ)節(jié)點(diǎn)（標(biāo)題、段落、列表）- 同基礎(chǔ)版，此處省略，完整代碼包含
    if node.name in [f'h{i}' for i in range(1,7)]:
        level = int(node.name[1])
        p = doc.add_paragraph()
        run = p.add_run(node.get_text(strip=True))
        run.font.size = Pt(20 - level * 2)
        run.font.bold = True
        run.font.name = '黑體'
        run._element.rPr.rFonts.set(qn('w:eastAsia'), '黑體')
    elif node.name == 'p':
        p = doc.add_paragraph()
        parse_inline_content(node, p)
    elif node.name == 'ul':
        for li in node.find_all('li', recursive=False):
            p = doc.add_paragraph(style='List Bullet')
            parse_inline_content(li, p)
    elif node.name == 'ol':
        for li in node.find_all('li', recursive=False):
            p = doc.add_paragraph(style='List Number')
            parse_inline_content(li, p)
    
    # 新增：處理表格
    elif node.name == 'table':
        rows = node.find_all('tr')
        row_count = len(rows)
        col_count = len(rows[0].find_all(['th', 'td'])) if row_count > 0 else 0
        if row_count == 0 or col_count == 0: return
        
        # 創(chuàng)建Word表格
        table = doc.add_table(rows=row_count, cols=col_count)
        table.alignment = WD_TABLE_ALIGNMENT.CENTER
        for r_idx, row in enumerate(rows):
            cells = row.find_all(['th', 'td'])
            for c_idx, cell in enumerate(cells):
                tc = table.cell(r_idx, c_idx)
                tc.vertical_alignment = WD_ALIGN_VERTICAL.CENTER
                p = tc.paragraphs[0]
                parse_inline_content(cell, p)
                # 表頭樣式加粗
                if cell.name == 'th':
                    for run in p.runs:
                        run.font.bold = True
    
    # 新增：處理代碼塊
    elif node.name == 'pre':
        code_node = node.find('code')
        if code_node:
            p = doc.add_paragraph()
            run = p.add_run(code_node.get_text())
            run.font.name = 'Consolas'  # 代碼專用等寬字體
            run.font.size = Pt(10)
            run.font.color.rgb = RGBColor(0, 0, 0)  # 黑色
    
    # 新增：處理圖片（MD：![描述](圖片路徑)）
    elif node.name == 'img':
        img_src = node.get('src', '')
        img_alt = node.get('alt', '圖片')
        if os.path.exists(img_src):
            try:
                doc.add_picture(img_src, width=Inches(4))  # 限制圖片寬度
                p = doc.add_paragraph(img_alt)
                p.alignment = WD_ALIGN_PARAGRAPH.CENTER
            except Exception as e:
                doc.add_paragraph(f"圖片加載失?。簕img_src} | 錯(cuò)誤：{str(e)}")
        else:
            doc.add_paragraph(f"圖片不存在：{img_src}（描述：{img_alt}）")

    for child in node.children:
        if child.name:
            parse_html_node(child, doc)

def parse_inline_content(node, paragraph):
    # 行內(nèi)元素（加粗、斜體、超鏈接）- 同基礎(chǔ)版
    for content in node.contents:
        if isinstance(content, str):
            run = paragraph.add_run(content)
            run.font.name = '宋體'
            run._element.rPr.rFonts.set(qn('w:eastAsia'), '宋體')
            run.font.size = Pt(12)
        elif content.name == 'strong':
            run = paragraph.add_run(content.get_text())
            run.font.bold = True
        elif content.name == 'em':
            run = paragraph.add_run(content.get_text())
            run.font.italic = True
        elif content.name == 'a':
            text = content.get_text()
            link = content.get('href', '')
            run = paragraph.add_run(f"{text}({link})")

# ------------------- 調(diào)用示例 -------------------
if __name__ == "__main__":
    INPUT_MD_FILE = "./test.md"  # 替換為你的MD文件路徑
    markdown_to_word(INPUT_MD_FILE)

INPUT_MD_FILE = "./你的文件.md"  # 相對(duì)路徑
# 或
INPUT_MD_FILE = "D:/project/note.md"  # 絕對(duì)路徑