使用python根据标题标签自动生成嵌套目录

import re

def generate_nested_directory(document):
    headings = re.findall(r'<h\d>(.*?)</h\d>', document)  # 解析标题
    tags = re.findall(r'<tag>(.*?)</tag>', document)  # 解析标签

    directory = {}  # 目录结构

    for heading, tag in zip(headings, tags):
        title_hierarchy = heading.split('.')  # 标题层级关系
        current_level = directory  # 当前层级目录

        for level in title_hierarchy:
            if level not in current_level:
                current_level[level] = {}  # 创建新的目录级别
            current_level = current_level[level]  # 进入下一层级

        current_level['tag'] = tag  # 保存标签信息

    return directory

def format_directory(directory, level=0):
    result = ''
    indent = '  ' * level

    for key, value in directory.items():
        if key != 'tag':
            result += f'{indent}- {key}\n'
            result += format_directory(value, level+1)
        else:
            tag = value
            result += f'{indent}  - Tag: {tag}\n'

    return result

# 示例文档
document = '''
<h1>Introduction</h1>
<tag>Python</tag>

<h2>Getting Started</h2>
<tag>Basics</tag>

<h3>Installing Python</h3>
<tag>Installation</tag>

<h2>Working with Data</h2>
<tag>Data Processing</tag>

<h3>Reading CSV Files</h3>
<tag>Data Loading</tag>

<h3>Writing CSV Files</h3>
<tag>Data Export</tag>

<h2>Conclusion</h2>
<tag>Summary</tag>
'''

directory = generate_nested_directory(document)
formatted_directory = format_directory(directory)
print(formatted_directory)

- Introduction
  - Tag: Python
  - Getting Started
    - Tag: Basics
    - Installing Python
      - Tag: Installation
  - Working with Data
    - Tag: Data Processing
    - Reading CSV Files
      - Tag: Data Loading
    - Writing CSV Files
      - Tag: Data Export
  - Conclusion
    - Tag: Summary