jaimeiniesta-metainspector 1.1.3 → 1.1.4

data/CHANGELOG.rdoc

@@ -1,3 +1,7 @@
+= 1.1.4
+=== 4th June, 2009
+* Simplified code: removed address setter, just instantiate a new MetaInspector object if you need to scrape a different URL
+
 = 1.1.3
 === 22nd May, 2009
 * Simplified code: now there's no need to call page.scrape!, just initialize it and go directly to page.address, page.title, page.description, page.keywords or page.links, the page will be scraped on the fly

data/README.rdoc

@@ -42,12 +42,6 @@ Once scraped, you can see the scraped data like this:
   page.keywords      # meta keywords, as string
   page.links         # array of strings, with every link found on the page
   
-You can also change the address of the page to be scraped using the address= setter, like this:
-
-  page.address="http://jaimeiniesta.com"
-
-Doing so resets the state of the MetaInspector instance to the initial state (not scraped yet, cleared stored meta data). The page will be re-scraped when you consult any of its metadata again.
-
 The full scraped document if accessible from:
 
   page.document # Nokogiri doc that you can use it to get any element from the page
@@ -80,12 +74,6 @@ You can find some sample scripts on the samples folder, including a basic scrapi
   
   >> page.document.class
   => Nokogiri::HTML::Document
-  
-  >> page.address="http://jaimeiniesta.com"
-  => "http://jaimeiniesta.com"
-  
-  >> page.title
-  => "ruby on rails freelance developer -- Jaime Iniesta"
     
 = To Do
 

data/lib/metainspector.rb

@@ -4,7 +4,7 @@ require 'nokogiri'
 
 # MetaInspector provides an easy way to scrape web pages and get its elements
 class MetaInspector
-  VERSION = '1.1.3'
+  VERSION = '1.1.4'
   
   attr_reader :address
   
@@ -16,11 +16,6 @@ class MetaInspector
     @document = @title = @description = @keywords = @links = nil
   end
   
-  # Setter for address. Initializes the whole state as the address is being changed.
-  def address=(address)
-    initialize(address)
-  end
-  
   # Returns the parsed document title
   def title
     @title ||= document.css('title').inner_html rescue nil

data/metainspector.gemspec

@@ -1,7 +1,7 @@
 Gem::Specification.new do |s|
   s.name = "metainspector"
-  s.version = "1.1.3"
-  s.date = "2009-05-19"
+  s.version = "1.1.4"
+  s.date = "2009-06-04"
   s.summary = "Ruby gem for web scraping"
   s.email = "jaimeiniesta@gmail.com"
   s.homepage = "http://github.com/jaimeiniesta/metainspector/tree/master"

data/samples/basic_scraping.rb

@@ -3,10 +3,9 @@
 require '../lib/metainspector.rb'
 
 puts "Enter a valid http address to scrape it"
-address = gets
+address = gets.strip
 page = MetaInspector.new(address)
-puts "Scraping #{address}"
-puts "...please wait..."
+puts "...please wait while scraping the page..."
 
 puts "Scraping #{page.address} returned these results:"
 puts "TITLE: #{page.title}"

data/samples/spider.rb

@@ -12,7 +12,7 @@ q.push(address)
 
 while q.size > 0
   visited_links << address = q.pop
-  page.address=address
+  page = MetaInspector.new(address)
   puts "Spidering #{page.address}"
 
   puts "TITLE: #{page.title}"

data/test/test_metainspector.rb

@@ -16,29 +16,4 @@ class TestMetaInspector < Test::Unit::TestCase
     assert_equal m.links[30], 'http://www.nuvio.cz/'
     assert_equal m.document.class, Nokogiri::HTML::Document
   end
-  
-  # Test changing the address resets the state of the instance so it causes a new scraping
-  def test_address_setter
-    m = MetaInspector.new('http://pagerankalert.com')
-    assert_equal m.address, 'http://pagerankalert.com'
-    title_1 = m.title
-    description_1 = m.description
-    keywords_1 = m.keywords
-    links_1 = m.links
-    document_1 = m.document 
-    
-    m.address = 'http://jaimeiniesta.com'
-    assert_equal m.address, 'http://jaimeiniesta.com'
-    title_2 = m.title
-    description_2 = m.description
-    keywords_2 = m.keywords
-    links_2 = m.links
-    document_2 = m.document
-    
-    assert_not_equal title_1, title_2
-    assert_not_equal description_1, description_2
-    assert_not_equal keywords_1, keywords_2
-    assert_not_equal links_1, links_2
-    assert_not_equal document_1, document_2
-  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: jaimeiniesta-metainspector
 version: !ruby/object:Gem::Version 
-  version: 1.1.3
+  version: 1.1.4
 platform: ruby
 authors: 
 - Jaime Iniesta
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-05-19 00:00:00 -07:00
+date: 2009-06-04 00:00:00 -07:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency