Scrape the YZU activities which have service hours and output the information to LINE NOTIFY when the website updates.

YZU_service_activity_scrape.py

# Need to create a YZUActivity.txt
from selenium import webdriver  
import time 
import requests
from bs4 import BeautifulSoup

URL='https://portalx.yzu.edu.tw/PortalSocialVB/FMain/PageActivityAll.aspx'
#https://portalx.yzu.edu.tw/PortalSocialVB/FPage/PageActivityDetail.aspx?Menu=Act&ActID=XXXX
driver = webdriver.Chrome(r"C:\Software\chromedriver_win32\chromedriver.exe")  # depend on your driver's location
driver.get(URL)
html_source = driver.page_source # 取得資料
driver.quit();
soup = BeautifulSoup(html_source, 'html.parser')
table=soup.find(text='服務學習').parent.parent.next_sibling
href = table.a.get('href')
ActID = href[-4:] # string(字串) href中,取最後4個Character(字元)
Datalist=[]
for string in soup.find(text='服務學習').parent.parent.next_sibling.strings:
    Datalist.append((repr(string)))
f = open('YZUActivity.txt', 'r+') # r+:read and write mode
TxtActID = f.read()
def PrintData():
	hyperLink = "https://portalx.yzu.edu.tw/PortalSocialVB/FPage/PageActivityDetail.aspx?Menu=Act&ActID=" + ActID
	Namelist=[]
	for string in soup.find(text='服務學習').parent.parent.strings:
		Namelist.append((repr(string)))
	if(len(Datalist) == 14):
		Namelist[0]+=' : '+Datalist[0]
		Namelist[1]+=' : '+Datalist[1]
		Namelist[2]+=' : '+Datalist[2]
		Namelist[3]+=' : '+Datalist[3]+Datalist[4]
		Namelist[4]+=' : '+Datalist[5]
		Namelist[5]+=' : '+Datalist[6]+Datalist[7]+Datalist[8]
		Namelist[6]+=' : '+Datalist[9]+ ' | ' +Datalist[10]+ ' | ' +Datalist[11]
		Namelist[7]+=' : '+Datalist[13]+Datalist[12]
	elif(len(Datalist) == 13):
		Namelist[0]+=' : '+Datalist[0]
		Namelist[1]+=' : '+Datalist[1]
		Namelist[2]+=' : '+Datalist[2]
		Namelist[3]+=' : '+Datalist[3]+Datalist[4]
		Namelist[4]+=' : '+Datalist[5]
		Namelist[5]+=' : '+Datalist[6]+Datalist[7]+Datalist[8]
		Namelist[6]+=' : '+Datalist[9]+ ' | ' +Datalist[10]
		Namelist[7]+=' : '+Datalist[12]+Datalist[11]
	else:
		Namelist[0]+=' : '+Datalist[0]
		Namelist[1]+=' : '+Datalist[1]
		Namelist[2]+=' : '+Datalist[2]
		Namelist[3]+=' : '+Datalist[3]+Datalist[4]
		Namelist[4]+=' : '+Datalist[5]
		Namelist[5]+=' : '+Datalist[6]+Datalist[7]+Datalist[8]
		Namelist[6]+=' : '+Datalist[9]
		Namelist[7]+=' : '+Datalist[11]+Datalist[10]
	msg="\n" 
	for i in Namelist:
		msg += i + '\n'
		print(i)
	msg += "\n報名連結 : " + hyperLink
	return msg
def lineNotify(token, msg):
        url = "https://notify-api.line.me/api/notify"
        headers = {
            "Authorization": "Bearer " + token, 
            "Content-Type" : "application/x-www-form-urlencoded"
        }
        payload = {'message': msg}
        r = requests.post(url, headers = headers, params = payload)
        return r.status_code
token = "LINE_TOKEN" # Your LINE NOTIFY TOKEN
msg = PrintData()
if(TxtActID != ActID):
	print("TxtActID != ActID") #TEST
	#f.truncate() 
	f = open('YZUActivity.txt', 'w')
	f.seek(0)
	f.truncate() # erase all data
	f.write(ActID)
	f.close()
	if(Datalist[-1] != '\'無\''): # escape character \'
		print("Datalist[-1]="+Datalist[-1])
		print("無") # TEST
		lineNotify(token, msg)