bpo-32861: urllib.robotparser fix incomplete __str__ methods. (GH-5711)

The urllib.robotparser's __str__ representation now includes wildcard
entries and the "Crawl-delay" and "Request-rate" fields. Also removes extra
newlines that were being appended to the end of the string.
This commit is contained in:
Michael Lazar 2018-05-14 10:10:41 -04:00 committed by Serhiy Storchaka
parent 5c0d462689
commit bd08a0af2d
3 changed files with 42 additions and 5 deletions

View file

@ -246,6 +246,32 @@ Disallow: /cyberworld/map/
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):