gfwlist2pac.py 文件源码

def reduce_domains(domains):
    # reduce 'www.google.com' to 'google.com'
    # remove invalid domains
    tld_content = pkgutil.get_data('gfwlist2pac', 'resources/tld.txt')
    tlds = set(tld_content.splitlines(False))
    new_domains = set()
    for domain in domains:
        domain_parts = domain.split('.')
        last_root_domain = None
        for i in xrange(0, len(domain_parts)):
            root_domain = '.'.join(domain_parts[len(domain_parts) - i - 1:])
            if i == 0:
                if not tlds.__contains__(root_domain):
                    # root_domain is not a valid tld
                    break
            last_root_domain = root_domain
            if tlds.__contains__(root_domain):
                continue
            else:
                break
        if last_root_domain is not None:
            new_domains.add(last_root_domain)
    return new_domains