samplescript.py

samplescript.py

import time
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from contextlib import closing
from bs4 import BeautifulSoup
import re


url = 'https://simconnect.simge.edu.sg/psp/paprd/EMPLOYEE/HRMS/s/WEBLIB_EOPPB.ISCRIPT1.FieldFormula.Iscript_SM_Redirect?cmd=login'
url2 = 'https://simconnect.simge.edu.sg/psp/paprd_2/EMPLOYEE/HRMS/c/SA_LEARNER_SERVICES.SSR_SSENRL_LIST.GBL?Page=SSR_SSENRL_LIST&Action=A&TargetFrameName=None'
url3= 'https://simconnect1.simge.edu.sg:444/psc/csprd_2/EMPLOYEE/HRMS/c/SA_LEARNER_SERVICES.SSR_SSENRL_LIST.GBL' #"API" that populates timetable. It was never designed for this purpose, but we're going to use it
#url='https://google.com/'
username = 'usn'#change here
password = 'pw'#change here

#initialize PhantomJS, define settings
driver = webdriver.PhantomJS(executable_path='./phantomjs',service_args=['--ignore-ssl-errors=true', '--ssl-protocol=TLSv1'])
driver.set_window_size(1124, 850)  
driver.get(url)
time.sleep(5) #we use sleep to let the page happily load throughout the script. 
driver.save_screenshot('out.png');
#finds userinput box
usr = driver.find_element_by_name('userid')
#finds password box
passw = driver.find_element_by_name('pwd')
#finds login button
logbtn = driver.find_element_by_name('Submit')

#login
usr.send_keys(username)
passw.send_keys(password)
logbtn.click()

driver.save_screenshot('post_login.png')
time.sleep(6)
driver.get(url3) 
formatted_result = driver.page_source
soup = BeautifulSoup(formatted_result,"html.parser")
file = open('testfile.txt','w') 
file.write(soup.prettify())
subjectdiv = soup.findAll('div',{'id':re.compile(r'(win2divDERIVED_REGFRM1_DESCR20\$)([0-9]{1})')})
#subjectdiv = soup.select('div[id*=win2divDERIVED_REGFRM1_DESCR2020$]')
for div in subjectdiv:
	#print(div)
	subjectitle = div.find("td",{'class':'PAGROUPDIVIDER'})
	print(subjectitle.text)
	singledigittablerow = div.findAll('tr',{'id':re.compile(r'(trCLASS_MTG_VW\$)([0-9]{1})(_row)([0-9]{1})')})
	for row in singledigittablerow:
		#here we're going to use regex.
		#why do we repeat same regex twice with variance>?
		#first we check for id with regex for single digit
		#for example, MTG_DATES$0
		#if in that div, MTGDATES$# WHERE # is a random number does not match regex, it means that we're in a row where MTGDATES$ is MTGDATES$##
		#thus we write another regex for that row.
		#This was probably never meant to be pulled as an API that's why its so fucked up.
		getdate = row.find("span",{'id':re.compile(r'(MTG_DATES\$)([0-9]{1})')})
		if not getdate.text.strip():
			getdate = row.find("span",{'id':re.compile(r'(MTG_DATES\$)([0-9]{1})([0-9]{1})')})
		#date is returned in the format DD/MM/YYYY - DD/MM/YYYY
		#because the end date is redundant (unless SIM decides to hold 24hr overnight classes)
		date = getdate.text 
		strippeddate = (((date.strip()).split("-"))[0]).strip() #strips spaces, splits by -, returns first date.
		print(strippeddate)
		gettime = row.find("span",{'id':re.compile(r'(MTG_SCHED\$)([0-9]{1})')})
		if not gettime.text.strip():
			gettime = row.find("span",{'id':re.compile(r'(MTG_SCHED\$)([0-9]{1})([0-9]{1})')})
		time = gettime.text
		#time is returned as a value of DD<space>STARTTIME<AM/PM><space>-<space>ENDTIME<AM/PM>
		strippedtime = (time.strip()[2:]).split("-") #removes space, removes DD,splits by -. This forms a list in the format [XXXXAM, YYYYAM] Where x is start, y is end
		starttime = (strippedtime[0]).strip()
		endtime = (strippedtime[1]).strip()
		if len(starttime) < 7:
			starttime = "0"+starttime
		if len(endtime) < 7:
			endtime = "0"+endtime
		starttime = strippeddate + " " + starttime
		endtime = strippeddate + " " + endtime
		print('Start Time:'+ starttime)
		print('End Time:'+ endtime)
		getlocation = row.find("span",{'id':re.compile(r'(MTG_LOC\$)([0-9]{1})')})
		if not getlocation.text.strip():
			getlocation = row.find("span",{'id':re.compile(r'(MTG_LOC\$)([0-9]{1})([0-9]{1})')})
		location = getlocation.text
		print(location)
driver.close()