Created
May 7, 2014 19:20
-
-
Save btaitelb/9a6fdbfb7d4e0431b494 to your computer and use it in GitHub Desktop.
How many recently visited domains used wordpress?
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env ruby | |
## Dependencies: | |
## * curl | |
## * jq (not really needed, but I like it) | |
## * sqlite | |
## * quit chrome before running this since the History file is locked | |
require 'uri' | |
HISTORY_FILE = File.expand_path("~/Library/Application Support/Google/Chrome/Default/History") | |
BW_KEY = "ENTER_YOUR_BUILTWITH_API_KEY" | |
LIMIT_TO_50 = true # 50 credits available with free key from api.builtwith.com | |
def domains_from_chrome(count=1000) | |
sql = "select url from urls order by last_visit_time desc limit #{count}" | |
`sqlite3 "#{HISTORY_FILE}" "#{sql}"`.split("\n").map{|u| URI.parse(u).host}.uniq | |
end | |
def built_with_wordpress?(url="builtwith.com") | |
lookup = "http://api.builtwith.com/v3/api.json?KEY=#{BW_KEY}&LOOKUP=#{url}" | |
bw_results = `curl -s "#{lookup}" | jq '.Result.Paths[].Technologies[].Name' | grep Wordpress`.strip | |
puts bw_results | |
!bw_results.empty? | |
end | |
domains = domains_from_chrome | |
if LIMIT_TO_50 | |
domains = domains[0...50] | |
end | |
count = domains.count | |
wp_count = 0 | |
domains.each do |domain| | |
print "domain: #{domain}" | |
wordpress = built_with_wordpress?(domain) | |
puts "\t wordpress? #{wordpress}\n\n" | |
wp_count += 1 if wordpress | |
end | |
puts "#{wp_count} / #{count} recently visited domains use wordpress" | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment