scrapouille 0.0.4 → 0.0.5

data/test/helper.rb

@@ -1,4 +1,5 @@
 $LOAD_PATH << File.join(__dir__, '../lib')
 require 'scrapouille'
 
+require 'pry'
 require 'minitest/autorun'

data/test/test_scraping.rb

@@ -2,8 +2,8 @@ require 'helper'
 
 class TestScraping < MiniTest::Unit::TestCase
 
-  def test_one_player_scrapping
-    scraper = Scrapouille.new do 
+  def test_scrap_text
+    scraper = Scrapouille.configure do 
       scrap 'fullname', at: "//div[@class='player-name']/h1/child::text()"
       scrap 'image_url', at: "//div[@id='basic']//img/attribute::src"
       scrap 'rank', at: "//div[@class='position']/text()" do |c|
@@ -14,16 +14,74 @@ class TestScraping < MiniTest::Unit::TestCase
     results = scraper.scrap!(File.join(__dir__, 'fixtures', 'tennis-player.html'))
 
     assert_equal({
-      fullname: 'Richard Gasquet',
-      image_url: 'http://cdn.tennis.com/uploads/img/2014/06/12/gasquet/regular.jpg',
-      rank: 21
+      'fullname' => 'Richard Gasquet',
+      'image_url' => 'http://cdn.tennis.com/uploads/img/2014/06/12/gasquet/regular.jpg',
+      'rank' => 21
       }, 
       results)
   end
 
+  def test_scrap_attribute_value
+    scraper = Scrapouille.configure do 
+      scrap :djokovic_picture_src, at: "//img[contains(@src, 'djokovicz')]/@src"
+    end
+
+    results = scraper.scrap!(File.join(__dir__, 'fixtures', 'tennis-players-listing.html'))
+
+    assert_equal(
+      { djokovic_picture_src: 'http://cdn.tennis.com/uploads/img/2014/06/12/djokoviczz/regular.jpg' }, 
+      results
+    )
+  end
+
+  def test_scrap_all_attributes_value
+    scraper = Scrapouille.configure do 
+      scrap_all :players_hrefs, at: "//table[contains(@class, 'ranking-table')]//a[child::img]/@href"
+    end
+
+    results = scraper.scrap!(File.join(__dir__, 'fixtures', 'tennis-players-listing.html'))
+
+    assert results[:players_hrefs]
+    assert results[:players_hrefs].all? {|p| p.start_with? '/player/'}
+    assert_equal 119, results[:players_hrefs].count
+    assert_equal '/player/532/novak-djokovic/', results[:players_hrefs].first
+  end
+
+  def test_scrap_all_text
+    scraper = Scrapouille.configure do 
+      scrap_all 'players_names', at: "//table[contains(@class, 'ranking-table')]//a[not(child::img)]/text()" do |c|
+        c.downcase
+      end
+    end
+
+    results = scraper.scrap!(File.join(__dir__, 'fixtures', 'tennis-players-listing.html'))
+
+    assert results['players_names']
+    assert_equal 119, results['players_names'].count
+    assert_equal 'stan wawrinka', results['players_names'][3]
+  end
+
+  def test_both_scrap_and_scrap_all
+    scraper = Scrapouille.configure do 
+      scrap :djokovic_picture_src, at: "//img[contains(@src, 'djokovicz')]/@src"
+      scrap_all :players_hrefs, at: "//table[contains(@class, 'ranking-table')]//a[child::img]/@href"
+    end
+
+    results = scraper.scrap!(File.join(__dir__, 'fixtures', 'tennis-players-listing.html'))
+
+    assert results[:players_hrefs]
+    assert_equal 119, results[:players_hrefs].count
+
+    assert_equal(
+      'http://cdn.tennis.com/uploads/img/2014/06/12/djokoviczz/regular.jpg',
+      results[:djokovic_picture_src] 
+    )
+  end
+
+
   def test_raise_when_no_at_options
     error = assert_raises(RuntimeError) do
-      scraper = Scrapouille.new do 
+      scraper = Scrapouille.configure do 
         scrap 'fullname', {}
       end
     end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: scrapouille
 version: !ruby/object:Gem::Version
-  version: 0.0.4
+  version: 0.0.5
 platform: ruby
 authors:
 - simcap
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-09-18 00:00:00.000000000 Z
+date: 2014-09-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -52,6 +52,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: minitest
   requirement: !ruby/object:Gem::Requirement
@@ -81,8 +95,11 @@ files:
 - Rakefile
 - bin/scrapouille
 - lib/scrapouille.rb
+- lib/scrapouille/scraper.rb
+- lib/scrapouille/xpath_runner.rb
 - scrapouille.gemspec
 - test/fixtures/tennis-player.html
+- test/fixtures/tennis-players-listing.html
 - test/helper.rb
 - test/test_scraping.rb
 homepage: https://github.com/simcap/scrapouille
@@ -110,5 +127,6 @@ specification_version: 4
 summary: Interactive and declarative XPath driven HTML scraper
 test_files:
 - test/fixtures/tennis-player.html
+- test/fixtures/tennis-players-listing.html
 - test/helper.rb
 - test/test_scraping.rb