/usr/share/w3af/plugins/discovery/findCaptchas.py is in w3af-console 1.0-rc3svn3489-1.
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 | '''
findCaptchas.py
Copyright 2006 Andres Riancho
This file is part of w3af, w3af.sourceforge.net .
w3af is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation version 2 of the License.
w3af is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with w3af; if not, write to the Free Software
Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
'''
import core.controllers.outputManager as om
# options
from core.data.options.option import option
from core.data.options.optionList import optionList
from core.controllers.basePlugin.baseDiscoveryPlugin import baseDiscoveryPlugin
import core.data.parsers.urlParser as urlParser
from core.controllers.w3afException import w3afException
import core.data.kb.knowledgeBase as kb
import core.data.kb.info as info
import sha
import mimetypes
import core.data.parsers.documentParser as documentParser
class findCaptchas(baseDiscoveryPlugin):
'''
Identify captcha images on web pages.
@author: Andres Riancho ( andres.riancho@gmail.com )
'''
def __init__(self):
baseDiscoveryPlugin.__init__(self)
def discover(self, fuzzableRequest ):
'''
Find captcha images.
@parameter fuzzableRequest: A fuzzableRequest instance that contains (among other things) the URL to test.
'''
# GET the document, and fetch the images
image_map_1 = self._get_images( fuzzableRequest )
# Re-GET the document, and fetch the images
image_map_2 = self._get_images( fuzzableRequest )
# Compare the images (different images may be captchas)
changed_images_list = []
if image_map_1.keys() != image_map_2.keys():
for img_src in image_map_1:
if img_src not in image_map_2 and self._has_image_extension( img_src ):
changed_images_list.append( img_src )
else:
# Compare content
for img_src in image_map_1:
if image_map_1[ img_src ] != image_map_2[ img_src ]:
changed_images_list.append( img_src )
for img_src in changed_images_list:
i = info.info()
i.setName('Captcha image detected')
i.setURL( img_src )
i.setMethod( 'GET' )
i.setDesc( 'Found a CAPTCHA image at: "' + img_src + '".')
kb.kb.append( self, 'findCaptchas', i )
om.out.information( i.getDesc() )
return []
def _has_image_extension( self, img_src ):
'''
Verify it the image source is an image or "a php script".
'''
if 'image' in mimetypes.guess_type( urlParser.getFileName(img_src) )[0]:
return True
else:
return False
def _get_images( self, fuzzable_request ):
'''
Get all img tags and retrieve the src.
@parameter fuzzable_request: The request to modify
@return: A map with the img src as a key, and a hash of the image contents as the value
'''
res = {}
try:
response = self._urlOpener.GET( fuzzable_request.getURI(), useCache=False )
except:
om.out.debug('Failed to retrieve the page for finding captchas.')
else:
# Do not use dpCache here, it's no good.
#dp = dpCache.dpc.getDocumentParserFor( response )
try:
document_parser = documentParser.documentParser( response )
except w3afException:
pass
else:
image_list = document_parser.getReferencesOfTag('img')
image_list = [ urlParser.uri2url(i) for i in image_list]
for img_src in image_list:
# TODO: Use self._tm.startFunction
try:
image_response = self._urlOpener.GET( img_src, useCache=False )
except:
om.out.debug('Failed to retrieve the image for finding captchas.')
else:
res[ img_src ] = sha.new(image_response.getBody()).hexdigest()
return res
def getOptions( self ):
'''
@return: A list of option objects for this plugin.
'''
ol = optionList()
return ol
def setOptions( self, OptionList ):
'''
This method sets all the options that are configured using the user interface
generated by the framework using the result of getOptions().
@parameter OptionList: A dictionary with the options for the plugin.
@return: No value is returned.
'''
pass
def getPluginDeps( self ):
'''
@return: A list with the names of the plugins that should be runned before the
current one.
'''
return []
def getLongDesc( self ):
'''
@return: A DETAILED description of the plugin functions and features.
'''
return '''
This plugin finds any CAPTCHA images that appear on a HTML document. The
discovery is performed by requesting the document two times, and comparing the
hashes of the images, if they differ, then they may be a CAPTCHA.
'''
|