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

Lib/test/test_robotparser.py

@@ -216,6 +216,20 @@ def RobotTest(index, robots_txt, good_urls, bad_urls,
 
 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):
 

Lib/urllib/robotparser.py

@@ -66,7 +66,9 @@ def read(self):
     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)
 
@@ -118,7 +120,7 @@ def parse(self, lines):
                         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):

Misc/NEWS

@@ -475,6 +475,9 @@ C-API
 Library
 -------
 
+- Issue #4108: In urllib.robotparser, if there are multiple 'User-agent: *'
+  entries, consider the first one.
+
 - Issue #6630: Allow customizing regex flags when subclassing the
   string.Template class.