annotate Lib/test/test_robotparser.py @ 70817:dd775b1561ba

Fix markup.
author Georg Brandl <georg@python.org>
date Tue, 14 Jun 2011 21:09:55 +0200
parents 3c9232a684ae
children 6e72490bbff6
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
42501
f6069f9dd52d SF patch# 1770008 by Christian Heimes (plus some extras).
Guido van Rossum <guido@python.org>
parents: 41554
diff changeset
1 import io
48334
5a416a6417d3 Make a new urllib package .
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 47201
diff changeset
2 import unittest
5a416a6417d3 Make a new urllib package .
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 47201
diff changeset
3 import urllib.robotparser
60202
5496503b8b1a Merged revision 79605 via svnmerge from
Florent Xicluna <florent.xicluna@gmail.com>
parents: 55593
diff changeset
4 from urllib.error import URLError
47201
9c930a32cebb #2621 rename test.test_support to test.support
Benjamin Peterson <benjamin@python.org>
parents: 43095
diff changeset
5 from test import support
22088
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
6
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
7 class RobotTestCase(unittest.TestCase):
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
8 def __init__(self, index, parser, url, good, agent):
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
9 unittest.TestCase.__init__(self)
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
10 if good:
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
11 self.str = "RobotTest(%d, good, %s)" % (index, url)
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
12 else:
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
13 self.str = "RobotTest(%d, bad, %s)" % (index, url)
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
14 self.parser = parser
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
15 self.url = url
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
16 self.good = good
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
17 self.agent = agent
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
18
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
19 def runTest(self):
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
20 if isinstance(self.url, tuple):
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
21 agent, url = self.url
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
22 else:
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
23 url = self.url
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
24 agent = self.agent
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
25 if self.good:
55593
0bb232078b8c Merged revisions 73715 via svnmerge from
Georg Brandl <georg@python.org>
parents: 48594
diff changeset
26 self.assertTrue(self.parser.can_fetch(agent, url))
22088
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
27 else:
55593
0bb232078b8c Merged revisions 73715 via svnmerge from
Georg Brandl <georg@python.org>
parents: 48594
diff changeset
28 self.assertFalse(self.parser.can_fetch(agent, url))
22088
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
29
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
30 def __str__(self):
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
31 return self.str
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
32
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
33 tests = unittest.TestSuite()
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
34
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
35 def RobotTest(index, robots_txt, good_urls, bad_urls,
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
36 agent="test_robotparser"):
23075
b7e87732f6ab Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents: 22088
diff changeset
37
42501
f6069f9dd52d SF patch# 1770008 by Christian Heimes (plus some extras).
Guido van Rossum <guido@python.org>
parents: 41554
diff changeset
38 lines = io.StringIO(robots_txt).readlines()
48334
5a416a6417d3 Make a new urllib package .
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 47201
diff changeset
39 parser = urllib.robotparser.RobotFileParser()
23075
b7e87732f6ab Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents: 22088
diff changeset
40 parser.parse(lines)
b7e87732f6ab Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents: 22088
diff changeset
41 for url in good_urls:
b7e87732f6ab Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents: 22088
diff changeset
42 tests.addTest(RobotTestCase(index, parser, url, 1, agent))
b7e87732f6ab Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents: 22088
diff changeset
43 for url in bad_urls:
b7e87732f6ab Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents: 22088
diff changeset
44 tests.addTest(RobotTestCase(index, parser, url, 0, agent))
22088
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
45
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
46 # Examples from http://www.robotstxt.org/wc/norobots.html (fetched 2002)
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
47
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
48 # 1.
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
49 doc = """
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
50 User-agent: *
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
51 Disallow: /cyberworld/map/ # This is an infinite virtual URL space
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
52 Disallow: /tmp/ # these will soon disappear
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
53 Disallow: /foo.html
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
54 """
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
55
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
56 good = ['/','/test.html']
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
57 bad = ['/cyberworld/map/index.html','/tmp/xxx','/foo.html']
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
58
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
59 RobotTest(1, doc, good, bad)
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
60
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
61 # 2.
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
62 doc = """
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
63 # robots.txt for http://www.example.com/
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
64
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
65 User-agent: *
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
66 Disallow: /cyberworld/map/ # This is an infinite virtual URL space
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
67
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
68 # Cybermapper knows where to go.
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
69 User-agent: cybermapper
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
70 Disallow:
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
71
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
72 """
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
73
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
74 good = ['/','/test.html',('cybermapper','/cyberworld/map/index.html')]
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
75 bad = ['/cyberworld/map/index.html']
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
76
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
77 RobotTest(2, doc, good, bad)
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
78
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
79 # 3.
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
80 doc = """
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
81 # go away
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
82 User-agent: *
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
83 Disallow: /
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
84 """
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
85
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
86 good = []
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
87 bad = ['/cyberworld/map/index.html','/','/tmp/']
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
88
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
89 RobotTest(3, doc, good, bad)
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
90
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
91 # Examples from http://www.robotstxt.org/wc/norobots-rfc.html (fetched 2002)
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
92
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
93 # 4.
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
94 doc = """
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
95 User-agent: figtree
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
96 Disallow: /tmp
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
97 Disallow: /a%3cd.html
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
98 Disallow: /a%2fb.html
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
99 Disallow: /%7ejoe/index.html
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
100 """
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
101
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
102 good = [] # XFAIL '/a/b.html'
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
103 bad = ['/tmp','/tmp.html','/tmp/a.html',
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
104 '/a%3cd.html','/a%3Cd.html','/a%2fb.html',
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
105 '/~joe/index.html'
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
106 ]
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
107
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
108 RobotTest(4, doc, good, bad, 'figtree')
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
109 RobotTest(5, doc, good, bad, 'FigTree Robot libwww-perl/5.04')
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
110
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
111 # 6.
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
112 doc = """
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
113 User-agent: *
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
114 Disallow: /tmp/
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
115 Disallow: /a%3Cd.html
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
116 Disallow: /a/b.html
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
117 Disallow: /%7ejoe/index.html
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
118 """
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
119
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
120 good = ['/tmp',] # XFAIL: '/a%2fb.html'
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
121 bad = ['/tmp/','/tmp/a.html',
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
122 '/a%3cd.html','/a%3Cd.html',"/a/b.html",
23075
b7e87732f6ab Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents: 22088
diff changeset
123 '/%7Ejoe/index.html']
22088
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
124
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
125 RobotTest(6, doc, good, bad)
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
126
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
127 # From bug report #523041
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
128
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
129 # 7.
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
130 doc = """
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
131 User-Agent: *
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
132 Disallow: /.
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
133 """
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
134
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
135 good = ['/foo.html']
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
136 bad = [] # Bug report says "/" should be denied, but that is not in the RFC
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
137
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
138 RobotTest(7, doc, good, bad)
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
139
48594
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
140 # From Google: http://www.google.com/support/webmasters/bin/answer.py?hl=en&answer=40364
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
141
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
142 # 8.
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
143 doc = """
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
144 User-agent: Googlebot
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
145 Allow: /folder1/myfile.html
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
146 Disallow: /folder1/
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
147 """
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
148
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
149 good = ['/folder1/myfile.html']
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
150 bad = ['/folder1/anotherfile.html']
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
151
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
152 RobotTest(8, doc, good, bad, agent="Googlebot")
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
153
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
154 # 9. This file is incorrect because "Googlebot" is a substring of
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
155 # "Googlebot-Mobile", so test 10 works just like test 9.
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
156 doc = """
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
157 User-agent: Googlebot
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
158 Disallow: /
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
159
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
160 User-agent: Googlebot-Mobile
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
161 Allow: /
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
162 """
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
163
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
164 good = []
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
165 bad = ['/something.jpg']
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
166
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
167 RobotTest(9, doc, good, bad, agent="Googlebot")
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
168
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
169 good = []
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
170 bad = ['/something.jpg']
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
171
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
172 RobotTest(10, doc, good, bad, agent="Googlebot-Mobile")
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
173
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
174 # 11. Get the order correct.
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
175 doc = """
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
176 User-agent: Googlebot-Mobile
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
177 Allow: /
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
178
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
179 User-agent: Googlebot
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
180 Disallow: /
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
181 """
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
182
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
183 good = []
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
184 bad = ['/something.jpg']
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
185
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
186 RobotTest(11, doc, good, bad, agent="Googlebot")
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
187
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
188 good = ['/something.jpg']
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
189 bad = []
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
190
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
191 RobotTest(12, doc, good, bad, agent="Googlebot-Mobile")
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
192
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
193
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
194 # 13. Google also got the order wrong in #8. You need to specify the
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
195 # URLs from more specific to more general.
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
196 doc = """
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
197 User-agent: Googlebot
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
198 Allow: /folder1/myfile.html
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
199 Disallow: /folder1/
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
200 """
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
201
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
202 good = ['/folder1/myfile.html']
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
203 bad = ['/folder1/anotherfile.html']
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
204
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
205 RobotTest(13, doc, good, bad, agent="googlebot")
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
206
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
207
63271
3119c4d7276b Merged revisions 83209 via svnmerge from
Senthil Kumaran <orsenthil@gmail.com>
parents: 60202
diff changeset
208 # 14. For issue #6325 (query string support)
3119c4d7276b Merged revisions 83209 via svnmerge from
Senthil Kumaran <orsenthil@gmail.com>
parents: 60202
diff changeset
209 doc = """
3119c4d7276b Merged revisions 83209 via svnmerge from
Senthil Kumaran <orsenthil@gmail.com>
parents: 60202
diff changeset
210 User-agent: *
3119c4d7276b Merged revisions 83209 via svnmerge from
Senthil Kumaran <orsenthil@gmail.com>
parents: 60202
diff changeset
211 Disallow: /some/path?name=value
3119c4d7276b Merged revisions 83209 via svnmerge from
Senthil Kumaran <orsenthil@gmail.com>
parents: 60202
diff changeset
212 """
3119c4d7276b Merged revisions 83209 via svnmerge from
Senthil Kumaran <orsenthil@gmail.com>
parents: 60202
diff changeset
213
3119c4d7276b Merged revisions 83209 via svnmerge from
Senthil Kumaran <orsenthil@gmail.com>
parents: 60202
diff changeset
214 good = ['/some/path']
3119c4d7276b Merged revisions 83209 via svnmerge from
Senthil Kumaran <orsenthil@gmail.com>
parents: 60202
diff changeset
215 bad = ['/some/path?name=value']
3119c4d7276b Merged revisions 83209 via svnmerge from
Senthil Kumaran <orsenthil@gmail.com>
parents: 60202
diff changeset
216
3119c4d7276b Merged revisions 83209 via svnmerge from
Senthil Kumaran <orsenthil@gmail.com>
parents: 60202
diff changeset
217 RobotTest(14, doc, good, bad)
3119c4d7276b Merged revisions 83209 via svnmerge from
Senthil Kumaran <orsenthil@gmail.com>
parents: 60202
diff changeset
218
63464
415ea2c3cfe8 Merged revisions 83238 via svnmerge from
Georg Brandl <georg@python.org>
parents: 63271
diff changeset
219 # 15. For issue #4108 (obey first * entry)
415ea2c3cfe8 Merged revisions 83238 via svnmerge from
Georg Brandl <georg@python.org>
parents: 63271
diff changeset
220 doc = """
415ea2c3cfe8 Merged revisions 83238 via svnmerge from
Georg Brandl <georg@python.org>
parents: 63271
diff changeset
221 User-agent: *
415ea2c3cfe8 Merged revisions 83238 via svnmerge from
Georg Brandl <georg@python.org>
parents: 63271
diff changeset
222 Disallow: /some/path
415ea2c3cfe8 Merged revisions 83238 via svnmerge from
Georg Brandl <georg@python.org>
parents: 63271
diff changeset
223
415ea2c3cfe8 Merged revisions 83238 via svnmerge from
Georg Brandl <georg@python.org>
parents: 63271
diff changeset
224 User-agent: *
415ea2c3cfe8 Merged revisions 83238 via svnmerge from
Georg Brandl <georg@python.org>
parents: 63271
diff changeset
225 Disallow: /another/path
415ea2c3cfe8 Merged revisions 83238 via svnmerge from
Georg Brandl <georg@python.org>
parents: 63271
diff changeset
226 """
415ea2c3cfe8 Merged revisions 83238 via svnmerge from
Georg Brandl <georg@python.org>
parents: 63271
diff changeset
227
415ea2c3cfe8 Merged revisions 83238 via svnmerge from
Georg Brandl <georg@python.org>
parents: 63271
diff changeset
228 good = ['/another/path']
415ea2c3cfe8 Merged revisions 83238 via svnmerge from
Georg Brandl <georg@python.org>
parents: 63271
diff changeset
229 bad = ['/some/path']
415ea2c3cfe8 Merged revisions 83238 via svnmerge from
Georg Brandl <georg@python.org>
parents: 63271
diff changeset
230
415ea2c3cfe8 Merged revisions 83238 via svnmerge from
Georg Brandl <georg@python.org>
parents: 63271
diff changeset
231 RobotTest(15, doc, good, bad)
415ea2c3cfe8 Merged revisions 83238 via svnmerge from
Georg Brandl <georg@python.org>
parents: 63271
diff changeset
232
48594
35b1a20470db Merged revisions 65209-65216,65225-65226,65233,65239,65246-65247,65255-65256 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 48563
diff changeset
233
48535
dece17edbed0 Bug 3347: robotparser failed because it didn't convert bytes to string.
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 48334
diff changeset
234 class NetworkTestCase(unittest.TestCase):
dece17edbed0 Bug 3347: robotparser failed because it didn't convert bytes to string.
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 48334
diff changeset
235
dece17edbed0 Bug 3347: robotparser failed because it didn't convert bytes to string.
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 48334
diff changeset
236 def testPasswordProtectedSite(self):
60202
5496503b8b1a Merged revision 79605 via svnmerge from
Florent Xicluna <florent.xicluna@gmail.com>
parents: 55593
diff changeset
237 support.requires('network')
64536
2400f55ea312 Merged revisions 84597-84599 via svnmerge from
Antoine Pitrou <solipsis@pitrou.net>
parents: 63464
diff changeset
238 with support.transient_internet('mueblesmoraleda.com'):
2400f55ea312 Merged revisions 84597-84599 via svnmerge from
Antoine Pitrou <solipsis@pitrou.net>
parents: 63464
diff changeset
239 url = 'http://mueblesmoraleda.com'
2400f55ea312 Merged revisions 84597-84599 via svnmerge from
Antoine Pitrou <solipsis@pitrou.net>
parents: 63464
diff changeset
240 parser = urllib.robotparser.RobotFileParser()
2400f55ea312 Merged revisions 84597-84599 via svnmerge from
Antoine Pitrou <solipsis@pitrou.net>
parents: 63464
diff changeset
241 parser.set_url(url)
2400f55ea312 Merged revisions 84597-84599 via svnmerge from
Antoine Pitrou <solipsis@pitrou.net>
parents: 63464
diff changeset
242 try:
2400f55ea312 Merged revisions 84597-84599 via svnmerge from
Antoine Pitrou <solipsis@pitrou.net>
parents: 63464
diff changeset
243 parser.read()
2400f55ea312 Merged revisions 84597-84599 via svnmerge from
Antoine Pitrou <solipsis@pitrou.net>
parents: 63464
diff changeset
244 except URLError:
2400f55ea312 Merged revisions 84597-84599 via svnmerge from
Antoine Pitrou <solipsis@pitrou.net>
parents: 63464
diff changeset
245 self.skipTest('%s is unavailable' % url)
2400f55ea312 Merged revisions 84597-84599 via svnmerge from
Antoine Pitrou <solipsis@pitrou.net>
parents: 63464
diff changeset
246 self.assertEqual(parser.can_fetch("*", url+"/robots.txt"), False)
43095
4a07a288f5c4 Merged revisions 57620-57771 via svnmerge from
Thomas Wouters <thomas@python.org>
parents: 42501
diff changeset
247
48535
dece17edbed0 Bug 3347: robotparser failed because it didn't convert bytes to string.
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 48334
diff changeset
248 def testPythonOrg(self):
60202
5496503b8b1a Merged revision 79605 via svnmerge from
Florent Xicluna <florent.xicluna@gmail.com>
parents: 55593
diff changeset
249 support.requires('network')
64536
2400f55ea312 Merged revisions 84597-84599 via svnmerge from
Antoine Pitrou <solipsis@pitrou.net>
parents: 63464
diff changeset
250 with support.transient_internet('www.python.org'):
2400f55ea312 Merged revisions 84597-84599 via svnmerge from
Antoine Pitrou <solipsis@pitrou.net>
parents: 63464
diff changeset
251 parser = urllib.robotparser.RobotFileParser(
2400f55ea312 Merged revisions 84597-84599 via svnmerge from
Antoine Pitrou <solipsis@pitrou.net>
parents: 63464
diff changeset
252 "http://www.python.org/robots.txt")
2400f55ea312 Merged revisions 84597-84599 via svnmerge from
Antoine Pitrou <solipsis@pitrou.net>
parents: 63464
diff changeset
253 parser.read()
2400f55ea312 Merged revisions 84597-84599 via svnmerge from
Antoine Pitrou <solipsis@pitrou.net>
parents: 63464
diff changeset
254 self.assertTrue(
2400f55ea312 Merged revisions 84597-84599 via svnmerge from
Antoine Pitrou <solipsis@pitrou.net>
parents: 63464
diff changeset
255 parser.can_fetch("*", "http://www.python.org/robots.txt"))
48535
dece17edbed0 Bug 3347: robotparser failed because it didn't convert bytes to string.
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 48334
diff changeset
256
22088
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
257 def test_main():
48535
dece17edbed0 Bug 3347: robotparser failed because it didn't convert bytes to string.
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 48334
diff changeset
258 support.run_unittest(NetworkTestCase)
47201
9c930a32cebb #2621 rename test.test_support to test.support
Benjamin Peterson <benjamin@python.org>
parents: 43095
diff changeset
259 support.run_unittest(tests)
22088
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
260
736fb5aec9b3 Correct various errors:
Martin v. Löwis <martin@v.loewis.de>
parents:
diff changeset
261 if __name__=='__main__':
48563
b51cd5d3795c Merged revisions 65012,65035,65037-65040,65048,65057,65077,65091-65095,65097-65099,65127-65128,65131,65133-65136,65139,65149-65151,65155,65158-65159,65176-65178,65183-65184,65187-65190,65192,65194 via svnmerge from
Georg Brandl <georg@python.org>
parents: 48535
diff changeset
262 support.verbose = 1
41554
06145fbc7ab9 Merged revisions 53952-54987 via svnmerge from
Guido van Rossum <guido@python.org>
parents: 24364
diff changeset
263 test_main()