Ruby code to detect the language of a webpage.

gistfile1.rb

# gem install nokogiri
# gem install cld

# Use CLD, a wrapper around the google Compact Language Detector to detect the language that a 
# webpage is in. Use Nokogiri to pull out the text of the page.

require 'cld'
require 'open-uri'
require 'nokogiri'

def detect_language url
  f = open url
  s = f.read
  doc = Nokogiri::HTML.parse(s)
  text = doc.text
  CLD.detect_language(text)
end