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 CrawlerComments < 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.xpath('//comment()').each do |comment|
17
      # searching for href
18
      hr = /href\s*=\s*"([^"]*)"/.match(comment)
19
      if hr
20
        begin
21
          hreq = urltohash('GET', hr[1], request['uri'], nil)
22
          insertnewpath(hreq)
23
        rescue URI::InvalidURIError
24
          # ignored
25
        end
26
      end
27

28
    end
29

30
  end
31
end
32

33