Sreality Scraper: Efficient Property Listing Analysis for Investment Opportunities

import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin

BASE_URL = "https://www.sreality.cz"

HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
    "Accept-Language": "cs-CZ,cs;q=0.9,en;q=0.8",
}

def scrape_sreality_listing(url):
    try:
        response = requests.get(
            url,
            headers=HEADERS,
            timeout=20
        )
        response.raise_for_status()

    except requests.RequestException as error:
        return {"Error": str(error)}

    soup = BeautifulSoup(response.text, "html.parser")

    def get_text(selector):
        element = soup.select_one(selector)
        return element.get_text(" ", strip=True) if element else "N/A"

    title = get_text("h1")
    price = get_text('[class*="price"]')
    location = get_text('[class*="location"]')
    area = get_text('[class*="area"]')

    link_element = soup.select_one("link[rel='canonical']")
    listing_url = (
        urljoin(BASE_URL, link_element.get("href", ""))
        if link_element
        else url
    )

    return {
        "Property Title": title,
        "Property Price": price,
        "Location": location,
        "Property Area": area,
        "Listing URL": listing_url
    }

# Example Sreality listing URL
listing_url = "https://www.sreality.cz/"

property_data = scrape_sreality_listing(listing_url)
print(property_data)