md_to_html.py

#!/usr/bin/env python3
"""
Markdown 转 HTML 工具
将重写后的 Markdown 转换为带配图的 HTML
"""

import os
import sys
import re
from pathlib import Path
from datetime import datetime

# 添加模块路径
sys.path.insert(0, os.path.dirname(__file__))

from modules.layout_engine import WeChatLayoutEngine
from modules.image_match import ImageMatcher


def convert_markdown_to_html(
    md_file: str,
    author: str = "ruby鑫燕",
    generate_images: bool = True,
    output_dir: str = None
):
    """将 Markdown 转换为 HTML

    Args:
        md_file: Markdown 文件路径
        author: 作者名称
        generate_images: 是否生成配图
        output_dir: 输出目录，默认为 output/

    Returns:
        HTML 文件路径
    """
    print("\n" + "="*70)
    print("📄 Markdown → HTML 转换")
    print("="*70 + "\n")

    md_path = Path(md_file)
    if not md_path.exists():
        print(f"❌ 文件不存在: {md_file}")
        return None

    # 读取 Markdown 内容
    with open(md_path, 'r', encoding='utf-8') as f:
        md_content = f.read()

    # 提取标题
    title_match = re.search(r'^#\s+(.+)$', md_content, re.MULTILINE)
    title = title_match.group(1) if title_match else "无标题"

    # 提取所有 h2 标题（用于生成配图提示词）
    sections = re.findall(r'##\s+(.+)', md_content)

    print(f"📝 文章标题: {title}")
    print(f"📊 章节数量: {len(sections)}")
    print()

    # 生成配图
    cover_image = None
    inline_images = []

    if generate_images:
        print("🎨 生成配图...")
        image_matcher = ImageMatcher()

        # 生成封面
        print("   • 封面图...")
        cover_image = image_matcher.generate_cover(title, "", "简约")
        if cover_image:
            print(f"     ✅ {cover_image}")

        # 生成章节配图（最多3张）
        print(f"   • 生成 {min(3, len(sections))} 张配图...")
        inline_images = image_matcher.generate_inline_images(sections, count=min(3, len(sections)), style="简约")

        print()

    # 转换为 HTML
    print("🔄 转换为 HTML...")
    layout_engine = WeChatLayoutEngine()

    html_content = layout_engine.render(
        title=title,
        author=author,
        content=md_content,
        cover_image=cover_image,
        inline_images=inline_images
    )

    # 确定输出路径
    if output_dir:
        out_dir = Path(output_dir)
    else:
        out_dir = md_path.parent

    out_dir.mkdir(parents=True, exist_ok=True)

    # 生成输出文件名
    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
    html_file = out_dir / md_path.name.replace('.md', '_final.html')

    # 如果使用了相对路径，转换为绝对路径
    if cover_image and not cover_image.startswith('/'):
        base_dir = str(Path(__file__).parent.absolute())
        html_content = html_content.replace(
            f'src="{cover_image}"',
            f'src="{base_dir}/{cover_image}"'
        )

    for img in inline_images:
        if not img.startswith('/'):
            base_dir = str(Path(__file__).parent.absolute())
            html_content = html_content.replace(
                f'src="{img}"',
                f'src="{base_dir}/{img}"'
            )

    # 保存 HTML
    with open(html_file, 'w', encoding='utf-8') as f:
        f.write(html_content)

    print("✅ 转换完成！\n")
    print("="*70)
    print(f"📁 输出文件: {html_file}")
    print(f"📸 封面: {cover_image if cover_image else '无'}")
    print(f"🖼️  配图: {len(inline_images)} 张")
    print("="*70 + "\n")

    return str(html_file)


def main():
    """主函数"""
    import argparse

    parser = argparse.ArgumentParser(description='Markdown 转 HTML')
    parser.add_argument('md_file', help='Markdown 文件路径')
    parser.add_argument('-a', '--author', default='ruby鑫燕', help='作者名称')
    parser.add_argument('--no-images', action='store_true', help='不生成配图')
    parser.add_argument('-o', '--output', help='输出目录')

    args = parser.parse_args()

    html_file = convert_markdown_to_html(
        md_file=args.md_file,
        author=args.author,
        generate_images=not args.no_images,
        output_dir=args.output
    )

    if html_file:
        print("💡 下一步:")
        print(f"   1. 预览: open {html_file}")
        print(f"   2. 审稿: python editor_review.py {html_file}")
        print(f"   3. 如有问题，运行自我学习: python self_learning.py output/article_*_review.md")
        print()


if __name__ == "__main__":
    main()