Sephora Scraper: Real-Time Makeup and Skincare Data Extraction Solution

import requests
from bs4 import BeautifulSoup

HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
    "Accept-Language": "en-US,en;q=0.9",
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"
}

def scrape_sephora_product(product_url):
    try:
        response = requests.get(product_url, headers=HEADERS, timeout=15)
        if response.status_code != 200:
            return {"Error": f"Request failed with status code {response.status_code}"}

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

        title_tag = soup.select_one("h1")
        price_tag = soup.select_one("span[data-at='price']")
        rating_tag = soup.select_one("span[aria-label*='stars']")
        availability_tag = soup.select_one("div[data-at='add-to-basket']")

        product_title = title_tag.get_text(strip=True) if title_tag else "N/A"
        product_price = price_tag.get_text(strip=True) if price_tag else "N/A"
        product_rating = rating_tag.get_text(strip=True) if rating_tag else "N/A"
        stock_status = "Available" if availability_tag else "Out of Stock"

        return {
            "Product Name": product_title,
            "Product Price": product_price,
            "Customer Rating": product_rating,
            "Availability Status": stock_status,
            "Product URL": product_url
        }

    except Exception as e:
        return {"Error": str(e)}

# Example Sephora product URL
sephora_product_url = "https://www.sephora.com/product/example-product"
output_data = scrape_sephora_product(sephora_product_url)

print(output_data)