利用DeepSeek将AI输出的混合latex标记的markdown文件渲染成html格式 - l1t1/note GitHub Wiki

import re
from mistune import HTMLRenderer, create_markdown

class LaTexRenderer(HTMLRenderer):
    def __init__(self, escape=False):  # 禁用自动转义
        super().__init__(escape)
        self.protected = []

    def protect_latex(self, text):
        """保护$$...$$之间的LaTeX内容"""
        def repl(match):
            self.protected.append(match.group(0))
            return f'LATEX_BLOCK_{len(self.protected)-1}_'
        return re.sub(r'\$\$([\s\S]+?)\$\$', repl, text)

    def restore_latex(self, text):
        """恢复被保护的LaTeX块"""
        for i, latex in enumerate(self.protected):
            text = text.replace(f'LATEX_BLOCK_{i}_', latex)
        return text

    def block_text(self, text):
        """处理块级文本时保护LaTeX"""
        protected = self.protect_latex(text)
        result = super().block_text(protected)
        return self.restore_latex(result)

def backslash_to_dollar(text):
    """
    将LaTeX分隔符转换为更通用的格式：
    - 将 \(...\) 转换为 $...$
    - 将 \[...\] 转换为 $$...$$
    同时保留所有反斜杠不变
    
    参数:
        text: 原始Markdown文本
        
    返回:
        转换后的文本，其中LaTeX分隔符已标准化
    """
    # 处理行内公式 \(...\) → $...$
    text = re.sub(
        r'\\\((.*?)\\\)',
        lambda m: f'${m.group(1)}$',
        text,
        flags=re.DOTALL
    )
    
    # 处理块级公式 \[...\] → $$...$$
    text = re.sub(
        r'\\\[(.*?)\\\]',
        lambda m: f'$${m.group(1)}$$',
        text,
        flags=re.DOTALL
    )
    
    return text

def convert_md_to_html(input_path, output_path):
    # 初始化渲染器
    renderer = LaTexRenderer()
    markdown = create_markdown(renderer=renderer)
    
    # 读取Markdown文件
    with open(input_path, 'r', encoding='utf-8') as f:
        text = f.read()
    text=backslash_to_dollar(text)
    # 转换Markdown
    html = markdown(text)
    
    # 添加MathJax支持
    mathjax_js = '''<script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/MathJax.js?config=TeX-MML-AM_CHTML"></script>
<script src="showLaTex.js"></script>'''
    
    # 写入输出文件
    with open(output_path, 'w', encoding='utf-8') as f:
        f.write(html + '\n' + mathjax_js)
    
    print(f"Conversion complete. Output length: {len(html)}")

if __name__ == "__main__":
    convert_md_to_html("file.md", "index4.html")