jronallo

#!/usr/bin/env ruby

# a quick, simple script to partially parse output from https://github.com/trivio/common_crawl_index/blob/master/bin/remote_read 
# and output subdomains in order of count

url_counts = {}
total_urls = 0
File.readlines(ARGV[0]).each do |line|
  url = line.split(' ').first
  reverse_hostname = url.split('/').first