scrapzirra 0.0.2

data/spec/scrapzirra/injector_spec.rb

@@ -0,0 +1,30 @@
+require File.join(File.dirname(__FILE__), %w[.. spec_helper])
+
+describe Scrapzirra::Injector do
+  let(:feed) do
+    Feedzirra::Parser::Atom.parse(sample_atom_feed)
+  end
+
+  let(:injector) { Scrapzirra::Injector.new feed}
+
+  let(:injected_feed) { injector.feed }
+
+  subject { injected_feed }
+
+  its(:title) { should eq("Amazon Web Services Blog")}
+  its(:url) { should eq("http://aws.typepad.com/aws/")}
+
+  describe '.scrap' do
+    its(:"scrap.class") { should be(Scrapzirra::Scrap)}
+    describe '.doc' do
+      subject { injected_feed.scrap.doc }
+      its(:class){ should be(Nokogiri::HTML::Document)}
+    end
+  end
+
+  describe '.entries' do
+    subject { feed.entries.first }
+    its(:url) { should eq("http://aws.typepad.com/aws/2009/01/aws-job-architect-designer-position-in-turkey.html")}
+    its(:"scrap.class") { should be(Scrapzirra::Scrap)}
+  end
+end

data/spec/scrapzirra/scrap_spec.rb

@@ -0,0 +1,21 @@
+require File.join(File.dirname(__FILE__), %w[.. spec_helper])
+
+describe Scrapzirra::Scrap do
+  let(:scrap) { Scrapzirra::Scrap.new nil, doc: open("#{File.dirname(__FILE__)}/../sample_feeds/swartz.html")}
+
+  describe '.doc' do
+    subject { scrap.doc }
+    its(:class){ should be(Nokogiri::HTML::Document)}
+
+    describe '.css' do
+      subject { scrap.doc.css('article header h1').collect{|a| a.content }.inject(:+) }
+      it { should match(/Aaron Swartz/) }
+    end
+  end
+
+  describe '.selector_content' do
+    subject { scrap.selector_content('article header h1')}
+    it { should match(/dziecko internetu/) }
+  end
+
+end

data/spec/spec_helper.rb

@@ -0,0 +1,28 @@
+begin
+  require 'simplecov'
+  SimpleCov.start do
+    add_filter "/spec/"
+  end
+rescue LoadError
+end
+
+require File.expand_path(File.dirname(__FILE__) + '/../lib/scrapzirra')
+require 'feedzirra'
+
+def load_sample(filename)
+  File.read("#{File.dirname(__FILE__)}/sample_feeds/#{filename}")
+end
+
+def sample_atom_feed
+  load_sample("AmazonWebServicesBlog.xml")
+end
+
+def sample_atom_entry_content
+  load_sample("AmazonWebServicesBlogFirstEntryContent.xml")
+end
+
+RSpec.configure do |config|
+  config.treat_symbols_as_metadata_keys_with_true_values = true
+  config.run_all_when_everything_filtered = true
+  config.filter_run :focus
+end

metadata

@@ -0,0 +1,103 @@
+--- !ruby/object:Gem::Specification
+name: scrapzirra
+version: !ruby/object:Gem::Version
+  prerelease: 
+  version: 0.0.2
+platform: ruby
+authors:
+- Tomasz Tokarski
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-01-27 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  type: :runtime
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  name: feedzirra
+- !ruby/object:Gem::Dependency
+  type: :development
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  name: rspec
+description: Addional script parsing tools for feedzirra
+email:
+- tomasz@tomasztokarski.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .travis.yml
+- .watchr
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/scrapzirra.rb
+- lib/scrapzirra/feed_utilities.rb
+- lib/scrapzirra/injector.rb
+- lib/scrapzirra/scrap.rb
+- lib/scrapzirra/version.rb
+- scrapzirra.gemspec
+- spec/sample_feeds/AmazonWebServicesBlog.xml
+- spec/sample_feeds/AmazonWebServicesBlogFirstEntryContent.xml
+- spec/sample_feeds/swartz.html
+- spec/scrapzirra/injector_spec.rb
+- spec/scrapzirra/scrap_spec.rb
+- spec/spec_helper.rb
+homepage: https://github.com/tiokksar/scrapzirra
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.24
+signing_key: 
+specification_version: 3
+summary: Addional script parsing tools for feedzirra
+test_files:
+- spec/sample_feeds/AmazonWebServicesBlog.xml
+- spec/sample_feeds/AmazonWebServicesBlogFirstEntryContent.xml
+- spec/sample_feeds/swartz.html
+- spec/scrapzirra/injector_spec.rb
+- spec/scrapzirra/scrap_spec.rb
+- spec/spec_helper.rb
+has_rdoc: