Function parse_url

src/urllib3/util/url.py:367–469

Given a url, return a parsed :class:`.Url` namedtuple. Best-effort is performed to parse incomplete urls. Fields not provided will be None. This parser is RFC 3986 and RFC 6874 compliant. The parser logic and helper functions are based heavily on work done in the ``rfc3986`` mo

(url: str)

def parse_url(url: str) -> Url:
    """
    Given a url, return a parsed :class:`.Url` namedtuple. Best-effort is
    performed to parse incomplete urls. Fields not provided will be None.
    This parser is RFC 3986 and RFC 6874 compliant.

    The parser logic and helper functions are based heavily on
    work done in the ``rfc3986`` module.

    :param str url: URL to parse into a :class:`.Url` namedtuple.

    Partly backwards-compatible with :mod:`urllib.parse`.

    Example:

    .. code-block:: python

        import urllib3

        print( urllib3.util.parse_url('http://google.com/mail/'))
        # Url(scheme='http', host='google.com', port=None, path='/mail/', ...)

        print( urllib3.util.parse_url('google.com:80'))
        # Url(scheme=None, host='google.com', port=80, path=None, ...)

        print( urllib3.util.parse_url('/foo?bar'))
        # Url(scheme=None, host=None, port=None, path='/foo', query='bar', ...)
    """
    if not url:
        # Empty
        return Url()

    source_url = url
    if not _SCHEME_RE.search(url):
        url = "//" + url

    scheme: str | None
    authority: str | None
    auth: str | None
    host: str | None
    port: str | None
    port_int: int | None
    path: str | None
    query: str | None
    fragment: str | None

    try:
        scheme, authority, path, query, fragment = _URI_RE.match(url).groups()  # type: ignore[union-attr]
        normalize_uri = scheme is None or scheme.lower() in _NORMALIZABLE_SCHEMES

        if scheme:
            scheme = scheme.lower()

        if authority:
            auth, _, host_port = authority.rpartition("@")
            auth = auth or None
            host, port = _HOST_PORT_RE.match(host_port).groups()  # type: ignore[union-attr]
            if auth and normalize_uri: