summaryrefslogtreecommitdiffstats
path: root/Lib/test/test_robotparser.py
blob: d1dfd9eeec026d4d501b1debca900bef6be1e50c (plain)
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
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
import io
import unittest
import urllib.robotparser
from urllib.error import URLError, HTTPError
from urllib.request import urlopen
from test import support

class RobotTestCase(unittest.TestCase):
    def __init__(self, index=None, parser=None, url=None, good=None, agent=None):
        # workaround to make unittest discovery work (see #17066)
        if not isinstance(index, int):
            return
        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.assertTrue(self.parser.can_fetch(agent, url))
        else:
            self.assertFalse(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")


# 14. For issue #6325 (query string support)
doc = """
User-agent: *
Disallow: /some/path?name=value
"""

good = ['/some/path']
bad = ['/some/path?name=value']

RobotTest(14, doc, good, bad)

# 15. For issue #4108 (obey first * entry)
doc = """
User-agent: *
Disallow: /some/path

User-agent: *
Disallow: /another/path
"""

good = ['/another/path']
bad = ['/some/path']

RobotTest(15, doc, good, bad)

# 16. Empty query (issue #17403). Normalizing the url first.
doc = """
User-agent: *
Allow: /some/path?
Disallow: /another/path?
"""

good = ['/some/path?']
bad = ['/another/path?']

RobotTest(16, doc, good, bad)


class NetworkTestCase(unittest.TestCase):

    def testPasswordProtectedSite(self):
        support.requires('network')
        with support.transient_internet('mueblesmoraleda.com'):
            url = 'http://mueblesmoraleda.com'
            robots_url = url + "/robots.txt"
            # First check the URL is usable for our purposes, since the
            # test site is a bit flaky.
            try:
                urlopen(robots_url)
            except HTTPError as e:
                if e.code not in {401, 403}:
                    self.skipTest(
                        "%r should return a 401 or 403 HTTP error, not %r"
                        % (robots_url, e.code))
            else:
                self.skipTest(
                    "%r should return a 401 or 403 HTTP error, not succeed"
                    % (robots_url))
            parser = urllib.robotparser.RobotFileParser()
            parser.set_url(url)
            try:
                parser.read()
            except URLError:
                self.skipTest('%s is unavailable' % url)
            self.assertEqual(parser.can_fetch("*", robots_url), False)

    def testPythonOrg(self):
        support.requires('network')
        with support.transient_internet('www.python.org'):
            parser = urllib.robotparser.RobotFileParser(
                "http://www.python.org/robots.txt")
            parser.read()
            self.assertTrue(
                parser.can_fetch("*", "http://www.python.org/robots.txt"))

def load_tests(loader, suite, pattern):
    suite = unittest.makeSuite(NetworkTestCase)
    suite.addTest(tests)
    return suite

if __name__=='__main__':
    support.use_resources = ['network']
    unittest.main()