CoCalc provides the best real-time collaborative environment for Jupyter Notebooks, LaTeX documents, and SageMath, scalable from individual users to large groups and classes!

1
##
2
# This module requires Metasploit: https://metasploit.com/download
3
# Current source: https://github.com/rapid7/metasploit-framework
4
##
5

6
require 'pathname'
7
require 'nokogiri'
8
require 'uri'
9

10
class CrawlerLink < BaseParser
11

12
  def parse(request,result)
13
    return unless result['Content-Type'].include?('text/html')
14

15
    doc = Nokogiri::HTML(result.body.to_s)
16
    doc.css('link').each do |link|
17
      hr = link['href']
18
      if hr && !hr.match(/^(\#|javascript\:)/)
19
        begin
20
          hreq = urltohash('GET', hr, request['uri'], nil)
21
          insertnewpath(hreq)
22
        rescue URI::InvalidURIError
23
          # ignored
24
        end
25
      end
26

27
    end
28
  end
29
end
30

31

32