Markdown 2 Word docx - python md_to_docx.py VB6.md VB6.docx

md_to_docx.py

import os
import json
import base64
import requests
import argparse
from docx import Document
from docx.shared import Inches, Pt
from docx.enum.text import WD_ALIGN_PARAGRAPH

def get_mermaid_image(code):
    # 將 mermaid 語法編碼並發送至 mermaid.ink
    data = {
        "code": code,
        "mermaid": {"theme": "default"}
    }
    json_str = json.dumps(data)
    b64_str = base64.b64encode(json_str.encode('utf-8')).decode('utf-8')
    url = f"https://mermaid.ink/img/{b64_str}"
    
    try:
        response = requests.get(url, timeout=20)
        if response.status_code == 200:
            return response.content
    except Exception as e:
        print(f"Error fetching mermaid image: {e}")
    return None

def main():
    parser = argparse.ArgumentParser(description="將 Markdown 檔案轉換為 Word (.docx) 檔案，並自動下載與嵌入 Mermaid 流程圖圖片。")
    parser.add_argument("md_path", help="來源 Markdown 檔案路徑")
    parser.add_argument("docx_path", nargs="?", help="輸出的 Word 檔案路徑 (預設為同檔名且副檔名為 .docx)")
    args = parser.parse_args()
    
    md_path = args.md_path
    docx_path = args.docx_path
    
    if not docx_path:
        docx_path = os.path.splitext(md_path)[0] + ".docx"
        
    if not os.path.exists(md_path):
        print(f"Error: 找不到檔案 {md_path}")
        return
    
    with open(md_path, "r", encoding="utf-8") as f:
        lines = f.readlines()
        
    doc = Document()
    
    # 設定文檔段落基本間距
    style = doc.styles['Normal']
    font = style.font
    font.name = 'Arial'
    font.size = Pt(11)
    
    in_mermaid = False
    mermaid_code = []
    
    i = 0
    while i < len(lines):
        line = lines[i]
        line_stripped = line.strip()
        
        # 處理 Mermaid 區塊
        if line_stripped.startswith("```mermaid"):
            in_mermaid = True
            mermaid_code = []
            i += 1
            continue
        elif in_mermaid and line_stripped.startswith("```"):
            in_mermaid = False
            # 渲染 Mermaid 圖片並插入
            code_str = "\n".join(mermaid_code)
            img_data = get_mermaid_image(code_str)
            if img_data:
                temp_path = "temp_mermaid.png"
                with open(temp_path, "wb") as img_f:
                    img_f.write(img_data)
                
                # 插入圖片說明
                p_desc = doc.add_paragraph()
                p_desc.alignment = WD_ALIGN_PARAGRAPH.CENTER
                run_desc = p_desc.add_run("【流程圖】")
                run_desc.bold = True
                run_desc.font.size = Pt(10)
                
                # 插入圖片，水平置中
                p = doc.add_paragraph()
                p.alignment = WD_ALIGN_PARAGRAPH.CENTER
                p.add_run().add_picture(temp_path, width=Inches(5.8))
                
                # 刪除暫存檔
                os.remove(temp_path)
            else:
                p = doc.add_paragraph()
                p.alignment = WD_ALIGN_PARAGRAPH.CENTER
                p.add_run("[無法載入 Mermaid 流程圖圖片]").bold = True
            
            # 加個空行
            doc.add_paragraph()
            i += 1
            continue
            
        if in_mermaid:
            mermaid_code.append(line.rstrip('\n'))
            i += 1
            continue
            
        # 處理標題
        if line_stripped.startswith("### "):
            doc.add_heading(line_stripped[4:], level=3)
        elif line_stripped.startswith("## "):
            doc.add_heading(line_stripped[3:], level=2)
        elif line_stripped.startswith("# "):
            doc.add_heading(line_stripped[2:], level=1)
        elif line_stripped.startswith("情況一：") or line_stripped.startswith("情況二："):
            # 大標題
            doc.add_heading(line_stripped, level=2)
        # 處理文字流程圖段落
        elif any(c in line for c in ["├──", "└──", "│", "───>"]):
            p = doc.add_paragraph()
            run = p.add_run(line.rstrip('\n'))
            run.font.name = 'Consolas'
            run.font.size = Pt(9.5)
            p.paragraph_format.space_after = Pt(2)
            p.paragraph_format.space_before = Pt(2)
        else:
            if line_stripped == "":
                pass
            else:
                doc.add_paragraph(line_stripped)
                
        i += 1
        
    doc.save(docx_path)
    print(f"Successfully converted to {docx_path}")

if __name__ == "__main__":
    main()