Real-time collaboration for Jupyter Notebooks, Linux Terminals, LaTeX, VS Code, R IDE, and more,
all in one place.

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 CrawlerSimple < BaseParser
11

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

15
    # doc = Hpricot(result.body.to_s)
16
    doc = Nokogiri::HTML(result.body.to_s)
17
    doc.css('a').each do |anchor_tag|
18
      hr = anchor_tag['href']
19
      if hr && !hr.match(/^(\#|javascript\:)/)
20
        begin
21
          hreq = urltohash('GET', hr, request['uri'], nil)
22
          insertnewpath(hreq)
23
        rescue URI::InvalidURIError
24
          #puts "Parse error"
25
          #puts "Error: #{link[0]}"
26
        end
27
      end
28
    end
29
  end
30
end
31

32

33