Little Farms Scraper: Real-Time Grocery Product and Pricing Data Collection

import requests
import json
from bs4 import BeautifulSoup

HEADERS = {"User-Agent": "Mozilla/5.0"}

def scrape_little_farms(url):
    response = requests.get(url, headers=HEADERS, timeout=15)
    response.raise_for_status()
    soup = BeautifulSoup(response.text, "html.parser")

    for script in soup.select('script[type="application/ld+json"]'):
        try:
            data = json.loads(script.string or script.get_text())
        except (json.JSONDecodeError, TypeError):
            continue

        items = data if isinstance(data, list) else (
            data.get("@graph", [data]) if isinstance(data, dict) else []
        )

        for item in items:
            if not isinstance(item, dict):
                continue
            if "Product" in ([item.get("@type")] if isinstance(item.get("@type"), str)
                             else item.get("@type", [])):
                offer = item.get("offers", {})
                if isinstance(offer, list):
                    offer = offer[0] if offer else {}

                return {
                    "Product": item.get("name", "N/A"),
                    "Price": offer.get("price", "N/A"),
                    "Currency": offer.get("priceCurrency", "SGD"),
                    "Availability": offer.get("availability", "N/A")
                }

    return {"Product": "N/A", "Price": "N/A",
            "Currency": "SGD", "Availability": "N/A"}

# Example Little Farms product page
url = "https://littlefarms.com/shop-groceries/fruit-vegetables/fruit/super-jumbo-blueberry-200g-7743"
print(scrape_little_farms(url))