[3.7] bpo-32861: urllib.robotparser fix incomplete __str__ methods. (GH-5711) (GH-6795)
The urllib.robotparser's __str__ representation now includes wildcard
entries and the "Crawl-delay" and "Request-rate" fields.
(cherry picked from commit bd08a0af2d88c590ede762102bd42da3437e9980)
Co-authored-by: Michael Lazar <lazar.michael22@gmail.com>
diff --git a/Lib/test/test_robotparser.py b/Lib/test/test_robotparser.py
index 75198b7..1406365 100644
--- a/Lib/test/test_robotparser.py
+++ b/Lib/test/test_robotparser.py
@@ -246,6 +246,33 @@
bad = ['/cyberworld/map/index.html']
+class StringFormattingTest(BaseRobotTest, unittest.TestCase):
+ robots_txt = """\
+User-agent: *
+Crawl-delay: 1
+Request-rate: 3/15
+Disallow: /cyberworld/map/ # This is an infinite virtual URL space
+
+# Cybermapper knows where to go.
+User-agent: cybermapper
+Disallow: /some/path
+ """
+
+ expected_output = """\
+User-agent: cybermapper
+Disallow: /some/path
+
+User-agent: *
+Crawl-delay: 1
+Request-rate: 3/15
+Disallow: /cyberworld/map/
+
+"""
+
+ def test_string_formatting(self):
+ self.assertEqual(str(self.parser), self.expected_output)
+
+
class RobotHandler(BaseHTTPRequestHandler):
def do_GET(self):