Using tldextract to remove www. safely and extract the domain name and its public suffix

extract_domain_name.py

def extract_domain_name(url):
    '''Extract the domain name from a given URL'''
    prefix_blacklist = ['www']
    parts = tldextract.extract(url)
    # We want to drop any prefixes mentioned in the blacklist
    # They typically do not add information that's useful to
    # distinguish the "identity" of a specific site

    # Sometimes the blacklisted domain is part of subdomain,
    # for example when parsing www.mail.example.com
    subdomain = parts.subdomain
    for prefix in prefix_blacklist:
        subdomain = parts.subdomain.replace(prefix_blacklist, '')

    if subdomain in prefix_blacklist:
        return '.'.join([parts.domain, parts.suffix])
    else:
        return '.'.join([subdomain, parts.domain, parts.suffix])