# Code attribution: Yiyin Shen, Tyler Caraza-Harter
# Imports
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
import matplotlib.pyplot as plt
from collections import deque

# Get the button and input and output fields
service = Service(executable_path="chromedriver-win64/chromedriver.exe")
driver = webdriver.Chrome(service=service)
url = "https://pages.cs.wisc.edu/~yw/CS320F23TH1.html"
driver.get(url)
print("DONE")

DONE

# Get the links on the page
def get_links():
    links = driver.find_elements("tag name", "a")
    pages = list(filter(lambda x : x.text == "Link", links))
    hrefs = list(map(lambda x : x.get_attribute("href"), pages))
    return hrefs

get_links()

['https://pages.cs.wisc.edu/~yw/CS320F23TH2.html',
 'https://pages.cs.wisc.edu/~yw/CS320F23TH3.html',
 'https://pages.cs.wisc.edu/~yw/CS320F23TH4.html']

# Check if there is an additional image on the page
def goal_check():
    image = driver.find_elements("tag name", "img")
    if len(image) == 2:
        image[0].screenshot("image.png")
        print(image[0].get_attribute("src"))
        plt.imshow(plt.imread("image.png"))
        return True
    return False

goal_check()

False

# BFS to find the goal page
def crawl(url):
    visited = set()
    queue = deque([url])
    found = False
    count = 0 # avoid infinite loop
    while count < 100:
        count = count + 1
        current = queue.popleft()
        visited.add(current)
        driver.get(current)
        found = goal_check()
        if found:
            return current
        links = get_links()
        for link in links:
            if not link in visited and not link in queue:
                queue.append(link)
        if len(queue) == 0:
            break

url = "https://pages.cs.wisc.edu/~yw/CS320F23TH1.html"
crawl(url)

https://pages.cs.wisc.edu/~yw/CS320/amongus.png

'https://pages.cs.wisc.edu/~yw/CS320F23TH23.html'

# Remember to quit when it's done
driver.quit()