summaryrefslogtreecommitdiffstats
path: root/Lib/test/test_robotparser.py
blob: 0f64ba8b060defbbc129423f063f18d4aa2ac498 (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
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
import io
import os
import unittest
import urllib.robotparser
from collections import namedtuple
from test import support
from http.server import BaseHTTPRequestHandler, HTTPServer
try:
    import threading
except ImportError:
    threading = None


class BaseRobotTest:
    robots_txt = ''
    agent = 'test_robotparser'
    good = []
    bad = []

    def setUp(self):
        lines = io.StringIO(self.robots_txt).readlines()
        self.parser = urllib.robotparser.RobotFileParser()
        self.parser.parse(lines)

    def get_agent_and_url(self, url):
        if isinstance(url, tuple):
            agent, url = url
            return agent, url
        return self.agent, url

    def test_good_urls(self):
        for url in self.good:
            agent, url = self.get_agent_and_url(url)
            with self.subTest(url=url, agent=agent):
                self.assertTrue(self.parser.can_fetch(agent, url))

    def test_bad_urls(self):
        for url in self.bad:
            agent, url = self.get_agent_and_url(url)
            with self.subTest(url=url, agent=agent):
                self.assertFalse(self.parser.can_fetch(agent, url))


class UserAgentWildcardTest(BaseRobotTest, unittest.TestCase):
    robots_txt = """\
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']


class CrawlDelayAndCustomAgentTest(BaseRobotTest, unittest.TestCase):
    robots_txt = """\
# robots.txt for http://www.example.com/

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:
    """
    good = ['/', '/test.html', ('cybermapper', '/cyberworld/map/index.html')]
    bad = ['/cyberworld/map/index.html']


class RejectAllRobotsTest(BaseRobotTest, unittest.TestCase):
    robots_txt = """\
# go away
User-agent: *
Disallow: /
    """
    good = []
    bad = ['/cyberworld/map/index.html', '/', '/tmp/']


class BaseRequestRateTest(BaseRobotTest):

    def test_request_rate(self):
        for url in self.good + self.bad:
            agent, url = self.get_agent_and_url(url)
            with self.subTest(url=url, agent=agent):
                if self.crawl_delay:
                    self.assertEqual(
                        self.parser.crawl_delay(agent), self.crawl_delay
                    )
                if self.request_rate:
                    self.assertEqual(
                        self.parser.request_rate(agent).requests,
                        self.request_rate.requests
                    )
                    self.assertEqual(
                        self.parser.request_rate(agent).seconds,
                        self.request_rate.seconds
                    )


class CrawlDelayAndRequestRateTest(BaseRequestRateTest, unittest.TestCase):
    robots_txt = """\
User-agent: figtree
Crawl-delay: 3
Request-rate: 9/30
Disallow: /tmp
Disallow: /a%3cd.html
Disallow: /a%2fb.html
Disallow: /%7ejoe/index.html
    """
    agent = 'figtree'
    request_rate = namedtuple('req_rate', 'requests seconds')(9, 30)
    crawl_delay = 3
    good = [('figtree', '/foo.html')]
    bad = ['/tmp', '/tmp.html', '/tmp/a.html', '/a%3cd.html', '/a%3Cd.html',
           '/a%2fb.html', '/~joe/index.html']


class DifferentAgentTest(CrawlDelayAndRequestRateTest):
    agent = 'FigTree Robot libwww-perl/5.04'
    # these are not actually tested, but we still need to parse it
    # in order to accommodate the input parameters
    request_rate = None
    crawl_delay = None


class InvalidRequestRateTest(BaseRobotTest, unittest.TestCase):
    robots_txt = """\
User-agent: *
Disallow: /tmp/
Disallow: /a%3Cd.html
Disallow: /a/b.html
Disallow: /%7ejoe/index.html
Crawl-delay: 3
Request-rate: 9/banana
    """
    good = ['/tmp']
    bad = ['/tmp/', '/tmp/a.html', '/a%3cd.html', '/a%3Cd.html', '/a/b.html',
           '/%7Ejoe/index.html']
    crawl_delay = 3


class InvalidCrawlDelayTest(BaseRobotTest, unittest.TestCase):
    # From bug report #523041
    robots_txt = """\
User-Agent: *
Disallow: /.
Crawl-delay: pears
    """
    good = ['/foo.html']
    # bug report says "/" should be denied, but that is not in the RFC
    bad = []


class AnotherInvalidRequestRateTest(BaseRobotTest, unittest.TestCase):
    # also test that Allow and Diasallow works well with each other
    robots_txt = """\
User-agent: Googlebot
Allow: /folder1/myfile.html
Disallow: /folder1/
Request-rate: whale/banana
    """
    agent = 'Googlebot'
    good = ['/folder1/myfile.html']
    bad = ['/folder1/anotherfile.html']


class UserAgentOrderingTest(BaseRobotTest, unittest.TestCase):
    # the order of User-agent should be correct. note
    # that this file is incorrect because "Googlebot" is a
    # substring of "Googlebot-Mobile"
    robots_txt = """\
User-agent: Googlebot
Disallow: /

User-agent: Googlebot-Mobile
Allow: /
    """
    agent = 'Googlebot'
    bad = ['/something.jpg']


class UserAgentGoogleMobileTest(UserAgentOrderingTest):
    agent = 'Googlebot-Mobile'


class GoogleURLOrderingTest(BaseRobotTest, unittest.TestCase):
    # Google also got the order wrong. You need
    # to specify the URLs from more specific to more general
    robots_txt = """\
User-agent: Googlebot
Allow: /folder1/myfile.html
Disallow: /folder1/
    """
    agent = 'googlebot'
    good = ['/folder1/myfile.html']
    bad = ['/folder1/anotherfile.html']


class DisallowQueryStringTest(BaseRobotTest, unittest.TestCase):
    # see issue #6325 for details
    robots_txt = """\
User-agent: *
Disallow: /some/path?name=value
    """
    good = ['/some/path']
    bad = ['/some/path?name=value']


class UseFirstUserAgentWildcardTest(BaseRobotTest, unittest.TestCase):
    # obey first * entry (#4108)
    robots_txt = """\
User-agent: *
Disallow: /some/path

User-agent: *
Disallow: /another/path
    """
    good = ['/another/path']
    bad = ['/some/path']


class EmptyQueryStringTest(BaseRobotTest, unittest.TestCase):
    # normalize the URL first (#17403)
    robots_txt = """\
User-agent: *
Allow: /some/path?
Disallow: /another/path?
    """
    good = ['/some/path?']
    bad = ['/another/path?']


class DefaultEntryTest(BaseRequestRateTest, unittest.TestCase):
    robots_txt = """\
User-agent: *
Crawl-delay: 1
Request-rate: 3/15
Disallow: /cyberworld/map/
    """
    request_rate = namedtuple('req_rate', 'requests seconds')(3, 15)
    crawl_delay = 1
    good = ['/', '/test.html']
    bad = ['/cyberworld/map/index.html']


class RobotHandler(BaseHTTPRequestHandler):

    def do_GET(self):
        self.send_error(403, "Forbidden access")

    def log_message(self, format, *args):
        pass


@unittest.skipUnless(threading, 'threading required for this test')
class PasswordProtectedSiteTestCase(unittest.TestCase):

    def setUp(self):
        self.server = HTTPServer((support.HOST, 0), RobotHandler)

        self.t = threading.Thread(
            name='HTTPServer serving',
            target=self.server.serve_forever,
            # Short poll interval to make the test finish quickly.
            # Time between requests is short enough that we won't wake
            # up spuriously too many times.
            kwargs={'poll_interval':0.01})
        self.t.daemon = True  # In case this function raises.
        self.t.start()

    def tearDown(self):
        self.server.shutdown()
        self.t.join()
        self.server.server_close()

    @support.reap_threads
    def testPasswordProtectedSite(self):
        addr = self.server.server_address
        url = 'http://' + support.HOST + ':' + str(addr[1])
        robots_url = url + "/robots.txt"
        parser = urllib.robotparser.RobotFileParser()
        parser.set_url(url)
        parser.read()
        self.assertFalse(parser.can_fetch("*", robots_url))


class NetworkTestCase(unittest.TestCase):

    base_url = 'http://www.pythontest.net/'
    robots_txt = '{}elsewhere/robots.txt'.format(base_url)

    @classmethod
    def setUpClass(cls):
        support.requires('network')
        with support.transient_internet(cls.base_url):
            cls.parser = urllib.robotparser.RobotFileParser(cls.robots_txt)
            cls.parser.read()

    def url(self, path):
        return '{}{}{}'.format(
            self.base_url, path, '/' if not os.path.splitext(path)[1] else ''
        )

    def test_basic(self):
        self.assertFalse(self.parser.disallow_all)
        self.assertFalse(self.parser.allow_all)
        self.assertGreater(self.parser.mtime(), 0)
        self.assertFalse(self.parser.crawl_delay('*'))
        self.assertFalse(self.parser.request_rate('*'))

    def test_can_fetch(self):
        self.assertTrue(self.parser.can_fetch('*', self.url('elsewhere')))
        self.assertFalse(self.parser.can_fetch('Nutch', self.base_url))
        self.assertFalse(self.parser.can_fetch('Nutch', self.url('brian')))
        self.assertFalse(self.parser.can_fetch('Nutch', self.url('webstats')))
        self.assertFalse(self.parser.can_fetch('*', self.url('webstats')))
        self.assertTrue(self.parser.can_fetch('*', self.base_url))

    def test_read_404(self):
        parser = urllib.robotparser.RobotFileParser(self.url('i-robot.txt'))
        parser.read()
        self.assertTrue(parser.allow_all)
        self.assertFalse(parser.disallow_all)
        self.assertEqual(parser.mtime(), 0)
        self.assertIsNone(parser.crawl_delay('*'))
        self.assertIsNone(parser.request_rate('*'))

if __name__=='__main__':
    unittest.main()