#!/usr/bin/ruby -w
#=======================================================================
# leeurl.rb - extraer los URL de un documento HTML
#-----------------------------------------------------------------------
#
#-----------------------------------------------------------------------
# FJA - neocipres@gmail.com Septiembre de 2008
#=======================================================================
require 'open-uri'
URL_LOCATIONS = %w{http https ftp img mailto}.freeze
texto = ''
html = ''
begin
cad_url, todos = ARGV
raise if !cad_url
uri = URI.parse(cad_url)
texto = uri.read
if todos
urls = URI.extract(texto)
else
urls = URI.extract(texto, URL_LOCATIONS)
end
print "\n\t", "="*79 ,"\n"
urls.each {|u| puts "\t #{u} "}
print "\t", "="*79,"\n\n"
html << '' << "\n"
html << '' << '' << '' << "\n"
html << '
' << '' << "# Host -> #{uri.host} Puerto -> #{uri.port} URL -> #{cad_url} #" << "
" << '
' << '
' << "\n"
urls.each do |u|
html << ' #{u}
" << "\n"
end
html << '' << "\n"
open("/tmp/urls.html", "w") do |f|
f.write(html)
end
print "\n\t Generado el archivo: /tmp/urls.html \n\n"
rescue
if !cad_url
print "\n\t", "="*65
print "\n\t Uso: leeurl [t]\n"
print "\n\t\t leeurl es un enlace simbólico a cb18.rb"
print "\n\t\t ejemplo de URL: http://www.gnu.org"
print "\n\t", "="*65, "\n\n"
else
print "\n\t Error-> #{$!} \n\n"
end
end