Class: Arachni::Spider

Inherits:
Object show all
Includes:
Module::Utilities, UI::Output
Defined in:
lib/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: 0.1

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods included from Module::Utilities

#exception_jail, #get_path, #normalize_url, #read_file, #seed

Methods included from UI::Output

#buffer, #debug!, #debug?, #flush_buffer, #mute!, #muted?, #only_positives!, #only_positives?, #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?, #unmute!, #verbose!, #verbose?

Constructor Details

#initialize(opts) ⇒ Spider

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

Parameters:



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
 
# File 'lib/spider.rb', line 59

def initialize( opts )
    @opts = opts

    @anemone_opts = {
        :threads              =>  1,
        :discard_page_bodies  =>  false,
        :delay                =>  0,
        :obey_robots_txt      =>  false,
        :depth_limit          =>  false,
        :link_count_limit     =>  false,
        :redirect_limit       =>  false,
        :storage              =>  nil,
        :cookies              =>  nil,
        :accept_cookies       =>  true,
        :proxy_addr           =>  nil,
        :proxy_port           =>  nil,
        :proxy_user           =>  nil,
        :proxy_pass           =>  nil
    }

    hash_opts = @opts.to_h
    @anemone_opts.each_pair {
        |k, v|
        @anemone_opts[k] = hash_opts[k.to_s] if hash_opts[k.to_s]
    }

    @anemone_opts = @anemone_opts.merge( hash_opts )

    @sitemap = []
    @on_every_page_blocks = []

    # 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

#on_every_page_blocks ⇒ Proc (readonly)

Code block to be executed on each page

Returns:

  • (Proc) 


51
52
53
 
# File 'lib/spider.rb', line 51

def on_every_page_blocks
  @on_every_page_blocks
end

#opts ⇒ Options (readonly)

Returns:



35
36
37
 
# File 'lib/spider.rb', line 35

def opts
  @opts
end

#pages ⇒ Object (readonly)

Returns the value of attribute pages.



37
38
39
 
# File 'lib/spider.rb', line 37

def pages
  @pages
end

#sitemap ⇒ Array (readonly)

Sitemap, array of links

Returns:

  • (Array) 


44
45
46
 
# File 'lib/spider.rb', line 44

def sitemap
  @sitemap
end

Instance Method Details

#on_every_page(&block) ⇒ self

Hook for further analysis of pages, statistics etc.

Parameters:

  • block (Proc) —

    code to be executed for every page

Returns:

  • (self) 


194
195
196
197
 
# File 'lib/spider.rb', line 194

def on_every_page( &block )
    @on_every_page_blocks.push( block )
    self
end

#run(&block) ⇒ Arachni::Parser::Page

Runs the Spider and passes parsed page to the block

Parameters:

  • block (Block)

Returns:



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
 
# File 'lib/spider.rb', line 102

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

    i = 1
    # start the crawl
    Anemone.crawl( @opts.url, @anemone_opts ) {
        |anemone|

        # apply 'exclude' patterns
        anemone.skip_links_like( @opts.exclude ) if @opts.exclude

        # apply 'include' patterns and grab matching pages
        # as they are discovered
        anemone.on_pages_like( @opts.include ) {
            |page|

            @pages = anemone.pages.keys || []

            url = url_sanitize( page.url.to_s )

            # something went kaboom, tell the user and skip the page
            if page.error
                print_error( "[Error: " + (page.error.to_s) + "] " + url )
                print_debug_backtrace( page.error )
                next
            end

            # push the url in the sitemap
            @sitemap.push( url )

            print_line
            print_status( "[HTTP: #{page.code}] " + url )

            # call the block...if we have one
            if block
                exception_jail{
                    new_page = Arachni::Parser.new( @opts,
                        Typhoeus::Response.new(
                            :effective_url => url,
                            :body          => page.body,
                            :headers_hash  => page.headers
                        )
                    ).run
                    new_page.code   = page.code
                    new_page.method = 'GET'
                    block.call( new_page.clone )
                }
            end

            # run blocks specified later
            @on_every_page_blocks.each {
                |block|
                block.call( page )
            }

            # we don't need the HTML doc anymore
            page.discard_doc!( )

            # make sure we obey the link count limit and
            # return if we have exceeded it.
            if( @opts.link_count_limit &&
                @opts.link_count_limit <= i )
                return @sitemap.uniq
            end

            i+=1
        }
    }

    return @sitemap.uniq
end

#url_sanitize(url) ⇒ Object

Decodes URLs to reverse multiple encodes and removes NULL characters



177
178
179
180
181
182
183
184
 
# File 'lib/spider.rb', line 177

def url_sanitize( url )

    while( url =~ /%/ )
        url = ( URI.decode( url ).to_s.unpack( 'A*' )[0] )
    end

    return url
end