CSDN文章导出md并迁移至博客园

fetch('https://blog.csdn.net/community/home-api/v1/get-business-list?page=1&size=100&businessType=blog&orderby=&noMore=false&year=&month=&username=qq_35204012')  
  .then(response => {  
    if (!response.ok) {  
      throw new Error('Network response was not ok');  
    }  
    return response.json(); // 假设服务器响应的是JSON格式的数据  
  })  
  .then(data => {  
    console.log(data); // 处理并显示响应的数据  
  })  
  .catch(error => {  
    console.error('There has been a problem with your fetch operation:', error);  
  });

import pandas as pd
import requests

import html2text

data = [
{
        "articleId": 139602661,
        "title": "微信AI机器人使用说明-2024本地部署版（非wechaty）",
        "description": "微信机器人实现的功能，先看视频的演示效果：2024年最新稳定的本地部署AI微信机器人使用方法演示可以对话可以语音可以绘画支持主账号管理好友权限管理。",
        "url": "https://blog.csdn.net/qq_35204012/article/details/139602661",
        "type": 1,
        "top": True,
        "forcePlan": False,
        "viewCount": 1581,
        "commentCount": 0,
        "editUrl": "https://mp.csdn.net/console/editor/html/139602661",
        "postTime": "2024-06-11 16:31:56",
        "diggCount": 34,
        "formatTime": "2024.06.11",
        "picList": [
            "https://img-blog.csdnimg.cn/img_convert/cf52fbe57e404f30babcdda6f1ef2c08.png"
        ],
        "collectCount": 6
    }
]


def html_to_md(html_content, output_file):
    """
    将HTML内容转换为Markdown，并保存到指定的文件。

    :param html_content: str, 要转换的HTML内容
    :param output_file: str, 输出的Markdown文件名（包括路径）
    """
    # 创建一个html2text转换器对象
    h = html2text.HTML2Text()
    # 使用转换器的handle方法将HTML转换为Markdown
    md_content = h.handle(html_content)

    # 将转换后的Markdown内容写入文件
    with open(output_file, 'w', encoding='utf-8') as f:
        f.write(md_content)


if __name__ == '__main__':

    url_list = [{'url': item['url'], 'title': item['title']} for item in data]
    # 解析地址
    base_url = 'https://www.helloworld.net/getUrlHtml?url='
    # 解析错误的url
    err_list = []
    for item in url_list:
        try:
            print(item['url'])
            res = requests.get(base_url + item['url'])
            content = res.json().get('html')
            title = item['title']
            print(title+'已完成')
            # 调用函数，将HTML转换为Markdown并保存为文件
            html_to_md(content, os.path.join('md', f'{title}.md')

) except Exception as e: print(e) err_list.append(item['url']) if err_list: print(err_list) df = pd.DataFrame([{'name': err_list}]) df.to_csv('err.csv', index=False)