Convert PDF to XML in Ruby using poppler-utils

pdf_to_xml.rb

# Install dependencies:
#
# posix-spawn (check all benefits at https://github.com/rtomayko/posix-spawn)
#   gem install posix-spawn
#
# Poppler utils (http://poppler.freedesktop.org/)
#   apt-get install poppler-utils
#

require 'posix/spawn'

def pdf_to_xml(pdf_path)
  cmd = "pdftohtml -stdout -xml -i -fontfullname \"#{pdf_path}\" 2>&1"
  POSIX::Spawn::Child.new(cmd).out
end

pdf_to_xml('sample.pdf')