unified_python/main.py

import requests
import html2text
import os


def extract_entries(entries, result_list):
    """
    递归提取嵌套结构中无子节点的条目信息
    :param entries: 当前层级的条目列表
    :param result_list: 存储结果的列表
    """
    for entry in entries:
        # 检查是否存在子节点
        if "children" not in entry or not entry["children"]:
            # 提取目标字段并拼接URL
            result_list.append({
                "title": entry.get("title", ""),
                "scm": entry.get("scm", ""),
                "url": "https://help.aliyun.com" + entry.get("url", "")
            })
        else:
            # 递归处理子节点
            extract_entries(entry["children"], result_list)


def main():
    url = "https://help.aliyun.com/help/json/menupath.json?alias=%2Fhologres%2Fproduct-overview%2F&website=cn&language=zh"
    response = requests.get(url)
    data = response.json()

    result = []
    extract_entries(data['data']['children'], result)  # 从顶层children开始递归

    # 打印结果（或根据需求存储/处理）
    i = 1
    for item in result:
        print(item['url'])
        print(i)
        md(item['url'], i)
        i += 1


def md(url, title):
    response = requests.get(url)
    html_content = response.content.decode('utf-8')  # 解码为字符串

    # 初始化 html2text 转换器，设置标题样式为 ATX
    converter = html2text.HTML2Text()
    converter.ignore_links = False
    converter.heading_style = "ATX"  # 使用 ATX 风格的标题（即 # Heading）

    markdown_text = converter.handle(html_content)
    print(markdown_text)

    # 确保目录存在
    os.makedirs("./md", exist_ok=True)

    # 保存 Markdown 文件
    with open(f"./md/{title}.md", "w", encoding="utf-8") as f:
        f.write(markdown_text)


if __name__ == "__main__":
    # md('https://help.aliyun.com/zh/hologres/product-overview/what-is-hologres', 1)
    main()