open_graphy 1.0.0

data/spec/lib/open_graphy/configuration_spec.rb

@@ -0,0 +1,22 @@
+RSpec.describe OpenGraphy do
+
+  describe OpenGraphy::Configuration do
+    before do
+      OpenGraphy.configure do |config|
+        config.metatags = ['og:', 'onthebeach:deal:', 'onthebeach:hotel:']
+        config.user_agent = 'OpenGraphyBot'
+      end
+    end
+
+    describe '#metatags' do
+      let(:expected_tags){ ['og:', 'onthebeach:deal:', 'onthebeach:hotel:'] }
+      it{ expect(OpenGraphy.configuration.metatags).to eq(expected_tags) }
+    end
+
+    describe '#user_agent' do
+      it 'returns the user agent' do
+        expect(OpenGraphy.configuration.user_agent).to eq('OpenGraphyBot')
+      end
+    end
+  end
+end

data/spec/lib/open_graphy/fetcher_spec.rb

@@ -0,0 +1,48 @@
+RSpec.describe OpenGraphy::Uri::Fetcher do
+  describe '#fetch' do
+    let(:fetcher) { OpenGraphy::Uri::Fetcher.new(uri) }
+    let(:uri) { 'https://www.onthebeach.co.uk/test' }
+    let(:port) { 443 }
+
+    let(:http) { double('HTTP') }
+    let(:request) {
+      double(
+        'Request',
+        value: 'test',
+      )
+    }
+
+    before do
+      allow(Net::HTTP).to receive(:new).
+        with('www.onthebeach.co.uk', port).
+        and_return(http)
+
+      allow(Net::HTTP::Get).to receive(:new).
+        with('/test', { 'User-Agent' => 'OpenGraphyBot' }).
+        and_return(request)
+
+      allow(request).to receive(:initialize_http_header)
+
+      allow(http).to receive(:request).
+        with(request).
+        and_return(request)
+    end
+
+    it 'uses ssl when the scheme is https' do
+      expect(http).to receive(:use_ssl=).with(true)
+
+      fetcher.fetch
+    end
+
+    context 'with non ssl url' do
+      let(:uri) { 'http://www.onthebeach.co.uk/test' }
+      let(:port) { 80 }
+
+      it 'uses ssl when the scheme is https' do
+        expect(http).to receive(:use_ssl=).with(false)
+
+        fetcher.fetch
+      end
+    end
+  end
+end

data/spec/lib/open_graphy/meta_tag_spec.rb

@@ -0,0 +1,51 @@
+module OpenGraphy
+  RSpec.describe MetaTag do
+    let(:meta_tag) { MetaTag.new(doc, meta_tag_element) }
+    let(:doc) { double('MokogiriDoc') }
+    let(:meta_tag_element) { double('MokogiriElement') }
+
+    describe '#valid?' do
+      subject { meta_tag.valid? }
+
+      context 'when the tag exists in the metatag list' do
+        before do
+          allow(meta_tag_element).to receive(:attr).
+            with('property').and_return('og:title')
+        end
+
+        it { should be_truthy }
+      end
+
+      context 'tag is not in the metatag list' do
+        before do
+          allow(meta_tag_element).to receive(:attr).
+            with('property').and_return('unidentified_tag_name')
+        end
+
+        it { should be_falsy }
+      end
+    end
+
+    describe '#name' do
+      before do
+        allow(meta_tag_element).to receive(:attr).
+          with('property').and_return('og:title')
+      end
+
+      it 'returns the tag name withouth the prefix' do
+        expect(meta_tag.name).to eql('title')
+      end
+    end
+
+    describe '#value' do
+      before do
+        allow(meta_tag_element).to receive(:attr).
+          with('content').and_return('Open Graph protocol is great!')
+      end
+
+      it 'returns the tag value' do
+        expect(meta_tag.value).to eql('Open Graph protocol is great!')
+      end
+    end
+  end
+end

data/spec/lib/open_graphy/meta_tags_spec.rb

@@ -0,0 +1,63 @@
+RSpec.describe OpenGraphy::MetaTags do
+  let(:meta_tags) { OpenGraphy::MetaTags.new }
+
+  describe '#add' do
+    context 'with a title' do
+      before do
+        meta_tags.add('title', 'Laguna Park II, Tenerife')
+      end
+
+      it 'has a title' do
+        expect(meta_tags.title?).to be(true)
+      end
+
+      it 'returns the title' do
+        expect(meta_tags.title).to eql('Laguna Park II, Tenerife')
+      end
+    end
+
+    context 'without a title but with a page title' do
+      before do
+        meta_tags.add('__html_title_tag', 'Laguna Park Hotel')
+      end
+
+      it 'has a title' do
+        expect(meta_tags.title?).to be(true)
+      end
+
+      it 'sets the title as the page title' do
+        expect(meta_tags.title).to eql('Laguna Park Hotel')
+      end
+    end
+
+    context 'with a good image url' do
+      before do
+        meta_tags.add('image', 'http://www.foobar.com/foo.jpg')
+      end
+
+      it 'has an image' do
+        expect(meta_tags.image?).to be(true)
+      end
+
+      it 'returns the image url' do
+        expect(meta_tags.image).to eql('http://www.foobar.com/foo.jpg')
+      end
+    end
+
+    context 'with a bad image url' do
+      before do
+        meta_tags.add('image', '123')
+      end
+
+      it 'does not have an image' do
+        expect(meta_tags.image?).to be(false)
+      end
+    end
+
+    context 'without a description' do
+      it 'has no description' do
+        expect(meta_tags.description?).to be(false)
+      end
+    end
+  end
+end

data/spec/lib/open_graphy/tag_namespace_spec.rb

@@ -0,0 +1,55 @@
+module OpenGraphy
+  RSpec.describe TagNamespace do
+    let(:tag_namespace) { TagNamespace.new(namespace) }
+    let(:namespace) { [] }
+
+    describe '#any?' do
+      context 'without any namespaces' do
+        let(:namespace) { [] }
+
+        it 'returns false' do
+          expect(tag_namespace.any?).to eql(false)
+        end
+      end
+
+      context 'with the default og namespace' do
+        let(:namespace) { ['og'] }
+
+        it 'returns false to avoid namespacing default tags' do
+          expect(tag_namespace.any?).to eql(false)
+        end
+      end
+
+      context 'with some custom namespaces' do
+        let(:namespace) { ['product', 'sku'] }
+
+        it 'returns true' do
+          expect(tag_namespace.any?).to eql(true)
+        end
+      end
+    end
+
+    describe '#next' do
+      it 'returns an instance of TagNamspace' do
+        expect(tag_namespace.next).to be_an_instance_of(TagNamespace)
+      end
+
+      context 'when there is no additional namespace' do
+        let(:namespace) { [] }
+
+        it 'returns a TagNamespace without any items' do
+          expect(tag_namespace.next.any?).to eql(false)
+        end
+      end
+
+      context 'with additional namespaces' do
+        let(:namespace) { ['product', 'sku'] }
+
+        it 'returns a TagNamespace with the addtional items' do
+          expect(tag_namespace.next.any?).to eql(true)
+        end
+      end
+    end
+
+  end
+end

data/spec/lib/open_graphy/uri_spec.rb

@@ -0,0 +1,21 @@
+RSpec.describe OpenGraphy do
+  subject {
+    VCR.use_cassette('pinterest/pin') do
+      OpenGraphy::Uri.open('http://uk.pinterest.com/pin/384213411933800344/')
+    end
+  }
+
+  describe '#open' do
+    context 'with a good url' do
+      it 'should redirect and return a response' do
+        expect(subject).to include('<meta property="og:site_name" content="Pinterest">')
+      end
+    end
+
+    context 'with a bad url' do
+      it 'should throw a BadUriError' do
+        expect{OpenGraphy::Uri.fetch('/title/test/')}.to raise_error(OpenGraphy::Uri::BadUriError)
+      end
+    end
+  end
+end

data/spec/lib/open_graphy/url_spec.rb

@@ -0,0 +1,35 @@
+module OpenGraphy
+  RSpec.describe Url do
+    describe '.fetch' do
+      let(:og_data) { Url.fetch(uri) }
+      let(:uri) { 'http://www.imdb.com/title/tt0107048/' }
+      let(:meta_tags) { [] }
+      let(:file) { File.new('spec/support/fixtures/groundhog_day.html') }
+
+      before do
+        expect(Uri).to receive(:open).with(uri).
+          and_return(file)
+      end
+
+      it 'has a url' do
+        expect(og_data.url).to eql('http://www.imdb.com/title/tt0107048/')
+      end
+
+      it 'has an image' do
+        expect(og_data.image).to eql('http://ia.media-imdb.com/images/M/MV5BMTU0MzQyNTExMV5BMl5BanBnXkFtZTgwMjA0Njk1MDE@._V1_.jpg')
+      end
+
+      it 'has a title' do
+        expect(og_data.title).to eql('Groundhog Day (1993)')
+      end
+
+      it 'thinks it has an image' do
+        expect(og_data.image?).to eql(true)
+      end
+
+      it 'does not have a cat' do
+        expect(og_data.cat?).to eql(false)
+      end
+    end
+  end
+end

data/spec/lib/open_graphy/url_validator_spec.rb

@@ -0,0 +1,22 @@
+module OpenGraphy
+  RSpec.describe UrlValidator do
+
+    describe '#fetch' do
+      context 'with a valid url' do
+        let (:url) { "http://www.onthebeach.co.uk" }
+
+        it 'is a valid' do
+          expect(UrlValidator.new(url).valid?).to be(true)
+        end
+      end
+
+      context 'with an invalid url' do
+        let(:url) { "abcde12345" }
+
+        it 'is not valid' do
+          expect(UrlValidator.new(url).valid?).to be(false)
+        end
+      end
+    end
+  end
+end

data/spec/open_graphy_spec.rb

@@ -0,0 +1,98 @@
+require 'spec_helper'
+
+describe OpenGraphy do
+  subject {
+    VCR.use_cassette('imdb/tt2084970') do
+      OpenGraphy.fetch(url)
+    end
+  }
+  let(:url) { 'http://www.imdb.com/title/tt2084970/?ref_=inth_ov_tt' }
+
+  describe '.fetch' do
+    it 'should return an object with the opengraph data' do
+      expect(subject).to be_kind_of(OpenGraphy::MetaTags)
+    end
+  end
+
+  describe 'custom metatags' do
+    let(:open_graphy) {
+      VCR.use_cassette('onthebeach/deals') do
+        OpenGraphy.fetch(url)
+      end
+    }
+    let(:url) { 'https://www.onthebeach.co.uk/deals/53ee67c676036401a67eab73026a97f9/e01a07efddb6e124da373b31222c162f/80507aab0fb81591a992fcc5b77d93a4' }
+
+    before do
+      OpenGraphy.configure do |config|
+        config.metatags = ["og:", "onthebeach:deal:", "onthebeach:hotel:"]
+      end
+    end
+
+    it { expect(open_graphy.title).to eq('Vilamoura Golf (Vilamoura, Costa de Algarve, Portugal)') }
+    it { expect(open_graphy.description).to include('With nearly 200 km of unrivalled coastline') }
+    it { expect(open_graphy.image).to eq('http://hotels.onthebeach.co.uk/assets/hotel_images/000/345/599/original/vilamoura-golf.jpg') }
+    it { expect(open_graphy.type).to eq('website') }
+    it { expect(open_graphy.url).to eq('https://www.onthebeach.co.uk/deals/53ee67c676036401a67eab73026a97f9/e01a07efddb6e124da373b31222c162f/80507aab0fb81591a992fcc5b77d93a4') }
+    it { expect(open_graphy.site_name).to eq('On The Beach') }
+    it { expect(open_graphy.onthebeach.deal.id).to eq('53ee67c676036401a67eab73026a97f9') }
+    it { expect(open_graphy.onthebeach.deal.hotel_id).to eq('281399') }
+    it { expect(open_graphy.onthebeach.deal.board_code).to eq('SC') }
+    it { expect(open_graphy.onthebeach.deal.price).to eq('287.40') }
+    it { expect(open_graphy.onthebeach.deal.hotel_result_id).to eq('53ee67c676036401a67eab73026a97f9') }
+    it { expect(open_graphy.onthebeach.deal.board_result_id).to eq('b736a3ddafc484424470a056445671d4') }
+    it { expect(open_graphy.onthebeach.deal.flight_result_id).to eq('80507aab0fb81591a992fcc5b77d93a4') }
+  end
+
+  describe 'try to fetch a webpage that does not exist' do
+    let(:open_graphy_data) {
+      VCR.use_cassette('google/404') do
+        OpenGraphy.fetch('http://google.com/404.html')
+      end
+    }
+
+    it "return data class with url" do
+      expect(open_graphy_data.url).to eql('http://google.com/404.html')
+    end
+  end
+
+  describe 'try to fetch a webpage that has no opengraph url' do
+    let(:url) { 'http://www.tripadvisor.co.uk/Hotel_Review-g198832-d236315-Reviews-Grand_Hotel_Kronenhof-Pontresina_Engadin_St_Moritz_Canton_of_Graubunden_Swiss_Alps.html'}
+    let(:open_graphy_data) {
+      VCR.use_cassette('tripadvisor/hotel') do
+        OpenGraphy.fetch(url)
+      end
+    }
+
+    it 'should return the url passed in' do
+      expect(open_graphy_data.url?).to be(true)
+      expect(open_graphy_data.url).to eql('http://www.tripadvisor.co.uk/Hotel_Review-g198832-d236315-Reviews-Grand_Hotel_Kronenhof-Pontresina_Engadin_St_Moritz_Canton_of_Graubunden_Swiss_Alps.html')
+    end
+  end
+
+
+  describe 'try and fetch a webpage that redirects' do
+    let(:url) { 'http://uk.pinterest.com/pin/384213411933800344/' }
+    let(:open_graphy_data) {
+      VCR.use_cassette('pinterest/pin') do
+        OpenGraphy.fetch(url)
+      end
+    }
+
+    it 'should follow the redirect and return data class' do
+      expect(open_graphy_data.url?).to be(true)
+      expect(open_graphy_data.url).to eql('https://www.pinterest.com/pin/384213411933800344/')
+      expect(open_graphy_data.title?).to be(true)
+      expect(open_graphy_data.title).to eql('car')
+      expect(open_graphy_data.image?).to be(true)
+      expect(open_graphy_data.image).to eql('https://s-media-cache-ak0.pinimg.com/736x/7c/e6/fe/7ce6fea0a4f281573a1c7f2c68d13d5a.jpg')
+      expect(open_graphy_data.type?).to be(true)
+      expect(open_graphy_data.type).to eql('pinterestapp:pin')
+      expect(open_graphy_data.description?).to be(true)
+      expect(open_graphy_data.description).to eql('Mercedes SLS | Luxury | Sport | Car | http://amazingsportcarcollections.blogspot.com')
+      expect(open_graphy_data.site_name?).to be(true)
+      expect(open_graphy_data.site_name).to eql('Pinterest')
+      expect(open_graphy_data.see_also?).to be(true)
+      expect(open_graphy_data.see_also).to eql('http://amazingsportcarcollections.blogspot.com/2013/09/recaro-performance-sport-car-seat-back.html')
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,98 @@
+require 'vcr'
+require 'open_graphy'
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# The generated `.rspec` file contains `--require spec_helper` which will cause this
+# file to always be loaded, without a need to explicitly require it in any files.
+#
+# Given that it is always loaded, you are encouraged to keep this file as
+# light-weight as possible. Requiring heavyweight dependencies from this file
+# will add to the boot time of your test suite on EVERY test run, even for an
+# individual file that may not need all of that loaded. Instead, consider making
+# a separate helper file that requires the additional dependencies and performs
+# the additional setup, and require it from the spec files that actually need it.
+#
+# The `.rspec` file also contains a few flags that are not defaults but that
+# users commonly want.
+#
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+#
+VCR.configure do |c|
+  c.cassette_library_dir = 'spec/cassettes'
+  c.hook_into :webmock
+  c.configure_rspec_metadata!
+end
+
+RSpec.configure do |config|
+  # rspec-expectations config goes here. You can use an alternate
+  # assertion/expectation library such as wrong or the stdlib/minitest
+  # assertions if you prefer.
+  config.expect_with :rspec do |expectations|
+    # This option will default to `true` in RSpec 4. It makes the `description`
+    # and `failure_message` of custom matchers include text for helper methods
+    # defined using `chain`, e.g.:
+    # be_bigger_than(2).and_smaller_than(4).description
+    #   # => "be bigger than 2 and smaller than 4"
+    # ...rather than:
+    #   # => "be bigger than 2"
+    expectations.include_chain_clauses_in_custom_matcher_descriptions = true
+  end
+
+  # rspec-mocks config goes here. You can use an alternate test double
+  # library (such as bogus or mocha) by changing the `mock_with` option here.
+  config.mock_with :rspec do |mocks|
+    # Prevents you from mocking or stubbing a method that does not exist on
+    # a real object. This is generally recommended, and will default to
+    # `true` in RSpec 4.
+    mocks.verify_partial_doubles = true
+  end
+
+# The settings below are suggested to provide a good initial experience
+# with RSpec, but feel free to customize to your heart's content.
+=begin
+  # These two settings work together to allow you to limit a spec run
+  # to individual examples or groups you care about by tagging them with
+  # `:focus` metadata. When nothing is tagged with `:focus`, all examples
+  # get run.
+  config.filter_run :focus
+  config.run_all_when_everything_filtered = true
+
+  # Limits the available syntax to the non-monkey patched syntax that is recommended.
+  # For more details, see:
+  #   - http://myronmars.to/n/dev-blog/2012/06/rspecs-new-expectation-syntax
+  #   - http://teaisaweso.me/blog/2013/05/27/rspecs-new-message-expectation-syntax/
+  #   - http://myronmars.to/n/dev-blog/2014/05/notable-changes-in-rspec-3#new__config_option_to_disable_rspeccore_monkey_patching
+  config.disable_monkey_patching!
+
+  # This setting enables warnings. It's recommended, but in some cases may
+  # be too noisy due to issues in dependencies.
+  config.warnings = true
+
+  # Many RSpec users commonly either run the entire suite or an individual
+  # file, and it's useful to allow more verbose output when running an
+  # individual spec file.
+  if config.files_to_run.one?
+    # Use the documentation formatter for detailed output,
+    # unless a formatter has already been configured
+    # (e.g. via a command-line flag).
+    config.default_formatter = 'doc'
+  end
+
+  # Print the 10 slowest examples and example groups at the
+  # end of the spec run, to help surface which specs are running
+  # particularly slow.
+  config.profile_examples = 10
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = :random
+
+  # Seed global randomization in this process using the `--seed` CLI option.
+  # Setting this allows you to use `--seed` to deterministically reproduce
+  # test failures related to randomization by passing the same `--seed` value
+  # as the one that triggered the failure.
+  Kernel.srand config.seed
+=end
+end