Merged revisions 83238 via svnmerge from

svn+ssh://pythondev@svn.python.org/python/branches/py3k

........
  r83238 | georg.brandl | 2010-07-29 19:55:01 +0200 (Do, 29 Jul 2010) | 1 line

  #4108: the first default entry (User-agent: *) wins.
........

diff --git a/Lib/robotparser.py b/Lib/robotparser.py
index 730426f6ae75e551d1e5aa49834b829621308f70..1722863d144db7fc1956292892ebf49dc3f0cd3a 100644 (file)
--- a/Lib/robotparser.py
+++ b/Lib/robotparser.py
@@ -68,7 +68,9 @@ class RobotFileParser:
     def _add_entry(self, entry):
         if "*" in entry.useragents:
             # the default entry is considered last
-            self.default_entry = entry
+            if self.default_entry is None:
+                # the first default entry wins
+                self.default_entry = entry
         else:
             self.entries.append(entry)
 
@@ -120,7 +122,7 @@ class RobotFileParser:
                         entry.rulelines.append(RuleLine(line[1], True))
                         state = 2
         if state == 2:
-            self.entries.append(entry)
+            self._add_entry(entry)
 
 
     def can_fetch(self, useragent, url):

diff --git a/Lib/test/test_robotparser.py b/Lib/test/test_robotparser.py
index 04158841077fc53dcbc30e773becb3e4d7aa6638..aa73ec5663d9c078c4d54e97483b9c726a7d08f1 100644 (file)
--- a/Lib/test/test_robotparser.py
+++ b/Lib/test/test_robotparser.py
@@ -213,6 +213,20 @@ bad = ['/some/path?name=value']
 
 RobotTest(14, doc, good, bad)
 
+# 15. For issue #4108 (obey first * entry)
+doc = """
+User-agent: *
+Disallow: /some/path
+
+User-agent: *
+Disallow: /another/path
+"""
+
+good = ['/another/path']
+bad = ['/some/path']
+
+RobotTest(15, doc, good, bad)
+
 
 class NetworkTestCase(unittest.TestCase):
 

diff --git a/Misc/NEWS b/Misc/NEWS
index 3326e067ffb21a37e212ec297a3545a8b0001143..175e11711b91fc23d5021cece03e1910a82c0494 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -24,6 +24,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #4108: In urllib.robotparser, if there are multiple 'User-agent: *'
+  entries, consider the first one.
+
 - Issue #8397: Raise an error when attempting to mix iteration and regular
   reads on a BZ2File object, rather than returning incorrect results.