metainspector 1.4.0 → 1.5.0

data/spec/metainspector_spec.rb

@@ -5,6 +5,9 @@ require File.join(File.dirname(__FILE__), "/spec_helper")
 describe MetaInspector do
 
   context 'Initialization' do
+
+    FakeWeb.register_uri(:get, "http://pagerankalert.com", :response => fixture_file("pagerankalert.com.response"))
+
     it 'should accept an URL with a scheme' do
       @m = MetaInspector.new('http://pagerankalert.com')
       @m.url.should == 'http://pagerankalert.com'
@@ -17,6 +20,12 @@ describe MetaInspector do
   end
 
   context 'Doing a basic scrape' do
+
+    FakeWeb.register_uri(:get, "http://pagerankalert.com", :response => fixture_file("pagerankalert.com.response"))
+    FakeWeb.register_uri(:get, "http://www.theonion.com/articles/apple-claims-new-iphone-only-visible-to-most-loyal,2772/", :response => fixture_file("theonion.com.response"))
+    FakeWeb.register_uri(:get, "http://www.iteh.at", :response => fixture_file("iteh.at.response"))
+    FakeWeb.register_uri(:get, "http://www.tea-tron.com/jbravo/blog/", :response => fixture_file("tea-tron.com.response"))
+
     EXPECTED_TITLE = 'PageRankAlert.com :: Track your PageRank changes'
 
     before(:each) do
@@ -36,10 +45,6 @@ describe MetaInspector do
       @m.image.should == "http://o.onionstatic.com/images/articles/article/2772/Apple-Claims-600w-R_jpg_130x110_q85.jpg"
     end
 
-    it "should get the links" do
-      @m.links.size.should == 9
-    end
-
     it "should have a Nokogiri::HTML::Document as parsed_document" do
       @m.parsed_document.class.should == Nokogiri::HTML::Document
     end
@@ -59,6 +64,36 @@ describe MetaInspector do
     end
   end
 
+  context 'Links' do
+    before(:each) do
+      @m = MetaInspector.new('http://pagerankalert.com')
+    end
+
+    it "should get the links" do
+      @m.links.should == [
+                          "/",
+                          "/es?language=es",
+                          "/users/sign_up",
+                          "/users/sign_in",
+                          "http://pagerankalert.posterous.com",
+                          "http://twitter.com/pagerankalert",
+                          "http://twitter.com/share"
+                          ]
+    end
+
+    it "should convert links to absolute urls" do
+      @m.absolute_links.should == [
+                                    "http://pagerankalert.com/",
+                                    "http://pagerankalert.com/es?language=es",
+                                    "http://pagerankalert.com/users/sign_up",
+                                    "http://pagerankalert.com/users/sign_in",
+                                    "http://pagerankalert.posterous.com",
+                                    "http://twitter.com/pagerankalert",
+                                    "http://twitter.com/share"
+                                  ]
+    end
+  end
+
   context 'Getting meta tags by ghost methods' do
     before(:each) do
       @m = MetaInspector.new('http://pagerankalert.com')
@@ -97,6 +132,10 @@ describe MetaInspector do
   end
 
   context 'Charset detection' do
+
+    FakeWeb.register_uri(:get, "http://www.pagerankalert.com", :response => fixture_file("pagerankalert.com.response"))
+    FakeWeb.register_uri(:get, "http://www.alazan.com", :response => fixture_file("alazan.com.response"))
+
     it "should detect windows-1252 charset" do
       @m = MetaInspector.new('http://www.alazan.com')
       @m.charset.should == "windows-1252"

data/spec/spec_helper.rb

@@ -1,4 +1,13 @@
 # -*- encoding: utf-8 -*-
 
 $: << File.join(File.dirname(__FILE__), "/../lib")
-require 'meta_inspector'
+require 'meta_inspector'
+require 'fakeweb'
+
+FakeWeb.allow_net_connect = false
+
+def fixture_file(filename)
+  return '' if filename == ''
+  file_path = File.expand_path(File.dirname(__FILE__) + '/fixtures/' + filename)
+  File.read(file_path)
+end

metadata

@@ -4,9 +4,9 @@ version: !ruby/object:Gem::Version
   prerelease: false
   segments: 
   - 1
-  - 4
+  - 5
   - 0
-  version: 1.4.0
+  version: 1.5.0
 platform: ruby
 authors: 
 - Jaime Iniesta
@@ -62,6 +62,21 @@ dependencies:
         version: 2.6.0
   type: :development
   version_requirements: *id003
+- !ruby/object:Gem::Dependency 
+  name: fakeweb
+  prerelease: false
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 1
+        - 3
+        - 0
+        version: 1.3.0
+  type: :development
+  version_requirements: *id004
 description: MetaInspector lets you scrape a web page and get its title, charset, link and meta tags
 email: 
 - jaimeiniesta@gmail.com
@@ -85,10 +100,15 @@ files:
 - meta_inspector.gemspec
 - samples/basic_scraping.rb
 - samples/spider.rb
+- spec/fixtures/alazan.com.response
+- spec/fixtures/iteh.at.response
+- spec/fixtures/pagerankalert.com.response
+- spec/fixtures/tea-tron.com.response
+- spec/fixtures/theonion.com.response
 - spec/metainspector_spec.rb
 - spec/spec_helper.rb
 has_rdoc: true
-homepage: https://rubygems.org/gems/metainspector
+homepage: https://github.com/jaimeiniesta/metainspector
 licenses: []
 
 post_install_message: 
@@ -120,5 +140,10 @@ signing_key:
 specification_version: 3
 summary: MetaInspector is a ruby gem for web scraping purposes, that returns a hash with metadata from a given URL
 test_files: 
+- spec/fixtures/alazan.com.response
+- spec/fixtures/iteh.at.response
+- spec/fixtures/pagerankalert.com.response
+- spec/fixtures/tea-tron.com.response
+- spec/fixtures/theonion.com.response
 - spec/metainspector_spec.rb
 - spec/spec_helper.rb