panchira 1.1.1 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '084250abfb3df8cee5d16db7e0312347663fac26ce27b88a0a8f35c12b8eed41'
-  data.tar.gz: 6d427b512e89d5c1797b7d713f70ceda702cd0397da22dc4b8ceefaf01a2f474
+  metadata.gz: 066440e461b75b84a9df04fd76f1960243785b26bc7f4c61289029248e0a8bd9
+  data.tar.gz: 1fc1f712c6a8d88363cf3c4162be2681e08631c515ffbe6631fba3fd204b91c0
 SHA512:
-  metadata.gz: 269c296c822ed831714ba70b771f3ec37f03f7b9910115ba6e2b435cfe26838a6dc9a30dd658458c754bd7a20c5270e59d4c7de57d83d2d84638e4e385b7ed20
-  data.tar.gz: 6f7f9884dca58326d32c1f95256193570c97625c579ec118919cde6cc0e83e758ea9b6ecdc4c390a45629ac1de0d95ff47d9126023d94cdfe3316a1b14234f8a
+  metadata.gz: 63a914d286eaf909f4a2ab7c128f3725a96a6badbac71a878362e4a09a4e29f720f1f81fab2fa4b1f0ddeb513fac04b5c00597132012f5dbe42d783f54b221b2
+  data.tar.gz: af6085627c05532b7019a7134da472329c52b0f61b3329079694a2f59115e52f1c7b0bc0acc2c9cc3ea19814a33c3e2cd9116fcd7f692278e2150de7874bb424

data/CHANGELOG.md

@@ -4,6 +4,13 @@ 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/).
 
+## 1.2.0 - 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.

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    panchira (1.1.1)
+    panchira (1.2.0)
       fastimage (~> 2.1.7)
       nokogiri (~> 1.10.9)
 
@@ -10,7 +10,7 @@ GEM
   specs:
     fastimage (2.1.7)
     mini_portile2 (2.4.0)
-    minitest (5.14.0)
+    minitest (5.14.2)
     nokogiri (1.10.10)
       mini_portile2 (~> 2.4.0)
     rake (12.3.3)

data/lib/panchira/panchira_result.rb

@@ -8,6 +8,6 @@ module Panchira
 
   # Result class for Panchira.fetch.
   class PanchiraResult
-    attr_accessor :canonical_url, :title, :description, :image, :tags
+    attr_accessor :canonical_url, :title, :description, :image, :tags, :author, :circle
   end
 end

data/lib/panchira/resolvers/dlsite_resolver.rb

@@ -6,6 +6,32 @@ module Panchira
 
     private
 
+    # 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(/(.+) \[(\S+)\] \|.+/)
+      @title_md[1]
+    end
+
+    def parse_author
+      @page.css('table[id*="work_"] tr').each do |tr|
+        if tr.css('th').text =~ /(作|著)者/
+          return @author = tr.css('td > a').first.text.strip
+        end
+      end
+
+      @author = nil
+    end
+
+    def parse_circle
+      @title_md[2] if @author != @title_md[2]
+    end
+
     def parse_image_url
       @page.css('//meta[property="og:image"]/@content').first.to_s.sub(/sam/, 'main')
     end

data/lib/panchira/resolvers/fanza_resolver.rb

@@ -19,6 +19,10 @@ module Panchira
 
       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
@@ -37,6 +41,10 @@ module Panchira
 
       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

data/lib/panchira/resolvers/komiflo_resolver.rb

@@ -17,20 +17,19 @@ module Panchira
     private
 
     def parse_title
-      comic_title = @json['content']['data']['title']
-      "#{comic_title} | Komiflo"
+      @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_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
+    def parse_description
+      @json['content']['parents'][0]['data']['title']
     end
 
     def parse_canonical_url

data/lib/panchira/resolvers/melonbooks_resolver.rb

@@ -4,8 +4,41 @@ module Panchira
   class MelonbooksResolver < Resolver
     URL_REGEXP = %r{melonbooks.co.jp/detail/detail.php\?product_id=(\d+)}.freeze
 
+    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
+
+      result.title, result.author, result.circle = parse_table
+      result.description = parse_description
+      result.image = parse_image
+      result.tags = parse_tags
+
+      result
+    end
+
     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)[0]
+        when '作家名'
+          author = tr.css('td > a').text.strip
+        end
+      end
+
+      [title, author, circle]
+    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'

data/lib/panchira/resolvers/narou_resolver.rb

@@ -6,7 +6,15 @@ module Panchira
   module Narou
     class Novel18Resolver < Resolver
       URL_REGEXP = %r{novel18\.syosetu\.com/}.freeze
-      ID_REGEXP = %{novel18\.syosetu\.com/(?<id>[^/]+)}.freeze
+      ID_REGEXP = %{novel18\.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 fetch_page(uri)
         u = URI.parse(uri)
@@ -17,24 +25,35 @@ module Panchira
         Nokogiri::HTML.parse(res.body, uri)
       end
 
-      def parse_tags
-        id = @url.match(ID_REGEXP)[:id]
-        return [] unless id
+      def parse_author
+        @desc&.xpath('//*[@id="noveltable1"]/tr[2]/td')&.text&.strip
+      end
 
-        desc = fetch_page("https://novel18.syosetu.com/novelview/infotop/ncode/#{id}/")
-        desc.xpath('//*[@id="noveltable1"]/tr[3]')&.text&.split("\n\n\n")&.dig(1)&.split(' ') # つらい。
+      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 = %r{ncode\.syosetu\.com}.freeze
-      ID_REGEXP = %{ncode\.syosetu\.com/(?<id>[^/]+)}.freeze
+      URL_REGEXP = /ncode\.syosetu\.com/.freeze
+      ID_REGEXP = %{ncode\.syosetu\.com/(?<id>[^/]+)}
 
-      def parse_tags
-        id = @url.match(ID_REGEXP)[:id]
-        return [] unless 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
 
-        desc = fetch_page("https://ncode.syosetu.com/novelview/infotop/ncode/#{id}/")
-        desc.xpath('//*[@id="noveltable1"]/tr[3]')&.text&.split("\n\n\n")&.dig(1)&.delete("\u00A0")&.split(' ')&.grep_v('') # めっちゃつらい。
+      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

data/lib/panchira/resolvers/nijie_resolver.rb

@@ -6,6 +6,21 @@ module Panchira
 
     private
 
+    def parse_title
+      full_title = super
+      @md = full_title.match(/\A(?<title>.+) \| (?<author>.+)\z/)
+
+      @md[:title]
+    end
+
+    def parse_author
+      @md[:author]
+    end
+
+    def parse_description
+      @page.css('p.illust_description')&.first&.text&.strip
+    end
+
     def parse_canonical_url
       @url.sub(/sp.nijie/, 'nijie').sub(/view_popup/, 'view')
     end

data/lib/panchira/resolvers/pixiv_resolver.rb

@@ -14,6 +14,14 @@ module Panchira
 
     private
 
+    def parse_title
+      @json['body']['title']
+    end
+
+    def parse_author
+      @json['body']['userName']
+    end
+
     def parse_canonical_url
       'https://pixiv.net/member_illust.php?mode=medium&illust_id=' + @illust_id
     end
@@ -32,7 +40,7 @@ module Panchira
     end
 
     def parse_tags
-      @json['body']['tags']['tags'].map{|content| content['tag']}
+      @json['body']['tags']['tags'].map { |content| content['tag'] }
     end
   end
 

data/lib/panchira/resolvers/resolver.rb

@@ -29,6 +29,8 @@ module Panchira
       result.description = parse_description
       result.image = parse_image
       result.tags = parse_tags
+      result.author = parse_author
+      result.circle = parse_circle
 
       result
     end
@@ -110,6 +112,14 @@ module Panchira
       ''
     end
 
+    def parse_author
+      @page.css('//meta[name="author"]/@content').first.to_s
+    end
+
+    def parse_circle
+      nil
+    end
+
     def user_agent
       "Mozilla/5.0 (compatible; PanchiraBot/#{VERSION}; +https://github.com/nuita/panchira)"
     end

data/lib/panchira/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Panchira
-  VERSION = '1.1.1'
+  VERSION = '1.2.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: panchira
 version: !ruby/object:Gem::Version
-  version: 1.1.1
+  version: 1.2.0
 platform: ruby
 authors:
 - kyp
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-08-09 00:00:00.000000000 Z
+date: 2020-10-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler