get_hangeul.py

def get_hangeul():
  
  # Scrape the website and get list of titles
  url = 'https://www.bbc.com/korean/popular/read'
  page = requests.get(url)
  soup = BeautifulSoup(page.content, 'html.parser')
  titles = soup.findAll('span', 
                       {'class': 'most-popular-list-item__headline'})
  
  # Iterate through titles -> remove punctuation -> append to the list
  result = []
  for title in titles:
    title = re.sub(r'[^\w\s]','',title.text)
    words = title.split()
    result += words
  
  # Return the unique words
  return set(result)