aozoragen 0.0.1

data/.gitignore

@@ -0,0 +1,6 @@
+*.gem
+.bundle
+Gemfile.lock
+pkg/*
+*.txt
+*.pdf

data/Gemfile

@@ -0,0 +1,4 @@
+source "http://rubygems.org"
+
+# Specify your gem's dependencies in aozoragen.gemspec
+gemspec

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/aozoragen.gemspec

@@ -0,0 +1,24 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "aozoragen/version"
+
+Gem::Specification.new do |s|
+  s.name        = "aozoragen"
+  s.version     = Aozoragen::VERSION
+  s.authors     = ["TADA Tadashi"]
+  s.email       = ["t@tdtds.jp"]
+  s.homepage    = ""
+  s.summary     = "Generating AOZORA format text of eBook novels via some Web sites."
+  s.description = "Scraping some Ebook web site and generating AOZORA format text files."
+
+  s.rubyforge_project = "aozoragen"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+
+  # specify any dependencies here; for example:
+  # s.add_development_dependency "rspec"
+  s.add_runtime_dependency "nokogiri"
+end

data/bin/aozora2pdf

@@ -0,0 +1,20 @@
+#!/usr/bin/env ruby
+# -*- coding: utf-8; -*-
+#
+# aozora2pdf: converting AOZORA format text to PDF using Aozora-Kindle servive.
+#             see: http://a2k.aill.org/
+#
+# sample usage:
+#    % aozora2pdf hoge*.txt > hoge.pdf
+#
+# Copyright (C) 2012 by TADA Tadashi <t@tdtds.jp>
+# Distributed under GPL
+#
+require 'uri'
+require 'net/http'
+require 'cgi'
+
+uri = URI( 'http://a2k.aill.org/download.cgi' )
+text = ARGF.read.force_encoding( 'UTF-8' )
+res = Net::HTTP.post_form( uri, 's' => 's', 'text' => text )
+print res.body

data/bin/aozoragen

@@ -0,0 +1,33 @@
+#!/usr/bin/env ruby
+# -*- coding: utf-8; -*-
+#
+# aozoragen: generating AOZORA format text files from scraping some ebook sites.
+#
+# Copyright (C) 2012 by TADA Tadashi <t@tdtds.jp>
+# Distributed under GPL
+#
+require 'uri'
+
+ARGV.each do |u|
+	uri = URI( u )
+	book = nil
+	case uri.host
+	when 'sai-zen-sen.jp'
+		require 'aozoragen/sai-zen-sen'
+		book = SaiZenSen::new( uri )
+	else
+		p "Error: unknown URI: #{uri}"
+	end
+	next unless book
+
+	meta = book.metainfo
+	open( "#{meta[:id]}.00.txt", 'w' ) do |w|
+		w.puts "#{meta[:title]}\n#{meta[:author].join ' / '}\n\n\n［＃改ページ］"
+	end
+
+	book.each_chapter do |chapter|
+		open( "#{meta[:id]}.#{chapter[:id]}.txt", 'w' ) do |w|
+			w.puts chapter[:text]
+		end
+	end
+end

data/lib/aozoragen/sai-zen-sen.rb

@@ -0,0 +1,64 @@
+# -*- coding: utf-8; -*-
+#
+# scraping sai-zen-sen.jp
+#
+require 'nokogiri'
+require 'open-uri'
+require 'pathname'
+
+class SaiZenSen
+	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}
+		info[:title] = (@index_html / '#page-content-heading h1')[0].text
+		(@index_html / '#authors h3').each do |author|
+			info[:author] = (info[:author] || [] ) << author.text.sub( /.*? /, '' )
+		end
+		info
+	end
+
+	def each_chapter
+		(@index_html / '#back-numbers li a').each do |a|
+			uri = @index_uri + a.attr('href')
+			chapter = Nokogiri( open( uri, 'r:utf-8', &:read ) )
+			text = ''
+			(chapter / 'section.book-page-spread').each do |page|
+				page./( 'hgroup', 'div.pgroup' ).each do |section|
+					case section.name
+					when 'hgroup'
+						text << "\n　　　　　#{detag section}\n\n"
+					when 'div'
+						if section.attr( 'class' ) =~ /delimiter/
+							text << '　' * 5 << '─' * 10 << "\n"
+						else
+							section.children.each do |paragraph|
+								next unless paragraph.name == 'p'
+								text << "　#{detag paragraph}\n"
+							end
+						end
+						text << "\n"
+					end
+				end
+				text << "［＃改ページ］\n"
+			end
+
+			yield( {id: Pathname( uri.path ).dirname.basename.to_s, uri: uri, text: text} )
+		end
+	end
+
+	def detag( elem )
+		(elem / 'ruby rp').each do |rp|
+			case rp.text
+			when '（'
+				rp.inner_html = '《'
+			when '）'
+				rp.inner_html = '》'
+			end
+		end
+		elem.to_html.gsub( /<.*?>/, '' ).strip
+	end
+end

data/lib/aozoragen/version.rb

@@ -0,0 +1,3 @@
+module Aozoragen
+  VERSION = "0.0.1"
+end

data/lib/aozoragen.rb

@@ -0,0 +1,5 @@
+require "aozoragen/version"
+
+module Aozoragen
+  # Your code goes here...
+end

metadata

@@ -0,0 +1,67 @@
+--- !ruby/object:Gem::Specification
+name: aozoragen
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- TADA Tadashi
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-02-23 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: &71959020 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *71959020
+description: Scraping some Ebook web site and generating AOZORA format text files.
+email:
+- t@tdtds.jp
+executables:
+- aozora2pdf
+- aozoragen
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Rakefile
+- aozoragen.gemspec
+- bin/aozora2pdf
+- bin/aozoragen
+- lib/aozoragen.rb
+- lib/aozoragen/sai-zen-sen.rb
+- lib/aozoragen/version.rb
+homepage: ''
+licenses: []
+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: aozoragen
+rubygems_version: 1.8.11
+signing_key: 
+specification_version: 3
+summary: Generating AOZORA format text of eBook novels via some Web sites.
+test_files: []