Beautiful Soup Scraper: Advanced HTML Parsing for Clean Structured Data Collection

import requests
from bs4 import BeautifulSoup

HEADERS = {
    "User-Agent": "Mozilla/5.0 (X11; Linux x86_64)",
    "Accept-Language": "en-US,en;q=0.8"
}

def fetch_product_details(page_url):
    try:
        response = requests.get(page_url, headers=HEADERS, timeout=10)
        response.raise_for_status()
    except requests.exceptions.RequestException:
        return {"error": "Failed to retrieve page"}

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

    def extract_text(tag, class_name):
        element = soup.find(tag, class_=class_name)
        return element.get_text(strip=True) if element else "Not Available"

    product_info = {
        "Product Name": extract_text("h1", "item-title"),
        "Current Price": extract_text("span", "price-value"),
        "User Rating": extract_text("div", "rating-score"),
        "Availability": extract_text("p", "stock-status")
    }

    return product_info

# Example product page URL
sample_url = "https://www.example.com/item/sample-product"

result = fetch_product_details(sample_url)
print(result)