使用前言

• 填写csdn的cookie，下载文章用
• 填写csdn文件的文章id
• 若需上传图片，填写typecho的cookie，并新建一篇文章后，保存，在此打开这篇文章，上传一张图片，获取上传图片的地址，填入config字典中

• pip安装html2text（html转md用）

  具体代码如下

  import requests
  import json
  import html2text
  import re
  import os
  
  # 记得更改vuar_url链接地址
  
  config = {
      'csdn_cookie': '',
      'csdn_url': 'https://blog-console-api.csdn.net/v1/editor/getArticle?id=',
      'csdn_id':'118547334',
      'vuar_cookie': '',
      'vuar_url': 'https://www.vuar.cn/index.php/action/upload?cid=121&_=11fd2ca6cf612bb0ce6b1ec98701bc3a'
  }
  
  
  def get_html(id):
      # 初始化数据
      url = config['csdn_url'] + id
      header = {
          "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Safari/537.36",
          "cookie": config['csdn_cookie']}
      # 请求
      response = requests.get(url, headers=header)
      if (response.status_code == 200):
          res = response.json()
          return res['data']['title'], res['data']['content']
      else:
          return '', ''
  
  
  def get_img(url):
      res = requests.get(url)
      if res.status_code == 200:
          name = re.search('https://.+(?=\?)', url)
          suffix = os.path.splitext(name.group())[1]
          return suffix, res.content
      else:
          return '', ''
  
  
  def html_to_md(html):
      # 处理html格式文件中的内容
      return html2text.HTML2Text().handle(html)
      # 写入处理后的内容
      # with open('1.md', 'w', encoding="utf-8") as f:
      #     f.write(text)
      # print("爬取完毕")
  
  
  def post_img(local_path):
      data = {
          'name': os.path.basename(local_path)
      }
      file = {
          'file': open(local_path, 'rb')
      }
      headers = {
          'Cookie': config['vuar_cookie'],
          'Referer': 'https://www.vuar.cn/admin/write-post.php?{0}'.format(get_url_cid(config['vuar_url'])),
          'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Safari/537.36'
      }
      res = requests.post(config['vuar_url'], data=data, headers=headers, files=file)
      if res.status_code == 200:
          print('上传完成{0}'.format(res.json()[0]))
          return res.json()[0]
      else:
          print('上传失败')
          return False
  
  
  def get_url_cid(url):
      cid = re.search('cid=[0-9]+', url)
      return cid.group()
  
  
  def deal_img(md, title):
      # 找出md文件中的所有图片路径
      pattern = re.compile('\(https://img-blog[\s\S]*?\)')
      img_url = pattern.findall(md)
      i = 1
      # 循环处理图片
      for url in img_url:
          # 将md中的url替换为数字
          md = md.replace(url, '[{0}]'.format(i))
          # 处理url，并下载
          url = url.replace('\n', '').lstrip('(').rstrip(')')
          suffix, img = get_img(url)
          # 下载完后，生成本地存储地址，并写入本地
          if suffix:
              img_local_path = '{0}/{1}{2}'.format(title, i, suffix)
              with open(img_local_path, 'wb') as f:
                  f.write(img)
              # 写入本地后，上传至云端，并在md文档后添加本图片的上传链接
              vuar_url = post_img(img_local_path)
              md = md + "\n[{i}]: {vuar_url}".format(i=i,vuar_url=vuar_url)
          else:
              print('图片下载失败：{0}'.format(url))
          i += 1
      return md
  
  
  def main():
      # 初始化参数
      # 获取html内容与title
      title, html = get_html(config['csdn_id'])
      # 创建文件夹
      if not os.path.exists(title):
          os.makedirs(title)
      # html转md
      md = html_to_md(html)
      # 匹配出图片并下载，将md中的图片地址替换为博客的地址
      md = deal_img(md, title)
      # 输出md文件
      with open('{0}/{0}.md'.format(title), 'w', encoding="utf-8") as f:
          f.write(md)
  
  if __name__ == '__main__':
      main()

  上述代码只会自动上传图片并保存md文件，许手动将md文件中的内容，粘贴至文章处