Hopiu/linkchecker
1
0
Fork 0
mirror of https://github.com/Hopiu/linkchecker.git synced 2026-05-02 03:44:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Make TestRobotsTxt Python 3.7 compatible

Browse source 
urllib.parse.quote() moved from RFC 2396 to RFC 3986 for quoting URL
strings. "~" is now included in the set of reserved characters.

https://docs.python.org/3/library/urllib.parse.html#urllib.parse.quote
This commit is contained in:
Chris Mayo 2019-04-22 19:50:32 +01:00
parent 5d26d2d93e
commit 8678feaa59
1 changed files with 5 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
tests/test_robotstxt.py
View file

@ -18,6 +18,7 @@
Test robots.txt parsing. Test robots.txt parsing.
""" """
import sys
import unittest import unittest
import linkcheck.robotparser2 import linkcheck.robotparser2
@ -224,7 +225,8 @@ class TestRobotsTxt (unittest.TestCase):
"Disallow: /tmp", "Disallow: /tmp",
"Disallow: /a%3Cd.html", "Disallow: /a%3Cd.html",
"Disallow: /a/b.html", "Disallow: /a/b.html",
"Disallow: /%7Ejoe/index.html", "Disallow: /%7Ejoe/index.html" if sys.version_info < (3, 7) \
else "Disallow: /~joe/index.html",
] ]
self.rp.parse(lines) self.rp.parse(lines)
self.assertEqual(str(self.rp), "\n".join(lines2)) self.assertEqual(str(self.rp), "\n".join(lines2))
@ -249,7 +251,8 @@ class TestRobotsTxt (unittest.TestCase):
"Disallow: /tmp/", "Disallow: /tmp/",
"Disallow: /a%3Cd.html", "Disallow: /a%3Cd.html",
"Disallow: /a/b.html", "Disallow: /a/b.html",
"Disallow: /%7Ejoe/index.html", "Disallow: /%7Ejoe/index.html" if sys.version_info < (3, 7) \
else "Disallow: /~joe/index.html",
] ]
self.rp.parse(lines) self.rp.parse(lines)
self.assertEqual(str(self.rp), "\n".join(lines2)) self.assertEqual(str(self.rp), "\n".join(lines2))