def get_domain_hyperlinks()

in web-qa.py [0:0]

• 23 lines of code
• 14 McCabe index (conditional complexity)

def get_domain_hyperlinks(local_domain, url):
    clean_links = []
    for link in set(get_hyperlinks(url)):
        clean_link = None

        # If the link is a URL, check if it is within the same domain
        if re.search(HTTP_URL_PATTERN, link):
            # Parse the URL and check if the domain is the same
            url_obj = urlparse(link)
            if url_obj.netloc == local_domain:
                clean_link = link

        # If the link is not a URL, check if it is a relative link
        else:
            if link.startswith("/"):
                link = link[1:]
            elif (
                link.startswith("#")
                or link.startswith("mailto:")
                or link.startswith("tel:")
            ):
                continue
            clean_link = "https://" + local_domain + "/" + link

        if clean_link is not None:
            if clean_link.endswith("/"):
                clean_link = clean_link[:-1]
            clean_links.append(clean_link)

    # Return the list of hyperlinks that are within the same domain
    return list(set(clean_links))