Lib/test/test_robotparser.py

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