delim = min(delim, wdelim) # use earliest delim position

return url[start:delim], url[delim:] # return (domain, rest)

def _checknetloc(netloc):

if not netloc or netloc.isascii():

return

# looking for characters like \u2100 that expand to 'a/c'

# IDNA uses NFKC equivalence, so normalize for this check

import unicodedata

netloc2 = unicodedata.normalize('NFKC', netloc)

if netloc == netloc2:

return

_, _, netloc = netloc.rpartition('@') # anything to the left of '@' is okay

for c in '/?#@:':

if c in netloc2:

raise ValueError("netloc '" + netloc2 + "' contains invalid " +

"characters under NFKC normalization")

def urlsplit(url, scheme='', allow_fragments=True):

"""Parse a URL into 5 components:

<scheme>://<netloc>/<path>?<query>#<fragment>

url, fragment = url.split('#', 1)

if '?' in url:

url, query = url.split('?', 1)

_checknetloc(netloc)

v = SplitResult('http', netloc, url, query, fragment)

_parse_cache[key] = v

return _coerce_result(v)

url, fragment = url.split('#', 1)

if '?' in url:

url, query = url.split('?', 1)

_checknetloc(netloc)

v = SplitResult(scheme, netloc, url, query, fragment)

_parse_cache[key] = v

return _coerce_result(v)