horsefield 0.3.14 → 0.4.1

data/spec/scraper_spec.rb

@@ -1,70 +0,0 @@
-require 'spec_helper'
-require 'horsefield/scraper'
-require 'watir-webdriver'
-
-describe Horsefield::Scraper do
-  describe 'with HTML' do
-    before do
-      @html = IO.read File.join(__dir__, 'fixtures/monster.html')
-    end
-
-    it 'should scrape' do
-      result = Horsefield::Scraper.new.scrape html: @html do
-        many :jobs, '.listingsTable .odd, .listingsTable .even' do
-          one :title, '.jobTitleContainer'
-          one :company, '.companyContainer'
-        end
-      end
-
-      expect(result[:jobs].length).to eq(9)
-    end
-
-    it 'should be able to scrape in scope' do
-      result = Horsefield::Scraper.new.scrape html: @html do
-        scope '#primaryResults' do
-          many :jobs, '.listingsTable .odd, .listingsTable .even' do
-            one :title, '.jobTitleContainer'
-            one :company, '.companyContainer'
-          end
-        end
-      end
-
-      expect(result[:jobs].length).to eq(9)
-    end
-
-    it 'should return nil for selectors that are not found' do
-      result = Horsefield::Scraper.new.scrape html: @html do
-        one :job, '.listingsTable .odd, .listingsTable .even' do
-          one :title, '.jobTitleContainer'
-          one :company, '.companyContainer'
-          one :missing, '.doesNotExist'
-        end
-      end
-
-      expect(result[:job][:missing]).to be_nil
-    end
-
-    it 'can return HTML instead of text' do
-      result = Horsefield::Scraper.new.scrape html: @html do
-        one :job, '.listingsTable .odd, .listingsTable .even' do
-          one :title, '.jobTitleContainer', :html
-          one :company, '.companyContainer'
-          one :missing, '.doesNotExist'
-        end
-      end
-
-      expect(result[:job][:title]).to match(/<a id=\"ctl00_ctl00_ctl00_body_body_wacCenterStage_ctl02_rptResults_ctl00_linkJobTitle\"/)
-    end
-
-    it 'works with Watir' do
-      browser = Watir::Browser.new :phantomjs
-
-      result = Horsefield::Scraper.new(browser).scrape 'https://github.com/cowboy' do
-        one :email, 'a.email'
-        many :organizations, '//div[@class="orgs"]//@original-title'
-      end
-
-      p result
-    end
-  end
-end

data/spec/spec_helper.rb

@@ -1,29 +0,0 @@
-require 'pry'
-#require 'vcr'
-#require 'webmock'
-
-#VCR.configure do |config|
-#  config.cassette_library_dir = 'spec/fixtures/vcr_cassettes'
-#  config.hook_into :webmock
-#  config.configure_rspec_metadata!
-#  config.allow_http_connections_when_no_cassette = true
-#end
-
-# This file was generated by the `rspec --init` command. Conventionally, all
-# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
-# Require this file using `require "spec_helper"` to ensure that it is only
-# loaded once.
-#
-# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
-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
-  config.treat_symbols_as_metadata_keys_with_true_values = true
-
-  # 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'
-end