Class: Anemone::Page

Inherits:

Object

• Object
• Anemone::Page

show all

Defined in:

lib/anemone/page.rb

Overview

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

Instance Method Summary (collapse)

• - (Object) doc

  Nokogiri document for the HTML body.

• - (String) extract_domain(url)

  Extracts the domain from a URI object.

• - (Boolean) in_domain?(uri)

  Returns true if uri is in the same domain as the page, returns false otherwise.

• - (Object) links (also: #old_links)

  Array of distinct A tag HREFs and (i)frame SRCs from the page
  The original links() method takes care of A tags and the added code takes care of (i)frame SRCs.

50
51
52
53
54

# File 'lib/anemone/page.rb', line 50

def doc
  return @doc if @doc
#      @doc = Nokogiri::HTML( @body ) if @body && html? rescue nil
  @doc = Nokogiri::HTML( @body ) if @body rescue nil
end

78
79
80
81
82
83
84
85
86
87

# File 'lib/anemone/page.rb', line 78

def extract_domain( url )

    if !url.host then return false end
        
    splits = url.host.split( /\./ )

    if splits.length == 1 then return true end

    splits[-2] + "." + splits[-1]
end

63
64
65
66
67
68
69

# File 'lib/anemone/page.rb', line 63

def in_domain?( uri )
    if( Arachni::Options.instance.follow_subdomains )
        return extract_domain( uri ) ==  extract_domain( @url )
    end

    uri.host == @url.host
end

32
33
34
35
36
37
38
39
40
41
42
43
44
45

# File 'lib/anemone/page.rb', line 32

def links
    @links = old_links
    return @links if !doc
    
    doc.css('frame', 'iframe').each do |a|
        u = a.attributes['src'].content rescue nil
        next if u.nil? or u.empty?
        abs = to_absolute(URI(u)) rescue next
        @links << abs if in_domain?(abs)
    end
    
    @links.uniq!
    @links
end