Function is_valid_medium_url

medium-parser/medium_parser/utils.py:420–450

Check if the url is a valid Medium article page Check if the domain is in the known Medium domains and subdomains list. If the doman/subdomain is in the list, then the url is valid

(url: str)

@alru_cache(maxsize=100)
async def is_valid_medium_url(url: str) -> bool:
    """
    Check if the url is a valid Medium article page

    Check if the domain is in the known Medium domains and subdomains list. If the doman/subdomain is in the list, then the url is valid
    """
    domain = get_fld(url)
    parsed_url = urlparse(url)
    domain_netloc = un_wwwify(parsed_url.netloc)

    # TODO: http://freedium.cfd/https://www.google.com.vn/url?sa=i&url=https%3A%2F%2Fmedium.com%2F%40dugguRK%2Fabout-android-hardware-abstraction-layer-hal-5d191dafeb2c&psig=AOvVaw17KP0U_haPMmhAByeMTxSg&ust=1711354113283000&source=images&cd=vfe&opi=89978449&ved=0CBQQjhxqFwoTCMCM_oG5jIUDFQAAAAAdAAAAABAa

    if domain in ["12ft.io", "google.com", "facebook.com", "googleusercontent.com"]:
        return True

    if domain in NOT_MEDIUM_DOMAINS or domain_netloc in NOT_MEDIUM_DOMAINS:
        raise exceptions.NotValidMediumURL("100% not valid Medium URL")

    if domain in KNOWN_MEDIUM_DOMAINS or domain_netloc in KNOWN_MEDIUM_CUSTOM_DOMAINS:
        return True

    logger.warning(f"url '{url}' wasn't detected in known Medium domains")

    # XXX: Unfourtunately, for now we don't know ALL Medium's domains, so we need resolve links
    resolve_result = bool(await resolve_medium_url(url))

    # send_message(f"We found that {domain=}, {domain_netloc=} is not listed in out known Medium database.\nURL: {url}")

    return resolve_result

    # return False