Unique domains list from ICANN zones files

unique_domains.rb

#!/usr/bin/env ruby

# Based on https://sive.rs/com - extended it to read from gzipped file, support any domain extension, and output to separate file

require 'hashie'
require 'zlib'

class Parser < Hashie::Dash

  property :extension, required: 'true' # e.g. "com" for dotcom database

  def uniqify
    domain = ''
    infile = open("#{self.extension}.txt.gz")
    instream = Zlib::GzipReader.new(infile)
    outstream = File.open("#{self.extension}.uniq.txt", 'w')
    while line = instream.gets
      temp = line[0...(line.index(".#{self.extension}"))]
      next if temp == domain
      domain = temp
      outstream.puts domain
    end
  end

end

Parser.new(extension: 'com').uniqify