diff options
author | Antoine Pitrou <solipsis@pitrou.net> | 2011-07-08 17:43:51 (GMT) |
---|---|---|
committer | Antoine Pitrou <solipsis@pitrou.net> | 2011-07-08 17:43:51 (GMT) |
commit | 95531ea2f1c69eed6b8a5d964f0fd47c124ccca8 (patch) | |
tree | f17ece654d4df717ec7c45bd2d84b98ebed82b7d /Lib/test/test_robotparser.py | |
parent | 72fff046a6d96131d2a929699e6fc8875f57e452 (diff) | |
download | cpython-95531ea2f1c69eed6b8a5d964f0fd47c124ccca8.zip cpython-95531ea2f1c69eed6b8a5d964f0fd47c124ccca8.tar.gz cpython-95531ea2f1c69eed6b8a5d964f0fd47c124ccca8.tar.bz2 |
Avoid failing in test_robotparser when mueblesmoraleda.com is flaky and
an overzealous DNS service (e.g. OpenDNS) redirects to a placeholder
Web site.
Diffstat (limited to 'Lib/test/test_robotparser.py')
-rw-r--r-- | Lib/test/test_robotparser.py | 19 |
1 files changed, 17 insertions, 2 deletions
diff --git a/Lib/test/test_robotparser.py b/Lib/test/test_robotparser.py index 2a6d047..178761d 100644 --- a/Lib/test/test_robotparser.py +++ b/Lib/test/test_robotparser.py @@ -1,7 +1,8 @@ import io import unittest import urllib.robotparser -from urllib.error import URLError +from urllib.error import URLError, HTTPError +from urllib.request import urlopen from test import support class RobotTestCase(unittest.TestCase): @@ -237,13 +238,27 @@ class NetworkTestCase(unittest.TestCase): support.requires('network') with support.transient_internet('mueblesmoraleda.com'): url = 'http://mueblesmoraleda.com' + robots_url = url + "/robots.txt" + # First check the URL is usable for our purposes, since the + # test site is a bit flaky. + try: + urlopen(robots_url) + except HTTPError as e: + if e.code not in {401, 403}: + self.skipTest( + "%r should return a 401 or 403 HTTP error, not %r" + % (robots_url, e.code)) + else: + self.skipTest( + "%r should return a 401 or 403 HTTP error, not succeed" + % (robots_url)) parser = urllib.robotparser.RobotFileParser() parser.set_url(url) try: parser.read() except URLError: self.skipTest('%s is unavailable' % url) - self.assertEqual(parser.can_fetch("*", url+"/robots.txt"), False) + self.assertEqual(parser.can_fetch("*", robots_url), False) def testPythonOrg(self): support.requires('network') |