From 0a0fc07d371a97c35a6fc7c5a9828af3930720a1 Mon Sep 17 00:00:00 2001 From: Georg Brandl Date: Thu, 29 Jul 2010 17:55:01 +0000 Subject: #4108: the first default entry (User-agent: *) wins. --- Lib/test/test_robotparser.py | 14 ++++++++++++++ Lib/urllib/robotparser.py | 6 ++++-- Misc/NEWS | 3 +++ 3 files changed, 21 insertions(+), 2 deletions(-) diff --git a/Lib/test/test_robotparser.py b/Lib/test/test_robotparser.py index 9d30405..fd00706 100644 --- a/Lib/test/test_robotparser.py +++ b/Lib/test/test_robotparser.py @@ -216,6 +216,20 @@ 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/Lib/urllib/robotparser.py b/Lib/urllib/robotparser.py index 30baa05..75be4af 100644 --- a/Lib/urllib/robotparser.py +++ b/Lib/urllib/robotparser.py @@ -66,7 +66,9 @@ 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) @@ -118,7 +120,7 @@ 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/Misc/NEWS b/Misc/NEWS index 26a5599..a4d301f 100644 --- a/Misc/NEWS +++ b/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. -- cgit v0.12