Realtor.com Scraper: Intelligent Property Listings and Real Estate Data Extraction

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_realtor_listing(url):
response = requests.get(url, headers=HEADERS)

if response.status_code != 200:
print("Failed to fetch page:", response.status_code)
return None

soup = BeautifulSoup(response.text, "lxml")

data = {
"Property Title": soup.find("h1", {"data-testid": "headline"}).text.strip() if soup.find("h1", {"data-testid": "headline"}) else "N/A",
"Price": soup.find("span", {"data-testid": "price"}).text.strip() if soup.find("span", {"data-testid": "price"}) else "N/A",
"Location": soup.find("div", {"data-testid": "address"}).text.strip() if soup.find("div", {"data-testid": "address"}) else "N/A",
"Beds": soup.find("li", {"data-testid": "property-meta-beds"}).text.strip() if soup.find("li", {"data-testid": "property-meta-beds"}) else "N/A",
"Baths": soup.find("li", {"data-testid": "property-meta-baths"}).text.strip() if soup.find("li", {"data-testid": "property-meta-baths"}) else "N/A",
"Area": soup.find("li", {"data-testid": "property-meta-sqft"}).text.strip() if soup.find("li", {"data-testid": "property-meta-sqft"}) else "N/A",
"Listing Status": soup.find("div", {"data-testid": "status"}).text.strip() if soup.find("div", {"data-testid": "status"}) else "N/A"
}

return data

# Example Realtor.com listing URL
realtor_url = "https://www.realtor.com/realestateandhomes-detail/example"

result = scrape_realtor_listing(realtor_url)

# Print extracted data
print(result)