TDM 40100: Project 10 — 2022

import time
from selenium import webdriver
from selenium.webdriver.firefox.options import Options
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
from selenium.webdriver.common.keys import Keys

firefox_options = Options()
firefox_options.add_argument("--window-size=810,1080")
# Headless mode means no GUI
firefox_options.add_argument("--headless")
firefox_options.add_argument("--disable-extensions")
firefox_options.add_argument("--no-sandbox")
firefox_options.add_argument("--disable-dev-shm-usage")

driver = webdriver.Firefox(options=firefox_options)

# navigate to the webpage
driver.get("https://purdue.edu/directory")

# full page source
print(driver.page_source)

# get html element
e = driver.find_element("xpath", "//html")

# print html element
print(e.get_attribute("outerHTML"))

# isolate the search bar "input" element
# important note: the following actually searches the entire DOM, not just the element e
inp = e.find_element("xpath", "//input")

# to start with the element e and _not_ search the entire DOM, you'd do the following
inp = e.find_element("xpath", ".//input")
print(inp.get_attribute("outerHTML"))

# use "send_keys" to type in the search bar
inp.send_keys("mdw")

# just like when you use a browser, you either need to push "enter" or click on the search button. This time, we will press enter.
inp.send_keys(Keys.RETURN)

# We can delay the program to allow the page to load
time.sleep(5)

# get the table
table = driver.find_element("xpath", "//table[@class='more']")

# print the table content
print(table.get_attribute("outerHTML"))