Fix Issue6325 - robotparse to honor urls with query strings.

orsenthil · orsenthil · commit 3f8ab965f722 · 2010-07-28T16:27:56.000Z
diff --git a/Lib/test/test_robotparser.py b/Lib/test/test_robotparser.py
@@ -205,6 +205,17 @@ def RobotTest(index, robots_txt, good_urls, bad_urls,
 RobotTest(13, doc, good, bad, agent="googlebot")
 
 
+# 14. For issue #6325 (query string support)
+doc = """
+User-agent: *
+Disallow: /some/path?name=value
+"""
+
+good = ['/some/path']
+bad = ['/some/path?name=value']
+
+RobotTest(14, doc, good, bad)
+
 
 class NetworkTestCase(unittest.TestCase):
 
diff --git a/Lib/urllib/robotparser.py b/Lib/urllib/robotparser.py
@@ -129,8 +129,10 @@ def can_fetch(self, useragent, url):
             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:
