Module: WebSite::RobotsTxt

Included in:
WebSite
Defined in:
lib/wpscan/web_site/robots_txt.rb

Class Method Summary (collapse)

Instance Method Summary (collapse)

Class Method Details

+ (Array) known_dirs (protected)

Returns:



54
55
56
57
58
59
60
61
 
# File 'lib/wpscan/web_site/robots_txt.rb', line 54

def self.known_dirs
  %w{
    /
    /wp-admin/
    /wp-includes/
    /wp-content/
  }
end

Instance Method Details

- (Boolean) has_robots?

Checks if a robots.txt file exists

Returns:

  • (Boolean) 


8
9
10
 
# File 'lib/wpscan/web_site/robots_txt.rb', line 8

def has_robots?
  Browser.get(robots_url).code == 200
end

- (Array) parse_robots_txt

Parse robots.txt

Returns:

  • (Array) —

    URLs generated from robots.txt



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
 
# File 'lib/wpscan/web_site/robots_txt.rb', line 23

def parse_robots_txt
  return unless has_robots?

  return_object = []
  response = Browser.get(robots_url.to_s)
  body = response.body
  # Get all allow and disallow urls
  entries = body.scan(/^(?:dis)?allow:\s*(.*)$/i)
  if entries
    entries.flatten!
    entries.compact.sort!
    wordpress_path = @uri.path
    RobotsTxt.known_dirs.each do |d|
      entries.delete(d)
      # also delete when wordpress is installed in subdir
      dir_with_subdir = "#{wordpress_path}/#{d}".gsub(/\/+/, '/')
      entries.delete(dir_with_subdir)
    end

    entries.each do |d|
      temp = @uri.clone
      temp.path = d
      return_object << temp.to_s
    end
  end
  return_object
end

- (String) robots_url

Gets a robots.txt URL

Returns:

  • (String) 


14
15
16
17
18
 
# File 'lib/wpscan/web_site/robots_txt.rb', line 14

def robots_url
  temp = @uri.clone
  temp.path = '/robots.txt'
  temp.to_s
end