Allegro Scraper: Real-Time E-Commerce Analytics for Product and Price Optimization

import requests
from bs4 import BeautifulSoup

# Custom headers to mimic a browser visit
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
    "Accept-Language": "en-US,en;q=0.9",
}

def scrape_allegro_product(url):
    response = requests.get(url, headers=HEADERS)
    if response.status_code != 200:
        return None

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

    # Extracting product details from Allegro page
    product_data = {
        "Title": soup.find("h1", {"class": "mpof_6"}).text.strip() if soup.find("h1", {"class": "mpof_6"}) else "N/A",
        "Price": soup.find("span", {"class": "fee0_2"}).text.strip() if soup.find("span", {"class": "fee0_2"}) else "N/A",
        "Seller": soup.find("div", {"class": "fk9_0"}).text.strip() if soup.find("div", {"class": "fk9_0"}) else "N/A",
        "Availability": soup.find("span", {"class": "mpof_3"}).text.strip() if soup.find("span", {"class": "mpof_3"}) else "N/A",
        "Rating": soup.find("span", {"class": "mpof_8"}).text.strip() if soup.find("span", {"class": "mpof_8"}) else "N/A"
    }

    return product_data

# Example Allegro product URL
allegro_product_url = "https://allegro.pl/oferta/example-product"
data = scrape_allegro_product(allegro_product_url)

print(data)