La Tercera

latercera.rb

require 'open-uri'
require 'net/http'
require 'fileutils.rb'

fecha = Time.now.strftime("%Y/%m/%d")

def remote_file_exists?(url)
	url = URI.parse(url)
	Net::HTTP.start(url.host, url.port) do |http|
		return http.head(url.request_uri).code == "200"
	end
end

puts "Creando directorio temporal de descarga"
FileUtils.mkdir("/tmp/latercera/")

count = 1

loop do
	file = "%03d.pdf" % count.to_s
	url = "http://papeldigital.info/lt/#{fecha}/01/paginas/" + file
		if remote_file_exists?(url) == true
  		open("/tmp/latercera/" + File.basename(url), "wb") do |file|
  			open(url) do |uri|
  				puts "Descargando #{url}"
     			file.write(uri.read)
 			end
 		end
  		else
  			break
  		end
	count += 1
end

out = "LATERCERA_" + Time.now.strftime("%Y-%m-%d") + ".pdf"

puts "Combinando PDF"
system("gs -q -dNOPAUSE -dBATCH -sDEVICE=pdfwrite -sOutputFile=#{out} /tmp/latercera/*.pdf")

puts "Eliminando archivos"
FileUtils.rm(Dir.glob('/tmp/latercera/0*.pdf'))

puts "Quitando directorio temporal"
FileUtils.rm_rf("/tmp/latercera/")