Extract Every Open Graph and Social Media Meta Tag from Web Pages in Python

from html.parser import HTMLParser
import re
from urllib.request import urlopen
from urllib.parse import urlparse

class MetaExtractor(HTMLParser):
    def __init__(self):
        super().__init__()
        self.meta_tags = []
    
    def handle_starttag(self, tag, attrs):
        if tag == 'meta':
            attrs_dict = dict(attrs)
            prop = attrs_dict.get('property', '') or attrs_dict.get('name', '')
            if any(prefix in prop for prefix in ['og:', 'twitter:', 'fb:', 'article:']):
                content = attrs_dict.get('content', '')
                if prop and content:
                    self.meta_tags.append((prop, content))
    
    def get_meta(self):
        return self.meta_tags

def extract_social_meta(url: str) -> list:
    try:
        with urlopen(url, timeout=5) as response:
            html = response.read().decode('utf-8', errors='ignore')
        extractor = MetaExtractor()
        extractor.feed(html)
        return extractor.get_meta()
    except Exception as e:
        print(f"Error fetching {url}: {e}")
        return []

if __name__ == "__main__":
    test_url = "https://example.com"
    print(f"Extracting social meta tags from: {test_url}")
    results = extract_social_meta(test_url)
    for prop, content in results:
        print(f"{prop}: {content}")
    if not results:
        print("No OpenGraph or social media meta tags found.")