.. versionchanged:: 3.2
Result is a structured object rather than a simple 2-tuple.
+.. function:: unwrap(url)
+
+ Extract the url from a wrapped URL (that is, a string formatted as
+ ``<URL:scheme://host/path>``, ``<scheme://host/path>``, ``URL:scheme://host/path``
+ or ``scheme://host/path``). If *url* is not a wrapped URL, it is returned
+ without changes.
+
.. _parsing-ascii-encoded-bytes:
Parsing ASCII Encoded Bytes
library/urllib.request,,:port,:port
library/urllib.request,,:lang,"xmlns=""http://www.w3.org/1999/xhtml"" xml:lang=""en"" lang=""en"">\n\n<head>\n"
library/urllib.request,,:password,"""joe:password@python.org"""
+library/urllib.parse,,:scheme,<URL:scheme://host/path>
+library/urllib.parse,,:scheme,URL:scheme://host/path
library/uuid,,:uuid,urn:uuid:12345678-1234-5678-1234-567812345678
library/venv,,:param,":param nodist: If True, setuptools and pip are not installed into the"
library/venv,,:param,":param progress: If setuptools or pip are installed, the progress of the"
'http://www.python.org/medi\u00e6val')
def test_unwrap(self):
- url = urllib.parse._unwrap('<URL:type://host/path>')
- self.assertEqual(url, 'type://host/path')
+ for wrapped_url in ('<URL:scheme://host/path>', '<scheme://host/path>',
+ 'URL:scheme://host/path', 'scheme://host/path'):
+ url = urllib.parse.unwrap(wrapped_url)
+ self.assertEqual(url, 'scheme://host/path')
class DeprecationTest(unittest.TestCase):
self.assertEqual(str(cm.warning),
'urllib.parse.to_bytes() is deprecated as of 3.8')
- def test_unwrap(self):
- with self.assertWarns(DeprecationWarning) as cm:
- urllib.parse.unwrap('')
- self.assertEqual(str(cm.warning),
- 'urllib.parse.unwrap() is deprecated as of 3.8')
-
if __name__ == "__main__":
unittest.main()
def unwrap(url):
- warnings.warn("urllib.parse.unwrap() is deprecated as of 3.8",
- DeprecationWarning, stacklevel=2)
- return _unwrap(url)
-
+ """Transform a string like '<URL:scheme://host/path>' into 'scheme://host/path'.
-def _unwrap(url):
- """unwrap('<URL:type://host/path>') --> 'type://host/path'."""
+ The string is returned unchanged if it's not a wrapped URL.
+ """
url = str(url).strip()
if url[:1] == '<' and url[-1:] == '>':
url = url[1:-1].strip()
- if url[:4] == 'URL:': url = url[4:].strip()
+ if url[:4] == 'URL:':
+ url = url[4:].strip()
return url
from urllib.error import URLError, HTTPError, ContentTooShortError
from urllib.parse import (
- urlparse, urlsplit, urljoin, _unwrap, quote, unquote,
+ urlparse, urlsplit, urljoin, unwrap, quote, unquote,
_splittype, _splithost, _splitport, _splituser, _splitpasswd,
_splitattr, _splitquery, _splitvalue, _splittag, _to_bytes,
unquote_to_bytes, urlunparse)
@full_url.setter
def full_url(self, url):
# unwrap('<URL:type://host/path>') --> 'type://host/path'
- self._full_url = _unwrap(url)
+ self._full_url = unwrap(url)
self._full_url, self.fragment = _splittag(self._full_url)
self._parse()
# External interface
def open(self, fullurl, data=None):
"""Use URLopener().open(file) instead of open(file, 'r')."""
- fullurl = _unwrap(_to_bytes(fullurl))
+ fullurl = unwrap(_to_bytes(fullurl))
fullurl = quote(fullurl, safe="%/:=&?~#+!$,;'@()*[]|")
if self.tempcache and fullurl in self.tempcache:
filename, headers = self.tempcache[fullurl]
def retrieve(self, url, filename=None, reporthook=None, data=None):
"""retrieve(url) returns (filename, headers) for a local object
or (tempfilename, headers) for a remote object."""
- url = _unwrap(_to_bytes(url))
+ url = unwrap(_to_bytes(url))
if self.tempcache and url in self.tempcache:
return self.tempcache[url]
type, url1 = _splittype(url)
--- /dev/null
+Remove deprecation and document urllib.parse.unwrap(). Patch contributed by
+Rémi Lapeyre.