# rss scraper for emol.com
# (c) Duncan Mac-Vicar P.

require 'hpricot'
require 'open-uri'
require 'time'

titles = Array.new
previews = Array.new
links = Array.new
times = Array.new

# load the emol news page
doc = Hpricot(open("http://www.emol.com/noticias/todas/_portada/todas.asp"))

doc.search('#noticias_listado').search('span.noticias_listado_titulos') do | el |
  link = el.at('a')
  titles << link.inner_html
  links << link['href']
  #puts link['href']
end

doc.search('#noticias_listado').search('span.noticias_preview') do | el |
  previews << el.inner_html
  #puts el.inner_html
end

doc.search('#noticias_listado').search('span.hora_noticias') do | el |
  times << el.inner_html
  #puts el.inner_html
end

#date = doc.search('#noticias_listado').search('span.verd1negra').at('strong').inner_html
#puts date

puts "<?xml version=\"1.0\" encoding=\"iso-8859-1\"?>"
puts "<rss version=\"2.0\">"
puts "<channel>"
puts "  <title>EMOL.com</title>"
puts "  <description>EMOL.com, Edición en línea del periódico.</description>"
puts "  <link>http://www.emol.com</link>"
i = 0;
titles.each do | title |
  puts "  <item>"
  puts "  <title>#{times[i]} - #{titles[i]}</title>"
  puts "  <description>#{previews[i]}</description>"
  puts "  <link>http://www.emol.com#{links[i]}</link>"
  #puts "   <pubDate>"Tue, 03 Jun 2003 09:39:21 GMT"</pubDate>
  #<guid>http://liftoff.msfc.nasa.gov/2003/06/03.html#item573</guid>
  puts "  </item>"
  i = i + 1
end
puts "</channel>"
puts "</rss>"