Instacart Scraper: Advanced Grocery Intelligence and Store-Level Insights

import requests
from bs4 import BeautifulSoup

# Headers to mimic a browser request
REQUEST_HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
    "Accept-Language": "en-US,en;q=0.8",
}

def scrape_instacart_product(product_url):
    """
    Scrapes product details from an Instacart product page
    including name, price, rating, and stock availability.
    """
    response = requests.get(product_url, headers=REQUEST_HEADERS)
    if response.status_code != 200:
        print("Failed to fetch page:", response.status_code)
        return None

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

    product_name = soup.select_one("h1")
    product_price = soup.select_one("span[data-testid='price']")
    product_rating = soup.select_one("span[data-testid='rating']")
    availability_status = soup.select_one("div[data-testid='availability']")

    product_data = {
        "Product Name": product_name.get_text(strip=True) if product_name else "Unavailable",
        "Price": product_price.get_text(strip=True) if product_price else "Unavailable",
        "Rating": product_rating.get_text(strip=True) if product_rating else "Unavailable",
        "Availability": availability_status.get_text(strip=True) if availability_status else "Unavailable"
    }

    return product_data

# Example Instacart product URL (Replace with actual Instacart product URL)
instacart_product_url = "https://www.instacart.com/products/example-item"
data = scrape_instacart_product(instacart_product_url)

# Print extracted data
print(data)