panchira 1.5.2 → 1.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: db34e8033acf822616172b330fc61ffe2ee5a1c9dfe46bc1737257717aeff4c0
-  data.tar.gz: 5ec893680ef7e04b2f85d16b3458ee9f6b2db76ac6c01544a088d280a574e98c
+  metadata.gz: 3c9dcae2b8945a7deca6a15ec2effb1c41b3839209d8ce50bc1ef0969e26f12a
+  data.tar.gz: ac932d71e0a592afce2dc5075a47ece87e27f8adf79fe2d00c1bfb62ecedb822
 SHA512:
-  metadata.gz: 71b2d7707d78b21004acdca984f1869cc81a9e9169bee9239b13261a79002ed859a5a87c8aa08350a89d37ce734abb47637c909aa01b5dab171eb871ad27d9e0
-  data.tar.gz: fbe9744acbbdbd13376e2a6bdaf1c4430c20861163b39f6bb7ed26436c8fd6c64876e329c0c9aae5c129a59257d7c06eac2508b7c1283bc27d405f0c2e836b0e
+  metadata.gz: dd3ddc556f55e3cc00f529ce5ea278d69225876bfd77b8e874224667ea5f37d072276a050fcaa35cb903d2d7ca13a4111f3f23d59af2a786e781dc7761686f21
+  data.tar.gz: 309a2b4a742794d55c9d4d98fdd9c46499181370cf08c116724815e32e4d9e54b81e08b4ea5cfec891425c8cf3bfcfdb0f60c55d9020c022270e86af421414bd

data/.rubocop.yml

@@ -37,6 +37,10 @@ Lint/MissingSuper:
 Lint/SymbolConversion:
   EnforcedStyle: consistent
 
+Metrics/BlockLength:
+  Exclude:
+    - panchira.gemspec
+
 Style/AsciiComments:
   Enabled: false
 
@@ -64,6 +68,10 @@ Style/NumericPredicate:
 Style/ParallelAssignment:
   Enabled: false
 
+Style/RegexpLiteral:
+  EnforcedStyle: slashes
+  AllowInnerSlashes: true
+
 Style/WordArray:
   EnforcedStyle: brackets
 

data/CHANGELOG.md

@@ -4,6 +4,21 @@ 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/).
 
+## 1.6.0 - 2023-01-05
+### Added
+- Added support for non-Japanese DLsite URLs.
+
+### Fixed
+- Fixed an issue where FANZA resolver don't work due to renewal of the website.
+- Fixed an issue where Melonbooks resolver don't work due to renewal of the website.
+
+## 1.5.3 - 2022-06-04
+### Fixed
+- Fixed an issue where Pixiv resolver can't retrieve image urls for manga.
+
+### Changed
+- DLsite resolver now returns descriptions without platform PR sentences.
+
 ## 1.5.2 - 2022-03-20
 ### Fixed
 - Fixed an issue where Pixiv resolver can't retrieve not-proxied image scales.
@@ -127,17 +142,3 @@ and this project adheres to [Semantic Versioning](http://semver.org/).
 ## 0.1.0 - 2020-05-13 [YANKED]
 ### Added
 - Released Panchira gem. At this time we can parse only 5 websites.
-
-[1.3.5]: https://github.com/nuita/panchira/releases/tag/v1.3.5
-[1.3.4]: https://github.com/nuita/panchira/releases/tag/v1.3.4
-[1.3.3]: https://github.com/nuita/panchira/releases/tag/v1.3.3
-[1.3.2]: https://github.com/nuita/panchira/releases/tag/v1.3.2
-[1.3.1]: https://github.com/nuita/panchira/releases/tag/v1.3.1
-[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
-[0.1.0]: https://github.com/nuita/panchira/releases/tag/v0.1.0

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    panchira (1.5.2)
+    panchira (1.6.0)
       fastimage (~> 2.1.7)
       nokogiri (>= 1.10.9, < 1.14.0)
 
@@ -10,35 +10,40 @@ GEM
   specs:
     ast (2.4.2)
     fastimage (2.1.7)
-    minitest (5.15.0)
-    nokogiri (1.13.3-x86_64-darwin)
+    json (2.6.3)
+    mini_portile2 (2.8.1)
+    minitest (5.17.0)
+    nokogiri (1.13.10)
+      mini_portile2 (~> 2.8.0)
       racc (~> 1.4)
-    parallel (1.21.0)
-    parser (3.1.1.0)
+    parallel (1.22.1)
+    parser (3.2.0.0)
       ast (~> 2.4.1)
-    racc (1.6.0)
+    racc (1.6.2)
     rainbow (3.1.1)
     rake (12.3.3)
-    regexp_parser (2.2.1)
+    regexp_parser (2.6.1)
     rexml (3.2.5)
-    rubocop (1.25.1)
+    rubocop (1.42.0)
+      json (~> 2.3)
       parallel (~> 1.10)
-      parser (>= 3.1.0.0)
+      parser (>= 3.1.2.1)
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 1.8, < 3.0)
-      rexml
-      rubocop-ast (>= 1.15.1, < 2.0)
+      rexml (>= 3.2.5, < 4.0)
+      rubocop-ast (>= 1.24.1, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 1.4.0, < 3.0)
-    rubocop-ast (1.16.0)
+    rubocop-ast (1.24.1)
       parser (>= 3.1.1.0)
-    rubocop-minitest (0.17.2)
+    rubocop-minitest (0.25.1)
       rubocop (>= 0.90, < 2.0)
     ruby-progressbar (1.11.0)
-    unicode-display_width (2.1.0)
+    unicode-display_width (2.4.2)
 
 PLATFORMS
   ruby
+  x86_64-linux
 
 DEPENDENCIES
   bundler (~> 2.0)
@@ -49,4 +54,4 @@ DEPENDENCIES
   rubocop-minitest (~> 0.10)
 
 BUNDLED WITH
-   2.1.4
+   2.4.2

data/lib/panchira/resolvers/dlsite_resolver.rb

@@ -18,6 +18,10 @@ module Panchira
         @title_md[1]
       end
 
+      def parse_description
+        super.split('「DLsite').first
+      end
+
       def parse_authors
         @page.css('table[id*="work_"] tr').each do |tr|
           next unless tr.css('th').text =~ /(作|著)者/
@@ -47,6 +51,10 @@ module Panchira
           end
         end
       end
+
+      def parse_canonical_url
+        super[/^.+\/product_id\/[^\/]+/]
+      end
   end
 
   ::Panchira::Extensions.register(Panchira::DlsiteResolver)

data/lib/panchira/resolvers/fanza_resolver.rb

@@ -15,29 +15,38 @@ module Panchira
     end
 
     class FanzaBookResolver < FanzaResolver
-      URL_REGEXP = %r{book\.dmm\.co\.jp/}.freeze
+      URL_REGEXP = /book\.dmm\.co\.jp\//.freeze
 
       private
 
-        def parse_author
-          @page.css('.m-boxDetailProductInfoMainList__description__list__item > a').first&.text.to_s
+        def after_fetch
+          text = @page.css('//script[type="application/ld+json"]').first.text
+          @schema = JSON.parse(text)
+        end
+
+        def parse_title
+          @schema['name']
+        end
+
+        def parse_authors
+          @schema['subjectOf']['author']['name']
         end
 
         def parse_image_url
-          @page.css('.m-imgDetailProductPack/@src').first.to_s
+          @schema['image'].sub('ps.', 'pl.')
         end
 
         def parse_tags
-          @page.css('.m-boxDetailProductInfo__list__description__item > a').map(&:text)
+          @schema['subjectOf']['genre']
         end
 
         def parse_description
-          @page.css('.m-boxDetailProduct__info__story').first&.text.to_s.gsub(/[\n\t]/, '')
+          @schema['description']
         end
     end
 
     class FanzaDoujinResolver < FanzaResolver
-      URL_REGEXP = %r{dmm\.co\.jp/dc/doujin/}.freeze
+      URL_REGEXP = /dmm\.co\.jp\/dc\/doujin\//.freeze
 
       private
 
@@ -57,7 +66,7 @@ module Panchira
     end
 
     class FanzaVideoResolver < FanzaResolver
-      URL_REGEXP = %r{www.dmm.co.jp/digital/}.freeze
+      URL_REGEXP = /www.dmm.co.jp\/digital\//.freeze
 
       private
 

data/lib/panchira/resolvers/iwara_resolver.rb

@@ -5,13 +5,14 @@ module Panchira
     URL_REGEXP = /(www|ecchi)\.iwara\.tv\//.freeze
 
     private
+
       def parse_title
         super.split(' | ')[0]
       end
 
       def parse_image_url
-        url = @page.at_css('#video-player')&.attributes['poster']&.value
-        'https:' + url if url
+        url = @page.at_css('#video-player')&.attributes&.fetch('poster')&.value
+        "https:#{url}" if url
       end
 
       def parse_author

data/lib/panchira/resolvers/komiflo_resolver.rb

@@ -4,7 +4,7 @@ module Panchira
   # KomifloResolver resolves Komiflo.
   # Komiflo has its API server, so we can utilize it.
   class KomifloResolver < Resolver
-    URL_REGEXP = %r{komiflo\.com(?:/#!)?/comics/(\d+)}.freeze
+    URL_REGEXP = /komiflo\.com(?:\/#!)?\/comics\/(\d+)/.freeze
 
     def initialize(url, options = nil)
       super(url, options)
@@ -33,7 +33,7 @@ module Panchira
       end
 
       def parse_canonical_url
-        id = @url.slice(%r{komiflo\.com(?:/#!)?/comics/(\d+)}, 1)
+        id = @url.slice(/komiflo\.com(?:\/#!)?\/comics\/(\d+)/, 1)
         "https://komiflo.com/comics/#{id}"
       end
 

data/lib/panchira/resolvers/melonbooks_resolver.rb

@@ -2,7 +2,7 @@
 
 module Panchira
   class MelonbooksResolver < Resolver
-    URL_REGEXP = %r{melonbooks.co.jp/detail/detail.php\?product_id=(\d+)}.freeze
+    URL_REGEXP = /melonbooks.co.jp\/detail\/detail.php\?product_id=(\d+)/.freeze
 
     def fetch
       result = PanchiraResult.new
@@ -12,11 +12,12 @@ module Panchira
 
       @page = fetch_page(result.canonical_url) if @url != result.canonical_url
 
-      result.title, result.author, result.circle = parse_table
+      result.title = parse_title
+      result.author, result.circle = parse_table
       result.description = parse_description
       result.image = parse_image
-      result.tags = parse_tags
       result.resolver = parse_resolver
+      result.tags = parse_tags
 
       result
     end
@@ -24,12 +25,10 @@ module Panchira
     private
 
       def parse_table
-        title, author, circle = nil, nil, nil
+        author, circle = nil, nil
 
-        @page.css('#description > table.stripe > tr').each do |tr|
+        @page.css('div.table-wrapper > table > 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'
@@ -37,7 +36,11 @@ module Panchira
           end
         end
 
-        [title, author, circle]
+        [author, circle]
+      end
+
+      def parse_title
+        @page.xpath('//h1[@class="page-header"]//text()').text
       end
 
       def parse_canonical_url
@@ -46,14 +49,7 @@ module Panchira
       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
+        @page.css('div.item-detail > div > p').first.text.strip
       end
 
       def parse_image_url
@@ -64,7 +60,7 @@ module Panchira
       end
 
       def parse_tags
-        @page.css('#related_tags .clearfix').children.children.map(&:text)
+        @page.css('div.item-detail2 > p > a').map { |m| m.text.sub('#', '') }
       end
   end
 

data/lib/panchira/resolvers/narou_resolver.rb

@@ -5,7 +5,7 @@ require 'net/https'
 module Panchira
   module Narou
     class Novel18Resolver < Resolver
-      URL_REGEXP = %r{novel18\.syosetu\.com/}.freeze
+      URL_REGEXP = /novel18\.syosetu\.com\//.freeze
       ID_REGEXP = %{novel18\.syosetu\.com/(?<id>[^/]+)}
 
       def initialize(url, options = nil)

data/lib/panchira/resolvers/nijie_resolver.rb

@@ -33,7 +33,7 @@ module Panchira
           return @page.css('//meta[property="og:image"]/@content').first.to_s
         end
 
-        if md = thumbnail_url.match(%r{pic.nijie.net/\w+(?<resolution>/\w+/)nijie.+\.(?<format>png|jpg|jpeg)})
+        if md = thumbnail_url.match(/pic.nijie.net\/\w+(?<resolution>\/\w+\/)nijie.+\.(?<format>png|jpg|jpeg)/)
           thumbnail_url.sub(md[:resolution], '/')
         else
           thumbnail_url

data/lib/panchira/resolvers/pixiv_resolver.rb

@@ -2,7 +2,7 @@
 
 module Panchira
   class PixivResolver < Resolver
-    URL_REGEXP = %r{pixiv\.net/.*(member_illust.php?.*illust_id=|artworks/)(\d+)}.freeze
+    URL_REGEXP = /pixiv\.net\/.*(member_illust.php?.*illust_id=|artworks\/)(\d+)/.freeze
 
     def initialize(url, options = nil)
       super(url, options)
@@ -44,7 +44,8 @@ module Panchira
         proxy_url = "https://pixiv.cat/#{@illust_id}.jpg"
 
         case Net::HTTP.get_response(URI.parse(proxy_url))
-        when Net::HTTPNotFound
+        when Net::HTTPMovedPermanently
+          # 301が返された場合、locationで渡されたURIにホストが含まれず扱いづらいため決め打ちする
           proxy_url = "https://pixiv.cat/#{@illust_id}-1.jpg"
         end
 
@@ -59,7 +60,7 @@ module Panchira
   end
 
   class PixivNovelResolver < Resolver
-    URL_REGEXP = %r{pixiv\.net/novel/show.php\?id=(\d+)}.freeze
+    URL_REGEXP = /pixiv\.net\/novel\/show.php\?id=(\d+)/.freeze
 
     def initialize(url, options = nil)
       super(url, options)

data/lib/panchira/resolvers/resolver.rb

@@ -26,6 +26,8 @@ module Panchira
 
       @page = fetch_page(result.canonical_url) if @url != result.canonical_url
 
+      after_fetch if respond_to?(:after_fetch, true)
+
       result.title = parse_title
       result.description = parse_description
       result.image = parse_image

data/lib/panchira/resolvers/twitter_resolver.rb

@@ -1,8 +1,10 @@
+# frozen_string_literal: true
+
 require 'uri'
 
 module Panchira
   class TwitterResolver < Resolver
-    URL_REGEXP = %r{twitter.com/(\w+)/status/(\d+)}.freeze
+    URL_REGEXP = /twitter.com\/(\w+)\/status\/(\d+)/.freeze
 
     def initialize(url, options = nil)
       super(url, options)

data/lib/panchira/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Panchira
-  VERSION = '1.5.2'
+  VERSION = '1.6.0'
 end

data/panchira.gemspec

@@ -25,10 +25,10 @@ Gem::Specification.new do |spec|
   # 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(__dir__)) do
-    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+    `git ls-files -z`.split("\x0").reject { |f| f.match(/^(test|spec|features)\//) }
   end
   spec.bindir        = 'exe'
-  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.executables   = spec.files.grep(/^exe\//) { |f| File.basename(f) }
   spec.require_paths = ['lib']
 
   spec.required_ruby_version = '>= 2.7'
@@ -41,4 +41,5 @@ Gem::Specification.new do |spec|
 
   spec.add_dependency 'fastimage', '~> 2.1.7'
   spec.add_dependency 'nokogiri', '>= 1.10.9', '< 1.14.0'
+  spec.metadata['rubygems_mfa_required'] = 'true'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: panchira
 version: !ruby/object:Gem::Version
-  version: 1.5.2
+  version: 1.6.0
 platform: ruby
 authors:
 - kyp
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2022-03-20 00:00:00.000000000 Z
+date: 2023-01-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -158,6 +158,7 @@ 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
+  rubygems_mfa_required: 'true'
 post_install_message:
 rdoc_options: []
 require_paths:
@@ -173,7 +174,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.4
+rubygems_version: 3.3.4
 signing_key:
 specification_version: 4
 summary: A parser for hentai websites