parse links

consultation_ipred/Gemfile

+source "http://rubygems.org"
+
+gem 'nokogiri'

consultation_ipred/Gemfile.lock

+GEM
+  remote: http://rubygems.org/
+  specs:
+    nokogiri (1.5.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  nokogiri

consultation_ipred/parser.rb

+
+require "rubygems"
+require "bundler/setup"
+
+require "nokogiri"
+
+files = %w(organisations.html public_authorities.html)
+
+file = files.first
+doc = Nokogiri::HTML(File.read(file))
+
+links = doc.css("a").map do |link|
+  href =link["href"] 
+  href if href =~ /\.pdf$/i
+end.compact
+
+p links