/usr/share/w3af/plugins/discovery/sitemapReader.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 | '''
sitemapReader.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.kb.knowledgeBase as kb
from core.controllers.coreHelpers.fingerprint_404 import is_404
import core.data.parsers.urlParser as urlParser
from core.controllers.w3afException import w3afException, w3afRunOnce
class sitemapReader(baseDiscoveryPlugin):
'''
Analyze the sitemap.xml file and find new URLs
@author: Andres Riancho ( andres.riancho@gmail.com )
'''
def __init__(self):
baseDiscoveryPlugin.__init__(self)
# Internal variables
self._exec = True
def discover(self, fuzzableRequest ):
'''
Get the sitemap.xml file and parse it.
@parameter fuzzableRequest: A fuzzableRequest instance that contains (among other things) the URL to test.
'''
if not self._exec:
# This will remove the plugin from the discovery plugins to be runned.
raise w3afRunOnce()
else:
# Only run once
self._exec = False
self._new_fuzzable_requests = []
base_url = urlParser.baseUrl( fuzzableRequest.getURL() )
sitemap_url = urlParser.urlJoin( base_url , 'sitemap.xml' )
response = self._urlOpener.GET( sitemap_url, useCache=True )
# Remember that httpResponse objects have a faster "__in__" than
# the one in strings; so string in response.getBody() is slower than
# string in response
if '</urlset>' in response and not is_404( response ):
om.out.debug('Analyzing sitemap.xml file.')
self._new_fuzzable_requests.extend( self._createFuzzableRequests( response ) )
import xml.dom.minidom
om.out.debug('Parsing xml file with xml.dom.minidom.')
try:
dom = xml.dom.minidom.parseString( response.getBody() )
except:
raise w3afException('Error while parsing sitemap.xml')
urlList = dom.getElementsByTagName("loc")
for url in urlList:
url = url.childNodes[0].data
# Send the requests using threads:
targs = ( url, )
self._tm.startFunction( target=self._get_and_parse, args=targs , ownerObj=self )
# Wait for all threads to finish
self._tm.join( self )
return self._new_fuzzable_requests
def _get_and_parse(self, url):
'''
GET and URL that was found in the robots.txt file, and parse it.
@parameter url: The URL to GET.
@return: None, everything is saved to self._new_fuzzable_requests.
'''
try:
http_response = self._urlOpener.GET( url, useCache=True )
except KeyboardInterrupt, k:
raise k
except w3afException, w3:
msg = 'w3afException while fetching page in discovery.sitemapReader, error: "'
msg += str(w3) + '"'
om.out.debug( msg )
else:
if not is_404( http_response ):
fuzz_reqs = self._createFuzzableRequests( http_response )
self._new_fuzzable_requests.extend( fuzz_reqs )
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 searches for the sitemap.xml file, and parses it.
The sitemap.xml file is used by the site administrator to give the Google crawler more
information about the site. By parsing this file, the plugin finds new URLs and other
usefull information.
'''
|