panchira 0.3.0 → 1.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e0715fad65f1b2f6654761d9d1132217ce644c49b621a94aff1f0a6372dd327b
-  data.tar.gz: 265c9ab995d2c2913465e0dd17e69c008389c1c06e3b8fbeb798e24dcdced89d
+  metadata.gz: 9f1b155399ed2e9caef218bd5599d72c3d6102c5b7e0da50fc297fe4db99614c
+  data.tar.gz: 92e31687ac7d5edbbd94df6eff606cabaa3dab891b57fda1a3b9a4af3815949c
 SHA512:
-  metadata.gz: 231b3b600e88c20f3479943c93efd3b8d720c7052c45c26301818b88a860ac8387610fdd7006c2c6211ecf482a76b24389e4e409290c8817869a3a19af0b0966
-  data.tar.gz: a69dfa20c85d5ef15c12d825dd791450835c7ac9edf511a2b3b5592621706ba0c80d94cf258fd513dc8568e5972270fd5e7271a3c7219c0a3ad8724e4a9a0b23
+  metadata.gz: 8b8a5e274a776a2a384c4901b754fa14025c1f4a3b735708d5e692656b2462f1fbdbc8df63edde2600c154b440195e3c4183a42a1a9d9245668e35b0494ae41d
+  data.tar.gz: 727acf463987e381620e0a6d5200c22063df44d4d5fa4c3f086abf950ea7543f105fab7077446cc6cdfcc3beb9c90b8da4a617ddb5146bd3930c4ab91c67f4e0

data/.github/workflows/ruby.yml

@@ -21,10 +21,7 @@ jobs:
     steps:
     - uses: actions/checkout@v2
     - name: Set up Ruby
-    # To automatically get bug fixes and new Ruby versions for ruby/setup-ruby,
-    # change this to (see https://github.com/ruby/setup-ruby#versioning):
-    # uses: ruby/setup-ruby@v1
-      uses: ruby/setup-ruby@ec106b438a1ff6ff109590de34ddc62c540232e0
+      uses: ruby/setup-ruby@v1
       with:
         ruby-version: 2.6
     - name: Install dependencies

data/.rubocop.yml

@@ -0,0 +1,64 @@
+inherit_from: .rubocop_todo.yml
+
+require:
+  - rubocop-minitest
+
+AllCops:
+  TargetRubyVersion: 2.6
+  NewCops: enable
+  Exclude:
+    - bin/*
+    - vendor/bundle/**/*
+  SuggestExtensions: false
+
+Layout/FirstHashElementIndentation:
+  EnforcedStyle: consistent
+
+Layout/IndentationConsistency:
+  EnforcedStyle: indented_internal_methods
+
+Layout/MultilineMethodCallIndentation:
+  EnforcedStyle: indented
+
+Layout/SpaceInsideHashLiteralBraces:
+  EnforcedStyle: no_space
+
+Lint/AssignmentInCondition:
+  Enabled: false
+
+Lint/MissingSuper:
+  Exclude: 
+    - lib/panchira/resolvers/*
+
+Style/AsciiComments:
+  Enabled: false
+
+Style/Documentation:
+  Enabled: false
+
+Style/EmptyMethod:
+  EnforcedStyle: expanded
+
+Style/GuardClause:
+  Enabled: false
+
+Style/IfInsideElse:
+  Enabled: false
+
+Style/SoleNestedConditional:
+  Enabled: false
+
+Style/IfUnlessModifier:
+  Enabled: false
+
+Style/NumericPredicate:
+  Enabled: false
+
+Style/ParallelAssignment:
+  Enabled: false
+
+Style/WordArray:
+  EnforcedStyle: brackets
+
+Style/SymbolArray:
+  EnforcedStyle: brackets

data/.rubocop_todo.yml

@@ -0,0 +1,45 @@
+# This configuration was generated by
+# `rubocop --auto-gen-config`
+# on 2021-01-03 15:08:31 UTC using RuboCop version 1.7.0.
+# The point is for the user to remove these configuration records
+# one by one as the offenses are removed from the code base.
+# Note that changes in the inspected code, or installation of new
+# versions of RuboCop, may require this file to be generated again.
+
+# Offense count: 1
+Lint/MixedRegexpCaptureTypes:
+  Exclude:
+    - 'lib/panchira/resolvers/nijie_resolver.rb'
+
+# Offense count: 1
+# Configuration parameters: AllowedMethods.
+# AllowedMethods: present?, blank?, presence, try, try!, in?
+Lint/SafeNavigationChain:
+  Exclude:
+    - 'lib/panchira/resolvers/melonbooks_resolver.rb'
+
+# Offense count: 8
+# Configuration parameters: IgnoredMethods, CountRepeatedAttributes.
+Metrics/AbcSize:
+  Max: 40
+
+# Offense count: 1
+# Configuration parameters: IgnoredMethods.
+Metrics/CyclomaticComplexity:
+  Max: 8
+
+# Offense count: 7
+# Configuration parameters: CountComments, CountAsOne, ExcludedMethods, IgnoredMethods.
+Metrics/MethodLength:
+  Max: 21
+
+# Offense count: 11
+Minitest/MultipleAssertions:
+  Max: 15
+
+# Offense count: 2
+# Cop supports --auto-correct.
+# Configuration parameters: AutoCorrect, AllowHeredoc, AllowURI, URISchemes, IgnoreCopDirectives, IgnoredPatterns.
+# URISchemes: http, https
+Layout/LineLength:
+  Max: 132

data/CHANGELOG.md

@@ -4,6 +4,46 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/)
 and this project adheres to [Semantic Versioning](http://semver.org/).
 
+## 1.3.0 - 2021-02-06
+### Added
+- Added support for multiple authors. PanchiraResult#authors now returns an array of authors.
+- PanchiraResult now returns a resolver name used in the process (PanchiraResult#resolver).
+
+### Fixed
+- Fixed an issue that fetching DLSite pages with multiple authors were not working.
+- Fixed a slight issue in MelonbooksResolver.
+
+## 1.2.0 - 2020-10-31
+### Added
+- You can now fetch author and circle name in resolvers (Resolver#fetch_author, Resolver#fetch_circle).
+
+### Changed
+- Resolver#fetch_title returns the title of the content (not the original title of the page).
+
+## 1.1.1 - 2020-08-09
+### Added
+- Added support for Fanza Doujin.
+- Added support for description in Fanza Book.
+
+### Fixed
+- Fixed an issue that fetching image was not working in Fanza Book.
+
+## 1.1.0 - 2020-08-06
+### Added
+- Added support for Fanza Books.
+- Added support for direct links to an image.
+- You can now set cookie by overriding Resolver#cookie in individual resolvers.
+
+### Changed
+- Resolver::USER_AGENT changed to Resolver#user_agent.
+
+## 1.0.0 - 2020-06-23
+### Added
+- Added support for tags.
+
+### Fixed
+- Fixed some outdated documents.
+
 ## 0.3.0 - 2020-06-04
 ### Added
 - You can now register and use your own Resolver with this gem. (see Panchira::Extensions#register)
@@ -27,6 +67,10 @@ and this project adheres to [Semantic Versioning](http://semver.org/).
 ### Added
 - Released Panchira gem. At this time we can parse only 5 websites.
 
+[1.3.0]: https://github.com/nuita/panchira/releases/tag/v1.3.0
+[1.2.0]: https://github.com/nuita/panchira/releases/tag/v1.2.0
+[1.1.0]: https://github.com/nuita/panchira/releases/tag/v1.1.0
+[1.0.0]: https://github.com/nuita/panchira/releases/tag/v1.0.0
 [0.3.0]: https://github.com/nuita/panchira/releases/tag/v0.3.0
 [0.2.0]: https://github.com/nuita/panchira/releases/tag/v0.2.0
 [0.1.1]: https://github.com/nuita/panchira/releases/tag/v0.1.1

data/Gemfile

@@ -1,4 +1,6 @@
-source "https://rubygems.org"
+# frozen_string_literal: true
+
+source 'https://rubygems.org'
 
 # Specify your gem's dependencies in panchira.gemspec
 gemspec

data/Gemfile.lock

@@ -1,19 +1,41 @@
 PATH
   remote: .
   specs:
-    panchira (0.3.0)
+    panchira (1.3.0)
       fastimage (~> 2.1.7)
-      nokogiri (~> 1.10.9)
+      nokogiri (>= 1.10.9, < 1.12.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
+    ast (2.4.1)
     fastimage (2.1.7)
-    mini_portile2 (2.4.0)
-    minitest (5.14.0)
-    nokogiri (1.10.9)
-      mini_portile2 (~> 2.4.0)
+    minitest (5.14.2)
+    nokogiri (1.11.0-x86_64-darwin)
+      racc (~> 1.4)
+    parallel (1.20.1)
+    parser (3.0.0.0)
+      ast (~> 2.4.1)
+    racc (1.5.2)
+    rainbow (3.0.0)
     rake (12.3.3)
+    regexp_parser (2.0.3)
+    rexml (3.2.4)
+    rubocop (1.7.0)
+      parallel (~> 1.10)
+      parser (>= 2.7.1.5)
+      rainbow (>= 2.2.2, < 4.0)
+      regexp_parser (>= 1.8, < 3.0)
+      rexml
+      rubocop-ast (>= 1.2.0, < 2.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 1.4.0, < 2.0)
+    rubocop-ast (1.4.0)
+      parser (>= 2.7.1.5)
+    rubocop-minitest (0.10.2)
+      rubocop (>= 0.87, < 2.0)
+    ruby-progressbar (1.11.0)
+    unicode-display_width (1.7.0)
 
 PLATFORMS
   ruby
@@ -23,6 +45,8 @@ DEPENDENCIES
   minitest (~> 5.0)
   panchira!
   rake (~> 12.3.3)
+  rubocop (~> 1.7)
+  rubocop-minitest (~> 0.10)
 
 BUNDLED WITH
-   2.0.2
+   2.1.4

data/README.md

@@ -6,7 +6,7 @@
 
 Due to some legal or ethical issues, most hentai and NSFW platforms don't clarify their content on meta tags. As a result, most hentai platforms are rendered poorly on the card previews on social media.
 
-To solve this issue, Panchira is made to parse correct and uncensored metadata from such web platforms (at this time we cover **DLSite, Komiflo, Melonbooks, Nijie and Pixiv**).
+To solve this issue, Panchira is made to parse correct and uncensored metadata from such web platforms (at this time we cover **DLSite, Komiflo, Melonbooks, Nijie, Pixiv, Shousetsuka ni narou, Fanza and Twitter**).
 
 If you need card previews of hentai on your web application, but can't get them with simply parsing metatags, then it is time for Panchira.
 
@@ -16,7 +16,7 @@ This gem is derived from the [Nuita](https://github.com/nuita/nuita) project.
 
 **Please use this gem with appropriate censoring and age-restricting. Never violate local laws and copyrights.**
 
-If you are running one of the websites we cover and feel negative about it, please contact the community or the author([@kypkyp](https://github.com/kypkyp)). 
+If you are running one of the websites we cover and feel negative about this gem, please contact the community or the author([@kypkyp](https://github.com/kypkyp)). 
 
 ## Installation
 
@@ -39,10 +39,12 @@ Or install it yourself as:
 ```
 > Panchira.fetch("https://www.pixiv.net/artworks/61711172")
 
-=> {:canonical_url=>"https://pixiv.net/member_illust.php?mode=medium&illust_id=61711172", :title=>"#輿水幸子 すずしい顔で締め切りを破る幸子 - むらためのイラスト - pixiv", :description=>"(UTF16の)Pietで実行すると「すずしい」と出力する幸子(5色+白Pietカラーゴルフ)。解説記事は http://chy72.hatenablog.com/entry/2016/12/24/1", :image=>{:url=>"https://pixiv.cat/61711172.jpg", :width=>810, :height=>500}}
+=> #<Panchira::PanchiraResult:0x00007ff15890e948 @canonical_url="https://pixiv.net/member_illust.php?mode=medium&illust_id=61711172", @title="すずしい顔で締め切りを破る幸子", @description="(UTF16の)Pietで実行すると「すずしい」と出力する幸子(5色+白Pietカラーゴルフ)。解説記事は http://chy72.hatenablog.com/entry/2016/12/24/1", @image=#<Panchira::PanchiraImage:0x00007ff15931fc48 @url="https://pixiv.cat/61711172.jpg", @width=810, @height=500>, @tags=["輿水幸子", "Piet", "プログラミング"], @authors=["むらため"], @circle=nil, @resolver="Panchira::PixivResolver">
 ```
 
-Panchira is in beta at this time and doesn't have stable API documentation yet.
+In most situation you would call `Panchira#fetch`. It is a singular method that takes a URI and returns an instance of `PanchiraResult`, which is a simple class that stores the website's information, such as title, description and so on.
+
+Panchira has a special treatment for each website. `Resolver` classes are where those treatments take place, and you can use your own `Resolver` classes by registering it to Panchira. See `Panchira::Extensions` documentation in source code for further details.
 
 ## Development
 

data/Rakefile

@@ -1,10 +1,12 @@
-require "bundler/gem_tasks"
-require "rake/testtask"
+# frozen_string_literal: true
+
+require 'bundler/gem_tasks'
+require 'rake/testtask'
 
 Rake::TestTask.new(:test) do |t|
-  t.libs << "test"
-  t.libs << "lib"
-  t.test_files = FileList["test/**/*_test.rb"]
+  t.libs << 'test'
+  t.libs << 'lib'
+  t.test_files = FileList['test/**/*_test.rb']
 end
 
-task :default => :test
+task default: :test

data/lib/panchira.rb

@@ -11,7 +11,10 @@ require_relative 'panchira/resolvers/resolver'
 require_relative 'panchira/extensions'
 
 project_root = File.dirname(File.absolute_path(__FILE__))
-Dir.glob(project_root + '/panchira/resolvers/*_resolver.rb').sort.each { |file| require file }
+Dir.glob("#{project_root}/panchira/resolvers/*_resolver.rb").sort.each { |file| require file }
+
+# register fallback ImageResolver at the end. (resolver is selected by registration order)
+::Panchira::Extensions.register(Panchira::ImageResolver)
 
 # Main Panchira code goes here.
 # If you simply want to get data from your URL, then ::Panchira::fetch() will do.
@@ -26,12 +29,12 @@ module Panchira
 
     private
 
-    def select_resolver(url)
-      Panchira::Extensions.resolvers.each do |resolver|
-        return resolver if resolver.applicable?(url)
-      end
+      def select_resolver(url)
+        Panchira::Extensions.resolvers.each do |resolver|
+          return resolver if resolver.applicable?(url)
+        end
 
-      Panchira::Resolver
-    end
+        Panchira::Resolver
+      end
   end
 end

data/lib/panchira/panchira_result.rb

@@ -8,6 +8,14 @@ module Panchira
 
   # Result class for Panchira.fetch.
   class PanchiraResult
-    attr_accessor :canonical_url, :title, :description, :image
+    attr_accessor :canonical_url, :title, :description, :image, :tags, :authors, :circle, :resolver
+
+    def author
+      authors&.join(' ')
+    end
+
+    def author=(value)
+      self.authors = [value] if value
+    end
   end
 end

data/lib/panchira/resolvers/dlsite_resolver.rb

@@ -6,9 +6,41 @@ module Panchira
 
     private
 
-    def parse_image_url
-      @page.css('//meta[property="og:image"]/@content').first.to_s.sub(/sam/, 'main')
-    end
+      # DLSiteのタイトルの[]に含まれている値はtitleタグだとサークル名 or 出版社名だが、
+      # Panchiraが優先するog:titleではサークル名 or 著者名 となる。
+      # 取得に際しては、以下の3パターンを考慮する必要があるため、titleタグとtableの解析が必要となる:
+      # 1) 同人系の一部, 特に音声など。タイトル[サークル名]. 本文中に著者・作者の記載なし
+      # 2) 同人系の一部, 特に一部の同人誌など。タイトル[サークル名]. 本文中に「作者」の記載あり
+      # 3) 商業系。タイトル[著者名]　サークル名なし
+      # 込み入った実装になってしまったため、parse自体をいじる必要があるかも
+      def parse_title
+        @title_md = super.match(/(.+) \[(.+)\] \|.+/)
+        @title_md[1]
+      end
+
+      def parse_authors
+        @page.css('table[id*="work_"] tr').each do |tr|
+          next unless tr.css('th').text =~ /(作|著)者/
+
+          return @authors = tr.css('td > a').map do |node|
+            node.text.strip
+          end
+        end
+
+        @authors = nil
+      end
+
+      def parse_circle
+        @title_md[2] if @authors&.slice(0..2)&.join(' ') != @title_md[2]
+      end
+
+      def parse_image_url
+        @page.css('//meta[property="og:image"]/@content').first.to_s.sub(/sam/, 'main')
+      end
+
+      def parse_tags
+        @page.css('.main_genre').children.children.map(&:text)
+      end
   end
 
   ::Panchira::Extensions.register(Panchira::DlsiteResolver)

data/lib/panchira/resolvers/fanza_resolver.rb

@@ -0,0 +1,56 @@
+# frozen_string_literal: true
+
+require 'net/https'
+
+module Panchira
+  module Fanza
+    FANZA_COOKIE = 'age_check_done=1;'
+
+    class FanzaResolver < Resolver
+      private
+
+        def cookie
+          ::Panchira::Fanza::FANZA_COOKIE
+        end
+    end
+
+    class FanzaBookResolver < FanzaResolver
+      URL_REGEXP = %r{book\.dmm\.co\.jp/}.freeze
+
+      private
+
+        def parse_author
+          @page.css('.m-boxDetailProductInfoMainList__description__list__item > a').first&.text.to_s
+        end
+
+        def parse_image_url
+          @page.css('.m-imgDetailProductPack/@src').first.to_s
+        end
+
+        def parse_tags
+          @page.css('.m-boxDetailProductInfo__list__description__item > a').map(&:text)
+        end
+
+        def parse_description
+          @page.css('.m-boxDetailProduct__info__story').first&.text.to_s.gsub(/[\n\t]/, '')
+        end
+    end
+
+    class FanzaDoujinResolver < FanzaResolver
+      URL_REGEXP = %r{dmm\.co\.jp/dc/doujin/}.freeze
+
+      private
+
+        def parse_circle
+          @page.css('a.circleName__txt').first.text
+        end
+
+        def parse_tags
+          @page.css('.genreTag__item').map { |t| t.text.strip }
+        end
+    end
+  end
+
+  ::Panchira::Extensions.register(Panchira::Fanza::FanzaBookResolver)
+  ::Panchira::Extensions.register(Panchira::Fanza::FanzaDoujinResolver)
+end

data/lib/panchira/resolvers/image_resolver.rb

@@ -0,0 +1,16 @@
+# frozen_string_literal: true
+
+module Panchira
+  class ImageResolver < Resolver
+    URL_REGEXP = /\.(png|gif|jpg|jpeg|webp)$/.freeze
+
+    def fetch
+      result = PanchiraResult.new
+      result.canonical_url = @url
+      result.image = PanchiraImage.new
+      result.image.url = @url
+      result.resolver = parse_resolver
+      result
+    end
+  end
+end

data/lib/panchira/resolvers/komiflo_resolver.rb

@@ -10,33 +10,36 @@ module Panchira
       @url = url
 
       @id = url.slice(URL_REGEXP, 1)
-      raw_json = URI.parse("https://api.komiflo.com/content/id/#{@id}").read('User-Agent' => USER_AGENT)
+      raw_json = URI.parse("https://api.komiflo.com/content/id/#{@id}").read('User-Agent' => user_agent)
       @json = JSON.parse(raw_json)
     end
 
     private
 
-    def parse_title
-      comic_title = @json['content']['data']['title']
-      "#{comic_title} | Komiflo"
-    end
+      def parse_title
+        @json['content']['data']['title']
+      end
 
-    def parse_image_url
-      'https://t.komiflo.com/564_mobile_large_3x/' + @json['content']['named_imgs']['cover']['filename']
-    end
+      def parse_image_url
+        "https://t.komiflo.com/564_mobile_large_3x/#{@json['content']['named_imgs']['cover']['filename']}"
+      end
 
-    def parse_description
-      author = @json['content']['attributes']['artists']['children'][0]['data']['name']
+      def parse_author
+        @json['content']['attributes']['artists']['children'][0]['data']['name']
+      end
 
-      parent = @json['content']['parents'][0]['data']['title']
-      description = '著: ' + author if author
-      description + " / #{parent}" if parent
-    end
+      def parse_description
+        @json['content']['parents'][0]['data']['title']
+      end
 
-    def parse_canonical_url
-      id = @url.slice(%r{komiflo\.com(?:/#!)?/comics/(\d+)}, 1)
-      'https://komiflo.com/comics/' + id
-    end
+      def parse_canonical_url
+        id = @url.slice(%r{komiflo\.com(?:/#!)?/comics/(\d+)}, 1)
+        "https://komiflo.com/comics/#{id}"
+      end
+
+      def parse_tags
+        @json['content']['attributes']['tags']['children'].map { |content| content['data']['name'] }
+      end
   end
 
   ::Panchira::Extensions.register(Panchira::KomifloResolver)

data/lib/panchira/resolvers/melonbooks_resolver.rb

@@ -4,27 +4,65 @@ module Panchira
   class MelonbooksResolver < Resolver
     URL_REGEXP = %r{melonbooks.co.jp/detail/detail.php\?product_id=(\d+)}.freeze
 
-    private
+    def fetch
+      result = PanchiraResult.new
+
+      @page = fetch_page(@url)
+      result.canonical_url = parse_canonical_url
+
+      @page = fetch_page(result.canonical_url) if @url != result.canonical_url
 
-    def parse_canonical_url
-      product_id = @url.slice(URL_REGEXP, 1)
-      'https://www.melonbooks.co.jp/detail/detail.php?product_id=' + product_id + '&adult_view=1'
+      result.title, result.author, result.circle = parse_table
+      result.description = parse_description
+      result.image = parse_image
+      result.tags = parse_tags
+      result.resolver = parse_resolver
+
+      result
     end
 
-    def parse_description
-      # スタッフの紹介文でidが分岐
-      special_description = @page.xpath('//div[@id="special_description"]//p/text()')
-      if special_description.any?
-        special_description.first.to_s
-      else
-        description = @page.xpath('//div[@id="description"]//p/text()')
-        description.first.to_s
+    private
+
+      def parse_table
+        title, author, circle = nil, nil, nil
+
+        @page.css('#description > table.stripe > tr').each do |tr|
+          case tr.css('th').text
+          when 'タイトル'
+            title = tr.css('td').text.strip
+          when 'サークル名'
+            circle = tr.css('td > a').text.match(/^(.+)\W\(作品数:/)&.values_at(1)&.first
+          when '作家名'
+            author = tr.css('td > a').text.strip
+          end
+        end
+
+        [title, author, circle]
       end
-    end
 
-    def parse_image_url
-      @page.css('//meta[property="og:image"]/@content').first.to_s.sub(/&c=1/, '')
-    end
+      def parse_canonical_url
+        product_id = @url.slice(URL_REGEXP, 1)
+        "https://www.melonbooks.co.jp/detail/detail.php?product_id=#{product_id}&adult_view=1"
+      end
+
+      def parse_description
+        # スタッフの紹介文でidが分岐
+        special_description = @page.xpath('//div[@id="special_description"]//p/text()')
+        if special_description.any?
+          special_description.first.to_s
+        else
+          description = @page.xpath('//div[@id="description"]//p/text()')
+          description.first.to_s
+        end
+      end
+
+      def parse_image_url
+        @page.css('//meta[property="og:image"]/@content').first.to_s.sub(/&c=1/, '')
+      end
+
+      def parse_tags
+        @page.css('#related_tags .clearfix').children.children.map(&:text)
+      end
   end
 
   ::Panchira::Extensions.register(Panchira::MelonbooksResolver)

data/lib/panchira/resolvers/narou_resolver.rb

@@ -3,18 +3,61 @@
 require 'net/https'
 
 module Panchira
-  class NarouResolver < Resolver
-    URL_REGEXP = %r{novel18\.syosetu\.com/}.freeze
+  module Narou
+    class Novel18Resolver < Resolver
+      URL_REGEXP = %r{novel18\.syosetu\.com/}.freeze
+      ID_REGEXP = %{novel18\.syosetu\.com/(?<id>[^/]+)}
 
-    def fetch_page(uri)
-      u = URI.parse(uri)
-      http = Net::HTTP.new(u.host, u.port)
-      http.use_ssl = u.port == 443
-      res = http.get u.request_uri, { 'cookie' => 'over18=yes;' }
+      def initialize(url)
+        super(url)
 
-      Nokogiri::HTML.parse(res.body, uri)
+        if id = @url.match(ID_REGEXP)[:id]
+          @desc = fetch_page("https://novel18.syosetu.com/novelview/infotop/ncode/#{id}/")
+        end
+      end
+
+      def fetch_page(uri)
+        u = URI.parse(uri)
+        http = Net::HTTP.new(u.host, u.port)
+        http.use_ssl = u.port == 443
+        res = http.get u.request_uri, {'cookie' => 'over18=yes;'}
+
+        Nokogiri::HTML.parse(res.body, uri)
+      end
+
+      def parse_author
+        @desc&.xpath('//*[@id="noveltable1"]/tr[2]/td')&.text&.strip
+      end
+
+      def parse_tags
+        # つらい。
+        @desc&.xpath('//*[@id="noveltable1"]/tr[3]')&.text&.split("\n\n\n")&.dig(1)&.split(' ')
+      end
+    end
+
+    class NcodeResolver < Resolver
+      URL_REGEXP = /ncode\.syosetu\.com/.freeze
+      ID_REGEXP = %{ncode\.syosetu\.com/(?<id>[^/]+)}
+
+      def initialize(url)
+        super(url)
+
+        if id = @url.match(ID_REGEXP)[:id]
+          @desc = fetch_page("https://novel18.syosetu.com/novelview/infotop/ncode/#{id}/")
+        end
+      end
+
+      def parse_author
+        @desc&.xpath('//*[@id="noveltable1"]/tr[2]/td')&.text&.strip
+      end
+
+      def parse_tags
+        # めっちゃつらい。
+        @desc&.xpath('//*[@id="noveltable1"]/tr[3]')&.text&.split("\n\n\n")&.dig(1)&.delete("\u00A0")&.split(' ')&.grep_v('')
+      end
     end
   end
 
-  ::Panchira::Extensions.register(Panchira::NarouResolver)
+  ::Panchira::Extensions.register(Panchira::Narou::NcodeResolver)
+  ::Panchira::Extensions.register(Panchira::Narou::Novel18Resolver)
 end

data/lib/panchira/resolvers/nijie_resolver.rb

@@ -6,24 +6,43 @@ module Panchira
 
     private
 
-    def parse_canonical_url
-      @url.sub(/sp.nijie/, 'nijie').sub(/view_popup/, 'view')
-    end
+      def parse_title
+        full_title = super
+        @md = full_title.match(/\A(?<title>.+) \| (?<author>.+)\z/)
 
-    def parse_image_url
-      str = @page.css('//script[@type="application/ld+json"]/text()').first.to_s
+        @md[:title]
+      end
+
+      def parse_author
+        @md[:author]
+      end
+
+      def parse_description
+        @page.css('p.illust_description')&.first&.text&.strip
+      end
 
-      if s = str.match(%r{https://pic.nijie.(net|info)/(?<servername>\d+)/[^/]+/nijie_picture/(?<imagename>[^"]+)})
-        # 動画は容量大きすぎるし取らない
-        if s[:imagename] =~ /(jpg|png)/
-          'https://pic.nijie.net/' + s[:servername] + '/nijie_picture/' + s[:imagename]
+      def parse_canonical_url
+        @url.sub(/sp.nijie/, 'nijie').sub(/view_popup/, 'view')
+      end
+
+      def parse_image_url
+        str = @page.css('//script[@type="application/ld+json"]/text()').first.to_s
+
+        if s = str.match(%r{https://pic.nijie.(net|info)/(?<servername>\d+)/[^/]+/nijie_picture/(?<imagename>[^"]+)})
+          # 動画は容量大きすぎるし取らない
+          if s[:imagename] =~ /(jpg|png)/
+            "https://pic.nijie.net/#{s[:servername]}/nijie_picture/#{s[:imagename]}"
+          else
+            s[0]
+          end
         else
-          s[0]
+          @page.css('//meta[property="og:image"]/@content').first.to_s
         end
-      else
-        @page.css('//meta[property="og:image"]/@content').first.to_s
       end
-    end
+
+      def parse_tags
+        @page.css('#view-tag span.tag_name').map(&:text)
+      end
   end
 
   ::Panchira::Extensions.register(Panchira::NijieResolver)

data/lib/panchira/resolvers/pixiv_resolver.rb

@@ -7,26 +7,41 @@ module Panchira
     def initialize(url)
       super(url)
       @illust_id = url.slice(URL_REGEXP, 2)
+
+      raw_json = URI.parse("https://www.pixiv.net/ajax/illust/#{@illust_id}").read('User-Agent' => user_agent)
+      @json = JSON.parse(raw_json)
     end
 
     private
 
-    def parse_canonical_url
-      'https://pixiv.net/member_illust.php?mode=medium&illust_id=' + @illust_id
-    end
+      def parse_title
+        @json['body']['title']
+      end
 
-    def parse_image_url
-      proxy_url = "https://pixiv.cat/#{@illust_id}.jpg"
+      def parse_author
+        @json['body']['userName']
+      end
 
-      case Net::HTTP.get_response(URI.parse(proxy_url))
-      when Net::HTTPNotFound
-        proxy_url = "https://pixiv.cat/#{@illust_id}-1.jpg"
+      def parse_canonical_url
+        "https://pixiv.net/member_illust.php?mode=medium&illust_id=#{@illust_id}"
       end
 
-      proxy_url
-    rescue StandardError
-      @page.css('//meta[property="og:image"]/@content').first.to_s
-    end
+      def parse_image_url
+        proxy_url = "https://pixiv.cat/#{@illust_id}.jpg"
+
+        case Net::HTTP.get_response(URI.parse(proxy_url))
+        when Net::HTTPNotFound
+          proxy_url = "https://pixiv.cat/#{@illust_id}-1.jpg"
+        end
+
+        proxy_url
+      rescue StandardError
+        @page.css('//meta[property="og:image"]/@content').first.to_s
+      end
+
+      def parse_tags
+        @json['body']['tags']['tags'].map { |content| content['tag'] }
+      end
   end
 
   ::Panchira::Extensions.register(Panchira::PixivResolver)

data/lib/panchira/resolvers/resolver.rb

@@ -11,8 +11,6 @@ module Panchira
     # You must override this in subclasses to limit which urls to resolve.
     URL_REGEXP = URI::DEFAULT_PARSER.make_regexp
 
-    USER_AGENT = "Mozilla/5.0 (compatible; PanchiraBot/#{VERSION}; +https://github.com/nuita/panchira)"
-
     def initialize(url)
       @url = url
     end
@@ -30,6 +28,14 @@ module Panchira
       result.title = parse_title
       result.description = parse_description
       result.image = parse_image
+      result.tags = parse_tags
+      if respond_to?(:parse_authors, true)
+        result.authors = parse_authors
+      else
+        result.author = parse_author
+      end
+      result.circle = parse_circle
+      result.resolver = parse_resolver
 
       result
     end
@@ -44,58 +50,87 @@ module Panchira
 
     private
 
-    def fetch_page(url)
-      raw_page = URI.parse(url).read('User-Agent' => self.class::USER_AGENT)
-      charset = raw_page.charset
-      Nokogiri::HTML.parse(raw_page, url, charset)
-    end
+      def fetch_page(url)
+        read_options = {
+          'User-Agent' => user_agent,
+          'Cookie' => cookie
+        }
 
-    def parse_canonical_url
-      history = []
+        raw_page = URI.parse(url).read(read_options)
+        charset = raw_page.charset
+        Nokogiri::HTML.parse(raw_page, url, charset)
+      end
 
-      # fetch page and refresh canonical_url until canonical_url converges.
-      loop do
-        url_in_res = @page.css('//link[rel="canonical"]/@href').to_s
+      def parse_canonical_url
+        history = []
 
-        if url_in_res.empty?
-          return history.last || @url
-        else
-          if history.include?(url_in_res) || history.length > 5
-            return url_in_res
+        # fetch page and refresh canonical_url until canonical_url converges.
+        loop do
+          url_in_res = @page.css('//link[rel="canonical"]/@href').to_s
+
+          if url_in_res.empty?
+            return history.last || @url
           else
-            history.push(url_in_res)
-            @page = fetch_page(url_in_res)
+            if history.include?(url_in_res) || history.length > 5
+              return url_in_res
+            else
+              history.push(url_in_res)
+              @page = fetch_page(url_in_res)
+            end
           end
         end
       end
-    end
 
-    def parse_title
-      if @page.css('//meta[property="og:title"]/@content').empty?
-        @page.title.to_s
-      else
-        @page.css('//meta[property="og:title"]/@content').to_s
+      def parse_title
+        if @page.css('//meta[property="og:title"]/@content').empty?
+          @page.title.to_s
+        else
+          @page.css('//meta[property="og:title"]/@content').to_s
+        end
       end
-    end
 
-    def parse_description
-      if @page.css('//meta[property="og:description"]/@content').empty?
-        @page.css('//meta[name$="description"]/@content').to_s
-      else
-        @page.css('//meta[property="og:description"]/@content').to_s
+      def parse_description
+        if @page.css('//meta[property="og:description"]/@content').empty?
+          @page.css('//meta[name$="description"]/@content').to_s
+        else
+          @page.css('//meta[property="og:description"]/@content').to_s
+        end
       end
-    end
 
-    def parse_image
-      image = PanchiraImage.new
-      image.url = parse_image_url
-      image.width, image.height = FastImage.size(image.url)
+      def parse_image
+        image = PanchiraImage.new
+        image.url = parse_image_url
+        image.width, image.height = FastImage.size(image.url)
 
-      image
-    end
+        image
+      end
 
-    def parse_image_url
-      @page.css('//meta[property="og:image"]/@content').first.to_s
-    end
+      def parse_image_url
+        @page.css('//meta[property="og:image"]/@content').first.to_s
+      end
+
+      def parse_tags
+        []
+      end
+
+      def cookie
+        ''
+      end
+
+      def parse_author
+        @page.css('//meta[name="author"]/@content').first.to_s
+      end
+
+      def parse_circle
+        nil
+      end
+
+      def parse_resolver
+        self.class.to_s
+      end
+
+      def user_agent
+        "Mozilla/5.0 (compatible; PanchiraBot/#{VERSION}; +https://github.com/nuita/panchira)"
+      end
   end
 end

data/lib/panchira/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Panchira
-  VERSION = '0.3.0'
+  VERSION = '1.3.0'
 end

data/panchira.gemspec

@@ -1,38 +1,44 @@
-lib = File.expand_path("lib", __dir__)
+# frozen_string_literal: true
+
+lib = File.expand_path('lib', __dir__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
-require "panchira/version"
+require 'panchira/version'
 
 Gem::Specification.new do |spec|
-  spec.name          = "panchira"
+  spec.name          = 'panchira'
   spec.version       = Panchira::VERSION
-  spec.authors       = ["kyp"]
-  spec.email         = ["kyp@kmc.gr.jp"]
+  spec.authors       = ['kyp']
+  spec.email         = ['kyp@kmc.gr.jp']
 
-  spec.summary       = "A parser for hentai websites"
+  spec.summary       = 'A parser for hentai websites'
   spec.description   = <<-TEXT
     Panchira allows you to parse attributes of hentais on some web platforms, such as Pixiv and DLSite.
     If you need card previews on hentai but can't get it with simply parsing metatags, then it is time for Panchira.
   TEXT
-  spec.homepage      = "https://github.com/nuita/panchira"
-  spec.license       = "MIT"
+  spec.homepage      = 'https://github.com/nuita/panchira'
+  spec.license       = 'MIT'
 
-  spec.metadata["homepage_uri"] = spec.homepage
-  spec.metadata["source_code_uri"] = "https://github.com/nuita/panchira"
-  spec.metadata["changelog_uri"] = "https://github.com/nuita/panchira/blob/master/CHANGELOG.md"
+  spec.metadata['homepage_uri']    = spec.homepage
+  spec.metadata['source_code_uri'] = 'https://github.com/nuita/panchira'
+  spec.metadata['changelog_uri']   = 'https://github.com/nuita/panchira/blob/master/CHANGELOG.md'
 
   # Specify which files should be added to the gem when it is released.
   # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
-  spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
+  spec.files = Dir.chdir(File.expand_path(__dir__)) do
     `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
   end
-  spec.bindir        = "exe"
+  spec.bindir        = 'exe'
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
-  spec.require_paths = ["lib"]
+  spec.require_paths = ['lib']
+
+  spec.required_ruby_version = '>= 2.6'
 
-  spec.add_development_dependency "bundler", "~> 2.0"
-  spec.add_development_dependency "rake", "~> 12.3.3"
-  spec.add_development_dependency "minitest", "~> 5.0"
+  spec.add_development_dependency 'bundler', '~> 2.0'
+  spec.add_development_dependency 'minitest', '~> 5.0'
+  spec.add_development_dependency 'rake', '~> 12.3.3'
+  spec.add_development_dependency 'rubocop', '~> 1.7'
+  spec.add_development_dependency 'rubocop-minitest', '~> 0.10'
 
-  spec.add_dependency "nokogiri", "~> 1.10.9"
-  spec.add_dependency "fastimage", "~> 2.1.7"
+  spec.add_dependency 'fastimage', '~> 2.1.7'
+  spec.add_dependency 'nokogiri', '>= 1.10.9', '< 1.12.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: panchira
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 1.3.0
 platform: ruby
 authors:
 - kyp
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2020-06-04 00:00:00.000000000 Z
+date: 2021-02-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -24,6 +24,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -39,33 +53,33 @@ dependencies:
       - !ruby/object:Gem::Version
         version: 12.3.3
 - !ruby/object:Gem::Dependency
-  name: minitest
+  name: rubocop
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '5.0'
+        version: '1.7'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '5.0'
+        version: '1.7'
 - !ruby/object:Gem::Dependency
-  name: nokogiri
+  name: rubocop-minitest
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.10.9
-  type: :runtime
+        version: '0.10'
+  type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.10.9
+        version: '0.10'
 - !ruby/object:Gem::Dependency
   name: fastimage
   requirement: !ruby/object:Gem::Requirement
@@ -80,6 +94,26 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 2.1.7
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.10.9
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: 1.12.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.10.9
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: 1.12.0
 description: |2
       Panchira allows you to parse attributes of hentais on some web platforms, such as Pixiv and DLSite.
       If you need card previews on hentai but can't get it with simply parsing metatags, then it is time for Panchira.
@@ -91,6 +125,8 @@ extra_rdoc_files: []
 files:
 - ".github/workflows/ruby.yml"
 - ".gitignore"
+- ".rubocop.yml"
+- ".rubocop_todo.yml"
 - CHANGELOG.md
 - Gemfile
 - Gemfile.lock
@@ -103,6 +139,8 @@ files:
 - lib/panchira/extensions.rb
 - lib/panchira/panchira_result.rb
 - lib/panchira/resolvers/dlsite_resolver.rb
+- lib/panchira/resolvers/fanza_resolver.rb
+- lib/panchira/resolvers/image_resolver.rb
 - lib/panchira/resolvers/komiflo_resolver.rb
 - lib/panchira/resolvers/melonbooks_resolver.rb
 - lib/panchira/resolvers/narou_resolver.rb
@@ -118,7 +156,7 @@ metadata:
   homepage_uri: https://github.com/nuita/panchira
   source_code_uri: https://github.com/nuita/panchira
   changelog_uri: https://github.com/nuita/panchira/blob/master/CHANGELOG.md
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -126,15 +164,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: '2.6'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
-signing_key: 
+rubygems_version: 3.1.4
+signing_key:
 specification_version: 4
 summary: A parser for hentai websites
 test_files: []