aozoragen 0.2.0 → 0.3.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 531310930df10ff69b5c5804afc7f935f3014646
+  data.tar.gz: 2370bb692b45d2ecde94c9a7c62913a0d748376d
+SHA512:
+  metadata.gz: f626776afd09a2897f8d124ef6bcd60f393fc4dd4a68ee5f1a9295be9ae54b8f85094c1d4577e8c00ba0600ca6f2c5e686ae7b097aadee25fe5332279d67a3d2
+  data.tar.gz: cf3b020e6d721f465c060d53d391cef74bbb00d670f24ff9309ed216d777061d953a28614aed6d62382e8eaf6325b54700559780daa948a8f3f45689fd53f92f

data/README.md

@@ -21,6 +21,8 @@ Gemを使ってインストールする:
  * 実行時に無償公開中の章のみが抽出される。
 * レンザブロー <http://renzaburo.jp/>
  * 指定例: http://renzaburo.jp/contents_t/061-katano/index.html
+* 小説を読もう! <http://yomou.syosetu.com/>
+ * 指定例: http://ncode.syosetu.com/n8725k/
 * Webミステリーズ! <http://www.webmysteries.jp/>
  * Webミステリーズ!の掲載作品には目次ページがないため、GitHubのWikiで代用する。
  * h1要素に書名、h2要素に続くリストで著者名、h3要素に続くリストで連載各回のURLを表現する。

data/bin/aozoragen

@@ -46,6 +46,8 @@ ARGV.each do |u|
 			'sai-zen-sen'
 		when 'renzaburo.jp'
 			'renzaburo'
+		when 'ncode.syosetu.com'
+			'syosetu'
 		when 'github.com'
 			case Pathname( uri.path ).basename.to_s.sub( %r|(.*?)-.*$|, '\1' )
 			when 'webmysteries'

data/lib/aozoragen/syosetu.rb

@@ -0,0 +1,46 @@
+# -*- coding: utf-8; -*-
+#
+# scraping yomou.syosetu.com
+#
+require 'aozoragen/util'
+require 'open-uri'
+require 'pathname'
+
+module Aozoragen
+	class Syosetu
+		include Util
+
+		def initialize(index_uri)
+			@index_uri = index_uri
+			@index_html = Nokogiri(open(@index_uri, 'r:utf-8', &:read))
+		end
+	
+		def metainfo
+			info = {:id => Pathname(@index_uri.path).basename.to_s, :author => []}
+			info[:title] = (@index_html / 'title')[0].text
+			info[:author] << (@index_html / '.novel_writername a')[0].text
+			info
+		end
+	
+		def each_chapter
+			(@index_html / '.subtitle a').each do |a|
+				uri = @index_uri + a.attr('href')
+
+				chapter = Nokogiri(open(uri, 'r:utf-8', &:read))
+				text = get_chapter_text(chapter)
+				chapter_id = '%03d' % Pathname(uri.path).basename.to_s.to_i
+				yield({id: chapter_id, uri: uri, text: text})
+			end
+		end
+	
+		def get_chapter_text(chapter)
+			text = ''
+			text << (chapter / '.novel_subtitle')[0].text.subhead
+			(chapter / '#novel_honbun').each do |page|
+				text << detag(page).gsub(/\n\n/, "\n")
+				text << "［＃改ページ］\n"
+			end
+			text.han2zen.for_tategaki
+		end
+	end
+end

data/lib/aozoragen/util.rb

@@ -20,7 +20,7 @@ class String
 	# replace characters fitting to vertical lyout
 	#
 	def for_tategaki
-		self.tr( '＜＞−', '∧∨‐' ).han2zen
+		self.tr( '＜＞－“”−', '∧∨―〃〃‐' ).han2zen
 	end
 
 	##
@@ -57,9 +57,9 @@ module Aozoragen
 				ruby.inner_html = '｜' + ruby.inner_html
 				(ruby / 'rp').each do |rp|
 					case rp.text
-					when '（'
+					when /[（\(]/
 						rp.inner_html = '《'
-					when '）'
+					when /[）\)]/
 						rp.inner_html = '》'
 					end
 				end

data/lib/aozoragen/version.rb

@@ -1,3 +1,3 @@
 module Aozoragen
-  VERSION = "0.2.0"
+  VERSION = "0.3.1"
 end

metadata

@@ -1,30 +1,27 @@
 --- !ruby/object:Gem::Specification
 name: aozoragen
 version: !ruby/object:Gem::Version
-  version: 0.2.0
-  prerelease: 
+  version: 0.3.1
 platform: ruby
 authors:
 - TADA Tadashi
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-05-28 00:00:00.000000000 Z
+date: 2014-09-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 description: Scraping some Ebook web site and generating AOZORA format text files.
@@ -36,7 +33,7 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
+- ".gitignore"
 - Gemfile
 - README.md
 - Rakefile
@@ -46,31 +43,31 @@ files:
 - lib/aozoragen.rb
 - lib/aozoragen/renzaburo.rb
 - lib/aozoragen/sai-zen-sen.rb
+- lib/aozoragen/syosetu.rb
 - lib/aozoragen/util.rb
 - lib/aozoragen/version.rb
 - lib/aozoragen/webmysteries.rb
 homepage: https://github.com/tdtds/aozoragen
 licenses: []
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.23
+rubygems_version: 2.2.2
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Generating AOZORA format text of eBook novels via some Web sites.
 test_files: []