mediaarts_scraper 0.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: c95b848f065f1110dcf0616253e774f9b4db26be
+  data.tar.gz: 86994c5d54fc3c8336ecc0cd2496b28267e2dcf3
+SHA512:
+  metadata.gz: 952ce1b825b4e18fc8b6c4ab22b7a3135edcfcbb7e2b4333c4140dfbb3183e0c86db2804554f2927aa5ca8405ad4be1eb77c384f5957836058f83aa091385690
+  data.tar.gz: ddef66e45a80cc515c7a8564cdd0a552b34cbf0285d622d2984c20f222f2dbe4bd0c9e50b93c36baeb29ec46a5de2a54bc5b7e5c8020d959d39426fe422898d8

data/.gitignore

@@ -0,0 +1,10 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+/tools/sit/data/actual.json
+/Gemfile.lock

data/Gemfile

@@ -0,0 +1,5 @@
+source "https://rubygems.org"
+
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
+
+gemspec

data/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2018 xmisao
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

data/README.md

@@ -0,0 +1,92 @@
+# MediaartsScraper
+
+Ruby scraper implementation for https://mediaarts-db.bunka.go.jp/
+
+文化庁のメディア芸術データベースをスクレイピングするGemライブラリです。
+
+# Installation
+
+```bash
+gem install 'mediaarts_scraper'
+```
+
+# Usage
+
+アニメシリーズIDを指定してスクレイピングする。
+
+```ruby
+require "mediaarts_scraper"
+
+# アニメシリーズID
+ans_id = 14810 # 魔法少女まどか★マギカ
+
+# ページオブジェクトを作る
+anime_series_page = MediaartsScraper::Page::AnimeSeriesPage.from_ans_id(ans_id)
+
+# データオブジェクトを得る
+anime_series = anime_series_page.data
+
+# データオブジェクトから取得できる属性を得る
+# 属性の名前はサイト上で言語をEnglishにした場合の項目名に準じます
+p anime_series.attributes #=> [:anime_series_id, :distribution_format, :anime_work_id, :title, :title_kana, :date_of_release, :date_of_end, :time_slot_or_duration, :number_of_broadc
+asts, :number_of_episodes, :distributor, :broadcast_period, :production_company, :original_source, :director, :credits, :cast, :theme_songs, :episode_t
+itles, :notes, :description, :story, :main_characters, :character_design, :characters, :music_or_sound_effects, :format_of_original_source, :eirin_no, 
+:rating_by_the_eirin, :copyright, :english_title_in_japan, :english_title_overseas, :hepburn_romanization_of_original_title, :romanization_of_original_
+title, :alternative_titles, :related_works, :tag, :carrier_type_of_original_material, :information_sources, :episodes, :materials, :packages, :related_
+series, :manga_work]
+
+# データオブジェクトから属性の値を得る
+p anime_series.title #=> "魔法少女まどか★マギカ"
+
+# データオブジェクトをハッシュに変換する
+p anime_series.to_hash #=> {"class"=>"MediaartsScraper::Data::AnimeSeries", :anime_series_id=>"ANS001019800", :distribution_format=>"TV", :anime_work_id=>"ANT001019800", :title=>
+"魔法少女まどか★マギカ",...
+
+# データオブジェクトをJSONに変換する
+p anime_series.to_json #=> "{\"class\":\"MediaartsScraper::Data::AnimeSeries\",\"anime_series_id\":\"ANS001019800\",\"distribution_format\":\"TV\",\"anime_work_id\":\"ANT001019800\",\"title\":\"魔法少女まどか★マギカ\",...
+```
+
+`examples`以下に使用例があります。
+
+# Supported Pages
+
+バージョン0.1はアニメーションのみの対応です。
+
+|Path|Page title|Page Object|Data Object|
+|:---|:---|:---|:---|
+|`/mg/`|マンガ|-|-|
+|`/an/anime_series/<ans_id>`|作品情報(シリーズ)|`AnimeSeriesPage`|`AnimeSeries`|
+|`/an/anime_series/<ans_id>/episodes`|各話情報一覧|`AnimeEpisodesPage`|`AnimeEpisodes`|
+|`/an/anime_series/<ans_id>/anime_packages/<anp_id>`|パッケージ情報|`AnimePackagesPage`|`AnimePackages`|
+|`/gm/`|ゲーム|-|-|
+|`/ma/`|メディアアート|-|-|
+
+`-` means unsupported yet.
+
+# Development
+
+## Debug
+
+Output internal logs of mediaarts_scraper by the following environment variable.
+
+```
+MEDIAARTS_SCRAPER_LOG_LEVEL=0
+```
+
+## Testing
+
+Run system integration testing. (Network connection is required.)
+
+```
+rake sit
+```
+
+Update expectation of system integration testing.
+
+```
+rake sit_update
+```
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/xmisao/mediaarts_scraper

data/Rakefile

@@ -0,0 +1,29 @@
+require "bundler/gem_tasks"
+task :default => :spec
+
+desc 'Run formatting by rufo'
+task :rufo do
+  fork do
+    exec("rufo Gemfile lib bin examples tools")
+  end
+
+  Process.wait
+end
+
+desc 'Run system integration testing'
+task :sit do
+  fork do
+    exec("ruby tools/sit/sit.rb")
+  end
+
+  Process.wait
+end
+
+desc 'Update expectation of system integration testing'
+task :sit_update do
+  fork do
+    exec("ruby tools/sit/sit_update.rb")
+  end
+
+  Process.wait
+end

data/lib/mediaarts_scraper/data/anime_episode.rb

@@ -0,0 +1,16 @@
+module MediaartsScraper::Data
+  class AnimeEpisode
+    include DataObject
+
+    attribute :episode_no, "Episode No."
+    attribute :episode_title, "Episode Title"
+    attribute :date_of_release, "Date of Release"
+    attribute :credits, "Credits"
+    attribute :cast, "Cast"
+    attribute :character, "Character"
+    attribute :story, "Story", true
+    attribute :main_mecha, "Main Mecha"
+    attribute :notes, "Notes"
+    attribute :information_sources, "Information Sources"
+  end
+end

data/lib/mediaarts_scraper/data/anime_episodes.rb

@@ -0,0 +1,8 @@
+module MediaartsScraper::Data
+  class AnimeEpisodes
+    include DataObject
+
+    attribute :title, "title"
+    attribute(:episodes, "story_table") { |episodes| episodes.map { |episode| AnimeEpisode.new(episode) } }
+  end
+end

data/lib/mediaarts_scraper/data/anime_packages.rb

@@ -0,0 +1,34 @@
+module MediaartsScraper::Data
+  class AnimePackages
+    include DataObject
+
+    attribute :package_id, "Package ID"
+    attribute :title, "Title"
+    attribute :title_kana, "Title-kana"
+    attribute :other_editions, "Other Editions"
+    attribute :volumes, "Volumes"
+    attribute :content_description, "Content Description"
+    attribute :number_of_discs, "Number of Discs / Duration"
+    attribute :series_title, "Series Title"
+    attribute :series_no, "Series No."
+    attribute :publisher_etc, "Publisher etc."
+    attribute :credits, "Credits"
+    attribute :publication_format, "Publication Format"
+    attribute :notes, "Notes"
+    attribute :size, "Size"
+    attribute :appendices, "Appendices"
+    attribute :content_specifications, "Content Specifications"
+    attribute :sales_no, "Sales No. (Model No./Stock No.)"
+    attribute :jan, "JAN (EAN/UPC)"
+    attribute :price, "Price"
+    attribute :date_of_publication, "Date of Publication"
+    attribute :language, "Language"
+    attribute :ratings, "Ratings"
+    attribute :place_of_publication, "Place of Publication"
+    attribute :national_bib_no_jpno, "National Bib. No. (JPNO)"
+    attribute :package_description, "Package Description"
+    attribute :tag, "Tag"
+
+    attribute(:physical_collection, "Physical Collection") { |physical_collection| AnimePackagesPhysicalCollection.new(physical_collection) }
+  end
+end

data/lib/mediaarts_scraper/data/anime_packages_physical_collection.rb

@@ -0,0 +1,10 @@
+module MediaartsScraper::Data
+  class AnimePackagesPhysicalCollection
+    include DataObject
+
+    attribute :package_ownership_information_id, "Package Ownership Information ID"
+    attribute :name_of_institution, "Name of Institution"
+    attribute :registration_no, "Registration No.(Institutional Collection Item ID)"
+    attribute :notes_from_istitution, "Notes from Institution"
+  end
+end

data/lib/mediaarts_scraper/data/anime_series.rb

@@ -0,0 +1,51 @@
+module MediaartsScraper::Data
+  class AnimeSeries
+    include DataObject
+
+    attribute :anime_series_id, "Anime Series ID"
+    attribute :distribution_format, "Distribution Format"
+    attribute :anime_work_id, "Anime Work ID"
+    attribute :title, "Title"
+    attribute :title_kana, "Title-kana"
+    attribute :date_of_release, "Date of Release"
+    attribute :date_of_end, "Date of End"
+    attribute :time_slot_or_duration, "Time Slot / Duration"
+    attribute :number_of_broadcasts, "Number of Broadcasts"
+    attribute :number_of_episodes, "Number of Episodes"
+    attribute :distributor, "Distributor"
+    attribute :broadcast_period, "Broadcast Period"
+    attribute :production_company, "Production Company"
+    attribute :original_source, "Original Source"
+    attribute :director, "Director"
+    attribute :credits, "Credits"
+    attribute :cast, "Cast"
+    attribute :theme_songs, "Theme Songs"
+    attribute :episode_titles, "Episode Titles"
+    attribute :notes, "Notes"
+    attribute :description, "Description", true
+    attribute :story, "Story", true
+    attribute :main_characters, "Main Characters", true
+    attribute :character_design, "Character Design"
+    attribute :characters, "Characters (Mecha)", true
+    attribute :music_or_sound_effects, "Music / Sound Effects"
+    attribute :format_of_original_source, "Format of Original Source"
+    attribute :eirin_no, "EIRIN No."
+    attribute :rating_by_the_eirin, "Rating (by the EIRIN)"
+    attribute :copyright, "Copyright"
+    attribute :english_title_in_japan, "English Title (In Japan)"
+    attribute :english_title_overseas, "English Title (Overseas)"
+    attribute :hepburn_romanization_of_original_title, "Hepburn Romanization of Original Title"
+    attribute :romanization_of_original_title, "Romanization of Original Title (w/Macron diacritics)"
+    attribute :alternative_titles, "Alternative Titles"
+    attribute :related_works, "Related Works"
+    attribute :tag, "Tag"
+    attribute :carrier_type_of_original_material, "Carrier Type of Original Material"
+    attribute :information_sources, "Information Sources"
+
+    attribute(:episodes, "Episodes") { |episodes| episodes.map { |episode| AnimeSeriesEpisode.new(episode) } }
+    attribute(:materials, "Materials") { |materials| materials.map { |material| AnimeSeriesMaterial.new(material) } }
+    attribute(:packages, "Packages") { |packages| packages.map { |package| AnimeSeriesPackage.new(package) } }
+    attribute(:related_series, "Related Series") { |related_serieses| related_serieses.map { |related_series| AnimeSeriesRelatedSeries.new(related_series) } }
+    attribute(:manga_work, "Manga Work") { |manga_works| manga_works.map { |manga_work| AnimeSeriesMangaWork.new(manga_work) } }
+  end
+end

data/lib/mediaarts_scraper/data/anime_series_episode.rb

@@ -0,0 +1,10 @@
+module MediaartsScraper::Data
+  class AnimeSeriesEpisode
+    include DataObject
+
+    attribute :episode_no, "Episode No."
+    attribute :episode_title, "Episode Title"
+    attribute :date_of_release, "Date of Release"
+    attribute :notes, "Notes"
+  end
+end

data/lib/mediaarts_scraper/data/anime_series_manga_work.rb

@@ -0,0 +1,14 @@
+module MediaartsScraper::Data
+  class AnimeSeriesMangaWork
+    include DataObject
+
+    attribute :title, "Title"
+    attribute :author, "Author"
+
+    attribute(:mmt_id, "href") { |href| self.to_mmt_id(href) }
+
+    def self.to_mmt_id(href)
+      /comic_works\/(\d+)/.match(href).to_a[1]&.to_i if href
+    end
+  end
+end

data/lib/mediaarts_scraper/data/anime_series_material.rb

@@ -0,0 +1,10 @@
+module MediaartsScraper::Data
+  class AnimeSeriesMaterial
+    include DataObject
+
+    attribute :material_name, "Material Name"
+    attribute :category, "Category"
+    attribute :list_of_authers, "List of Authors"
+    attribute :access_to_this_material, "Access to this Material"
+  end
+end

data/lib/mediaarts_scraper/data/anime_series_package.rb

@@ -0,0 +1,23 @@
+module MediaartsScraper::Data
+  class AnimeSeriesPackage
+    include DataObject
+
+    attribute :title, "Title"
+    attribute :volumes, "Volumes"
+    attribute :other_editions, "Other Editions"
+    attribute :publication_format, "Publication Format"
+    attribute :date_of_publication, "Date of Publication"
+    attribute :access_to_this_material, "Access to this Material"
+
+    attribute(:ans_id, "href") { |href| self.to_ans_id(href) }
+    attribute(:anp_id, "href") { |href| self.to_anp_id(href) }
+
+    def self.to_ans_id(href)
+      /anime_series\/(\d+)/.match(href).to_a[1]&.to_i if href
+    end
+
+    def self.to_anp_id(href)
+      /anime_packages\/(\d+)/.match(href).to_a[1]&.to_i if href
+    end
+  end
+end

data/lib/mediaarts_scraper/data/anime_series_related_series.rb

@@ -0,0 +1,20 @@
+module MediaartsScraper::Data
+  class AnimeSeriesRelatedSeries
+    include DataObject
+
+    attribute :title, "Title"
+    attribute :distribution_format, "Distribution Format"
+    attribute :director, "Director"
+    attribute :production_company, "Production Company"
+    attribute :date_of_release, "Date of Release"
+    attribute :date_of_end, "Date of End"
+    attribute :number_of_broadcasts, "Number of Broadcasts"
+    attribute :number_of_episodes, "Number of Episodes"
+
+    attribute(:ans_id, "href") { |href| self.to_ans_id(href) }
+
+    def self.to_ans_id(href)
+      /anime_series\/(\d+)/.match(href).to_a[1]&.to_i if href
+    end
+  end
+end

data/lib/mediaarts_scraper/data/data_object.rb

@@ -0,0 +1,93 @@
+module MediaartsScraper
+  module Data
+    module DataObject
+      NULL = Object.new.freeze
+
+      def self.included(klass)
+        klass.class_eval do
+          attr_reader :raw_data
+
+          def initialize(raw_data)
+            @raw_data = raw_data
+            @attributes = Hash.new(NULL)
+          end
+
+          def attributes
+            self.class.attributes
+          end
+
+          def attributes_without_copyrighted
+            self.class.attributes_without_copyrighted
+          end
+
+          def self.attribute(method, en, copyrighted = false)
+            attributes << method
+            attributes_without_copyrighted << method unless copyrighted
+
+            define_method(method) do
+              if @attributes[method] == NULL
+                if block_given?
+                  @attributes[method] = yield @raw_data[en]
+                else
+                  @attributes[method] = @raw_data[en]
+                end
+              end
+
+              @attributes[method]
+            end
+          end
+
+          def self.attributes
+            @_attributes_ = [] unless @_attributes_
+
+            @_attributes_
+          end
+
+          def self.attributes_without_copyrighted
+            @_attributes_without_copyrighted_ = [] unless @_attributes_without_copyrighted_
+
+            @_attributes_without_copyrighted_
+          end
+
+          def to_json(*options)
+            to_hash.to_json(*options)
+          end
+
+          def to_json_without_copyrighted(*options)
+            to_hash_without_copyrighted.to_json(*options)
+          end
+
+          def to_hash
+            to_hash0(attributes, :to_hash)
+          end
+
+          def to_hash_without_copyrighted
+            to_hash0(attributes_without_copyrighted, :to_hash_without_copyrighted)
+          end
+
+          private
+
+          def to_hash0(attributes, method)
+            {}.tap { |hash|
+              hash["class"] = self.class.name
+
+              attributes.each do |attr|
+                value = send(attr)
+
+                hash[attr] = if value.is_a?(Array)
+                               value.map { |item| item.respond_to?(method) ? item.send(method) : item }
+                             elsif value.is_a?(Hash)
+                               value.transform_values { |item| item.respond_to(method) ? item.send(method) : item }
+                             elsif value.respond_to?(method)
+                               value.send(method)
+                             else
+                               value
+                             end
+              end
+            }
+          end
+        end
+      end
+    end
+  end
+end

data/lib/mediaarts_scraper/logger.rb

@@ -0,0 +1,18 @@
+module MediaartsScraper
+  def self.logger=(logger)
+    @@logger = logger
+  end
+
+  def self.logger
+    @@logger
+  end
+
+  def self.init_logger
+    @@logger = Logger.new(STDOUT)
+    @@logger.progname = "MediaartsScraper"
+
+    @@logger.level = ENV["MEDIAARTS_SCRAPER_LOG_LEVEL"] ? ENV["MEDIAARTS_SCRAPER_LOG_LEVEL"].to_i : Logger::Severity::UNKNOWN
+  end
+
+  init_logger
+end

data/lib/mediaarts_scraper/page/anime_episodes_page.rb

@@ -0,0 +1,56 @@
+module MediaartsScraper
+  module Page
+    class AnimeEpisodesPage < PageBase
+      data_class MediaartsScraper::Data::AnimeEpisodes
+
+      PATH = "/anime_episodes?"
+      OPTION = "?display_view=pc&locale=en"
+      PAGE_OPTION = "&page="
+
+      attr_accessor :ans_id
+
+      def self.from_ans_id(ans_id, page_num = 1)
+        self.new(url: generate_url(ans_id, page_num))
+      end
+
+      def self.from_url(url)
+        self.new(url: url)
+      end
+
+      def self.generate_url(ans_id, page_num)
+        [MediaartsScraper.base_url,
+         AnimeSeriesPage::PATH,
+         ans_id,
+         PATH,
+         OPTION,
+         PAGE_OPTION,
+         page_num].join
+      end
+
+      def next_page
+        @next_page ||= parse_next_page
+      end
+
+      private
+
+      def parse(html)
+        title = /\s(.+)$/.match(doc.at_xpath("//section[@class='storyBlock']/h1").text.strip).to_a[1]
+
+        story_table = parse_common_serial_rows_table(doc.at_xpath("//table[@class='storyTbl']"))
+
+        {
+          "title" => title,
+          "story_table" => story_table,
+        }
+      end
+
+      def parse_next_page
+        nav = doc.at_xpath("//nav[@class='pager']")
+
+        next_page_url = nav.at_xpath("//a[@rel='next']")&.attribute("href")&.value
+
+        next_page_url ? self.class.from_url(resolve_relative_url(url, next_page_url)) : nil
+      end
+    end
+  end
+end

data/lib/mediaarts_scraper/page/anime_packages_page.rb

@@ -0,0 +1,39 @@
+module MediaartsScraper
+  module Page
+    class AnimePackagesPage < PageBase
+      data_class MediaartsScraper::Data::AnimePackages
+
+      PATH = "/anime_packages/"
+      OPTION = "?display_view=pc&locale=en"
+
+      attr_accessor :ans_id
+
+      def self.from_ans_anp_id(ans_id, anp_id)
+        self.new(url: generate_url(ans_id, anp_id))
+      end
+
+      def self.generate_url(ans_id, anp_id)
+        [MediaartsScraper.base_url,
+         AnimeSeriesPage::PATH,
+         ans_id,
+         PATH,
+         anp_id,
+         OPTION].join
+      end
+
+      private
+
+      def parse(html)
+        doc = Nokogiri::HTML.parse(html, nil, "utf8")
+
+        document_table = doc.at_xpath("//div[@class='main']/section/table[@class='documentTbl']")
+        r1 = parse_common_key_value_table(document_table)
+
+        document_table2 = doc.at_xpath("//div[@class='sub']/section/table[@class='documentTbl2']")
+        r2 = parse_common_key_value_table(document_table2)
+
+        r1.merge("Physical Collection" => r2)
+      end
+    end
+  end
+end

data/lib/mediaarts_scraper/page/anime_series_page.rb

@@ -0,0 +1,89 @@
+module MediaartsScraper
+  module Page
+    class AnimeSeriesPage < PageBase
+      data_class MediaartsScraper::Data::AnimeSeries
+
+      PATH = "/an/anime_series/"
+      OPTION = "?display_view=pc&locale=en"
+
+      attr_accessor :ans_id
+
+      def self.from_ans_id(ans_id)
+        self.new(url: generate_url(ans_id))
+      end
+
+      def self.generate_url(ans_id)
+        [MediaartsScraper.base_url,
+         PATH,
+         ans_id,
+         OPTION].join
+      end
+
+      def episodes_page
+        @episodes_page ||= parse_episode_page
+      end
+
+      def packages_pages
+        @package_page ||= parse_packages_pages
+      end
+
+      private
+
+      def parse(html)
+        {}.tap do |result|
+          doc.xpath("//div[@class='main']/section/table").each do |table|
+            result.merge!(parse_common_key_value_table(table))
+          end
+
+          doc.xpath("//div[@class='sub']/section").each do |section|
+            result.merge!(parse_sub_section(section))
+          end
+
+          doc.xpath("//div[@class='moreContents']")&.each do |div|
+            result.merge!(parse_more_contents(div))
+          end
+        end
+      end
+
+      def parse_sub_section(section)
+        base_key = section.xpath("h3").first.children.first.text.strip
+
+        tables = section.xpath("table[@class='seriesTbl2']")
+
+        raise ParseError unless tables.count == 1
+
+        table = tables.first
+
+        {base_key => parse_common_serial_rows_table(table)}
+      end
+
+      def parse_more_contents(div)
+        base_key = div.xpath("h3").text.strip
+
+        table_items = div.xpath("section/table[@class='seriesTbl']").each_with_object({}) do |table, memo|
+          memo.merge!(parse_common_key_value_table(table))
+        end
+
+        {base_key => table_items}
+      end
+
+      def parse_episode_page
+        move_story_element = doc.at_xpath("//div[@class='sub']/section/p[@class='moveStory']/a")
+
+        return unless move_story_element
+
+        relative_url = move_story_element.attribute("href").value
+
+        AnimeEpisodesPage.from_url(resolve_relative_url(url, relative_url))
+      end
+
+      def parse_packages_pages
+        doc.xpath("//div[@class='sub']/section/table[@class='seriesTbl2']/tbody/tr/td[@class='i']/a").map do |package_anchor_element|
+          relative_url = package_anchor_element.attribute("href").value
+
+          AnimePackagesPage.from_url(resolve_relative_url(url, relative_url))
+        end
+      end
+    end
+  end
+end

data/lib/mediaarts_scraper/page/common_table_parser.rb

@@ -0,0 +1,80 @@
+module MediaartsScraper
+  module Page
+    module CommonTableParser
+      KEY_SEPARATOR = "/"
+
+      def parse_common_key_value_table(table)
+        result = {}
+
+        table.xpath("tbody/tr").each do |tr|
+          ths = tr.xpath("th")
+          tds = tr.xpath("td")
+
+          if ths.count == tds.count
+            keys = ths.map(&:text).map(&:strip)
+
+            values = tds.each_with_index.map do |td, i|
+              if td.xpath("p").count == 1
+                dls = td.xpath("div/div/dl")
+
+                if dls.count > 0
+                  dls.each do |dl|
+                    dts = dl.xpath("dt").map(&:text).map(&:strip)
+                    dds = dl.xpath("dd").map(&:text).map(&:strip)
+
+                    if dts.count == dds.count
+                      dts.each do |dt|
+                        dds.each do |dd|
+                          result[keys[i] + KEY_SEPARATOR + dt] = dd
+                        end
+                      end
+                    else
+                      raise ParseError
+                    end
+                  end
+                end
+
+                td.xpath("p").first.text.strip
+              else
+                td.text.strip
+              end
+            end
+
+            keys.each_with_index do |key, i|
+              result[key] = values[i]
+            end
+          else
+            raise ParseError
+          end
+        end
+
+        result
+      end
+
+      def parse_common_serial_rows_table(table)
+        header = table.xpath("thead/tr/th").map(&:text).map(&:strip)
+
+        table.xpath("tbody/tr").map do |tr|
+          tds = tr.xpath("td")
+
+          data = tds.map { |td|
+            child = td.child
+
+            if child
+              child.text.strip
+            else
+              td.text.strip
+            end
+          }
+
+          tr_result = Hash[*header.zip(data).flatten]
+
+          link_element = tds.detect { |td| td.xpath("a").first }
+          tr_result["href"] = link_element.xpath("a").first.attributes["href"].value if link_element
+
+          tr_result
+        end
+      end
+    end
+  end
+end

data/lib/mediaarts_scraper/page/helper.rb

@@ -0,0 +1,9 @@
+module MediaartsScraper
+  module Page
+    module Helper
+      def resolve_relative_url(base_url, relative_url)
+        URI.join(base_url, relative_url).to_s
+      end
+    end
+  end
+end

data/lib/mediaarts_scraper/page/page_base.rb

@@ -0,0 +1,48 @@
+module MediaartsScraper
+  module Page
+    class PageBase
+      include Helper
+      include CommonTableParser
+
+      def initialize(url:)
+        @original_url = url
+      end
+
+      def self.from_url(url)
+        self.new(url: url)
+      end
+
+      def self.data_class(data_class)
+        define_method("data_class") do
+          data_class
+        end
+      end
+
+      def data
+        @data ||= data_class.new(raw_data)
+      end
+
+      def html
+        @html ||= fetch(url)
+      end
+
+      def url
+        @original_url
+      end
+
+      def raw_data
+        @raw_data ||= parse(html)
+      end
+
+      def doc
+        @doc ||= Nokogiri::HTML.parse(html, nil, "utf8")
+      end
+
+      def fetch(url)
+        MediaartsScraper.logger.debug { {class: self.class.name, method: "fetch", url: url} }
+
+        open(url) { |f| f.read }
+      end
+    end
+  end
+end

data/lib/mediaarts_scraper/page/parse_error.rb

@@ -0,0 +1,5 @@
+module MediaartsScraper
+  module Page
+    class ParseError < StandardError; end
+  end
+end

data/lib/mediaarts_scraper/version.rb

@@ -0,0 +1,3 @@
+module MediaartsScraper
+  VERSION = "0.0.0"
+end

data/lib/mediaarts_scraper.rb

@@ -0,0 +1,42 @@
+require "nokogiri"
+
+require "open-uri"
+require "pp"
+require "json"
+require "logger"
+
+require_relative "mediaarts_scraper/version"
+
+require_relative "mediaarts_scraper/logger"
+
+require_relative "mediaarts_scraper/data/data_object"
+require_relative "mediaarts_scraper/data/anime_series"
+require_relative "mediaarts_scraper/data/anime_series_episode"
+require_relative "mediaarts_scraper/data/anime_series_material"
+require_relative "mediaarts_scraper/data/anime_series_package"
+require_relative "mediaarts_scraper/data/anime_series_related_series"
+require_relative "mediaarts_scraper/data/anime_series_manga_work"
+require_relative "mediaarts_scraper/data/anime_episode"
+require_relative "mediaarts_scraper/data/anime_episodes"
+require_relative "mediaarts_scraper/data/anime_packages"
+require_relative "mediaarts_scraper/data/anime_packages_physical_collection"
+
+require_relative "mediaarts_scraper/page/parse_error"
+require_relative "mediaarts_scraper/page/helper"
+require_relative "mediaarts_scraper/page/common_table_parser"
+require_relative "mediaarts_scraper/page/page_base"
+require_relative "mediaarts_scraper/page/anime_series_page"
+require_relative "mediaarts_scraper/page/anime_episodes_page"
+require_relative "mediaarts_scraper/page/anime_packages_page"
+
+module MediaartsScraper
+  def self.base_url=(base_url)
+    @@base_url = base_url
+  end
+
+  def self.base_url
+    @@base_url
+  end
+
+  @@base_url = "https://mediaarts-db.bunka.go.jp"
+end

data/mediaarts_scraper.gemspec

@@ -0,0 +1,29 @@
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "mediaarts_scraper/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "mediaarts_scraper"
+  spec.version       = MediaartsScraper::VERSION
+  spec.authors       = ["xmisao"]
+  spec.email         = ["mail@xmisao.com"]
+
+  spec.summary       = %q{Scraper for Media Art Database}
+  spec.description   = %q{Ruby scraper implementation for https://mediaarts-db.bunka.go.jp/}
+  spec.homepage      = "https://github.com/xmisao/mediaarts_scraper"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+    f.match(%r{^(tools|examples|bin)/})
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.16"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rufo", ">= 0.3.1"
+  spec.add_development_dependency "pry", ">= 0.11.3"
+
+  spec.add_runtime_dependency "nokogiri", ">= 1.8.4"
+end

metadata

@@ -0,0 +1,141 @@
+--- !ruby/object:Gem::Specification
+name: mediaarts_scraper
+version: !ruby/object:Gem::Version
+  version: 0.0.0
+platform: ruby
+authors:
+- xmisao
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2018-09-01 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rufo
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.3.1
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.3.1
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.11.3
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.11.3
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.8.4
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.8.4
+description: Ruby scraper implementation for https://mediaarts-db.bunka.go.jp/
+email:
+- mail@xmisao.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- lib/mediaarts_scraper.rb
+- lib/mediaarts_scraper/data/anime_episode.rb
+- lib/mediaarts_scraper/data/anime_episodes.rb
+- lib/mediaarts_scraper/data/anime_packages.rb
+- lib/mediaarts_scraper/data/anime_packages_physical_collection.rb
+- lib/mediaarts_scraper/data/anime_series.rb
+- lib/mediaarts_scraper/data/anime_series_episode.rb
+- lib/mediaarts_scraper/data/anime_series_manga_work.rb
+- lib/mediaarts_scraper/data/anime_series_material.rb
+- lib/mediaarts_scraper/data/anime_series_package.rb
+- lib/mediaarts_scraper/data/anime_series_related_series.rb
+- lib/mediaarts_scraper/data/data_object.rb
+- lib/mediaarts_scraper/logger.rb
+- lib/mediaarts_scraper/page/anime_episodes_page.rb
+- lib/mediaarts_scraper/page/anime_packages_page.rb
+- lib/mediaarts_scraper/page/anime_series_page.rb
+- lib/mediaarts_scraper/page/common_table_parser.rb
+- lib/mediaarts_scraper/page/helper.rb
+- lib/mediaarts_scraper/page/page_base.rb
+- lib/mediaarts_scraper/page/parse_error.rb
+- lib/mediaarts_scraper/version.rb
+- mediaarts_scraper.gemspec
+homepage: https://github.com/xmisao/mediaarts_scraper
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.5.2.1
+signing_key: 
+specification_version: 4
+summary: Scraper for Media Art Database
+test_files: []