preadly-bulbasaur 0.7.2 → 0.8.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a3585babf7ec241a14a1bb08d933cb648216658e
-  data.tar.gz: e283f5b067e6a8d7642e28e747df9a36e49877fd
+  metadata.gz: 975df2c7ace7a0947cd98b55bfcf896a970e5660
+  data.tar.gz: 5a5b086ba797209a5493d4d1db2026631f2091a2
 SHA512:
-  metadata.gz: 3ec4836696c83dd0eef9e32ca7cf9375ecc37bc4ed973f5761357702a23a3c5eeaa7198b195ebab39a4e11e3c505a2b6d50ad37034a95cf45a06a680e3d0b048
-  data.tar.gz: e1324f9d951aaa744e91b4a1113a3f2cc9b2e8222217e3a2ecc9303fb6455ec838819b218a52d64ffbf28a16a5dae7bff6ea4a1c56e9b06f86d464b66e52a4ee
+  metadata.gz: a62e0c0d111f954d147003c25d37ede0ee09c1717ac3a15f8194d07d847e2cedf474667b03bf9c2a84f52a93d53920f6d5162c44b399ebbc9551b4db88bf65c9
+  data.tar.gz: fc8dd0769358ef5e52da253d0a412065667920a401c78a07eb52b8f14bb5368542db7098874987386b9ddd9952df0847d2c6c6acd43ef4a21765e596b75ec3f2

data/lib/bulbasaur/extracts/extract_images_from_all_resources.rb

@@ -11,6 +11,7 @@ module Bulbasaur
       images = images + extract_images_html(@html)
       images = images + extract_images_youtube(@html)
       images = images + extract_images_vimeo(@html)
+      images = images + extract_images_meta(@html)
       images
     end
 
@@ -40,5 +41,13 @@ module Bulbasaur
       end
     end
 
+    def extract_images_meta(html)
+      begin
+        Bulbasaur::ExtractImagesFromMeta.new(html).call
+      rescue Exception => e
+        []
+      end
+    end
+
   end
 end

data/lib/bulbasaur/extracts/extract_images_from_html.rb

@@ -24,7 +24,7 @@ module Bulbasaur
       Nokogiri::HTML(@html).xpath("//img").each do |item|
         url = item.xpath("@src").text
         alt = item.xpath("@alt").text
-        images << create_struct(url, alt)
+        images << create_struct(url, 'img', alt)
       end
       images
     end
@@ -32,7 +32,7 @@ module Bulbasaur
     def extract_images_by_tag_style
       images = Array.new
       @html.scan(CSS_IMPORT_URL_REGEX).each do |url|
-        images << create_struct(url)
+        images << create_struct(url, 'style')
       end
       images
     end
@@ -41,13 +41,13 @@ module Bulbasaur
       images = Array.new
       Nokogiri::HTML(@html).xpath('//a').each do |link|
         url = link.xpath('@href').text
-        images << create_struct(url) if url =~ IMG_CANDIDATE_URL_REGEX
+        images << create_struct(url, 'link') if url =~ IMG_CANDIDATE_URL_REGEX
       end
       images
     end
 
-    def create_struct(url, alt=nil)
-      {url: url, alt: alt } 
+    def create_struct(url, source, alt = nil)
+      { url: url, alt: alt, source: source }
     end
   end
 end

data/lib/bulbasaur/extracts/extract_images_from_meta.rb

@@ -0,0 +1,21 @@
+module Bulbasaur
+  class ExtractImagesFromMeta
+    PROPERTY = 'og:image'
+
+    def initialize(html)
+      @html = html
+    end
+
+    def call
+      meta_informations = Bulbasaur::ExtractMetaInformationsFromHTML.new(@html).call
+      image_urls = image_meta_tags(meta_informations).map { |meta| { url: meta[:value], source: 'meta' } }
+      image_urls
+    end
+
+    private
+
+    def image_meta_tags(meta_informations)
+      meta_informations.select { |meta| meta[:name] == PROPERTY }
+    end
+  end
+end

data/lib/bulbasaur/extracts/extract_images_from_vimeo.rb

@@ -16,7 +16,7 @@ module Bulbasaur
       @html.scan(EXTRACT_URL_PATTERN).each do |video|
         vid = get_vid(video)
         url_image = image_url_for(vid)
-        images << { url: url_image }
+        images << { url: url_image, video_url: video, source: 'vimeo' }
       end
       images
     end

data/lib/bulbasaur/extracts/extract_images_from_youtube.rb

@@ -13,7 +13,7 @@ module Bulbasaur
       images = Array.new
       @html.scan(EXTRACT_URL_PATTERN).each do |video|
         vid = get_vid(video)
-        images << { url: image_url(vid) }
+        images << { url: image_url(vid), video_url: video, source: 'youtube' }
       end
       images
     end

data/lib/bulbasaur/version.rb

@@ -2,8 +2,8 @@ module Bulbasaur
 
   module Version
     MAJOR = 0
-    MINOR = 7
-    PATCH = 2
+    MINOR = 8
+    PATCH = 0
     STRING = "#{MAJOR}.#{MINOR}.#{PATCH}"
   end
   

data/lib/bulbasaur.rb

@@ -2,6 +2,7 @@ require "nokogiri"
 require "bulbasaur/extracts/extract_images_from_youtube"
 require "bulbasaur/extracts/extract_images_from_vimeo"
 require "bulbasaur/extracts/extract_images_from_html"
+require "bulbasaur/extracts/extract_images_from_meta"
 require "bulbasaur/extracts/extract_images_from_all_resources"
 require "bulbasaur/extracts/extract_text_from_html.rb"
 require "bulbasaur/extracts/extract_meta_informations_from_html.rb"

data/spec/bulbasaur/extracts/extract_images_from_all_resources_spec.rb

@@ -14,6 +14,7 @@ RSpec.describe Bulbasaur::ExtractImagesFromAllResources do
     
     let(:html) do
         %Q(
+          <meta property="og:image" content="http://somewhere.to/get/an_image.jpg" />
           <p>
             <iframe width="560" height="315" src="https://www.youtube.com/embed/video0" frameborder="0" allowfullscreen></iframe>
           </p>
@@ -39,8 +40,8 @@ RSpec.describe Bulbasaur::ExtractImagesFromAllResources do
         )
     end
 
-    it "Does return 15 itens" do
-      expect(subject.size).to eq 15
+    it "Does return 16 items" do
+      expect(subject.size).to eq 16
     end
   end
 end

data/spec/bulbasaur/extracts/extract_images_from_html_spec.rb

@@ -37,6 +37,10 @@ RSpec.describe Bulbasaur::ExtractImagesFromHTML do
       it "Does return the image alt" do
         expect(subject.first[:alt]).to eq "image alt test"
       end
+
+      it 'Does return the image source' do
+        expect(subject.first[:source]).to eq 'img'
+      end
     end
     
     context "When send html with a image style inline" do
@@ -59,6 +63,10 @@ RSpec.describe Bulbasaur::ExtractImagesFromHTML do
       it "Does return the image alt" do
         expect(subject.first[:alt]).to be_nil
       end
+
+      it 'Does return the image source' do
+        expect(subject.first[:source]).to eq 'style'
+      end
     end
 
     context 'When sending HTML with a link pointing to an image' do
@@ -90,25 +98,29 @@ RSpec.describe Bulbasaur::ExtractImagesFromHTML do
       end
 
       it 'Does return the image URL with parameters' do
-        expect(subject).to include Hash url: 'http://somewhere.to/get/the_original_image.jpg?width=400&height=400', alt: nil
+        expect(subject).to include Hash url: 'http://somewhere.to/get/the_original_image.jpg?width=400&height=400', alt: nil, source: 'link'
       end
 
       it 'Does return the image URL without parameters' do
-        expect(subject).to include Hash url: 'http://somewhere.to/get/the_original_image.jpg', alt: nil
+        expect(subject).to include Hash url: 'http://somewhere.to/get/the_original_image.jpg', alt: nil, source: 'link'
       end
 
       it 'Does return the image URL with tilde parameters' do
-        expect(subject).to include Hash url: 'http://somewhere.to/get/the_original_image.jpg~original', alt: nil
+        expect(subject).to include Hash url: 'http://somewhere.to/get/the_original_image.jpg~original', alt: nil, source: 'link'
       end
 
       it 'Does return the image URL with upcased and special characters' do
-        expect(subject).to include Hash url: 'http://somewhere.to/get/The_Original_Image%C3%A7a_3.JPG', alt: nil
+        expect(subject).to include Hash url: 'http://somewhere.to/get/The_Original_Image%C3%A7a_3.JPG', alt: nil, source: 'link'
       end
 
       it 'Does return the image alt' do
         expect(subject.first[:alt]).to be_nil
       end
 
+      it 'Does return the image source' do
+        expect(subject.first[:source]).to eq 'link'
+      end
+
       it 'Does not include links other than for images' do
         expect(subject).not_to include Hash url: 'http://somewhere.to/get/the_original_image.jpg.exe', alt: nil
         expect(subject).not_to include Hash url: 'http://somewhere.to/go/to/another_page.html', alt: nil

data/spec/bulbasaur/extracts/extract_images_from_meta_spec.rb

@@ -0,0 +1,45 @@
+require 'spec_helper'
+
+RSpec.describe Bulbasaur::ExtractImagesFromMeta do
+  subject { described_class.new(html).call }
+
+  describe '#call' do
+    context 'when there are no image meta tags' do
+      let(:html) { %Q(<meta property="og:description" content="Just a RSpec test." />) }
+
+      it 'returns an empty array' do
+        expect(subject).to be_empty
+      end
+    end
+
+    context 'when there is one image meta tag' do
+      let :html do
+        %Q(
+        <meta property="og:image" content="http://somewhere.to/get/an_image.jpg" />
+        <meta property="og:description" content="Just a RSpec test." />
+        )
+      end
+
+      it 'returns the image URL found' do
+        expect(subject.count).to be 1
+        expect(subject).to include Hash url: 'http://somewhere.to/get/an_image.jpg', source: 'meta'
+      end
+    end
+
+    context 'when there are multiple image meta tags' do
+      let :html do
+        %Q(
+        <meta property="og:image" content="http://somewhere.to/get/an_image.jpg" />
+        <meta property="og:image" content="http://somewhere.to/get/another_image.jpg" />
+        <meta property="og:image" content="http://somewhere.to/get/a_third_image.jpg" />
+        <meta property="og:description" content="Just a RSpec test." />
+        )
+      end
+
+      it 'returns the image URLs found' do
+        expect(subject.count).to be 3
+        expect(subject.map { |meta| meta[:url] }).to include 'http://somewhere.to/get/an_image.jpg', 'http://somewhere.to/get/another_image.jpg', 'http://somewhere.to/get/a_third_image.jpg'
+      end
+    end
+  end
+end

data/spec/bulbasaur/extracts/extract_images_from_vimeo_spec.rb

@@ -31,6 +31,8 @@ RSpec.describe Bulbasaur::ExtractImagesFromVimeo do
 
       it "Does return vime url" do
         expect(subject.first[:url]).to eq "https://i.vimeocdn.com/video/123456789_640.webp"
+        expect(subject.first[:source]).to eq 'vimeo'
+        expect(subject.first[:video_url]).to eq 'player.vimeo.com/video/123456789'
       end
     end
     

data/spec/bulbasaur/extracts/extract_images_from_youtube_spec.rb

@@ -35,6 +35,8 @@ RSpec.describe Bulbasaur::ExtractImagesFromYoutube do
 
       it "Does return youtube url" do
         expect(subject.first[:url]).to eq "http://img.youtube.com/vi/123idfake321/maxresdefault.jpg"
+        expect(subject.first[:source]).to eq 'youtube'
+        expect(subject.first[:video_url]).to eq 'www.youtube.com/embed/123idfake321'
       end
     end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: preadly-bulbasaur
 version: !ruby/object:Gem::Version
-  version: 0.7.2
+  version: 0.8.0
 platform: ruby
 authors:
 - Magno Costa
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-08-13 00:00:00.000000000 Z
+date: 2015-08-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -92,6 +92,7 @@ files:
 - lib/bulbasaur.rb
 - lib/bulbasaur/extracts/extract_images_from_all_resources.rb
 - lib/bulbasaur/extracts/extract_images_from_html.rb
+- lib/bulbasaur/extracts/extract_images_from_meta.rb
 - lib/bulbasaur/extracts/extract_images_from_vimeo.rb
 - lib/bulbasaur/extracts/extract_images_from_youtube.rb
 - lib/bulbasaur/extracts/extract_meta_informations_from_html.rb
@@ -104,6 +105,7 @@ files:
 - lib/bulbasaur/version.rb
 - spec/bulbasaur/extracts/extract_images_from_all_resources_spec.rb
 - spec/bulbasaur/extracts/extract_images_from_html_spec.rb
+- spec/bulbasaur/extracts/extract_images_from_meta_spec.rb
 - spec/bulbasaur/extracts/extract_images_from_vimeo_spec.rb
 - spec/bulbasaur/extracts/extract_images_from_youtube_spec.rb
 - spec/bulbasaur/extracts/extract_inner_text_from_html_spec.rb
@@ -140,6 +142,7 @@ summary: Bulbasaur is a helper for crawler operations used in Pread.ly
 test_files:
 - spec/bulbasaur/extracts/extract_images_from_all_resources_spec.rb
 - spec/bulbasaur/extracts/extract_images_from_html_spec.rb
+- spec/bulbasaur/extracts/extract_images_from_meta_spec.rb
 - spec/bulbasaur/extracts/extract_images_from_vimeo_spec.rb
 - spec/bulbasaur/extracts/extract_images_from_youtube_spec.rb
 - spec/bulbasaur/extracts/extract_inner_text_from_html_spec.rb