#17403: urllib.parse.robotparser normalizes the urls before adding to ruleline.

This helps in handling certain types invalid urls in a conservative manner.

Author: orsenthil

Lib/test/test_robotparser.py

@@ -234,6 +234,18 @@ def RobotTest(index, robots_txt, good_urls, bad_urls,
 
 RobotTest(15, doc, good, bad)
 
+# 16. Empty query (issue #17403). Normalizing the url first.
+doc = """
+User-agent: *
+Allow: /some/path?
+Disallow: /another/path?
+"""
+
+good = ['/some/path?']
+bad = ['/another/path?']
+
+RobotTest(16, doc, good, bad)
+
 
 class NetworkTestCase(unittest.TestCase):
 

Lib/urllib/robotparser.py

@@ -157,6 +157,7 @@ def __init__(self, path, allowance):
         if path == '' and not allowance:
             # an empty value means allow all
             allowance = True
+        path = urllib.parse.urlunparse(urllib.parse.urlparse(path))
         self.path = urllib.parse.quote(path)
         self.allowance = allowance
 

Misc/NEWS

@@ -24,6 +24,10 @@ Core and Builtins
 Library
 -------
 
+- Issue #17403: urllib.parse.robotparser normalizes the urls before adding to
+  ruleline. This helps in handling certain types invalid urls in a conservative
+  manner.
+
 - Issue #18025: Fixed a segfault in io.BufferedIOBase.readinto() when raw
   stream's read() returns more bytes than requested.