Python script to find out who has taught previous Northeastern courses.

check_course.py

"""
Script to find out who has taught previous Northeastern courses.

Prerequisites:
 - Have Python bindings for Selenium installed (https://selenium-python.readthedocs.io/)
 - Have chromedriver installed and in PATH environment variable (http://chromedriver.storage.googleapis.com/index.html)

Usage: python3 check_course.py `subject_name` `subject_code` `course_number`

Examples:
python3 check_course.py Mathematics MATH 4541
python3 check_course.py "Computer Science" CS 4400
"""

import sys
import os
import time
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.common.exceptions import NoSuchElementException

subject_name = sys.argv[1]
subject_code = sys.argv[2]
course_number = sys.argv[3]

start_year = 2016
end_year = 2021
# Add all semesters from Fall start_year-1 to Spring end_year,
#  from most recent to least recent

semesters = []
for year in range(end_year, start_year-1, -1):
    semesters.append((f"Spring { year }", str(year)+"30"))
    semesters.append((f"Fall { year-1 }", str(year)+"10"))

def no_op():
    """
    Do nothing
    """
    pass

def look_for_element_by_id(driver, id, setup=no_op):
    """
    Return driver.find_element_by_id(id), once it exists
    """
    while True:
        try:
            elem = driver.find_element_by_id(id)
            return elem
        except NoSuchElementException:
            setup()

driver = webdriver.Chrome()

for semester_name, semester_id in semesters:
    print(f"Begin search for { semester_name }")
    # Go to course search page
    driver.get("https://nubanner.neu.edu/StudentRegistrationSsb/ssb/term/termSelection?mode=search")

    def setup_semester_search():
        """
        Searches for semester in the "Select a Term" page
        We have to use this setup function, because sometimes,
          we need to call this setup multiple times for it to work:
          If the initial setup is too fast, then it will complete before the page completely loads
          and then will be overwritten by our last search result
          because the last search result is the default value.
        """
        # Several errors are possible here,
        #  so we'll just keep trying until there are no errors.
        # (Not the highest quality code, I know.)
        try:
            # Click on the semester search box
            semester_search_box = driver.find_element_by_id("s2id_txt_term")
            semester_search_box = semester_search_box.find_element_by_class_name("select2-choice")
            semester_search_box.click()

            # Enter the semester name
            semester_search_input = driver.find_element_by_id("s2id_autogen1_search")
            semester_search_input.clear()
            semester_search_input.send_keys(semester_name+" Semester")
        except:
            pass
        
    # Keep setting up the search result until the search result pops up
    semester_search_result = look_for_element_by_id(
        driver, semester_id, setup_semester_search
    )
    semester_search_result.click()

    # Click the Continue button
    semester_search_submit = driver.find_element_by_id("term-go")
    semester_search_submit.click()
    
    # Keep trying to click on the subject search box
    #  until the page finishes loading
    subject_search_box = look_for_element_by_id(driver, "s2id_txt_subject")
    subject_search_box.click()

    # Enter the subject name
    subject_search_input = driver.find_element_by_id("s2id_autogen1")
    subject_search_input.send_keys(subject_name)
    # Wait for search result to load before selecting result
    subject_search_result = look_for_element_by_id(driver, subject_code)
    subject_search_result.click()

    # Enter the course number
    course_search_input = driver.find_element_by_id("txt_courseNumber")
    course_search_input.send_keys(course_number)

    # Click the Search button
    course_search_submit = driver.find_element_by_id("search-go")
    course_search_submit.click()
    
    # Wait for the page to load
    table = look_for_element_by_id(driver, "table1")
    
    # Get the instructors of each course
    instructor_elems = driver.find_elements_by_css_selector("[data-property=instructor]")
    # If there are no instructors, output indication message.
    # Notice that we check < 2 because the first element in instructor_elems
    #  will just be the "Instructor" heading in the table.
    if len(instructor_elems) < 2:
        print("No sections of this course found")
    else:
        for instructor_elem in instructor_elems[1:]:
            # Separate different instructors by semicolons
            instructors_lst = "; ".join(instructor_elem.text.split("\n"))
            print(f"Section taught by { instructors_lst }")