1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
|
import io
import unittest
import urllib.robotparser
from test import support
class RobotTestCase(unittest.TestCase):
def __init__(self, index, parser, url, good, agent):
unittest.TestCase.__init__(self)
if good:
self.str = "RobotTest(%d, good, %s)" % (index, url)
else:
self.str = "RobotTest(%d, bad, %s)" % (index, url)
self.parser = parser
self.url = url
self.good = good
self.agent = agent
def runTest(self):
if isinstance(self.url, tuple):
agent, url = self.url
else:
url = self.url
agent = self.agent
if self.good:
self.failUnless(self.parser.can_fetch(agent, url))
else:
self.failIf(self.parser.can_fetch(agent, url))
def __str__(self):
return self.str
tests = unittest.TestSuite()
def RobotTest(index, robots_txt, good_urls, bad_urls,
agent="test_robotparser"):
lines = io.StringIO(robots_txt).readlines()
parser = urllib.robotparser.RobotFileParser()
parser.parse(lines)
for url in good_urls:
tests.addTest(RobotTestCase(index, parser, url, 1, agent))
for url in bad_urls:
tests.addTest(RobotTestCase(index, parser, url, 0, agent))
# Examples from http://www.robotstxt.org/wc/norobots.html (fetched 2002)
# 1.
doc = """
User-agent: *
Disallow: /cyberworld/map/ # This is an infinite virtual URL space
Disallow: /tmp/ # these will soon disappear
Disallow: /foo.html
"""
good = ['/','/test.html']
bad = ['/cyberworld/map/index.html','/tmp/xxx','/foo.html']
RobotTest(1, doc, good, bad)
# 2.
doc = """
# robots.txt for http://www.example.com/
User-agent: *
Disallow: /cyberworld/map/ # This is an infinite virtual URL space
# Cybermapper knows where to go.
User-agent: cybermapper
Disallow:
"""
good = ['/','/test.html',('cybermapper','/cyberworld/map/index.html')]
bad = ['/cyberworld/map/index.html']
RobotTest(2, doc, good, bad)
# 3.
doc = """
# go away
User-agent: *
Disallow: /
"""
good = []
bad = ['/cyberworld/map/index.html','/','/tmp/']
RobotTest(3, doc, good, bad)
# Examples from http://www.robotstxt.org/wc/norobots-rfc.html (fetched 2002)
# 4.
doc = """
User-agent: figtree
Disallow: /tmp
Disallow: /a%3cd.html
Disallow: /a%2fb.html
Disallow: /%7ejoe/index.html
"""
good = [] # XFAIL '/a/b.html'
bad = ['/tmp','/tmp.html','/tmp/a.html',
'/a%3cd.html','/a%3Cd.html','/a%2fb.html',
'/~joe/index.html'
]
RobotTest(4, doc, good, bad, 'figtree')
RobotTest(5, doc, good, bad, 'FigTree Robot libwww-perl/5.04')
# 6.
doc = """
User-agent: *
Disallow: /tmp/
Disallow: /a%3Cd.html
Disallow: /a/b.html
Disallow: /%7ejoe/index.html
"""
good = ['/tmp',] # XFAIL: '/a%2fb.html'
bad = ['/tmp/','/tmp/a.html',
'/a%3cd.html','/a%3Cd.html',"/a/b.html",
'/%7Ejoe/index.html']
RobotTest(6, doc, good, bad)
# From bug report #523041
# 7.
doc = """
User-Agent: *
Disallow: /.
"""
good = ['/foo.html']
bad = [] # Bug report says "/" should be denied, but that is not in the RFC
RobotTest(7, doc, good, bad)
# From Google: http://www.google.com/support/webmasters/bin/answer.py?hl=en&answer=40364
# 8.
doc = """
User-agent: Googlebot
Allow: /folder1/myfile.html
Disallow: /folder1/
"""
good = ['/folder1/myfile.html']
bad = ['/folder1/anotherfile.html']
RobotTest(8, doc, good, bad, agent="Googlebot")
# 9. This file is incorrect because "Googlebot" is a substring of
# "Googlebot-Mobile", so test 10 works just like test 9.
doc = """
User-agent: Googlebot
Disallow: /
User-agent: Googlebot-Mobile
Allow: /
"""
good = []
bad = ['/something.jpg']
RobotTest(9, doc, good, bad, agent="Googlebot")
good = []
bad = ['/something.jpg']
RobotTest(10, doc, good, bad, agent="Googlebot-Mobile")
# 11. Get the order correct.
doc = """
User-agent: Googlebot-Mobile
Allow: /
User-agent: Googlebot
Disallow: /
"""
good = []
bad = ['/something.jpg']
RobotTest(11, doc, good, bad, agent="Googlebot")
good = ['/something.jpg']
bad = []
RobotTest(12, doc, good, bad, agent="Googlebot-Mobile")
# 13. Google also got the order wrong in #8. You need to specify the
# URLs from more specific to more general.
doc = """
User-agent: Googlebot
Allow: /folder1/myfile.html
Disallow: /folder1/
"""
good = ['/folder1/myfile.html']
bad = ['/folder1/anotherfile.html']
RobotTest(13, doc, good, bad, agent="googlebot")
class NetworkTestCase(unittest.TestCase):
def testPasswordProtectedSite(self):
if not support.is_resource_enabled('network'):
return
# whole site is password-protected.
url = 'http://mueblesmoraleda.com'
parser = urllib.robotparser.RobotFileParser()
parser.set_url(url)
parser.read()
self.assertEqual(parser.can_fetch("*", url+"/robots.txt"), False)
def testPythonOrg(self):
if not support.is_resource_enabled('network'):
return
parser = urllib.robotparser.RobotFileParser(
"http://www.python.org/robots.txt")
parser.read()
self.assertTrue(parser.can_fetch("*",
"http://www.python.org/robots.txt"))
def test_main():
support.run_unittest(NetworkTestCase)
support.run_unittest(tests)
if __name__=='__main__':
support.verbose = 1
test_main()
|
