diff options
| author | Victor Stinner <victor.stinner@gmail.com> | 2017-06-20 13:37:24 (GMT) |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2017-06-20 13:37:24 (GMT) |
| commit | 536c1f1246f4faa302f9f5613fc3444e7ae09b4a (patch) | |
| tree | 699718dbe3fa36c47e03dab75a8bfd68e2b5a6ff /Lib/urllib/parse.py | |
| parent | 0a4fe1d8578fa59004518f8deef137282be4d71a (diff) | |
| download | cpython-536c1f1246f4faa302f9f5613fc3444e7ae09b4a.zip cpython-536c1f1246f4faa302f9f5613fc3444e7ae09b4a.tar.gz cpython-536c1f1246f4faa302f9f5613fc3444e7ae09b4a.tar.bz2 | |
bpo-30500: urllib: Simplify splithost by calling into urlparse. (#1849) (#2289)
The current regex based splitting produces a wrong result. For example::
http://abc#@def
Web browsers parse that URL as ``http://abc/#@def``, that is, the host
is ``abc``, the path is ``/``, and the fragment is ``#@def``.
(cherry picked from commit 90e01e50ef8a9e6c91f30d965563c378a4ad26de)
Diffstat (limited to 'Lib/urllib/parse.py')
| -rw-r--r-- | Lib/urllib/parse.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py index 888247b..3cab2d1 100644 --- a/Lib/urllib/parse.py +++ b/Lib/urllib/parse.py @@ -944,7 +944,7 @@ def splithost(url): """splithost('//host[:port]/path') --> 'host[:port]', '/path'.""" global _hostprog if _hostprog is None: - _hostprog = re.compile('//([^/?]*)(.*)', re.DOTALL) + _hostprog = re.compile('//([^/#?]*)(.*)', re.DOTALL) match = _hostprog.match(url) if match: |