import cloudscraper
from bs4 import BeautifulSoup

url = 'https://www.tripadvisor.co.uk/Hotel_Feature-g297414-d505948-zft9166-Shantou_International_Hotel.html%0A'

# Use cloudscraper to bypass Cloudflare protection

try:
    scraper = cloudscraper.create_scraper()
    response = scraper.get(url, timeout=30)
    print(f"Status code: {response.status_code}")
    response.raise_for_status()
    
except Exception as e:
    print(f"Error: {e}")
    # exit(1)

if 'text/html' not in response.headers.get('content-type', ''):
    print(f"Skipped non-HTML content: {url}")

html = response.text
soup = BeautifulSoup(html, "lxml")
for script in soup(["script", "style"]):
    script.decompose()

raw_content = soup.get_text(separator='\n', strip=True)
print(raw_content)