scrapula 0.6.3

data/spec/lib/scrapula_spec.rb

@@ -0,0 +1,141 @@
+require 'scrapula'
+
+describe Scrapula do
+
+  let(:url) { 'http://example.com' }
+
+  # TODO
+  %w[get].each do |http_method|
+
+    describe ".#{http_method}" do
+      it { is_expected.to respond_to http_method }
+
+      describe 'creates a request' do
+
+        let(:args) {
+          { url: url, params: [{ q: 'lol' }] }
+        }
+
+        let(:request_double) {
+          instance_double described_class::Request
+        }
+
+        let(:page_double) {
+          instance_double Scrapula::Page
+        }
+        
+        let(:expect_new_request) {
+          allow(request_double).to receive :execute
+          expect(described_class::Request).to receive(:new).and_return request_double
+        }
+
+        let(:expect_page_response) {
+          expect_new_request
+          allow(request_double).to receive(:execute).and_return page_double
+        }
+
+        describe 'with the' do
+          context 'URL received as String' do
+            it 'without parameters' do
+              expect_new_request.with hash_including({ url: args[:url] })
+
+              described_class.__send__ http_method, args[:url]
+            end
+
+            it 'with parameters' do
+              expect_new_request.with hash_including args
+
+              described_class.__send__ http_method, args[:url], args[:params]
+            end
+          end
+
+          it 'arguments received as Hash' do
+            expect_new_request.with hash_including args
+
+            described_class.__send__ http_method, args
+          end
+        end
+
+        it "inferring the #{http_method.upcase} method" do
+          expect_new_request.with hash_including method: http_method
+
+          described_class.__send__ http_method, args
+        end
+
+        it 'and executes it' do
+          expect(request_double).to receive :execute
+          expect(described_class::Request).to receive(:new).and_return request_double
+
+          described_class.__send__ http_method, args
+        end
+
+        # TODO
+        describe 'when fails' do
+        end
+
+        describe 'after receiving the page' do
+
+          context 'without block' do
+            it 'returns that page' do
+              expect_page_response
+              expect(described_class.__send__ http_method, args).to eq page_double
+            end
+          end
+
+          context 'with block' do
+
+            it 'scrapes that page using that block' do
+              expect_page_response
+
+              block = proc{}
+
+              expect(page_double).to receive(:scrape) do |&block|
+                expect(block).to be block
+              end
+
+              described_class.__send__ http_method, args, &block
+            end
+
+            it 'returns the scrapped data' do
+              expect_page_response
+              expect(page_double).to receive(:scrape).and_return({ example: 'example value' })
+
+              result = described_class.__send__ http_method, args do
+                example '#example'
+              end
+
+              expect(result).to eq({ example: 'example value' })
+            end
+          end
+        end
+
+      end
+    end
+  end
+
+  describe '.meta' do
+    let(:metas) { double }
+    let(:page_double) { instance_double Scrapula::Page }
+
+    it 'performs a GET request' do
+      allow(page_double).to receive(:meta!).and_return metas
+      expect(described_class).to receive(:get).with(url).and_return page_double
+      described_class.meta url
+    end
+
+    it 'returns the meta elements of the page' do
+      expect(page_double).to receive(:meta!).and_return metas
+      allow(described_class).to receive(:get).with(url).and_return page_double
+      expect(described_class.meta url).to eq metas
+    end
+  end
+
+  # TODO
+  describe '.metas' do
+  end
+
+  describe '.configure' do
+    
+  end
+
+end

data/spec/spec_helper.rb

@@ -0,0 +1,26 @@
+if ENV['COVERAGE']
+	puts "\n\t > COVERAGE ON"
+	require 'simplecov'
+end
+
+require 'vcr'
+
+require_relative '../lib/scrapula'
+
+RSpec.configure do |config|
+  config.order = 'random'
+
+  VCR.configure do |config|
+    config.cassette_library_dir = 'spec/cassettes'
+    config.hook_into :webmock
+    config.ignore_localhost = true
+    config.allow_http_connections_when_no_cassette = false
+    config.default_cassette_options = {
+      decode_compressed_response: true,
+      record: :new_episodes,
+    }
+  end
+
+  config.extend VCR::RSpec::Macros
+
+end

metadata

@@ -0,0 +1,118 @@
+--- !ruby/object:Gem::Specification
+name: scrapula
+version: !ruby/object:Gem::Version
+  version: 0.6.3
+platform: ruby
+authors:
+- Juan A. Martín Lucas
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-09-17 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: mechanize
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.7'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.7.3
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.7'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.7.3
+description: |2
+      Scrapula is a library for scraping web pages that simplifies some of the
+      common actions that are involved.
+
+      It has a very simple API that can be used in several ways and contexts, and
+      another, shorter, that facilitates processing pages when characters are
+      scarce, like irb / pry, or quick and dirty scripts.
+email: scrapula@jaml.site
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".simplecov"
+- CHANGELOG.md
+- CONTRIBUTING.md
+- Gemfile
+- Gemfile.lock
+- Guardfile
+- LICENSE
+- README.md
+- ROADMAP.md
+- Rakefile
+- examples/block_syntax.rb
+- examples/find_nodes.rb
+- examples/get_first_and_scrape_later.rb
+- examples/metas.rb
+- examples/more_api.rb
+- examples/nested_results.rb
+- examples/one_liners.rb
+- examples/posting_data.rb
+- examples/s.rb
+- examples/validation.rb
+- lib/scrapula.rb
+- lib/scrapula/_old_scraper.rb
+- lib/scrapula/agent.rb
+- lib/scrapula/data.rb
+- lib/scrapula/page.rb
+- lib/scrapula/page/meta.rb
+- lib/scrapula/request.rb
+- lib/scrapula/s.rb
+- lib/scrapula/scraper.rb
+- lib/scrapula/version.rb
+- scrapula.gemspec
+- spec/cassettes/Scrapula_Page_Meta/_.yml
+- spec/cassettes/Scrapula_Page_Meta/_/Open_Graph.yml
+- spec/cassettes/Scrapula_Page_Meta/_/other_names.yml
+- spec/cassettes/Scrapula_Page_Meta/_/standard_names.yml
+- spec/lib/scrapula/agent_spec.rb
+- spec/lib/scrapula/data_spec.rb
+- spec/lib/scrapula/page/meta_spec.rb
+- spec/lib/scrapula/page_spec.rb
+- spec/lib/scrapula/request_spec.rb
+- spec/lib/scrapula/s_spec.rb
+- spec/lib/scrapula/scraper_spec.rb
+- spec/lib/scrapula_spec.rb
+- spec/spec_helper.rb
+homepage: http://github.com/j-a-m-l/scrapula
+licenses:
+- MIT
+metadata: {}
+post_install_message: |2
+      Thanks for installing, but keep in mind that this project is not complete!
+rdoc_options:
+- "--charset=UTF-8"
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.2.2
+signing_key: 
+specification_version: 4
+summary: Succinctest scraper in the world?
+test_files: []
+has_rdoc: