pdf2text.rb

require 'rake'
require 'logger'
require 'pdf-reader'

#Usage 
# [1] Create a new directory and copy pdf2txt.rb in this directory.
# [2] Insert  also your pdf files in this directory. 
# For every pdf file in this directory, this script will  create a new textfile extracting the text from your original pdf file. 

# File paths nad Log paths
BASE_DIR=File.expand_path(File.dirname(__FILE__))
LOG_DIR = BASE_DIR

# Logger
logger = Logger.new(LOG_DIR + '/pdf2text.log', 'daily')
logger.datetime_format = "%H:%M:%S"


FileList[ BASE_DIR + '/*.pdf'].each do |tpdf|

  begin
    reader = PDF::Reader.new(tpdf)
    logger.info("Reading #{tpdf}")
  rescue
    logger.error("Cannot read #{tpdf}")
  end
  # # # puts reader.pdf_version
  # # # puts reader.info[:Producer]
  # # puts reader.metadata
  # puts reader.page_count

  #print reader.pages[11].text, "\n"  #extract a single page
  ttxt = File.join(File.dirname(tpdf), File.basename(tpdf,".*") + ".txt")
  begin
    File.open(ttxt,"w+") { |f|
    # f << "=== #{BASE_DIR("\\")[-1]} ===\n\n"
      reader.pages.each do |page|
        f << page.text
      end
    }
    logger.info("#{ttxt} created")
  rescue
    logger.error("Cannot create #{ttxt}")   
  end
  
end