Contents

require 'pdf-reader'

module Util
  class ExtractPdfText
    def initialize(pdf)
      @pdf = pdf
      @extracted_text = ''
      read_text
    end

    attr_reader :extracted_text

    def read_text
      reader = PDF::Reader.new(@pdf.path)
      reader.pages.each do |page|
        @extracted_text += page.text
      end
    end
  end
end

Version data entries

45 entries across 45 versions & 1 rubygems

Version	Path
inspec_tools-3.1.0	lib/utilities/extract_pdf_text.rb
inspec_tools-3.1.0.pre1	lib/utilities/extract_pdf_text.rb
inspec_tools-3.0.0	lib/utilities/extract_pdf_text.rb
inspec_tools-2.3.8	lib/utilities/extract_pdf_text.rb
inspec_tools-2.3.7	lib/utilities/extract_pdf_text.rb
inspec_tools-2.3.6	lib/utilities/extract_pdf_text.rb
inspec_tools-2.3.5	lib/utilities/extract_pdf_text.rb
inspec_tools-2.3.4	lib/utilities/extract_pdf_text.rb
inspec_tools-2.3.3	lib/utilities/extract_pdf_text.rb
inspec_tools-2.3.2	lib/utilities/extract_pdf_text.rb
inspec_tools-2.3.1	lib/utilities/extract_pdf_text.rb
inspec_tools-2.2.0	lib/utilities/extract_pdf_text.rb
inspec_tools-2.1.0	lib/utilities/extract_pdf_text.rb
inspec_tools-2.0.7	lib/utilities/extract_pdf_text.rb
inspec_tools-2.0.6	lib/utilities/extract_pdf_text.rb
inspec_tools-2.0.5	lib/utilities/extract_pdf_text.rb
inspec_tools-2.0.4	lib/utilities/extract_pdf_text.rb
inspec_tools-2.0.3	lib/utilities/extract_pdf_text.rb
inspec_tools-2.0.2.pre13	lib/utilities/extract_pdf_text.rb
inspec_tools-0.0.0.1.ENOTAG	lib/utilities/extract_pdf_text.rb