from bs4 import BeautifulSoup
import requests
from urllib.parse import urlparse

async def get_link_preview(url):
    try:
        # Ensure the URL has a scheme
        parsed_url = urlparse(url)
        if not parsed_url.scheme:
            # Default to 'https' if the scheme is missing
            url = f'https://{url}'
            parsed_url = urlparse(url)

        # Validate the URL scheme
        if parsed_url.scheme not in ['http', 'https']:
            raise ValueError("Only 'http' and 'https' protocols are allowed.")

        # Perform the HTTP request
        response = requests.get(url)
        if response.status_code != 200:
            return {}

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

        metadata = {
            "title": soup.find('meta', property='og:title') or 
                     soup.find('meta', attrs={'name': 'twitter:title'}) 
                     or soup.title.string,
            "description": soup.find('meta', property='og:description') or 
                           soup.find('meta', attrs={'name': 'twitter:description'}) or 
                           soup.find('meta', attrs={'name': 'description'}),
            "img": soup.find('meta', property='og:image') or 
                   soup.find('meta', attrs={'name': 'twitter:image'}) or 
                   soup.find('link', rel='image_src') or 
                   soup.find('img')['src'] if soup.find('img') 
                   else None,
            "url": soup.find('meta', property='og:url') or url,
            "sitename": parsed_url.hostname #soup.find('meta', property='og:site_name')
        }

        # Clean up metadata
        for key, value in metadata.items():
            if value and hasattr(value, 'get'):
                metadata[key] = value.get('content')
        return metadata
    except Exception as e:
        raise Exception(e)
        #return {}