Extract Schema.org Structured Data from Any Website in Python

import requests
from bs4 import BeautifulSoup
import json

def extract_schema_org(url):
    """Extract structured data (Schema.org) from a website."""
    try:
        response = requests.get(url, timeout=10)
        response.raise_for_status()
    except requests.exceptions.RequestException as e:
        return {"error": f"Failed to fetch URL: {e}"}

    soup = BeautifulSoup(response.text, 'html.parser')
    schema_data = []

    # Find all script tags with type="application/ld+json"
    for script in soup.find_all('script', type='application/ld+json'):
        try:
            data = json.loads(script.string)
            schema_data.append(data)
        except (json.JSONDecodeError, TypeError):
            continue

    if not schema_data:
        # Fall back to checking for other common Schema patterns (e.g., microdata)
        # For simplicity, return empty list if no JSON-LD found
        return {"message": "No Schema.org data found (JSON-LD format).", "data": []}

    return {"url": url, "schema_count": len(schema_data), "data": schema_data}

if __name__ == "__main__":
    test_url = "https://schema.org/docs/gs.html"  # Example page that may contain Schema.org data
    result = extract_schema_org(test_url)
    print(json.dumps(result, indent=2, default=str))