Biedronka Scraper: Advanced Grocery Data Collection for Competitive Retail Intelligence

import requests
from bs4 import BeautifulSoup

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

def scrape_biedronka_product(product_url):
    response = requests.get(
        product_url,
        headers=HEADERS,
        timeout=15
    )

    if response.status_code != 200:
        return {
            "Error": f"Request failed: HTTP {response.status_code}"
        }

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

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

    return {
        "Product Name": extract_text("h1"),
        "Price": extract_text('[itemprop="price"]'),
        "Brand": extract_text('[itemprop="brand"]'),
        "Availability": extract_text('[itemprop="availability"]'),
        "Product Category": extract_text(
            '[itemprop="category"]'
        ),
    }

# Replace with an authorized, publicly accessible product page URL.
biedronka_product_url = "https://example.com/product-page"

product_data = scrape_biedronka_product(biedronka_product_url)
print(product_data)