from bs4 import BeautifulSoup
from selenium import webdriver
option = webdriver.ChromeOptions()
# I use the following options as my machine is a window subsystem linux.
# I recommend to use the headless option at least, out of the 3
option.add_argument('--headless')
option.add_argument('--no-sandbox')
option.add_argument('--disable-dev-sh-usage')
# Replace YOUR-PATH-TO-CHROMEDRIVER with your chromedriver location
driver = webdriver.Chrome('YOUR-PATH-TO-CHROMEDRIVER', options=option)
driver.get('https://www.imdb.com/chart/top/') # Getting page HTML through request
soup = BeautifulSoup(driver.page_source, 'html.parser') # Parsing content using beautifulsoup. Notice driver.page_source instead of page.content
links = soup.select("table tbody tr td.titleColumn a") # Selecting all of the anchors with titles
first10 = links[:10] # Keep only the first 10 anchors
for anchor in first10:
print(anchor.text) # Display the innerText of each anchor