用Python脚本自动采集金融网站当天发布的免费报告

# -*- coding:utf-8 -*-
"""
开发环境：Python 3.86
脚本名称：2023-07-07 报告厅baogaoting
创建日期：2023年07月07日
"""
import datetime
import os, sys, time, traceback
import pathlib
from parsel import Selector
import requests

headers = {
 "xxx"
}
cookies = {
 "xxx"
}

def _down_file(dow_url,file_name):
 """
 :param dow_url:   下载链接
 :param file_name:  图片绝对路径 包括后缀名
 :return:
 """
 re_重试次数=0
 while True:
  try:
   response = requests.get(dow_url, headers=headers, cookies=cookies, timeout=10)
   if response.status_code == 200:
    break
   elif response.status_code == 404:
    break
   else:
    print(response.status_code)
    re_重试次数 += 1
  except Exception as e:
   adress = sys.exc_info()[-1]  # 异常地址
   line_error = traceback.extract_tb(adress, limit=1)[-1][1]  # 读取错误日志,最后一列的第二个元素即为模块出错行
   print(
    f"===================\n【异常原因】:{e}\n【异常类型】:{type(e)}\n【异常位置】:{line_error}\n===================")
   time.sleep(5)
   re_重试次数 += 1
  if re_重试次数 >= 10:
   response=""
   break
 if response:
  with open(file_name, "wb+") as f:  # , errors='ignore'
   f.write(response.content)
 else:
  print(f"【跳过】:下载失败{file_name}")


import winreg
def get_desktop():
 key = winreg.OpenKey(winreg.HKEY_CURRENT_USER,r'Software\Microsoft\Windows\CurrentVersion\Explorer\Shell Folders')
 return winreg.QueryValueEx(key, "Desktop")[0]

if __name__ == '__main__':
 zm_path=get_desktop()
 x_date = time.strftime("%Y-%m-%d")
 list_file_path=list(pathlib.Path(x_date).rglob("*"))
 dict_file_path={i.name:True for i in list_file_path}
 
 url = "https://www.baogaoting.com/space/30909237"
 for page in  range(1,3):
  params = {
   "page": page,
   "size": "15"
  }
  response = requests.get(url, headers=headers, cookies=cookies, params=params)
  """
    此处略去多行代码
    """
     print(f"【{title}】:热度{h3} 是当天上传的资料,准备访问下载{href_download}")
     if href_download:
      if not os.path.exists(f"{zm_path}//今日研报"):
       os.makedirs(f"{zm_path}//今日研报",exist_ok=True)
      title=title+ pathlib.Path(href_download).suffix
      #print(href_download, h3,title)
      for k in ["<", ">", "|", '"', "*", '\\', ":", "/", "?", "\n", "\r", "\t", "！", "☆"]:
       date = date.replace(k, '').strip()
      if dict_file_path.get(f"{date}_"+title):
       print(f"【状态】:已经下载了哦,自动跳过")
       continue
      else:
       _down_file(href_download, f"{zm_path}//今日研报//{title}")
     else:
      print(f"【状态】:链接{href_download} {title}无效,跳过不下载")
      
    else:
     print(f"【状态】:不是免费的，不下载")
    time.sleep(0.5)
   else:
    print(f"【状态】:{date} 上传时间不符合，直接结束!")
    break
 input(f"【状态】:完成了哦,按任意键退出软件")