from urllib.parse import urldefrag
import tldextract


def append_to_results(results, key, value):
    if key not in results:
        results[key] = []
    results[key].append(value)


def clean_url(url):
    url, __ = urldefrag(url)  # remove anchors
    return url


def get_domain(url):
    if not url:
        return
    is_a_real_src = url.startswith("http") or url.startswith("/")
    if not is_a_real_src:
        return
    ext = tldextract.extract(url)
    return '{}.{}'.format(ext.domain, ext.suffix)