StreetEasy Scraper: NYC Property Listings and Rental Market Intelligence

import requests
from bs4 import BeautifulSoup

HEADERS = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7)",
    "Accept-Language": "en-US,en;q=0.8"
}

def scrape_streeteasy_listing(url):
    response = requests.get(url, headers=HEADERS, timeout=10)
    
    if response.status_code != 200:
        print(f"Request failed with status: {response.status_code}")
        return None

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

    def extract_text(tag, attrs):
        element = soup.find(tag, attrs=attrs)
        return element.get_text(strip=True) if element else "N/A"

    listing_data = {
        "Listing_Title": extract_text("h1", {"data-testid": "listing-title"}),
        "Price": extract_text("span", {"data-testid": "price"}),
        "Property_Type": extract_text("div", {"data-testid": "property-type"}),
        "Location": extract_text("address", {"data-testid": "address"}),
        "Beds_Baths": extract_text("div", {"data-testid": "beds-baths"}),
        "Availability_Status": extract_text("div", {"data-testid": "availability-status"})
    }

    return listing_data

# Example StreetEasy listing URL
streeteasy_url = "https://streeteasy.com/building/example-listing"
data = scrape_streeteasy_listing(streeteasy_url)

print(data)