简书文章下载器，python下载爬虫

首发于 个人博客

简书文章下载

之前的笔记都写在简书上，因为简单方便，在线markdown编辑很舒服，不用考虑notion之类的要考虑“科学”问题，
随时登录随时写，但发布文章存在限制，于是自己搭个简易博客，迁移到博客里。

自己搭博客又不想买昂贵的vps，所以选择了可以vercel部署的框架，这类框架大部分都是静态页面。如果后期想扩展更多功能，静态页面功能受限，
vercel自家的netxjs框架可以很方便的部署，而且支持ssr+ssg。但是基于nextjs的博客框架很少又不想自己写，最终找到了这个框架，感觉不错，
就迁移过来了。

https://www.www.animeirl.top

代码如下：

import os
import requests
import datetime
import threadpool

headers = {
      'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Maxthon/5.3.8.2000 Chrome/78.0.3904.108 Safari/537.36'
  }

cookies = ''
cookies_dict = {cook.split('=')[0]: cook.split('=')[1] for cook in cookies.split('; ')}

def create_file(file_path, content):
    if os.path.exists(file_path):
        # 检查文件大小和修改日期是否与现有文件相同
        if os.path.getsize(file_path) == len(content):
            print("文件已存在，不需要覆盖。", file_path)
            return
    with open(file_path, "w", encoding="utf-8", newline="\n") as f:
        f.write(content)
    print("文件已创建并写入。", file_path)

def saveMarkdown(noteName:str, title:str, noteId:str):
  try:
    os.mkdir(noteName)
    print("创建目录：", noteName)
  except FileExistsError:
    print("目录已存在", noteName)
  res = requests.get("https://www.jianshu.com/author/notes/"+noteId+"/content", headers=headers, cookies=cookies_dict)
  if not res.ok:
    print(f"获取文件内容出错:{res.status_code}")
    exit(-1)
  note = res.json()
  content = note['content']
  create_file(noteName+"/"+title+".md", content)

def saveMarkdownT(arg:list):
   saveMarkdown(arg[0], arg[1], arg[2])

def getJianshuTaskArgs():
  url = 'https://www.jianshu.com/author/notebooks'


  args = []

  res = requests.get(url, headers=headers, cookies=cookies_dict)
  if not res.ok:
    print(f"{res.status_code}")
    exit(-1)
  # print(type(res.json()),res.json(), len(res.json()))
  for v in res.json():
    print(v['name'], v['id'])
    notebookName = v['name']
    notebookId = v['id']
    res = requests.get("https://www.jianshu.com/author/notebooks/"+str(notebookId)+"/notes", headers=headers, cookies=cookies_dict)
    if not res.ok:
      print(f"{res.status_code}")
      exit(-1)

    notesInfo = res.json()
    # print(type(notesInfo),notesInfo)

    for noteInfo in notesInfo:
      title = noteInfo['title']
      timestamp = noteInfo['content_updated_at']
      dt_object = datetime.datetime.utcfromtimestamp(timestamp)
      local_dt_object = \
      dt_object.replace(tzinfo=datetime.timezone.utc).astimezone(tz=datetime.timezone(datetime.timedelta(hours=8)))
      date = dt_object.date().__str__()
      time = dt_object.time().__str__()
      print(title, date, time)

      filePath = notebookName+"/"+title+".md"
      print(filePath)
      # saveMarkdown(notebookName, title, str(noteInfo['id']))
      args.append([notebookName, title, str(noteInfo['id']), date, time])
  return args
  # return args

def downloanJianshuNotes():
  args = getJianshuTaskArgs()
  pool = threadpool.ThreadPool(20)
  tasks = threadpool.makeRequests(saveMarkdownT, args)
  [pool.putRequest(task) for task in tasks]
  pool.wait()
  print("线程池执行完成")

将自己的cookie填入即可食用。