pdf-reader — Ruby gem

PDF To Doc coversion with the help of pdf-reader gem

require ‘rubygems’
require ‘pdf/reader’
class PageTextReceiver
attr_accessor :content

def initialize
@content = []
end

1. Called when page parsing starts

def begin_page(arg = nil)
@content << “”
end

1. record text that is drawn on the page

def show_text(string, *params)
@content.last << string.strip
end

1. there’s a few text callbacks, so make sure we process them all

alias :super_show_text :show_text
alias :move_to_next_line_and_show_text :show_text
alias :set_spacing_next_line_show_text :show_text

1. this final text callback takes slightly different arguments

def show_text_with_positioning(*params)
params = params.first
params.each { |str| show_text(str) if str.kind_of?(String)}
end
end

receiver = PageTextReceiver.new
pdf = PDF::Reader.file(“c:\\user.pdf”, receiver)
file=File.open(“test.doc”,”w”)

file.puts receiver.content.inspect
file.close