Class: Arachni::Spider

Inherits:
Object
  • Object
show all
Includes:
UI::Output
Defined in:
lib/spider.rb

Overview

Spider class

Crawls the URL in opts[:url] and grabs the HTML code and headers.

@author: Anastasios “Zapotek” Laskos 

                                     <tasos.laskos@gmail.com>
                                     <zapotek@segfault.gr>

@version: 0.1-pre

Instance Attribute Summary (collapse)

Instance Method Summary (collapse)

Methods included from UI::Output

#debug!, #debug?, #only_positives!, #only_positives?, #print_debug, #print_debug_backtrace, #print_debug_pp, #print_error, #print_info, #print_line, #print_ok, #print_status, #print_verbose, #verbose!, #verbose?

Constructor Details

- (Spider) initialize(opts)

Constructor
Instantiates Spider class with user options.

Parameters:



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
 
# File 'lib/spider.rb', line 63

def initialize( opts )
    @opts = opts
    @anemone_opts = {
        :threads              =>  3,
        :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 =
        @opts.include.empty? ? [ Regexp.new( '.*' ) ] : @opts.include
end

Instance Attribute Details

- (Proc) on_every_page_blocks (readonly)

Code block to be executed on each page

Returns:

  • (Proc) 


55
56
57
 
# File 'lib/spider.rb', line 55

def on_every_page_blocks
  @on_every_page_blocks
end

- (Options) opts (readonly)

Returns:



41
42
43
 
# File 'lib/spider.rb', line 41

def opts
  @opts
end

- (Array) sitemap (readonly)

Sitemap, array of links

Returns:

  • (Array) 


48
49
50
 
# File 'lib/spider.rb', line 48

def sitemap
  @sitemap
end

Instance Method Details

- (self) on_every_page(&block)

Hook for further analysis of pages, statistics etc.

Parameters:

  • (Proc) block —

    code to be executed for every page

Returns:

  • (self) 


172
173
174
175
 
# File 'lib/spider.rb', line 172

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

- (Array) run(&block)

Runs the Spider and passes the url, html and headers Hash

Parameters:

  • (Proc) block —

    a block expecting url, html, cookies

Returns:

  • (Array) —

    array of links, a sitemap 



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
 
# File 'lib/spider.rb', line 107

def run( &block )

    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|

            url = 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
                block.call( url, page.body, page.headers )
            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