Tripadvisor Scraper: Intelligent Travel Analytics for Competitive Advantage

import requests
from bs4 import BeautifulSoup

HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
    "Accept-Language": "en-US,en;q=0.9",
}

def scrape_tripadvisor_hotel(url):
    response = requests.get(url, headers=HEADERS)
    if response.status_code != 200:
        return None
    
    soup = BeautifulSoup(response.text, "lxml")
    
    hotel_name = soup.find("h1")
    price = soup.find("span", {"class": "price"})
    rating = soup.find("span", {"class": "rating"})
    reviews = soup.find("span", {"class": "reviewCount"})
    
    return {
        "Hotel_Name": hotel_name.text.strip() if hotel_name else "N/A",
        "Price_Per_Night": price.text.strip() if price else "N/A",
        "Rating": rating.text.strip() if rating else "N/A",
        "Total_Reviews": reviews.text.strip() if reviews else "N/A"
    }

# Example Tripadvisor hotel URL
tripadvisor_url = "https://www.tripadvisor.com/Hotel_Review-example"
hotel_data = scrape_tripadvisor_hotel(tripadvisor_url)

print(hotel_data)