pdf-reader

pdf_reader.rb

require 'pdf/reader'

raw_string = ''
#INSTRUCTION: save it locally http://www.energy.umich.edu/sites/default/files/pdf-sample.pdf
filename = File.expand_path(File.dirname(__FILE__)) + '/pdf-sample.pdf'
PDF::Reader.open(filename) do |reader|
  reader.pages.each do |page|
    raw_string  = page.raw_content
    puts page.raw_content
  end
end

#check if 'raw_string' is Malformed PDF or not
PDF::Reader.new(StringIO.new(raw_string))
puts 'done'

trying to find out why I keep getting ``find_first_xref_offset': PDF does not contain EOF marker (PDF::Reader::MalformedPDFError)` error.

note: this gist requires pdf-reader gem (https://github.com/yob/pdf-reader)