|
|
|
@ -1,8 +1,7 @@
|
|
|
|
|
'''
|
|
|
|
|
Author:@阳春布泽
|
|
|
|
|
date:23-1-5
|
|
|
|
|
列表 [(日期,title,网址)]
|
|
|
|
|
写入提取日期
|
|
|
|
|
note:目前只完成了爬虫部分,需要解决前端信息推送问题,有会QQ机器人或者微信小程序等同学欢迎合作
|
|
|
|
|
'''
|
|
|
|
|
import requests
|
|
|
|
|
from bs4 import BeautifulSoup
|
|
|
|
@ -14,8 +13,8 @@ header = {
|
|
|
|
|
}
|
|
|
|
|
title_list = []
|
|
|
|
|
output_list = []
|
|
|
|
|
path = 'C:\\Users\\LZH\\Desktop\\jwc.txt'
|
|
|
|
|
path_data = 'C:\\Python(旧)\\程序\\爬取教务处通知\\old_data.txt'
|
|
|
|
|
path = 'jwc.txt'
|
|
|
|
|
path_data = 'old_data.txt'
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def get_title(url, header, title_list):
|
|
|
|
|