etd department extraction

gistfile1.rb

#!/usr/bin/env ruby
require 'pdf-reader'
class Extracter

  def main
    Dir['*.pdf'].each do |pdf|
      puts "Analyzing #{pdf}"
      reader = PDF::Reader.new(pdf)
      lines = reader.pages.collect {|p| p.text.lines.collect {|l| l.strip}}.flatten
      lines.each_with_index do |line, i|
        puts lines[i-1] if line.match(/^University of Illinois/i)
      end
      puts "\n"
    end
  end
  
end

Extracter.new.main