/usr/lib/python2.7/test/test_robotparser.py is in libpython2.7-testsuite 2.7.15~rc1-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | import os
import robotparser
import unittest
from test import support
from BaseHTTPServer import BaseHTTPRequestHandler, HTTPServer
import StringIO
try:
import threading
except ImportError:
threading = None
class BaseRobotTest:
robots_txt = ''
agent = 'test_robotparser'
good = []
bad = []
def setUp(self):
lines = StringIO.StringIO(self.robots_txt).readlines()
self.parser = 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)
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)
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 RejectAllRobotsTest(BaseRobotTest, unittest.TestCase):
robots_txt = """\
# go away
User-agent: *
Disallow: /
"""
good = []
bad = ['/cyberworld/map/index.html', '/', '/tmp/']
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(BaseRobotTest, unittest.TestCase):
robots_txt = """\
User-agent: *
Crawl-delay: 1
Request-rate: 3/15
Disallow: /cyberworld/map/
"""
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 = 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 = 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)
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 = robotparser.RobotFileParser(self.url('i-robot.txt'))
parser.read()
self.assertTrue(parser.allow_all)
self.assertFalse(parser.disallow_all)
self.assertEqual(parser.mtime(), 0)
def test_main():
support.run_unittest(
UserAgentWildcardTest,
RejectAllRobotsTest,
UserAgentOrderingTest,
UserAgentGoogleMobileTest,
GoogleURLOrderingTest,
DisallowQueryStringTest,
UseFirstUserAgentWildcardTest,
EmptyQueryStringTest,
DefaultEntryTest,
PasswordProtectedSiteTestCase,
NetworkTestCase)
if __name__ == "__main__":
test_main()
|