dmm-crawler 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: de55b4e7acaeea3d391451c3d2c7f52c70ee69f2
-  data.tar.gz: 78e43451a03c47801ad2d79389ef873df6055822
+  metadata.gz: '06925a3fd6d470aaaf623d6b2da213c5b8ff631f'
+  data.tar.gz: 40dfc7eb3824eade889b6218d8c2042c4c62ae02
 SHA512:
-  metadata.gz: 007f0a66ef96674827c9dbdee83bec84304e6932ecf3f9821a2c377a2904ac288cbfcbe56026c580a62d92a734af1dcf8d57bf4e19b4575e50f5b4051a7a915d
-  data.tar.gz: cf63c892f60a777ce5ede4c2fb1746809eddbed0c273112e3120067fc800d94b810ff17fd3c7b0d5ae91ba6fe294e39889b8fd042293dadb49b906db481be339
+  metadata.gz: 32e43bd62c3af54c67b60eda38d7455f2209a9d3b2351b7893b94ec9329964c0a38c1ac9975fb3d6b720d2cd5d8be3c0c00a3d927c6021b1c2a9849f64bc3520
+  data.tar.gz: 42b519cd6268171d10634953c9392b5fdd1b220067dd7ca36c2e8ca1b2496c8d3b147026eb965417c52d7bde2a656caf0d39679d5c3a0fe18b79653f82008767

data/CHANGELOG.md

@@ -1,5 +1,10 @@
 # Change logs
 
+## 0.1.2
+- Extract Attributes klass from Ranking klass.
+- Support art page.
+- Add an attribute for submedia.
+
 ## 0.1.1
 - Convert double quotes to single qoutes for description_raw.
 

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    dmm-crawler (0.1.1)
+    dmm-crawler (0.1.2)
       mechanize
 
 GEM

data/lib/dmm-crawler.rb

@@ -1,8 +1,10 @@
 require 'mechanize'
 
 module DMMCrawler
+  BASE_URL = 'http://www.dmm.co.jp'.freeze
 end
 
 require 'dmm-crawler/agent'
+require 'dmm-crawler/attributes'
 require 'dmm-crawler/ranking'
 require 'dmm-crawler/version'

data/lib/dmm-crawler/attributes.rb

@@ -0,0 +1,89 @@
+module DMMCrawler
+  class Attributes
+    def initialize(element, submedia = nil)
+      @agent = Agent.instance.agent
+      @element = element
+
+      @submedia = submedia
+    end
+
+    def to_a
+      [
+        title,
+        title_link,
+        image_url,
+        description,
+        description_raw,
+        submedia,
+        tags
+      ]
+    end
+
+    private
+
+    def title
+      if art_page?
+        @element.search('.productTitle__txt span').remove
+        @element.search('.productTitle__txt').text.strip
+      else
+        @element.search('.rank-name').first.text.strip
+      end
+    end
+
+    def image_url
+      if art_page?
+        @element.search('.productPreview__item img').last.attributes['data-src'].value
+      else
+        @element.search('img').last.attributes['src'].value
+      end
+    end
+
+    def title_link
+      if art_page?
+        @element.uri.to_s
+      else
+        File.join(BASE_URL, @element.search('.rank-name').first.search('a').first.attributes.first[1].value)
+      end
+    end
+
+    def description
+      if art_page?
+        @element.search('.summary .summary__txt').text
+      else
+        @element.search('.rank-desc').text
+      end
+    end
+
+    def description_raw
+      if art_page?
+        @element.search('.summary .summary__txt').to_s.gsub(/\sclass=".*"/, '').tr('"', "'")
+      else
+        @element.search('.rank-desc').to_s.tr('"', "'")
+      end
+    end
+
+    def submedia
+      return @submedia if @submedia
+
+      @element
+        .search('.productAttribute-listItem .c_icon_productGenre')
+        .first
+        .attributes['class']
+        .value
+        .gsub('c_icon_productGenre ', '')
+        .delete('-')
+    end
+
+    def tags
+      if art_page?
+        @element.search('.genreTagList .genreTagList__item a').map { |e| e.text.strip }
+      else
+        @element.search('.rank-labelListItem').map { |e| e.search('a').text.strip }
+      end
+    end
+
+    def art_page?
+      @element.search('.rank-name').empty?
+    end
+  end
+end

data/lib/dmm-crawler/ranking.rb

@@ -1,7 +1,5 @@
 module DMMCrawler
   class Ranking
-    BASE_URL = 'http://www.dmm.co.jp'.freeze
-
     def initialize(arguments)
       @term = discriminate_term(arguments[:term])
       @submedia = discriminate_submedia(arguments[:submedia])
@@ -11,79 +9,22 @@ module DMMCrawler
 
     def arts
       arts = page.search('.rank-rankListItem.fn-setPurchaseChange').map do |element|
-        Attribute.new(element).to_a
+        Attributes.new(element, @submedia).to_a
       end
 
-      arts.map.with_index(1) do |(title, title_link, image_url, description, description_raw, tags), rank|
+      arts.map.with_index(1) do |(title, title_link, image_url, description, description_raw, submedia, tags), rank|
         {
           title: "#{rank}位: #{title}",
           title_link: title_link,
           image_url: image_url,
           description: description,
           description_raw: description_raw,
+          submedia: submedia,
           tags: tags
         }
       end
     end
 
-    class Attribute
-      def initialize(element)
-        @element = element
-        @agent = Agent.instance.agent
-      end
-
-      def to_a
-        [
-          title,
-          title_link,
-          image_url,
-          description,
-          description_raw,
-          tags
-        ]
-      end
-
-      private
-
-      def title
-        @element.search('.rank-name').first.text.strip
-      end
-
-      def image_url
-        @element.search('img').last.attributes['src'].value
-      end
-
-      def title_link
-        File.join(BASE_URL, @element.search('.rank-name').first.search('a').first.attributes.first[1].value)
-      end
-
-      def description
-        @element.search('.rank-desc').text.nil? ? fetch_description : @element.search('.rank-desc').text
-      end
-
-      def description_raw
-        @element.search('.rank-desc').text.nil? ? fetch_description_raw : @element.search('.rank-desc').to_s.tr('"', "'")
-      end
-
-      def fetch_description
-        url = File.join(BASE_URL, @element.search('.rank-name a').first.attributes['href'].value)
-        page = @agent.get(url)
-        page.search('.summary .summary__txt').text
-      end
-
-      def fetch_description_raw
-        url = File.join(BASE_URL, @element.search('.rank-name a').first.attributes['href'].value)
-        page = @agent.get(url)
-        page.search('.summary .summary__txt').to_s.gsub(/\sclass=".*"/, '').tr('"', "'")
-      end
-
-      def tags
-        @element.search('.rank-labelListItem').map { |e| e.search('a').text.strip }
-      end
-    end
-
-    private_constant :Attribute
-
     private
 
     def page

data/lib/dmm-crawler/version.rb

@@ -1,3 +1,3 @@
 module DMMCrawler
-  VERSION = '0.1.1'.freeze
+  VERSION = '0.1.2'.freeze
 end

data/spec/dmm-crawler/ranking_spec.rb

@@ -21,7 +21,7 @@ describe DMMCrawler::Ranking do
       let(:term) { '24' }
 
       it { is_expected.not_to be_empty }
-      it { is_expected.to all(include(:title, :title_link, :image_url, :description, :description_raw, :tags)) }
+      it { is_expected.to all(include(:title, :title_link, :image_url, :description, :description_raw, :submedia, :tags)) }
     end
 
     context 'with not registered argument' do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: dmm-crawler
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
 platform: ruby
 authors:
 - Satoshi Ohmori
@@ -115,6 +115,7 @@ files:
 - doc/ja/README.md
 - lib/dmm-crawler.rb
 - lib/dmm-crawler/agent.rb
+- lib/dmm-crawler/attributes.rb
 - lib/dmm-crawler/ranking.rb
 - lib/dmm-crawler/version.rb
 - spec/dmm-crawler/ranking_spec.rb