python-2.5.2/win32/Lib/test/test_robotparser.py
changeset 0 ae805ac0140d
equal deleted inserted replaced
-1:000000000000 0:ae805ac0140d
       
     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.failUnless(self.parser.can_fetch(agent, url))
       
    24         else:
       
    25             self.failIf(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 class TestCase(unittest.TestCase):
       
   138     def runTest(self):
       
   139         test_support.requires('network')
       
   140         # whole site is password-protected.
       
   141         url = 'http://mueblesmoraleda.com'
       
   142         parser = robotparser.RobotFileParser()
       
   143         parser.set_url(url)
       
   144         parser.read()
       
   145         self.assertEqual(parser.can_fetch("*", url+"/robots.txt"), False)
       
   146 
       
   147 def test_main():
       
   148     test_support.run_suite(tests)
       
   149     TestCase().run()
       
   150 
       
   151 if __name__=='__main__':
       
   152     test_support.Verbose = 1
       
   153     test_support.run_suite(tests)