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
|
from unittest import mock
from twisted.internet import reactor, error
from twisted.internet.defer import Deferred, DeferredList, maybeDeferred
from twisted.python import failure
from twisted.trial import unittest
from scrapy.downloadermiddlewares.robotstxt import (RobotsTxtMiddleware,
logger as mw_module_logger)
from scrapy.exceptions import IgnoreRequest, NotConfigured
from scrapy.http import Request, Response, TextResponse
from scrapy.settings import Settings
from tests.test_robotstxt_interface import rerp_available, reppy_available
class RobotsTxtMiddlewareTest(unittest.TestCase):
def setUp(self):
self.crawler = mock.MagicMock()
self.crawler.settings = Settings()
self.crawler.engine.download = mock.MagicMock()
def tearDown(self):
del self.crawler
def test_robotstxt_settings(self):
self.crawler.settings = Settings()
self.crawler.settings.set('USER_AGENT', 'CustomAgent')
self.assertRaises(NotConfigured, RobotsTxtMiddleware, self.crawler)
def _get_successful_crawler(self):
crawler = self.crawler
crawler.settings.set('ROBOTSTXT_OBEY', True)
ROBOTS = """
User-Agent: *
Disallow: /admin/
Disallow: /static/
# taken from https://en.wikipedia.org/robots.txt
Disallow: /wiki/K%C3%A4ytt%C3%A4j%C3%A4:
Disallow: /wiki/Käyttäjä:
User-Agent: UnicödeBöt
Disallow: /some/randome/page.html
""".encode('utf-8')
response = TextResponse('http://site.local/robots.txt', body=ROBOTS)
def return_response(request, spider):
deferred = Deferred()
reactor.callFromThread(deferred.callback, response)
return deferred
crawler.engine.download.side_effect = return_response
return crawler
def test_robotstxt(self):
middleware = RobotsTxtMiddleware(self._get_successful_crawler())
return DeferredList([
self.assertNotIgnored(Request('http://site.local/allowed'), middleware),
self.assertIgnored(Request('http://site.local/admin/main'), middleware),
self.assertIgnored(Request('http://site.local/static/'), middleware),
self.assertIgnored(Request('http://site.local/wiki/K%C3%A4ytt%C3%A4j%C3%A4:'), middleware),
self.assertIgnored(Request('http://site.local/wiki/Käyttäjä:'), middleware)
], fireOnOneErrback=True)
def test_robotstxt_ready_parser(self):
middleware = RobotsTxtMiddleware(self._get_successful_crawler())
d = self.assertNotIgnored(Request('http://site.local/allowed'), middleware)
d.addCallback(lambda _: self.assertNotIgnored(Request('http://site.local/allowed'), middleware))
return d
def test_robotstxt_meta(self):
middleware = RobotsTxtMiddleware(self._get_successful_crawler())
meta = {'dont_obey_robotstxt': True}
return DeferredList([
self.assertNotIgnored(Request('http://site.local/allowed', meta=meta), middleware),
self.assertNotIgnored(Request('http://site.local/admin/main', meta=meta), middleware),
self.assertNotIgnored(Request('http://site.local/static/', meta=meta), middleware)
], fireOnOneErrback=True)
def _get_garbage_crawler(self):
crawler = self.crawler
crawler.settings.set('ROBOTSTXT_OBEY', True)
response = Response('http://site.local/robots.txt', body=b'GIF89a\xd3\x00\xfe\x00\xa2')
def return_response(request, spider):
deferred = Deferred()
reactor.callFromThread(deferred.callback, response)
return deferred
crawler.engine.download.side_effect = return_response
return crawler
def test_robotstxt_garbage(self):
# garbage response should be discarded, equal 'allow all'
middleware = RobotsTxtMiddleware(self._get_garbage_crawler())
deferred = DeferredList([
self.assertNotIgnored(Request('http://site.local'), middleware),
self.assertNotIgnored(Request('http://site.local/allowed'), middleware),
self.assertNotIgnored(Request('http://site.local/admin/main'), middleware),
self.assertNotIgnored(Request('http://site.local/static/'), middleware)
], fireOnOneErrback=True)
return deferred
def _get_emptybody_crawler(self):
crawler = self.crawler
crawler.settings.set('ROBOTSTXT_OBEY', True)
response = Response('http://site.local/robots.txt')
def return_response(request, spider):
deferred = Deferred()
reactor.callFromThread(deferred.callback, response)
return deferred
crawler.engine.download.side_effect = return_response
return crawler
def test_robotstxt_empty_response(self):
# empty response should equal 'allow all'
middleware = RobotsTxtMiddleware(self._get_emptybody_crawler())
return DeferredList([
self.assertNotIgnored(Request('http://site.local/allowed'), middleware),
self.assertNotIgnored(Request('http://site.local/admin/main'), middleware),
self.assertNotIgnored(Request('http://site.local/static/'), middleware)
], fireOnOneErrback=True)
def test_robotstxt_error(self):
self.crawler.settings.set('ROBOTSTXT_OBEY', True)
err = error.DNSLookupError('Robotstxt address not found')
def return_failure(request, spider):
deferred = Deferred()
reactor.callFromThread(deferred.errback, failure.Failure(err))
return deferred
self.crawler.engine.download.side_effect = return_failure
middleware = RobotsTxtMiddleware(self.crawler)
middleware._logerror = mock.MagicMock(side_effect=middleware._logerror)
deferred = middleware.process_request(Request('http://site.local'), None)
deferred.addCallback(lambda _: self.assertTrue(middleware._logerror.called))
return deferred
def test_robotstxt_immediate_error(self):
self.crawler.settings.set('ROBOTSTXT_OBEY', True)
err = error.DNSLookupError('Robotstxt address not found')
def immediate_failure(request, spider):
deferred = Deferred()
deferred.errback(failure.Failure(err))
return deferred
self.crawler.engine.download.side_effect = immediate_failure
middleware = RobotsTxtMiddleware(self.crawler)
return self.assertNotIgnored(Request('http://site.local'), middleware)
def test_ignore_robotstxt_request(self):
self.crawler.settings.set('ROBOTSTXT_OBEY', True)
def ignore_request(request, spider):
deferred = Deferred()
reactor.callFromThread(deferred.errback, failure.Failure(IgnoreRequest()))
return deferred
self.crawler.engine.download.side_effect = ignore_request
middleware = RobotsTxtMiddleware(self.crawler)
mw_module_logger.error = mock.MagicMock()
d = self.assertNotIgnored(Request('http://site.local/allowed'), middleware)
d.addCallback(lambda _: self.assertFalse(mw_module_logger.error.called))
return d
def test_robotstxt_user_agent_setting(self):
crawler = self._get_successful_crawler()
crawler.settings.set('ROBOTSTXT_USER_AGENT', 'Examplebot')
crawler.settings.set('USER_AGENT', 'Mozilla/5.0 (X11; Linux x86_64)')
middleware = RobotsTxtMiddleware(crawler)
rp = mock.MagicMock(return_value=True)
middleware.process_request_2(rp, Request('http://site.local/allowed'), None)
rp.allowed.assert_called_once_with('http://site.local/allowed', 'Examplebot')
def assertNotIgnored(self, request, middleware):
spider = None # not actually used
dfd = maybeDeferred(middleware.process_request, request, spider)
dfd.addCallback(self.assertIsNone)
return dfd
def assertIgnored(self, request, middleware):
spider = None # not actually used
return self.assertFailure(maybeDeferred(middleware.process_request, request, spider),
IgnoreRequest)
class RobotsTxtMiddlewareWithRerpTest(RobotsTxtMiddlewareTest):
if not rerp_available():
skip = "Rerp parser is not installed"
def setUp(self):
super().setUp()
self.crawler.settings.set('ROBOTSTXT_PARSER', 'scrapy.robotstxt.RerpRobotParser')
class RobotsTxtMiddlewareWithReppyTest(RobotsTxtMiddlewareTest):
if not reppy_available():
skip = "Reppy parser is not installed"
def setUp(self):
super().setUp()
self.crawler.settings.set('ROBOTSTXT_PARSER', 'scrapy.robotstxt.ReppyRobotParser')
|
