opendmm 0.1.4 → 0.1.5

data/lib/opendmm/makers/s_cute.rb

@@ -1,61 +1,47 @@
-module OpenDMM
-  module Maker
-    module SCute
-      include Maker
+base_uri 'www.s-cute.com'
 
-      module Site
-        include HTTParty
-        base_uri 'www.s-cute.com'
+register_product(
+  /^S[-_]?Cute\s*(\d{3})[-_](\w+)[-_](\d{2})$/i,
+  '/contents/#{$1}_#{$2}_#{$3}/',
+  'S-Cute #{$1}_#{$2}_#{$3}',
+)
+register_product(
+  /^S[-_]?Cute\s*(ps\d|swm)[-_](\d{2})[-_](\w+)$/i,
+  '/contents/#{$1}_#{$2}_#{$3}/',
+  'S-Cute #{$1}_#{$2}_#{$3}',
+)
 
-        def self.item(name)
-          case name
-          when /^S[-_]?Cute\s*(\d{3}[-_]\w+[-_]\d{2})$/i, /^S[-_]?Cute\s*((ps\d|swm)[-_]\d{2}[-_]\w+)$/i
-            get("/contents/#{$1}/")
-          end
-        end
-      end
+private
 
-      module Parser
-        def self.parse(content)
-          page_uri = content.request.last_uri
-          html = Nokogiri::HTML(content)
-          code = page_uri.to_s.split('/').last
-          specs = html.xpath('//*[@class="detail"]/article/p[2]').text.split('|')
-          return {
-            actresses:       parse_actresses(code),
-            code:            'S-Cute ' + code,
-            cover_image:     parse_cover_image(html, code),
-            description:     html.css('//*[@class="detail"]/article/p[4]').text,
-            maker:           'S-Cute',
-            movie_length:    specs[1],
-            page:            page_uri.to_s,
-            release_date:    specs[0],
-            sample_images:   html.css('#grid-gallery > div.item > div > a').map { |a| a['href'] },
-            thumbnail_image: html.at_css('div.cast > a > img')['src'],
-            title:           html.css('div.detail > article > h3').text,
-          }
-        end
-
-        def self.parse_actresses(code)
-          case code
-          when /^\d{3}[-_](\w+)[-_]\d{2}$/i, /^(?:ps\d|swm)[-_]\d{2}[-_](\w+)$/i
-            [ $1.match(/[a-z]+/)[0].humanize ]
-          else
-            nil
-          end
-        end
+def self.parse_product_html(html)
+  specs = html.xpath('//*[@class="detail"]/article/p[2]').text.split('|')
+  details = {
+    description:     html.css('//*[@class="detail"]/article/p[4]').text,
+    maker:           'S-Cute',
+    movie_length:    specs[1],
+    release_date:    specs[0],
+    sample_images:   html.css('#grid-gallery > div.item > div > a').map { |a| a['href'] },
+    thumbnail_image: html.at_css('div.cast > a > img')['src'],
+    title:           html.css('div.detail > article > h3').text,
+  }
+  cover_img = html.at_css('#movie > div > div > div > a > img')
+  details[:cover_image] = cover_img['src'] if cover_img
+  details
+end
 
-        def self.parse_cover_image(html, code)
-          cover_img = html.at_css('#movie > div > div > div > a > img')
-          return cover_img['src'] if cover_img
-          case code
-          when /^(\d{3})[-_](\w+)[-_](\d{2})$/i
-            "http://static.s-cute.com/images/#{$1}_#{$2}/#{$1}_#{$2}_#{$3}/#{$1}_#{$2}_#{$3}_sample.jpg"
-          else
-            nil
-          end
-        end
-      end
-    end
+def self.product_extra_info(name, url, page, html)
+  code = product_code(name)
+  extra_info = Hash.new
+  if code =~ /(\d{3}_\w+_\d{2})/i
+    extra_info[:cover_image] = "http://static.s-cute.com/images/#{$1}_#{$2}/#{$1}_#{$2}_#{$3}/#{$1}_#{$2}_#{$3}_sample.jpg"
+  end
+  if code =~ /\d{3}_(\w+)_\d{2}/i || code =~ /(?:ps\d|swm)_\d{2}_(\w+)/i
+    extra_info[:actresses] = [ $1.match(/[a-z]+/)[0].humanize ]
   end
+  extra_info
+end
+
+def self.parse_cover_image(html)
+  cover_img = html.at_css('#movie > div > div > div > a > img')
+  cover_img ? cover_img['src'] : nil
 end

data/lib/opendmm/makers/sod.rb

@@ -1,43 +1,27 @@
-module OpenDMM
-  module Maker
-    module Sod
-      include Maker
+base_uri 'ec.sod.co.jp'
 
-      module Site
-        base_uri 'ec.sod.co.jp'
+register_product(
+  /^(NAGE|SDDE|SDMT|SDMU|SDNM|STAR)-?(\d{3})$/i,
+  '/detail/index/-_-/iid/#{$1.upcase}-#{$2}',
+)
 
-        def self.item(name)
-          case name
-          when /^(NAGE|SDDE|SDMT|SDMU|SDNM|STAR)-?(\d{3})$/i
-            get("/detail/index/-_-/iid/#{$1.upcase}-#{$2}")
-          end
-        end
-      end
+private
 
-      module Parser
-        def self.parse(content)
-          page_uri = content.request.last_uri
-          html = Nokogiri::HTML(content)
-          specs = Utils.hash_by_split(html.xpath('//*[@id="main"]/tr/td[2]/table/tr[1]/td[1]/table/tr[1]/td/table/tr/td[2]/table/tr').map(&:text))
-          return {
-            actresses:       specs['出演'].split,
-            code:            specs['品番'],
-            cover_image:     html.at_xpath('//*[@id="main"]/tr/td[2]/table/tr[1]/td[1]/table/tr[1]/td/table/tr/td[1]/a[1]')['href'],
-            description:     html.css('div.detail-datacomment').text,
-            directors:       specs['監督'].split,
-            genres:          specs['ジャンル'].split,
-            label:           specs['レーベル'],
-            maker:           specs['メーカー'],
-            movie_length:    specs['収録時間'],
-            page:            page_uri.to_s,
-            release_date:    specs['発売日'],
-            sample_images:   html.css('div.detail-thumb-sample-box > a').map { |a| a['href'] },
-            series:          specs['シリーズ'],
-            thumbnail_image: html.at_xpath('//*[@id="main"]/tr/td[2]/table/tr[1]/td[1]/table/tr[1]/td/table/tr/td[1]/a[1]/img')['src'],
-            title:           html.css('div.title-base > div.title-base-dvd1 > div.title-base-dvd2 > h1').text,
-          }
-        end
-      end
-    end
-  end
+def self.parse_product_html(html)
+  specs = Utils.hash_by_split(html.xpath('//*[@id="main"]/tr/td[2]/table/tr[1]/td[1]/table/tr[1]/td/table/tr/td[2]/table/tr').map(&:text))
+  {
+    actresses:       specs['出演'].split,
+    cover_image:     html.at_xpath('//*[@id="main"]/tr/td[2]/table/tr[1]/td[1]/table/tr[1]/td/table/tr/td[1]/a[1]')['href'],
+    description:     html.css('div.detail-datacomment').text,
+    directors:       specs['監督'].split,
+    genres:          specs['ジャンル'].split,
+    label:           specs['レーベル'],
+    maker:           specs['メーカー'],
+    movie_length:    specs['収録時間'],
+    release_date:    specs['発売日'],
+    sample_images:   html.css('div.detail-thumb-sample-box > a').map { |a| a['href'] },
+    series:          specs['シリーズ'],
+    thumbnail_image: html.at_xpath('//*[@id="main"]/tr/td[2]/table/tr[1]/td[1]/table/tr[1]/td/table/tr/td[1]/a[1]/img')['src'],
+    title:           html.css('div.title-base > div.title-base-dvd1 > div.title-base-dvd2 > h1').text,
+  }
 end

data/lib/opendmm/makers/tameikegoro.rb

@@ -1,42 +1,26 @@
-module OpenDMM
-  module Maker
-    module Tameikegoro
-      include Maker
+base_uri 'tameikegoro.jp'
 
-      module Site
-        base_uri 'tameikegoro.jp'
+register_product(
+  /^(MDYD)-?(\d{3})$/i,
+  '/works/-/detail/=/cid=#{$1.downcase}#{$2}',
+)
 
-        def self.item(name)
-          case name
-          when /^(MDYD)-?(\d{3})$/i
-            get("/works/-/detail/=/cid=#{$1.downcase}#{$2}")
-          end
-        end
-      end
+private
 
-      module Parser
-        def self.parse(content)
-          page_uri = content.request.last_uri
-          html = Nokogiri::HTML(content)
-          specs = Utils.hash_by_split(html.css('#work-detail > h4, p').map(&:text))
-          return {
-            actresses:       specs['出演女優'].split,
-            code:            specs['品番'],
-            cover_image:     html.at_css('#work-pake')['src'].gsub(/pm.jpg$/, 'pl.jpg'),
-            description:     html.css('#work-detail > h5').text,
-            directors:       specs['監督'].split,
-            genres:          specs['ジャンル'].split,
-            label:           specs['レーベル'],
-            maker:           '溜池ゴロー',
-            page:            page_uri.to_s,
-            release_date:    specs['発売日'].remove('DVD/'),
-            sample_images:   html.css('#sample-pic > a > img').map { |img| img['src'].gsub(/js(?=-\d+\.jpg)/, 'jp') },
-            series:          specs['シリーズ'],
-            thumbnail_image: html.at_css('#work-pake')['src'],
-            title:           html.css('#work-detail > h3').text,
-          }
-        end
-      end
-    end
-  end
+def self.parse_product_html(html)
+  specs = Utils.hash_by_split(html.css('#work-detail > h4, p').map(&:text))
+  {
+    actresses:       specs['出演女優'].split,
+    cover_image:     html.at_css('#work-pake')['src'].gsub(/pm.jpg$/, 'pl.jpg'),
+    description:     html.css('#work-detail > h5').text,
+    directors:       specs['監督'].split,
+    genres:          specs['ジャンル'].split,
+    label:           specs['レーベル'],
+    maker:           '溜池ゴロー',
+    release_date:    specs['発売日'].remove('DVD/'),
+    sample_images:   html.css('#sample-pic > a > img').map { |img| img['src'].gsub(/js(?=-\d+\.jpg)/, 'jp') },
+    series:          specs['シリーズ'],
+    thumbnail_image: html.at_css('#work-pake')['src'],
+    title:           html.css('#work-detail > h3').text,
+  }
 end

data/lib/opendmm/makers/to_satsu.rb

@@ -1,40 +1,24 @@
-module OpenDMM
-  module Maker
-    module ToSatsu
-      include Maker
+base_uri 'to-satsu.com'
 
-      module Site
-        base_uri 'to-satsu.com'
+register_product(
+  /^(CLUB)-?(\d{3})$/i,
+  '/works/#{$1.downcase}/#{$1.downcase}#{$2}/#{$1.downcase}#{$2}.html',
+)
 
-        def self.item(name)
-          case name
-          when /^(CLUB)-?(\d{3})$/i
-            get("/works/#{$1.downcase}/#{$1.downcase}#{$2}/#{$1.downcase}#{$2}.html")
-          end
-        end
-      end
+private
 
-      module Parser
-        def self.parse(content)
-          page_uri = content.request.last_uri
-          html = Nokogiri::HTML(content)
-          specs = Utils.hash_from_dl(html.css('#main > div > div.main-detail > div.ttl-data > dl'))
-          return {
-            code:            specs['品番：'].text,
-            cover_image:     html.at_css('#main > div > div.main-detail > div.ttl-pac > a')['href'],
-            description:     html.xpath('//*[@id="main"]/div/div[@class="main-detail"]/div[@class="ttl-comment"]/div[not(@class)]').text,
-            genres:          specs['ジャンル：'].text,
-            maker:           '変態紳士倶楽部',
-            movie_length:    specs['収録時間：'].text,
-            page:            page_uri.to_s,
-            release_date:    specs['発売日：'].text,
-            sample_images:   html.css('#main > div > div.main-detail > div.ttl-sample > img').map { |img| img['src'] },
-            series:          specs['シリーズ：'].text,
-            thumbnail_image: html.at_css('#main > div > div.main-detail > div.ttl-pac > a > img')['src'],
-            title:           html.css('#main > div > div.capt2').text,
-          }
-        end
-      end
-    end
-  end
+def self.parse_product_html(html)
+  specs = Utils.hash_from_dl(html.css('#main > div > div.main-detail > div.ttl-data > dl'))
+  {
+    cover_image:     html.at_css('#main > div > div.main-detail > div.ttl-pac > a')['href'],
+    description:     html.xpath('//*[@id="main"]/div/div[@class="main-detail"]/div[@class="ttl-comment"]/div[not(@class)]').text,
+    genres:          specs['ジャンル：'].text,
+    maker:           '変態紳士倶楽部',
+    movie_length:    specs['収録時間：'].text,
+    release_date:    specs['発売日：'].text,
+    sample_images:   html.css('#main > div > div.main-detail > div.ttl-sample > img').map { |img| img['src'] },
+    series:          specs['シリーズ：'].text,
+    thumbnail_image: html.at_css('#main > div > div.main-detail > div.ttl-pac > a > img')['src'],
+    title:           html.css('#main > div > div.capt2').text,
+  }
 end

data/lib/opendmm/makers/waap.rb

@@ -1,45 +1,28 @@
-module OpenDMM
-  module Maker
-    module Waap
-      include Maker
+base_uri 'www.waap.co.jp'
 
-      module Site
-        base_uri 'www.waap.co.jp'
+register_product(
+  /^(AIR|CWM|ECB|WSS)-?(\d{3})$/i,
+  '/work/item.php?itemcode=#{$1.upcase}#{$2}',
+)
 
-        def self.item(name)
-          name =~ /(\w+)-?(\d+)/
-          case name
-          when /^(AIR|CWM|ECB|WSS)-?(\d{3})$/i
-            get("/work/item.php?itemcode=#{$1.upcase}#{$2}")
-          end
-        end
-      end
+private
 
-      module Parser
-        def self.parse(content)
-          page_uri = content.request.last_uri
-          html = Nokogiri::HTML(content)
-          specs = Utils.hash_by_split(html.css('ul.title_shosai li.wkact_ser_maker02').map(&:text))
-          return {
-            actresses:       specs['出演者'].split,
-            brand:           specs['ブランド'],
-            code:            specs['品番'],
-            cover_image:     html.at_css('ul#title_img_all li.title_img a')['href'],
-            description:     html.css('div#title_cmt_all').text,
-            directors:       specs['監督'].split,
-            genres:          specs['ジャンル'].split,
-            label:           specs['レーベル'],
-            maker:           specs['メーカー'],
-            movie_length:    specs['収録時間'],
-            page:            page_uri.to_s,
-            release_date:    specs['発売日'],
-            sample_images:   html.css('ul.samplepicture_list li a').map { |a| a['href'] },
-            series:          specs['シリーズ'],
-            thumbnail_image: html.at_css('#title_img_all > li.title_img > a > img')['src'],
-            title:           html.css('ul#pan_list li').last.text,
-          }
-        end
-      end
-    end
-  end
+def self.parse_product_html(html)
+  specs = Utils.hash_by_split(html.css('ul.title_shosai li.wkact_ser_maker02').map(&:text))
+  {
+    actresses:       specs['出演者'].split,
+    brand:           specs['ブランド'],
+    cover_image:     html.at_css('ul#title_img_all li.title_img a')['href'],
+    description:     html.css('div#title_cmt_all').text,
+    directors:       specs['監督'].split,
+    genres:          specs['ジャンル'].split,
+    label:           specs['レーベル'],
+    maker:           specs['メーカー'],
+    movie_length:    specs['収録時間'],
+    release_date:    specs['発売日'],
+    sample_images:   html.css('ul.samplepicture_list li a').map { |a| a['href'] },
+    series:          specs['シリーズ'],
+    thumbnail_image: html.at_css('#title_img_all > li.title_img > a > img')['src'],
+    title:           html.css('ul#pan_list li').last.text,
+  }
 end

data/lib/opendmm/search_engine.rb

@@ -0,0 +1,20 @@
+require 'opendmm/utils'
+
+Dir[File.dirname(__FILE__) + '/search_engines/*.rb'].each do |file|
+  module_name = File.basename(file, '.rb').camelize
+  eval <<-ENGINE
+
+module OpenDMM
+  module SearchEngine
+    module #{module_name}
+      include Site
+      #{File.read(file)}
+      def self.search(name)
+        self.product(name)
+      end
+    end
+  end
+end
+
+ENGINE
+end

data/lib/opendmm/search_engines/dmm.rb

@@ -1,63 +1,43 @@
-require 'opendmm/utils'
+base_uri 'www.dmm.co.jp'
 
-module OpenDMM
-  module SearchEngine
-    module Dmm
-      module Site
-        include HTTParty
-        base_uri 'www.dmm.co.jp'
-        follow_redirects false
+def self.search_url(name)
+  name = name.split(/[-_\s]/).map do |token|
+    token =~ /\d{1,4}/ ? sprintf("%05d", token.to_i) : token
+  end.join(' ')
+  "/search/=/searchstr=#{CGI::escape(name)}"
+end
 
-        def self.search(name)
-          name = name.split(/[-_\s]/).map do |token|
-            token =~ /\d{1,4}/ ? sprintf("%05d", token.to_i) : token
-          end.join(' ')
-          get("/search/=/searchstr=#{CGI::escape(name)}")
-        end
+def self.product_url(name)
+  search_page = get_with_retry search_url(name)
+  return nil unless search_page
+  search_html = Utils.html_in_utf8 search_page
+  first_result = search_html.at_css('#list > li > div > p.tmb > a')
+  first_result['href'] if first_result
+end
 
-        def self.get(uri)
-          super(uri)
-        rescue Errno::ETIMEDOUT => e
-          tries ||= 0
-          tries++
-          tries <= 5 ? retry : raise
-        end
-      end
-
-      module Parser
-        def self.parse_search_result(content)
-          html = Nokogiri::HTML(content)
-          first_result = html.css('#list > li > div > p.tmb > a').first
-          first_result['href'] if first_result
-        end
+def self.product_extra_info(name, url, page, html)
+  dmm_id = page.request.last_uri.to_s.split('/').last.split('=').last
+  if dmm_id =~ /\d*([a-z]+)0*(\d+)/i
+    dmm_id = "#{$1.upcase}-#{$2.rjust(3, '0')}"
+  end
+  { code: dmm_id }
+end
 
-        def self.parse_item(content)
-          page_uri = content.request.last_uri
-          html = Nokogiri::HTML(content)
-          specs = Utils.hash_by_split(html.css('//*[@id="mu"]/div/table/tr/td[1]/table/tr').map(&:text))
-          return {
-            actresses:       specs['出演者'].split,
-            code:            specs['品番'],
-            cover_image:     html.at_css('#sample-video > a')['href'],
-            directors:       specs['監督'].split,
-            genres:          specs['ジャンル'].split,
-            label:           specs['レーベル'],
-            maker:           specs['メーカー'],
-            movie_length:    specs['収録時間'],
-            page:            page_uri.to_s,
-            release_date:    specs['商品発売日'],
-            series:          specs['シリーズ'],
-            thumbnail_image: html.at_css('#sample-video > a > img')['src'],
-            title:           html.css('#title').text,
-          }
-        end
-      end
+private
 
-      def self.search(name)
-        search_result = Site.search(name)
-        item_uri = Parser.parse_search_result(search_result)
-        Parser.parse_item(Site.get(item_uri)) if item_uri
-      end
-    end
-  end
-end
+def self.parse_product_html(html)
+  specs = Utils.hash_by_split(html.css('//*[@id="mu"]/div/table/tr/td[1]/table/tr').map(&:text))
+  {
+    actresses:       specs['出演者'].split,
+    cover_image:     html.at_css('#sample-video > a')['href'],
+    directors:       specs['監督'].split,
+    genres:          specs['ジャンル'].split,
+    label:           specs['レーベル'],
+    maker:           specs['メーカー'],
+    movie_length:    specs['収録時間'],
+    release_date:    specs['商品発売日'],
+    series:          specs['シリーズ'],
+    thumbnail_image: html.at_css('#sample-video > a > img')['src'],
+    title:           html.css('#title').text,
+  }
+end