content_scrapper 0.0.3

data/.document

@@ -0,0 +1,5 @@
+README.rdoc
+lib/**/*.rb
+bin/*
+features/**/*.feature
+LICENSE

data/.gitignore

@@ -0,0 +1,21 @@
+## MAC OS
+.DS_Store
+
+## TEXTMATE
+*.tmproj
+tmtags
+
+## EMACS
+*~
+\#*
+.\#*
+
+## VIM
+*.swp
+
+## PROJECT::GENERAL
+coverage
+rdoc
+pkg
+
+## PROJECT::SPECIFIC

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2009 Gyorgy Frivolt
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.rdoc

@@ -0,0 +1,17 @@
+= content_scrapper
+
+Description goes here.
+
+== Note on Patches/Pull Requests
+ 
+* Fork the project.
+* Make your feature addition or bug fix.
+* Add tests for it. This is important so I don't break it in a
+  future version unintentionally.
+* Commit, do not mess with rakefile, version, or history.
+  (if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
+* Send me a pull request. Bonus points for topic branches.
+
+== Copyright
+
+Copyright (c) 2010 Gyorgy Frivolt. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,56 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "content_scrapper"
+    gem.summary = "Gem for those who want to screen scrap only the content part of web pages, blogs or articles."
+    gem.description = "If you want to cut only the content of pages, without any other part (like the menu, header, footer, commercials, etc.), you might find this gem very handy. A DSL is also defined for nifty definitions for your screen scrapping and sanitization."
+    gem.email = "gyorgy.frivolt@gmail.com"
+    gem.homepage = "http://github.com/fifigyuri/content_scrapper"
+    gem.authors = ["Gyorgy Frivolt"]
+    gem.add_development_dependency 'thoughtbot-shoulda', '>=2.10.2'
+    gem.add_development_dependency 'mocha', '>=0.9.8'
+
+    gem.add_dependency 'sanitize', '>=1.2.0'
+    gem.add_dependency 'nokogiri', '>=1.4.1'
+  end
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
+end
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+begin
+  require 'rcov/rcovtask'
+  Rcov::RcovTask.new do |test|
+    test.libs << 'test'
+    test.pattern = 'test/**/test_*.rb'
+    test.verbose = true
+  end
+rescue LoadError
+  task :rcov do
+    abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
+  end
+end
+
+task :test => :check_dependencies
+
+task :default => :test
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "content_scrapper #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.0.3

data/config/content_scrapper.rb

@@ -0,0 +1,3 @@
+
+sanitize_tags ({:elements => ['p','br', 'b', 'em', 'i', 'strong', 'u', 'a', 'h1', 'h2', 'h3', 'li', 'ol', 'ul'], \
+  :attributes => { 'a' => ['href'] }})

data/content_scrapper.gemspec

@@ -0,0 +1,72 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{content_scrapper}
+  s.version = "0.0.3"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Gyorgy Frivolt"]
+  s.date = %q{2010-02-13}
+  s.description = %q{If you want to cut only the content of pages, without any other part (like the menu, header, footer, commercials, etc.), you might find this gem very handy. A DSL is also defined for nifty definitions for your screen scrapping and sanitization.}
+  s.email = %q{gyorgy.frivolt@gmail.com}
+  s.extra_rdoc_files = [
+    "LICENSE",
+     "README.rdoc"
+  ]
+  s.files = [
+    ".document",
+     ".gitignore",
+     "LICENSE",
+     "README.rdoc",
+     "Rakefile",
+     "VERSION",
+     "config/content_scrapper.rb",
+     "content_scrapper.gemspec",
+     "lib/content_scrapper.rb",
+     "lib/content_scrapper/content_mapping.rb",
+     "lib/content_scrapper/feedzirra.rb",
+     "rails/init.rb",
+     "test/helper.rb",
+     "test/test_content_mapping.rb",
+     "test/test_content_scrapper.rb",
+     "test/test_pages/pretty.html",
+     "test/test_pages/twocontent.html",
+     "test/test_pages/ugly.html"
+  ]
+  s.homepage = %q{http://github.com/fifigyuri/content_scrapper}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.5}
+  s.summary = %q{Gem for those who want to screen scrap only the content part of web pages, blogs or articles.}
+  s.test_files = [
+    "test/test_content_mapping.rb",
+     "test/test_content_scrapper.rb",
+     "test/helper.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+      s.add_development_dependency(%q<thoughtbot-shoulda>, [">= 2.10.2"])
+      s.add_development_dependency(%q<mocha>, [">= 0.9.8"])
+      s.add_runtime_dependency(%q<sanitize>, [">= 1.2.0"])
+      s.add_runtime_dependency(%q<nokogiri>, [">= 1.4.1"])
+    else
+      s.add_dependency(%q<thoughtbot-shoulda>, [">= 2.10.2"])
+      s.add_dependency(%q<mocha>, [">= 0.9.8"])
+      s.add_dependency(%q<sanitize>, [">= 1.2.0"])
+      s.add_dependency(%q<nokogiri>, [">= 1.4.1"])
+    end
+  else
+    s.add_dependency(%q<thoughtbot-shoulda>, [">= 2.10.2"])
+    s.add_dependency(%q<mocha>, [">= 0.9.8"])
+    s.add_dependency(%q<sanitize>, [">= 1.2.0"])
+    s.add_dependency(%q<nokogiri>, [">= 1.4.1"])
+  end
+end
+

data/lib/content_scrapper.rb

@@ -0,0 +1,62 @@
+
+require 'open-uri'
+require 'nokogiri'
+require 'sanitize'
+
+require 'content_scrapper/content_mapping'
+
+class ContentScrapper
+
+  class << self
+    attr_accessor :default_config_file, :default
+    default_config_file = "#{File.dirname(__FILE__)}/../config/content_scrapper.rb"
+
+    def create_new_default(*args)
+      self.default = self.new(*args)
+    end
+  end
+
+  def set_as_default
+    ContentScrapper.default = self
+  end
+
+  attr_accessor :content_mappings, :sanitize_settings
+
+  def initialize(scrapper_config_file = nil)
+    @content_mappings = []
+    config_file = ContentScrapper.default_config_file
+    self.instance_eval(File.read(config_file), config_file) unless config_file.nil?
+  end
+
+  def content_mapping(&block)
+    new_mapping = ContentMapping.new
+    new_mapping.instance_eval(&block)
+    @content_mappings << new_mapping
+  end
+
+  def sanitize_tags(settings)
+    @sanitize_settings = settings
+  end
+
+  def scrap_content(url)
+    content_mappings.each do | content_mapping |
+      if content_mapping.matches_url?(url) and !content_mapping.content_xpaths_list.empty?
+        begin
+          doc = Nokogiri::HTML(Kernel.open(url))
+          content = content_mapping.scrap_content(doc)
+          if content.nil?
+            return nil
+          else
+            return Sanitize.clean(content, sanitize_settings)
+          end
+        rescue Exception
+          scrap_content_exception($!)
+        end
+      end
+    end
+    nil
+  end
+
+  def scrap_content_exception(exception)
+  end
+end

data/lib/content_scrapper/content_mapping.rb

@@ -0,0 +1,29 @@
+
+class ContentMapping
+
+  attr_reader :content_xpaths_list, :url_pattern_regexp
+
+  def initialize
+    @content_xpaths_list = []
+  end
+
+  def url_pattern(pattern)
+    @url_pattern_regexp = pattern
+  end
+
+  def content_at(content_xpath)
+    @content_xpaths_list << content_xpath
+  end
+
+  def matches_url?(url)
+    url =~ @url_pattern_regexp
+  end
+
+  def scrap_content(doc)
+    @content_xpaths_list.each do |content_xpath|
+      content_section = doc.xpath(content_xpath)
+      return content_section.to_a.join("\n") if content_section.count > 0
+    end
+    nil
+  end
+end

data/lib/content_scrapper/feedzirra.rb

@@ -0,0 +1,17 @@
+# feedzirra entries are extended by methods for scrapping content
+require 'feedzirra/feed_entry_utilities'
+
+module Feedzirra
+  module FeedEntryUtilities
+
+    # Scrap the content based on the URL and the existing content and return it
+    def scrap_content(scrapper = ContentScrapper.default)
+      scrapper.scrap_content(self.url) || self.content.to_s
+    end
+
+    # Scrap the content or use the existing one and change the feed entry
+    def scrap_content!(scrapper = ContentScrapper.default)
+      content = scrap_content(scrapper)
+    end
+  end
+end

data/rails/init.rb

@@ -0,0 +1,3 @@
+require 'content_scrapper'
+
+ContentScrapper.default_config_file = "#{RAILS_ROOT}/config/content_scrapper.yml"

data/test/helper.rb

@@ -0,0 +1,10 @@
+require 'rubygems'
+require 'test/unit'
+require 'shoulda'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'content_scrapper'
+
+class Test::Unit::TestCase
+end

data/test/test_content_mapping.rb

@@ -0,0 +1,43 @@
+
+require 'helper'
+require 'mocha'
+
+class TestContentMapping < Test::Unit::TestCase
+
+  context "on empty content mapping creation" do
+    setup do
+      @mapping = ContentMapping.new
+      @mapping.instance_eval do
+        url_pattern /^http:\/\/www\.matchme\.com\//
+        content_at '//div[@id="failing_content"]'
+        content_at '//div[@id="itext_content"]'
+        content_at '//div[@id="itext_second_content"]'
+      end
+    end
+    should "match the right urls" do
+      assert @mapping.matches_url?('http://www.matchme.com/')
+    end
+    should "not match the wrong urls" do
+      assert !@mapping.matches_url?('https://www.somethingelse.org/hfas')
+    end
+    context "scrapping content for a specific site" do
+      setup do
+        pretty_content = File.open("#{File.dirname(__FILE__)}/test_pages/pretty.html").read 
+        @document = Nokogiri::HTML(pretty_content)
+      end
+      should "extract the content" do
+        assert_match(%r{<p><strong>This is a strong text</strong></p>}, @mapping.scrap_content(@document))
+      end
+    end
+    context "on document with two content parts" do
+      setup do
+        two_content = File.open("#{File.dirname(__FILE__)}/test_pages/twocontent.html").read 
+        @document = Nokogiri::HTML(two_content)
+      end
+      should "evaluate the contents in the order as they were added" do
+        assert_match(%r{The first one is matched}, @mapping.scrap_content(@document))
+      end
+    end
+  end
+
+end

data/test/test_content_scrapper.rb

@@ -0,0 +1,123 @@
+require 'helper'
+require 'mocha'
+
+class TestContentScrapper < Test::Unit::TestCase
+
+  ContentScrapper.default_config_file = nil
+
+  context "on common setting" do
+    setup do
+      @scrapper = ContentScrapper.new
+      @scrapper.instance_eval do
+        content_mapping do
+          url_pattern /^http:\/\/www\.pretty\.url/
+          content_at '//div[@id="failing_content"]'
+          content_at '//div[@id="itext_content"]'
+        end
+
+        content_mapping do
+          url_pattern /^http:\/\/www\.twopatterns\.url/
+          content_at '//div[@id="failing_content"]'
+          content_at '//div[@id="itext_content"]'
+        end
+
+        content_mapping do
+          url_pattern /^http:\/\/www\.twopatterns\.url/
+          content_at '//div[@id="itext_second_content"]'
+        end
+
+        sanitize_tags ({:elements => ['p','br', 'b', 'em', 'i', 'strong', 'u', 'a', 'h1', 'h2', 'h3', 'li', 'ol', 'ul'], \
+                       :attributes => { 'a' => ['href'] }})
+      end
+    end
+
+    context "for known sources with expected content scrapping" do
+      setup do
+        pretty_content = File.open("#{File.dirname(__FILE__)}/test_pages/pretty.html").read 
+        stringio = StringIO.new(pretty_content)
+        Kernel.expects(:open).returns(stringio)
+        @entry_content = @scrapper.scrap_content('http://www.pretty.url/fsdsd')
+      end
+      should("identify the content") do
+        assert_match(%r{<p><strong>This is a strong text</strong></p>}, @entry_content)
+      end
+    end
+
+    context "for known pages with unexpected content scrapping" do
+      setup do
+        ugly_content = File.open("#{File.dirname(__FILE__)}/test_pages/ugly.html").read
+        stringio = StringIO.new(ugly_content)
+        Kernel.expects(:open).returns(stringio)
+        @entry_content = @scrapper.scrap_content('http://www.pretty.url/hsdae')
+      end
+      should("return nil") { assert_nil @entry_content }
+    end
+
+    context "for unknown pages" do
+      setup { @entry_content = @scrapper.scrap_content('http://www.unknown.url/hsdae') }
+      should("return nil") { assert_nil @entry_content }
+    end
+
+    context "multiple matching url patterns" do
+      setup do
+        twocontent = File.open("#{File.dirname(__FILE__)}/test_pages/twocontent.html").read
+        stringio = StringIO.new(twocontent)
+        Kernel.expects(:open).with('http://www.twopatterns.url').returns(stringio)
+        @entry_content = @scrapper.scrap_content('http://www.twopatterns.url')
+      end
+      should "match the first content" do
+        assert_equal 'The first one is matched', @entry_content
+      end
+    end
+
+    context "on scrapping with feedzirra" do
+      setup do
+        require 'content_scrapper/feedzirra'
+        require 'sax-machine'
+        require 'feedzirra/parser/rss_entry'
+        require 'feedzirra/parser/atom_entry'
+      end
+
+      context "feed entry with not parsable remote content, but with feed content set" do
+        setup do
+          @feed_entries = [ Feedzirra::Parser::RSSEntry.new, Feedzirra::Parser::AtomEntry.new ]
+          @feed_entries.each do |feed_entry|
+            feed_entry.url = 'http://www.unknown.url/wedhsf'
+            feed_entry.content = 'Pretty well written content is this.'
+          end
+          Kernel.expects(:open).with('http://www.unknown.url/wedhsf').never
+        end
+        should("return the original feed content") do
+          @feed_entries.each do |feed_entry|
+            assert_equal 'Pretty well written content is this.', feed_entry.scrap_content(@scrapper)
+            feed_entry.scrap_content!(@scrapper)
+            assert_equal 'Pretty well written content is this.', feed_entry.content
+          end
+        end
+      end
+    end
+  end
+
+  context "on setting default content scrapper" do
+    setup { @scrapper = ContentScrapper.create_new_default }
+    should "set the default to the recently created" do
+      assert_equal @scrapper, ContentScrapper.default
+    end
+    context "when changing default content scrapper" do
+      setup { @new_scrapper = ContentScrapper.new.set_as_default }
+      should "change the default to the new content scrapper" do
+        assert_equal @new_scrapper, ContentScrapper.default
+      end
+    end
+    context "for feed entry" do
+      setup do
+        @feed_entry = Feedzirra::Parser::RSSEntry.new
+        @feed_entry.url = 'http://www.unknown.url/gerhe'
+        @feed_entry.content = 'We should get this.'
+      end
+      should("scrap content by the default scrapper") do
+        assert_equal 'We should get this.', @feed_entry.scrap_content
+      end
+    end
+  end
+end

data/test/test_pages/pretty.html

@@ -0,0 +1,17 @@
+<html xmlns="http://www.w3.org/1999/xhtml">
+  <head>
+    <title>Pretty title</title>
+  </head>
+  <body>
+    <div class="articlec col">
+      <div id="itext_content">
+        <p><strong>This is a strong text</strong></p><br/>
+        SOMEWHERE. Things happened...
+        <p>paragraph1</p>
+        <p>paragraph2</p>
+        <h3>Section</h3>
+        <p>paragraph3</p>
+        <p>paragraph4</p>
+        <p>paragraph5</p>
+      </body>
+    </html>

data/test/test_pages/twocontent.html

@@ -0,0 +1,11 @@
+<html xmlns="http://www.w3.org/1999/xhtml">
+  <head>
+    <title>Pretty title</title>
+  </head>
+  <body>
+    <div class="articlec col">
+      <div id="itext_second_content">The second pattern should not be matched</div>
+      <div id="itext_content">The first one is matched</div>
+    </div>
+  </body>
+</html>

data/test/test_pages/ugly.html

@@ -0,0 +1,399 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+<head>
+<link rel="canonical" href="http://veda.sme.sk/c/5030948/zijeme-vo-veku-hlupakov.html" />
+<meta http-equiv="Content-Type" content="text/html; charset=windows-1250" />
+<meta name="description" content="Zd� sa, �e v prebiehaj�cej diskusii o kl�me chc� v�etci svetu iba dobre. Pre�o potom pad� to�ko ostr�ch slov?" />
+<meta name="keywords" content="veda, technika, botanika, zool�gia, medic�na, psychol�gia, sociol�gia, dinosaury" />
+<meta name="copyright" content="Petit Press, a.s." />
+<meta name="author" content="SME - Petit Press, a.s." />
+<meta name="revisit-after" content="1 days" />
+<meta name="classification" content="Media" />
+<meta name="distribution" content="Global" />
+<meta name="rating" content="General" />
+<meta name="doc-type" content="Web Page" />
+<meta name="doc-class" content="Published" />
+<meta name="doc-rights" content="Copywritten Work" />
+<meta name="doc-publisher" content="Petit Press, a.s." />
+<link rel="shortcut icon" href="/favicon.ico" type="image/x-icon" />
+<link rel="alternate" type="application/rss+xml" title="RSS" href="http://rss.sme.sk/rss/rss.asp?sek=veda" />
+<title>�ijeme vo veku hlup�kov? | Ekol�gia | veda.sme.sk</title>
+<link rel="stylesheet" type="text/css" href="http://www.sme.sk/css/sme_layout.css?rev=19" />
+<link rel="stylesheet" type="text/css" href="http://veda.sme.sk/css/sme_sub_layout.css?rev=24" />
+<link rel="stylesheet" type="text/css" href="http://www.sme.sk/css/sme_header.css" />
+<link rel="stylesheet" type="text/css" href="http://veda.sme.sk/css/sme_sub_header.css" />
+<link rel="stylesheet" type="text/css" href="http://www.sme.sk/css/sme_article.css?rev=8" />
+<link rel="stylesheet" href="http://www.sme.sk/css/sme_article2.css?rev=4" type="text/css" />
+<link rel="stylesheet" href="http://www.sme.sk/css/sme_article_hist.css" type="text/css" />
+<script type="text/javascript" src="http://veda.sme.sk/jscript/main.js?rev=19"></script>
+<script type="text/javascript" src="http://veda.sme.sk/storm_real/jscript/anketa.js?rev=18"></script>
+<script type="text/javascript" src="http://veda.sme.sk/jscript/x.js"></script>
+<script type="text/javascript" src="http://veda.sme.sk/jscript/my_x.js"></script>
+<link rel="stylesheet" type="text/css" href="http://www.sme.sk/storm_real/pager/pager.css" />
+<link rel="stylesheet" type="text/css" href="http://www.sme.sk/css/sme_pager.css" />
+<script type="text/javascript" src="http://www.sme.sk/storm_real/pager/pager_common.js"></script>
+<script type="text/javascript" src="http://www.sme.sk/storm_real/pager/pager.js"></script>
+</head>
+<body onload="resizeLogo(); ">
+<div class="top-ban"><div id='bmone2n-2337.47.2.64'>
+<noscript><div style='display:inline'><a href='http://ad2.bbmedia.cz/please/redirect/2337/47/2/64/'><img src='http://ad2.bbmedia.cz/please/showit/2337/47/2/64/?typkodu=img' width='300' height='300' style='border-width:0' alt='' /></a></div></noscript>
+</div>
+</div>
+<div id="logo">
+	<a href="http://www.sme.sk/"><img src="http://www.sme.sk/imgs/logo4.gif" width="139" height="39" alt="SME logo" /></a>
+<!-- header -->
+<div id="pager">
+<div id="cita">��ta 23�684 �ud�</div>
+<script type="text/javascript">
+pager_generate(pager_commonPager, 0);
+</script>
+</div>
+<!-- END header -->
+</div>
+<!-- header HS/PS -->
+<div id="headerw">
+<a href="http://veda.sme.sk"><img id="logoImg" src="http://veda.sme.sk/imgs/logo2/veda.gif" alt="logo" /></a>
+</div>
+<!-- END header -->
+<div id="pagew">
+  <!-- navigacia & search -->
+  <div id="sroww">
+    <div id="sr_left"><a href="http://www.sme.sk">Sme.sk</a> | <a href="/">Veda</a> | <a href="/r/veda_eko/ekologia.html">Ekol�gia</a> | �ijeme vo veku hlup�kov?</div>
+    <div id="sr_searchw">
+      <div id="search">
+<!-- SiteSearch Google -->
+<form method="get" action="/gsearch/" target="_top">
+<input type="hidden" name="domains" value="veda.sme.sk"></input>
+<input id="sbi" name="q" type="text" value=" vyh�ad�vanie" onFocus="if(this.value==' vyh�ad�vanie') this.value='';" class="box" />
+<label><input name="sitesearch" type="radio" value="veda.sme.sk" style="font-size: 5px" checked />v tejto sekcii</label>
+<label><input name="sitesearch" type="radio" value="sme.sk" style="font-size: 5px" />v celom SME</label>
+<input id="sbb" type="image" src="http://www.sme.sk/imgs/find_go.gif" width="20" height="17" align="absmiddle" />
+<input type="hidden" name="client" value="pub-6456364300478111"></input>
+<input type="hidden" name="forid" value="1"></input>
+<input type="hidden" name="channel" value="5047212324"></input>
+<input type="hidden" name="ie" value="windows-1250"></input>
+<input type="hidden" name="oe" value="windows-1250"></input>
+<input type="hidden" name="cof" value="GALT:#008000;GL:1;DIV:#D00000;VLC:663399;AH:center;BGC:FFFFFF;LBGC:D00000;ALC:D00000;LC:D00000;T:000000;GFNT:D00000;GIMP:D00000;FORID:11"></input>
+<input type="hidden" name="hl" value="sk"></input>
+</form>
+<!-- SiteSearch Google -->
+      </div>
+    </div>
+  </div>
+  <!-- END navigacia -->
+  <!-- hlavny kontent -->
+  <div id="mainw" class="col2">
+    <!-- stredny + pravy stlpec -->
+    <div id="col2w" class="col2">
+      <!-- hlavny obsah stedneho stlpca -->
+      <div id="contentw">
+<!-- storm-c-box -->
+<script type="text/javascript" src="http://www.sme.sk/storm/jscript/euroConvertor_data.js?rev=6-25"></script>
+<script type="text/javascript" src="http://www.sme.sk/storm/jscript/euroConvertor2.js?rev=10"></script>
+<link rel="stylesheet" href="http://www.sme.sk/storm/css/euroConvertor2.css?rev=2" type="text/css" />
+
+<!-- eTarget ContextAd Start -->
+<div id="contenth" class="art">
+<div class="options"><a href="/clanok_tlac.asp?cl=5030948"><img src="/storm/imgs/toolbar/tlac.gif" title="vytla�i�" border="0" /><span>VYTLA�I�</span></a> <a href="/diskusie/reaction_show.php?id_extern_theme=5030948&extern_type=sme-clanok"><img src="/storm/imgs/toolbar/koment.gif" title="diskutujte" border="0" /><span>diskutujte</span></a> <a href="#" onclick="send_err_info('art', 5030948);"><img src="/storm/imgs/toolbar/chyba.gif" title="Upozornite na chybu" border="0" /><span>UPOZORNITE NA CHYBU</span></a> <span class="sharespan">Po�lite:</span>
+<a href="/clanok_tool.asp?t=odp&cl=5030948" class="sharelink"><img src="/storm/imgs/toolbar/email.gif" title="po�lite e-mailom" border="0" /><span>E-MAILOM</span></a> <a href="javascript:location.href='http://www.facebook.com/share.php?u='+encodeURIComponent(location.href);" onclick="return art_poslite_click('fb')" class="sharelink"><img src="/storm/imgs/toolbar/fb.gif" border="0" title="prida� na facebook" ><span>na facebook</span></a>
+<a href="javascript:location.href='http://vybrali.sme.sk/sub.php?url='+encodeURIComponent(location.href);" class="sharelink" onclick="return art_poslite_click('vbsme');"><img src="/storm/imgs/toolbar/doasdf_c.gif" title="prida� na vybrali.sme.sk" border="0" /><span>VYBRALI.SME</span></a> | <a href="#" class="sharelink" onmouseover="sharelinkOver()" onmouseout="sharelinkOut()"><span>�al�ie</span><img src="/storm/imgs/toolbar/share_arrow.gif" alt="+" border="0"></a>
+<div class="share_more" id="share_more" onmouseover="sharemoreOver();" onmouseout="sharemoreOut();">
+<ul>
+<li><a href="http://delicious.com/save" onclick="return art_poslite_click('del')" class="sharelink"><img src="/storm/imgs/toolbar/delicious.gif" title="prida� na delicious" border="0"><span>delicious.com</span></a></li>
+<li><a href="http://www.google.com/bookmarks" onclick="return art_poslite_click('g')" class="sharelink"><img src="/storm/imgs/toolbar/google.gif" title="prida� na google" border="0"><span>Google Bookmarks</span></a></li>
+<li><a href="http://www.myspace.com/Modules/PostTo/Pages/" onclick="return art_poslite_click('myspc')" class="sharelink"><img src="/storm/imgs/toolbar/myspc.gif" title="prida� na myspace" border="0"><span>MySpace</span></a></li>
+<li><a href="http://www.twitter.com/home?status=" onclick="return art_poslite_click('twit')" class="sharelink"><img src="/storm/imgs/toolbar/twit.gif" title="prida� na twitter" border="0"><span>Twitter</span></a></li>
+</ul>
+</div>
+</div>
+<h1>�ijeme vo veku hlup�kov?</h1>
+</div>
+<div class="articlec col">
+<div id="CORRUPTED_HERE_itext_content">
+<p><strong>Zd� sa, �e v prebiehaj�cej diskusii o kl�me chc� v�etci svetu iba dobre. Pre�o potom pad� to�ko ostr�ch slov?</strong><br /><br />BRATISLAVA. V pondelok mal v bratislavskom A4 - Nultom priestore premi�ru film Franny Armstrongovej The Age of Stupid (Vek hlup�kov), odohr�vaj�ci sa v roku 2055 po glob�lnom jadrovom konflikte, vyvolanom zmenou kl�my.</p>
+<p>Star� mu�, ktor� �ije v zni�enom svete, si pozer� z�bery z filmov�ho arch�vu z na�ich �ias a p�ta sa: Pre�o sme nezastavili klimatick� zmenu, ke� bol e�te �as?</p>
+<p>Odpove� znie, �e �udstvo sa odjak�iva spr�valo hl�po, d�kazom �oho s� pretrv�vaj�ce vojny o majetky a neschopnos� pozrie� sa dopredu. Ani na za�iatku 21. storo�ia zo svojich zvyklost� nevybo�ilo.<br />�o in� teda mohli hlup�ci �aka�, ke� si tak systematicky p�lili pod sebou kon�r?</p>
+<h3>Dva scen�re</h3>
+<p>V�etko sa zdalo tak� jednoduch�. Ak je pravda, �e kl�mu men�� �lovek, sta�ilo obmedzi� spa�ovanie uhlia a ropy, pr�padne sa nau�i� odb�rava� oxid uhli�it� � a <a href="http://www.sme.sk/storm/itextg.asp?idh=4791644&ids=6" class="itext_link">glob�lne otep�ovanie</a> by sa (�asom) zastavilo. Hlup�ci to v�ak neboli schopn� urobi�.</p>
+<p style="text-align: center;"><img src="http://i.sme.sk/vydania/20090924/photo2/sm-0924-026c-kniha.rw.jpg" /></p>
+<p style="text-align: center;"><span style="font-size: x-small;">Lord Lawson nap�sal knihu o glob�lnom otep�ovan� �triezvo a bez em�ci�, hoci s�m sa em�ci�m v�dy nevyhol.<br />P�e, �e veda o kl�me je iba jedn�m aspektom glob�lneho otep�ovania. D�le�it� je rozozna�, ak� opatrenia<br />s� politicky re�lne. Urobia� politici spr�vne rozhodnutie? </span></p>
+<p>Teraz predlo�me in� scen�r, v ktorom tie� hraj� hlavn� �lohu nerozumn� �udia, tentoraz z knihy britsk�ho ekon�ma Nigela Lawsona Vr�me sa k rozumu (v �eskom preklade Petra Hol��ka, Doko��n, <a href="http://www.sme.sk/storm/itextg.asp?idh=4791640&ids=7" class="itext_link">Praha</a> 2009).<br />Lord Lawson of Blaby, minister vo vl�de Margaret Thatcherovej kon�tatuje, �e svet netreba zachra�ova� pred glob�lnym otep�ovan�m, ale pred t�mi, ktor� preh��aj� jeho nebezpe�enstvo.</p>
+<p>�Nov� n�bo�enstvo glob�lneho otep�ovania... obsahuje zrnko pravdy a obrovsk� kopu nezmyslov... Zd� sa, �e sme vst�pili do nov�ho veku nerozumu, �o je hlboko znepokojuj�ce.�</p>
+<p>Lawsonova poz�cia je zalo�en� na ve�mi optimistickom presved�en�, �e s��asn� klimatick� po��ta�ov� modely nemo�no prece�ova�, lebo pracuj� s pr�li� zlo�it�m a� chaotick�m syst�mom.</p>
+<p>Nem�me teda istotu, �e glob�lne teploty sa bud� �alej zvy�ova�.</p>
+<h3>Na�o pom�ha� bohat�m?</h3>
+<p>Lawson v�ak prip���a, �e otep�ovanie m��e pokra�ova�. V tom pr�pade treba zv�i� n�klady, ktor� prinesie zni�ovanie emisi�, a pr�nosy, ktor� z toho pre na�ich potomkov vyplyn�.</p>
+<p>Ke�e Lawsonovi je jasn�, �e v glob�le svet speje k v��iemu bohatstvu, je nerozumn� zajtra vynalo�i� obrovsk� �iastky na nov� technol�gie iba preto, aby bohat� �udia koncom tohto storo�ia boli iba o trochu chudobnej�� (aj tak im hroz� nieko�kon�sobne v��ie bohatstvo ako m�me k dispoz�cii my dnes).</p>
+<p>�al��m argumentom je postoj� ��ny a Indie. Obe krajiny maj� obrovsk� z�soby uhlia a obe chc� pre svojich �ud� vy��iu �ivotn� �rove�, ak� si po�as priemyselnej revol�cie vybudovali s vyu�it�m fos�lnych pal�v Eur�pa a Severn� Amerika.</p>
+<p>Taktie� nie je jednoduch� rozhodn��, ktor� z mo�n�ch glob�lnych hrozieb (terorizmus,� celosvetov� pand�mia, dopad asteroidu) je v porovnan� s glob�lnym otep�ovan�m naliehavej�ia; spom�na knihu s��asn�ho predsedu britskej Kr�ovskej spolo�nosti Martina Reesa Na�a posledn� hodina, z ktorej rozhodne nevypl�va, �e by svet mal prednostne rie�i� pr�ve glob�lne otep�ovanie.</p>
+<p>V re�lnom svete m�me kone�n� zdroje a mus�me ur�ova� priority, tomuto sa unikn�� ned�, p�e Lawson.<br />�V�znam by mohla ma� iba z�sadn� zmena n�ho sp�sobu �ivota, ak� by priniesol podstatn� n�rast cien energie; ten je nevyhnutn� nielen preto, aby sme jej spotreb�vali menej, ale aj preto, aby sa bezuhl�kov� energia stala konkurencieschopnou.�</p>
+<p>�</p>
+<div class="clanok-plus">
+<div class="clanok-plus-nadpis">�erven� �iara nad kl�mou?</div>
+<p><strong>Film Vek hlup�kov stoj� za to, aby sme si ho pozreli. Za pre��tanie stoj� aj kniha lorda Lawsona.</strong><br /><br />Jeden z div�kov k filmu The Age of Stupid povedal: �Vedci, filmov� producenti a nakoniec aj �ir�ia verejnos� si za��naj� pomaly uvedomova� osudov� prepojenos� a zlo�itos� s��asn�ho sveta. Film ukazuje, �e ka�dodenn� �ivot �ud� m��e ma� ve�mi v�znamn� dopady na �ivoty �ud� na opa�nej strane sveta. Hoci sa zameriava najm� na kl�mu, jeho posolstvo je hlb�ie; sna�� sa nazna�i�, �e s na��m s��asn�m poh�adom na pr�rodu a svet nie je v�etko v poriadku.�</p>
+<p>Kniha lorda Lawsona Vr�me sa k rozumu je zas pozoruhodn� najm� t�m, �e analyzuje glob�lne otep�ovanie z praktickej str�nky. Zrejme si naozaj m�lokto uvedomuje, �o v�etko bude treba obetova�, aby sme dok�zali obmedzi� emisie z ropy a uhlia nato�ko, aby sa prestal zvy�ova� obsah oxidu uhli�it�ho v ovzdu��.</p>
+<p>Autor s�ubuje poh�ad bez em�ci�, preto je �koda, �e na z�ver stoto��uje bojovn�kov proti oxidu uhli�it�mu s marxistami, ktor� ke� zistili, �e sa komunizmus skon�il, sa r�chlo prefarbili na zeleno.</p>
+<p>Je to nef�r �vaha, najm� ke� oxidom uhli�it�m kedysi argumentovala aj Lawsonova ��fka, ��elezn� lady� Margaret Thatcherov� vo svojom spravodlivom boji proti rebeluj�cim ban�kom.</p>
+<p>�Alarmisti� v�ak m��u kontrova�: ak rozv�ny Lawson navrhuje v�bec nejak� opatrenia, potom najm� tak�, ak�ch bol schopn� u� nevzdelan� rusk� mu�ik v �asoch Petra I. (hovor� sa im adapt�cia): ke� bude zima, d�m si ko�uch. Ke� bude teplo, tak ho vyzle�iem. Nu� a ak bude ve�a vody, navle�iem si vy��ie gum�ky.</p>
+<div class="clanok-plus-autor">(a�)</div>
+</div>
+<div class="clanok-plus">
+<div class="clanok-plus-nadpis">Energia a Parkinsonove z�kony</div>
+<p><strong>N�jdu sa spolo�n� stanovisk� pri spolo�nej snahe uplat�ova� n�zkouhl�kov� energetick� zdroje?</strong><br /><br />BRATISLAVA. Parkinsonov z�kon rovnosti expertov hovor�, �e na ka�d�ho experta pripad� in� expert s opa�n�m n�zorom.</p>
+<p>Uk�zalo sa to aj v diskusii po filme The Age of Stupid v bratislavskom V-klube, ktor� vtipne moderoval Juraj Rizman zo slovenskej pobo�ky Greenpeace.</p>
+<p style="text-align: center;"><img src="http://i.sme.sk/vydania/20090924/photo2/sm-0924-026c-ropnaveza.rw.jpg" /></p>
+<p style="text-align: center;"><span style="font-size: x-small;">Symbol glob�lnej civiliz�cie � ropn� vrtn� ve�a. ILUSTRA�N� FOTO � TASR/AP</span></p>
+<p>Traja z�stancovia nevyhnutnosti obmedzi� obsah uhl�ka vo vzduchu sa v nej nemohli zhodn��, ako to re�lne dosiahnu�: vyu��va� viac vetern� a slne�n� energiu a energiu biomasy alebo aj nepopul�rnu jadrov�?<br />Je jasn�, �e ve�mi v�tan�mi zdrojmi s� aj vietor (pozrite sa do Rak�ska, do Ma�arska �i do Ve�kej Brit�nie), aj Slnko (pozrite sa do Nemecka). Zatia� v�ak vo svete aj u n�s tvoria iba okrajov� doplnok energie, z�skavanej z klasick�ch zdrojov.</p>
+<p>No a ak sa pozriete treb�rs do Franc�zska, zist�te, �e zabezpe�uje v��inu elektrickej energie z jadrov�ch reaktorov.</p>
+<p>Zrejme v�aka v�asn�mu n�stupu hne� po druhej svetovej vojne, ke� e�te jadrov� reaktory bu� neboli tak� drah�, alebo tak� hroziv�.</p>
+<p>�o teda potrebujeme, ak berieme klimatick� zmenu v�ne? Zrejme v�etky tieto zdroje. Ide�lne by bolo, keby raz nastal s�hlas expertov aspo� v tomto.</p>
+<p>Preto�e ak sa nevedia dohodn�� traja �udia z jednej krajiny, ktor�m ide o spolo�n� vec, ako sa maj� dohodn�� tis�cky expertov zo stoviek kraj�n, z�ujmy ktor�ch s� ve�mi r�znorod�?</p>
+<p>Ke�e z�stupcovia vl�dnych in�tit�ci� pozvanie na diskusiu vo �v��ku� ignorovali, vraj ako v�dy, nedozvedeli sme sa, �o maj� v skuto�nosti v pl�ne oni, ak v�bec nie�o.</p>
+<div class="clanok-plus-autor">(a�)</div>
+</div>
+</div>
+<!-- eTarget ContextAd End -->
+
+<p class="autor_line"><b>�tvrtok 24. 9. 2009</b> | <a href="http://www.sme.sk/autor_info.asp?id=58">Michal A�</a><br /><span class="copyr_sme">�l�nok bol uverejnen� v tla�enom vydan� SME. (<a href="http://predplatne.sme.sk">Predpla�te si SME cez internet.</a>)</span><br /><span class="copyr"><a href="#" onClick="st_openWindow('/footer/', 'PetitPress','width=650,height=550'); return false;">&copy 2009 Petit Press. Autorsk� pr�va s� vyhraden� a vykon�va ich vydavate�. Spravodajsk� licencia vyhraden�.</a></span></p>
+<div class="cb"></div>
+<div class="cb"></div>
+<div class="article-etarget">
+<iframe id="etarget_iframe" src="/storm_real/extra/etarget/etarget_load2.asp?q=5030948&idsek=veda&idrub=veda_eko&nazrub=Ekol%F3gia&l=3&nobr=1&st_odb=sme5&st_cssr=1" border="0" width="100%" height="1" hspace="0" vspace="0" SCROLLING="no" BORDERCOLOR="#FFFFFF" MARGINWIDTH="0" MARGINHEIGHT="0" FRAMEBORDER="0"></iframe>
+</div>
+<div>
+<script type="text/javascript" src="http://diskusie.sme.sk/diskusie/extern_action.php?action=get&id_extern_theme=5030948&extern_type=sme-clanok&limit=5&domain=veda.sme.sk"></script>
+</div>
+<div class="cb"></div>
+</div>
+<script type="text/javascript">
+storm_pg_stat_hit('art', 5030948, '', 1);
+</script>
+				 <!-- koniec hlavneho obsahu clanku -->
+        <!-- FLOATBOX pravy - tu sa rusi nutnost davat cely "floatboxw" do <p></p> -->
+        <div id="floatboxw">
+<div class="floatbox extra">
+<p><img src="http://i.sme.sk/cdata/8/50/5030948/otva-r773.jpg" alt="Smog je probl�mom prakticky v�etk�ch kraj�n. Tento z�ber je zo severn�ch �iech." /></p>
+<p>Smog je probl�mom prakticky v�etk�ch kraj�n. Tento z�ber je zo severn�ch �iech.</p>
+<p>Foto: ILUSTRA�N� � �TK</p>
+</div>
+<div class="floatbox"><div id='bmone2n-2337.47.6.20'>
+<noscript><div style='display:inline'><a href='http://ad2.bbmedia.cz/please/redirect/2337/47/6/20/'><img src='http://ad2.bbmedia.cz/please/showit/2337/47/6/20/?typkodu=img' width='300' height='300' style='border-width:0' alt='' /></a></div></noscript>
+</div>
+</div>
+          <!-- zaciatok TABy -->
+<!-- storm-art-najcit-box -->
+          <div class="floatbox tabbed">
+    <div><img src="/imgs/box/najcit_cl.gif" style="top: 0px; right: 0px; border: 0px" alt="naj��tanej�ie" /></div>
+    <div class="c3blok">
+      <div class="tabs">
+<ul><li class="ac" id="tab1_1hod_button" onclick='tabButtonClicked("tab1", "1hod")'>4 hodiny</li><li class="ia" id="tab1_2hod_button" onclick='tabButtonClicked("tab1", "2hod")'>24h</li><li class="ia" id="tab1_3hod_button" onclick='tabButtonClicked("tab1", "3hod")'>3dni</li><li class="ia" id="tab1_4hod_button" onclick='tabButtonClicked("tab1", "4hod")'>7dn�</li></ul>
+      </div>
+<div class="tabsc" id="tab1_1hod_content">
+	<ol>
+<li><a href="/c/5031672/vyvinuli-vakcinu-ktora-dokaze-bojovat-s-hiv.html">Vyvinuli vakc�nu, ktor� dok�e bojova� s HIV</a> 926</li>
+<li><a href="/c/5030948/zijeme-vo-veku-hlupakov.html">�ijeme vo veku hlup�kov?</a> 514</li>
+<li><a href="/c/5031698/na-mesiaci-je-voda-potvrdili-to-viacere-misie.html">Na Mesiaci je voda. Potvrdili to viacer� misie</a> 187</li>
+<li><a href="/c/5032517/nasli-najvacsi-anglosasky-poklad.html">Na�li najv��� anglosask� poklad</a> 142</li>
+<li><a href="/c/5028991/ako-vyzera-stred-nasej-galaxie.html">Ako vyzer� stred na�ej galaxie?</a> 85</li>
+<li><a href="/c/5030764/dnesny-clovek-vznikol-vdaka-vareniu-nie-sexu.html">Dne�n� �lovek vznikol v�aka vareniu. Nie sexu</a> 80</li>
+<li><a href="/c/5016600/zomrel-zachranca-miliardy-ludi.html">Zomrel z�chranca miliardy �ud�</a> 48</li>
+<li><img src="/storm/imgs/ico_video_1s.gif" class="ico_uni_l" /><a href="/c/5031325/pandy-by-mali-vymriet-tvrdi-to-prirodovedec.html">Pandy by mali vymrie�. Tvrd� to pr�rodovedec</a> 47</li>
+<li><a href="/c/5028949/ulovili-sestmetroveho-morskeho-kraka-len-druhy-raz.html">Ulovili �es�metrov�ho morsk�ho kraka. Len druh� raz</a> 46</li>
+<li><a href="/c/5030792/nemcov-oslnili-solarne-panely.html">Nemcov oslnili  sol�rne panely</a> 41</li>
+	</ol>
+</div>
+<div class="tabsc" style="display: none" id="tab1_2hod_content">
+<ol>
+<li><a href="/c/5030948/zijeme-vo-veku-hlupakov.html">�ijeme vo veku hlup�kov?</a> 17�487</li>
+<li><a href="/c/5031698/na-mesiaci-je-voda-potvrdili-to-viacere-misie.html">Na Mesiaci je voda. Potvrdili to viacer� misie</a> 11�513</li>
+<li><a href="/c/5031672/vyvinuli-vakcinu-ktora-dokaze-bojovat-s-hiv.html">Vyvinuli vakc�nu, ktor� dok�e bojova� s HIV</a> 11�012</li>
+<li><a href="/c/5032517/nasli-najvacsi-anglosasky-poklad.html">Na�li najv��� anglosask� poklad</a> 3�275</li>
+<li><img src="/storm/imgs/ico_video_1s.gif" class="ico_uni_l" /><a href="/c/5031325/pandy-by-mali-vymriet-tvrdi-to-prirodovedec.html">Pandy by mali vymrie�. Tvrd� to pr�rodovedec</a> 2�806</li>
+<li><a href="/c/5030764/dnesny-clovek-vznikol-vdaka-vareniu-nie-sexu.html">Dne�n� �lovek vznikol v�aka vareniu. Nie sexu</a> 2�199</li>
+<li><a href="/c/5028991/ako-vyzera-stred-nasej-galaxie.html">Ako vyzer� stred na�ej galaxie?</a> 2�126</li>
+<li><a href="/c/5028949/ulovili-sestmetroveho-morskeho-kraka-len-druhy-raz.html">Ulovili �es�metrov�ho morsk�ho kraka. Len druh� raz</a> 1�929</li>
+<li><a href="/c/5016600/zomrel-zachranca-miliardy-ludi.html">Zomrel z�chranca miliardy �ud�</a> 1�825</li>
+<li><a href="/c/5030792/nemcov-oslnili-solarne-panely.html">Nemcov oslnili  sol�rne panely</a> 1�147</li>
+</ol>
+</div>
+<div class="tabsc" style="display: none" id="tab1_3hod_content">
+<ol>
+<li><a href="/c/5030948/zijeme-vo-veku-hlupakov.html">�ijeme vo veku hlup�kov?</a> 17�980</li>
+<li><img src="/storm/imgs/ico_video_1s.gif" class="ico_uni_l" /><a href="/c/5027440/vtak-ktory-jedol-ludi-jestvoval.html">Vt�k, ktor� jedol �ud�, jestvoval</a> 14�645</li>
+<li><a href="/c/5030764/dnesny-clovek-vznikol-vdaka-vareniu-nie-sexu.html">Dne�n� �lovek vznikol v�aka vareniu. Nie sexu</a> 13�155</li>
+<li><a href="/c/5028827/objavili-syrsky-kralovsky-poklad.html">Objavili s�rsky kr�ovsk� poklad</a> 11�819</li>
+<li><a href="/c/5031698/na-mesiaci-je-voda-potvrdili-to-viacere-misie.html">Na Mesiaci je voda. Potvrdili to viacer� misie</a> 11�513</li>
+<li><a href="/c/5031672/vyvinuli-vakcinu-ktora-dokaze-bojovat-s-hiv.html">Vyvinuli vakc�nu, ktor� dok�e bojova� s HIV</a> 11�012</li>
+<li><a href="/c/5030792/nemcov-oslnili-solarne-panely.html">Nemcov oslnili  sol�rne panely</a> 10�797</li>
+<li><img src="/storm/imgs/ico_video_1s.gif" class="ico_uni_l" /><a href="/c/5031325/pandy-by-mali-vymriet-tvrdi-to-prirodovedec.html">Pandy by mali vymrie�. Tvrd� to pr�rodovedec</a> 9�313</li>
+<li><a href="/c/5029357/objavili-novu-cast-velkeho-cinskeho-muru.html">Objavili nov� �as� Ve�k�ho ��nskeho m�ru</a> 6�772</li>
+<li><a href="/c/5028991/ako-vyzera-stred-nasej-galaxie.html">Ako vyzer� stred na�ej galaxie?</a> 6�185</li>
+</ol>
+</div>
+<div class="tabsc" style="display: none" id="tab1_4hod_content">
+<ol>
+<li><img src="/storm/imgs/ico_video_1s.gif" class="ico_uni_l" /><a href="/c/5027440/vtak-ktory-jedol-ludi-jestvoval.html">Vt�k, ktor� jedol �ud�, jestvoval</a> 26�503</li>
+<li><a href="/c/5030948/zijeme-vo-veku-hlupakov.html">�ijeme vo veku hlup�kov?</a> 17�980</li>
+<li><a href="/c/5030764/dnesny-clovek-vznikol-vdaka-vareniu-nie-sexu.html">Dne�n� �lovek vznikol v�aka vareniu. Nie sexu</a> 13�155</li>
+<li><a href="/c/5028827/objavili-syrsky-kralovsky-poklad.html">Objavili s�rsky kr�ovsk� poklad</a> 11�819</li>
+<li><a href="/c/5031698/na-mesiaci-je-voda-potvrdili-to-viacere-misie.html">Na Mesiaci je voda. Potvrdili to viacer� misie</a> 11�513</li>
+<li><a href="/c/5031672/vyvinuli-vakcinu-ktora-dokaze-bojovat-s-hiv.html">Vyvinuli vakc�nu, ktor� dok�e bojova� s HIV</a> 11�012</li>
+<li><a href="/c/5030792/nemcov-oslnili-solarne-panely.html">Nemcov oslnili  sol�rne panely</a> 10�797</li>
+<li><img src="/storm/imgs/ico_video_1s.gif" class="ico_uni_l" /><a href="/c/5031325/pandy-by-mali-vymriet-tvrdi-to-prirodovedec.html">Pandy by mali vymrie�. Tvrd� to pr�rodovedec</a> 9�313</li>
+<li><a href="/c/5016600/zomrel-zachranca-miliardy-ludi.html">Zomrel z�chranca miliardy �ud�</a> 7�605</li>
+<li><a href="/c/5029357/objavili-novu-cast-velkeho-cinskeho-muru.html">Objavili nov� �as� Ve�k�ho ��nskeho m�ru</a> 6�772</li>
+</ol>
+</div>
+    </div>
+<!--###stp1###-->
+          </div>
+<!-- storm-art-najcit-box-end -->
+          <!-- end TABy -->
+<div class="floatbox tabbed"><div style="margin: 2px 2px 2px 8px;"><iframe id="netsuccess_stip_iframe" src="/storm_real/extra/nss_tip/show.asp?id=1-10" border="0" width="300" height="1" hspace="0" vspace="0" SCROLLING="no" BORDERCOLOR="#FFFFFF" MARGINWIDTH="0" MARGINHEIGHT="0" FRAMEBORDER="0"></iframe></div></div>
+        </div>
+        <!-- koniec floatboxw -->
+       <div class="cb"></div>
+<script type="text/javascript" src="http://www.sme.sk/storm/jscript/clanok.js?rev=10"></script>
+
+<script type="text/javascript">
+addLoadEvent(function(){searchSk();});
+</script>
+<!-- storm-c-box-end -->
+      </div>
+      <!-- END hlavny obsah stedneho dvojstlpca -->
+    </div>
+    <!-- END stredny stlpec -->
+    <!-- lavy stlpec -->
+    <div id="col1w">
+<a href="http://www.sme.sk"><img src="/imgs/title_back2.gif" width="125" height="31" style="border: 0px" alt="sp� na SME.sk" /></a><div id="mainmenu"><ul>
+<li class="menu_section_home"><a href="/" id="st_bm_cat_ext_324">Veda</a></li>
+<li><a href="/r/veda_matema/matematika.html" id="st_bm_cat_veda_matema">Matematika</a></li>
+<li><a href="/r/veda_aktual/aktuality.html" id="st_bm_cat_veda_aktual">Aktuality</a></li>
+<li><a href="/r/veda_vesmir/vesmir.html" id="st_bm_cat_veda_vesmir">Vesm�r</a></li>
+<li><a href="/r/veda_fyzika/fyzika.html" id="st_bm_cat_veda_fyzika">Fyzika</a></li>
+<li><a href="/r/veda_botanik/botanika.html" id="st_bm_cat_veda_botanik">Botanika</a></li>
+<li><a href="/r/veda_dinosau/dinosaury.html" id="st_bm_cat_veda_dinosau">Dinosaury</a></li>
+<li><a href="/r/veda_eko/ekologia.html" id="st_bm_cat_veda_eko">Ekol�gia</a></li>
+<li><a href="/r/veda_histor/historia.html" id="st_bm_cat_veda_histor">Hist�ria</a></li>
+<li><a href="/r/veda_psych/psychologia.html" id="st_bm_cat_veda_psych">Psychol�gia</a></li>
+<li><a href="/r/veda_medic/medicina.html" id="st_bm_cat_veda_medic">Medic�na</a></li>
+<li><a href="/r/veda_archeo/archeologia.html" id="st_bm_cat_veda_archeo">Archeol�gia</a></li>
+<li><a href="/r/veda_zoo/zoologia.html" id="st_bm_cat_veda_zoo">Zool�gia</a></li>
+<li><a href="/r/veda_geo/geologia.html" id="st_bm_cat_veda_geo">Geol�gia</a></li>
+<li><a href="/r/veda_techno/technologie.html" id="st_bm_cat_veda_techno">Technol�gie</a></li>
+<li><a href="/r/veda_profil/profily.html" id="st_bm_cat_veda_profil">Profily</a></li>
+<li><a href="/r/veda_pfoto/press-foto.html" id="st_bm_cat_veda_pfoto">Press foto</a></li>
+<li><a href="/r/veda_recenz/recenzie.html" id="st_bm_cat_veda_recenz">Recenzie</a></li>
+<li style="background: url(/imgs/archiv-menu.gif) no-repeat 45px -2px; overflow: visible; height: 27px; padding-top: 3px;"><a href="http://dennik.sme.sk">DENN�K</a></li>
+      </ul>
+    </div>
+<div style="text-align: center;"><div id='bmone2n-2337.47.4.64'>
+<noscript><div style='display:inline'><a href='http://ad2.bbmedia.cz/please/redirect/2337/47/4/64/'><img src='http://ad2.bbmedia.cz/please/showit/2337/47/4/64/?typkodu=img' width='300' height='300' style='border-width:0' alt='' /></a></div></noscript>
+</div>
+</div><div id="menu-reklama-1"></div>
+<div id="prilmenu">
+<h5>ANKETA</h5>
+<div id="stbox_ank_veda_hs_el"></div>
+<script type="text/javascript">
+function stbox_ank_veda_hs_set(){}
+var stbox_ank_veda_hs = new stbox_ank_veda_hs_set();
+addLoadEvent (function () {
+	storm_anketa_init(stbox_ank_veda_hs);
+	stbox_ank_veda_hs.ank_idg = 'veda_hs';
+	stbox_ank_veda_hs.ank_id = 0;
+	stbox_ank_veda_hs.f_show_num = 1;
+	stbox_ank_veda_hs.ank_max_width = 75;
+	stbox_ank_veda_hs.id_el = 'stbox_ank_veda_hs_el';
+	stbox_ank_veda_hs.obj_variable = 'stbox_ank_veda_hs';
+	storm_anketa_render(stbox_ank_veda_hs);
+});
+</script>
+<div class="note"><a href="/anketa_archiv.asp?pol=veda_hs">star�ie ankety</a></div>
+</div>
+<div id="c1blokw">
+<div class="c1blok">
+<h5>PR�LOHY</h5>
+<ul>
+<li><a href="http://pocitace.sme.sk">Po��ta�e</a></li>
+<li><a href="http://mobil.sme.sk">Mobil</a></li>
+<li><a href="http://www.sme.sk/zdravie/">Zdravie</a></li>
+<li><a href="http://auto.sme.sk">Auto - Moto</a></li>
+<li><a href="http://bratislava.sme.sk">Bratislava</a></li>
+<li><a href="http://www.sme.sk/forum/">F�rum</a></li>
+<li><a href="http://www.sme.sk/kariera/">Kari�ra</a></li>
+<li><a href="http://cestovanie.sme.sk">Na cest�ch</a></li>
+<li><a href="http://www.sme.sk/vikend/">V�kend</a></li>
+<li><a href="http://zaujimavosti.sme.sk">Zauj�mavosti</a></li>
+</ul>
+</div>
+<div class="c1blok">
+<h5>PETIT PRESS</h5>
+<ul>
+<li><a href="http://www.sme.sk/dok/tiraz/">Tir�</a></li>
+<li><a href="http://inzercia.sme.sk/">Inzercia</a></li>
+<li><a href="http://predplatne.sme.sk">Predplatn�</a></li>
+<li><a href="http://www.sme.sk/kodex/">Etick� k�dex</a></li>
+</ul>
+</div>
+</div>
+    </div>
+  </div>
+  <!-- END hlavny kontent -->
+  <!-- footer -->
+  <div id="footer">
+    <p><a href="http://www.sme.sk/mapa-stranky/">Mapa str�nky</a> | <a href="http://www.sme.sk/dok/kontakt/">kontakt</a> | <a href="http://www.sme.sk/dok/faq/">pomoc</a> | <a href="#null" onClick="st_openWindow('http://www.sme.sk/footer/homeNS.htm', 'Ako homepage', 'width=500,height=600');"><!--[if IE 5]><a href="#null" onClick="this.style.behavior='url(#default#homepage)'; this.setHomePage('http://veda.sme.sk');"><![endif]-->nastavi� ako homepage <!--[if IE 5]></a><![endif]--></a> | <a href="#" onClick="bookmark_site('www.sme.sk', 'www.sme.sk');">prida� medzi ob��ben�</a> | <a href="#null" onClick="st_openWindow('http://www.sme.sk/footer/win.htm', 'PetitPress','width=500,height=300');">&copy; Petit Press, a.s.</a></p>
+  </div>
+  <!-- END footer -->
+</div>
+
+<div id="helpbox" style="width:200px;text-align:left;visibility:hidden;background-color:#FFFFAA;border:1px solid #940400;font:12px Arial, sans-serif;padding:3px;position:absolute;color:black;"></div>
+<script type="text/javascript">
+<!--
+	main_onload();
+// -->
+</script>
+
+
+<script type="text/javascript">
+st_active_cat = 'veda_eko';
+show_active_menu_categ();
+</script>
+<!-- BBmedia one2many code -->
+<!-- HowTo: All the ad codes must be above this code! -->
+<!-- HowTo: It is good idea to place this code just below the last ad code. -->
+<script type='text/javascript' charset='windows-1250' src='http://ad2.bbmedia.cz/bb/bb_one2n.js?56020090925101'></script>
+<script type='text/javascript'>/* <![CDATA[ */ 
+bmone2n.addPosition('2337.47.6.20','');
+bmone2n.addPosition('2337.47.2.64','');
+bmone2n.addPosition('2337.47.4.64','');
+bmone2n.getAd('ad2.bbmedia.cz','',''+(typeof(bburlparam)=='string'?'&'+bburlparam:''));
+ /* ]]> */</script>
+<div id='bmone2t-2337.47.6.20' style='display:none'><script type='text/javascript'>/* <![CDATA[ */ bmone2n.makeAd('2337.47.6.20'); /* ]]> */</script></div>
+<div id='bmone2t-2337.47.2.64' style='display:none'><script type='text/javascript'>/* <![CDATA[ */ bmone2n.makeAd('2337.47.2.64'); /* ]]> */</script></div>
+<div id='bmone2t-2337.47.4.64' style='display:none'><script type='text/javascript'>/* <![CDATA[ */ bmone2n.makeAd('2337.47.4.64'); /* ]]> */</script></div>
+<script type='text/javascript'>/* <![CDATA[ */ bmone2n.moveAd(); /* ]]> */</script>
+<!-- Gemius SA - gemiusAudience / sme.sk -->
+<script type="text/javascript">
+var pp_gemius_identifier = new String('AfUw5KdgJ28KVrrUYjtEp7e9Dow8ZYLaUcGoNn881W7.J7');
+</script>
+<script type="text/javascript" src="http://services.sme.sk/meranie/genius/xgenius.js"></script>
+<script type="text/javascript">
+var gaJsHost = (("https:" == document.location.protocol) ? "https://ssl." : "http://www.");
+document.write(unescape("%3Cscript src='" + gaJsHost + "google-analytics.com/ga.js' type='text/javascript'%3E%3C/script%3E"));
+</script>
+<script type="text/javascript">
+var pageTracker = _gat._getTracker("UA-66869-23"); pageTracker._initData(); pageTracker._trackPageview(); 
+</script>
+<!-- StartK�d: go.cz.bbelements.com 3.1 Dynamick� + p�edchoz� plugin-detekce  test(581) / UnikatiTEST(19) / POST(1) / nestandard(27) -->
+<script type='text/javascript' charset='windows-1250'>
+/* <![CDATA[ */
+var bbs=screen,bbn=navigator,bbh;bbh='&ubl='+bbn.browserLanguage+'&ucc='+bbn.cpuClass+'&ucd='+bbs.colorDepth+'&uce='+bbn.cookieEnabled+'&udx='+bbs.deviceXDPI+'&udy='+bbs.deviceYDPI+'&usl='+bbn.systemLanguage+'&uje='+bbn.javaEnabled()+'&uah='+bbs.availHeight+'&uaw='+bbs.availWidth+'&ubd='+bbs.bufferDepth+'&uhe='+bbs.height+'&ulx='+bbs.logicalXDPI+'&uly='+bbs.logicalYDPI+'&use='+bbs.fontSmoothingEnabled+'&uto='+(new Date()).getTimezoneOffset()+'&uti='+(new Date()).getTime()+'&uui='+bbs.updateInterval+'&uul='+bbn.userLanguage+'&uwi='+bbs.width;
+if(typeof(bburlparam)=='string') { bbh+='&'+bburlparam; }
+if(typeof(bbkeywords)=='string') { bbh+='&keywords='+escape(bbkeywords); }
+document.write("<scr"+"ipt  charset='windows-1250' type='text/javascript' src='http://go.cz.bbelements.com/please/showit/581/19/1/27/?typkodu=non-standard"+bbh+"&alttext=0&border=0&bgcolor=FFFFFF&text=000000&link=0000FF&target=_blank&bust="+Math.random()+"'>");
+document.write("<"+"\/scr"+"ipt>");
+/* ]]> */
+</script>
+<!-- KonecK�d: go.cz.bbelements.com 3.1 Dynamick� + p�edchoz� plugin-detekce -->
+</body>
+</html>

metadata

@@ -0,0 +1,114 @@
+--- !ruby/object:Gem::Specification 
+name: content_scrapper
+version: !ruby/object:Gem::Version 
+  version: 0.0.3
+platform: ruby
+authors: 
+- Gyorgy Frivolt
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-02-13 00:00:00 +01:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: thoughtbot-shoulda
+  type: :development
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 2.10.2
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: mocha
+  type: :development
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.9.8
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: sanitize
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 1.2.0
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: nokogiri
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 1.4.1
+    version: 
+description: If you want to cut only the content of pages, without any other part (like the menu, header, footer, commercials, etc.), you might find this gem very handy. A DSL is also defined for nifty definitions for your screen scrapping and sanitization.
+email: gyorgy.frivolt@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.rdoc
+files: 
+- .document
+- .gitignore
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- config/content_scrapper.rb
+- content_scrapper.gemspec
+- lib/content_scrapper.rb
+- lib/content_scrapper/content_mapping.rb
+- lib/content_scrapper/feedzirra.rb
+- rails/init.rb
+- test/helper.rb
+- test/test_content_mapping.rb
+- test/test_content_scrapper.rb
+- test/test_pages/pretty.html
+- test/test_pages/twocontent.html
+- test/test_pages/ugly.html
+has_rdoc: true
+homepage: http://github.com/fifigyuri/content_scrapper
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.5
+signing_key: 
+specification_version: 3
+summary: Gem for those who want to screen scrap only the content part of web pages, blogs or articles.
+test_files: 
+- test/test_content_mapping.rb
+- test/test_content_scrapper.rb
+- test/helper.rb