mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-07-25 04:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

Fix Issue6325 - robotparse to honor urls with query strings.

Browse source
This commit is contained in:
Senthil Kumaran 2010-07-28 16:27:56 +00:00
parent 96a60ae90c
commit 3f8ab965f7
2 changed files with 15 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

6
Lib/urllib/robotparser.py
View file

@ -129,8 +129,10 @@ class RobotFileParser:
return True
# search for given user agent matches
# the first match counts
url = urllib.parse.quote(
urllib.parse.urlparse(urllib.parse.unquote(url))[2])
parsed_url = urllib.parse.urlparse(urllib.parse.unquote(url))
url = urllib.parse.urlunparse(('','',parsed_url.path,
parsed_url.params,parsed_url.query, parsed_url.fragment))
url = urllib.parse.quote(url)
if not url:
url = "/"
for entry in self.entries: