Class: Arachni::Spider

Inherits:
Object show all
Includes:
Module::Utilities, UI::Output
Defined in:
lib/arachni/spider.rb

Overview

Spider class

Crawls the URL in opts and grabs the HTML code and headers.

@author: Tasos “Zapotek” Laskos

<[email protected]>
<[email protected]>

@version: 0.2.3

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods included from Module::Utilities

#exception_jail, #get_path, #hash_keys_to_str, #normalize_url, #read_file, #seed, #uri_decode, #uri_encode, #uri_parse, #uri_parser, #url_sanitize

Methods included from UI::Output

#buffer, #debug!, #debug?, #flush_buffer, #mute!, #muted?, #only_positives!, #only_positives?, #print_bad, #print_debug, #print_debug_backtrace, #print_debug_pp, #print_error, #print_error_backtrace, #print_info, #print_line, #print_ok, #print_status, #print_verbose, #reroute_to_file, #reroute_to_file?, #uncap_buffer!, #unmute!, #verbose!, #verbose?

Constructor Details

#initialize(opts) ⇒ Spider

Constructor <br/> Instantiates Spider class with user options.

Parameters:



58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
 
# File 'lib/arachni/spider.rb', line 58

def initialize( opts )
    @opts = opts

    @sitemap   = []
    @redirects = []
    @on_every_page_blocks = []

    @seed_url = @opts.url.to_s

    @extend_paths   = @opts.extend_paths   || []
    @restrict_paths = @opts.restrict_paths || []

    @paths = [ @seed_url ]

    if restricted_to_paths?
        @paths |= @sitemap = @restrict_paths
    else
        @paths |= @extend_paths
    end

    # if we have no 'include' patterns create one that will match
    # everything, like '.*'
    @opts.include =[ Regexp.new( '.*' ) ] if @opts.include.empty?
end

Instance Attribute Details

#opts ⇒ Options (readonly)

Returns:



36
37
38
 
# File 'lib/arachni/spider.rb', line 36

def opts
  @opts
end

#redirects ⇒ Array (readonly)

URLs that caused redirects

Returns:



50
51
52
 
# File 'lib/arachni/spider.rb', line 50

def redirects
  @redirects
end

#sitemap ⇒ Array (readonly)

Discovered paths

Returns:



43
44
45
 
# File 'lib/arachni/spider.rb', line 43

def sitemap
  @sitemap
end

Instance Method Details

#http ⇒ Object 



180
181
182
 
# File 'lib/arachni/spider.rb', line 180

def http
    Arachni::HTTP.instance
end

#pause! ⇒ Object 



218
219
220
 
# File 'lib/arachni/spider.rb', line 218

def pause!
    @pause = true
end

#paused? ⇒ Boolean

Returns:

  • (Boolean) 


226
227
228
229
 
# File 'lib/arachni/spider.rb', line 226

def paused?
    @pause ||= false
    return @pause
end

#redundant?(url) ⇒ Boolean

Returns:

  • (Boolean) 


188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
 
# File 'lib/arachni/spider.rb', line 188

def redundant?( url )
    @opts.redundant.each_with_index {
        |redundant, i|

        if( url =~ redundant['regexp'] )

            if( @opts.redundant[i]['count'] == 0 )
                print_verbose( 'Discarding redundant page: \'' + url + '\'' )
                return true
            end

            print_info( 'Matched redundancy rule: ' +
            redundant['regexp'].to_s + ' for page \'' +
            url + '\'' )

            print_info( 'Count-down: ' + @opts.redundant[i]['count'].to_s )

            @opts.redundant[i]['count'] -= 1
        end
    }
    return false
end

#restricted_to_paths? ⇒ Boolean

Returns:

  • (Boolean) 


83
84
85
 
# File 'lib/arachni/spider.rb', line 83

def restricted_to_paths?
    !@restrict_paths.empty?
end

#resume! ⇒ Object 



222
223
224
 
# File 'lib/arachni/spider.rb', line 222

def resume!
    @pause = false
end

#run(parse = true, &block) ⇒ Arachni::Parser::Page

Runs the Spider and passes parsed page to the block

Parameters:

  • block (Block)

Returns:



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
 
# File 'lib/arachni/spider.rb', line 94

def run( parse = true, &block )
    return if @opts.link_count_limit == 0

    visited = []

    opts = {
        :timeout    => nil,
        :remove_id  => true,
        :follow_location => true,
        :update_cookies  => true
    }

    # we need a parser in order to have access to skip() in case
    # there's a redirect that shouldn't be followed
    seed_page = http.get( @seed_url, opts.merge( :async => false ) ).response

    print_status( "[HTTP: #{seed_page.code}] " + seed_page.effective_url )

    parser = Parser.new( @opts, seed_page )
    parser.url = @seed_url
    @paths = parser.paths | [@seed_url]

    while( !@paths.empty? )
        while( !@paths.empty? && url = parser.to_absolute( @paths.pop ) )
            next if skip?( url ) || visited.include?( url )

            wait_if_paused

            visited << url

            http.get( url, opts ).on_complete {
                |res|

                next if parser.skip?( res.effective_url )

                print_status( "[HTTP: #{res.code}] " + res.effective_url )

                if parse
                    page = Arachni::Parser::Page.from_http_response( res, @opts )
                    paths = page.paths
                    check_url = page.url
                else
                    c_parser = Parser.new( @opts, res )
                    paths = c_parser.text? ? c_parser.paths : []
                    check_url = c_parser.url
                end

                if !restricted_to_paths?
                    @sitemap |= paths

                    if !res.headers_hash['Location'].empty?
                        @redirects << res.request.url
                    end

                    @paths   |= @sitemap - visited
                end

                # call the block...if we have one
                if block
                    exception_jail{
                        if !skip?( check_url )
                            block.call( parse ? page.clone : res )
                        else
                            print_info( 'Matched skip rule.' )
                        end
                    }
                end
            }

            # make sure we obey the link count limit and
            # return if we have exceeded it.
            if( @opts.link_count_limit &&
                @opts.link_count_limit > 0 &&
                visited.size >= @opts.link_count_limit )
                http.run
                return @sitemap.uniq
            end

        end

        http.run
    end

    return @sitemap.uniq
end

#skip?(url) ⇒ Boolean

Returns:

  • (Boolean) 


184
185
186
 
# File 'lib/arachni/spider.rb', line 184

def skip?( url )
    redundant?( url )
end

#wait_if_paused ⇒ Object 



212
213
214
215
216
 
# File 'lib/arachni/spider.rb', line 212

def wait_if_paused
    while( paused? )
        ::IO::select( nil, nil, nil, 1 )
    end
end