kindler 0.0.1

data/.gitignore

@@ -0,0 +1,19 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+kindler_generated*
+.DS_Store

data/Gemfile

@@ -0,0 +1,20 @@
+source 'http://rubygems.org'
+
+group :development, :test do
+	gem 'rspec'
+  # Testing infrastructure
+  gem 'guard'
+  gem 'guard-rspec'
+
+  if RUBY_PLATFORM =~ /darwin/
+    # OS X integration
+    gem "ruby_gntp"
+    gem "rb-fsevent", "~> 0.4.3.1"
+  end
+end
+
+gem "ruby-readability",:git=>'https://github.com/iterationlabs/ruby-readability.git', :require => 'readability'
+gem 'mini_magick'
+
+# Specify your gem's dependencies in kindler.gemspec
+gemspec

data/Guardfile

@@ -0,0 +1,8 @@
+# A sample Guardfile
+# More info at https://github.com/guard/guard#readme
+guard 'rspec', :version => 2 do
+  watch(%r{^spec/.+_spec\.rb$})
+  watch(%r{^lib/(.+)\.rb$})     { |m| "spec/lib/#{m[1]}_spec.rb" }
+  watch('spec/spec_helper.rb')  { "spec" }
+end
+

data/Rakefile

@@ -0,0 +1,2 @@
+#!/usr/bin/env rake
+require "bundler/gem_tasks"

data/Readme.md

@@ -0,0 +1,26 @@
+### Todo
+1.show images within page
+2.support magzine like format
+
+### A kindle mobi book generator
+which receive a couple of urls then output one mobi file
+
+### Command Line Use [Todo]
+kindler url1 url2 url3 url4 -o test.mobi
+
+outputs : test.mobi
+
+### Api use
+```ruby
+# generate my book
+book = Kindler::Book.new ({:urls=>["http://blog.farmostwood.net/643.html",
+													"http://www.ifanr.com/69878","http://www.oneplus.info/archives/455"],
+													:title=>'Test_book',:author=>'mike'})
+# you will get my_book.mobi file
+book.generate 'my_book'
+```
+
+
+Hope you love it !
+
+

data/kindler.gemspec

@@ -0,0 +1,21 @@
+# -*- encoding: utf-8 -*-
+require File.expand_path('../lib/kindler/version', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.authors       = ["dongbin.li"]
+  gem.email         = ["mike.d.1984@gmail.com"]
+  gem.description   = %q{a simple gem to generate kindle mobi book}
+  gem.summary       = %q{a simple gem to generate kindle mobi book}
+  gem.homepage      = "https://github.com/29decibel/kindler"
+
+	gem.rubyforge_project = "kindler"
+	gem.add_dependency 'mini_magick'
+	gem.add_dependency 'ruby-readability'	
+
+  gem.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  gem.files         = `git ls-files`.split("\n")
+  gem.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  gem.name          = "kindler"
+  gem.require_paths = ["lib"]
+  gem.version       = Kindler::VERSION
+end

data/lib/kindler/html_generator.rb

@@ -0,0 +1,7 @@
+module Kindler
+	module HtmlGenerator
+		def g_html
+			
+		end
+	end
+end

data/lib/kindler/railtie.rb

@@ -0,0 +1,7 @@
+module Kindler
+  class Railtie < Rails::Railtie
+    config.after_initialize do
+			# do nothing
+    end
+  end
+end

data/lib/kindler/toc_generator.rb

@@ -0,0 +1,7 @@
+module Kindler
+	module TocGenerator
+		def g_toc
+			
+		end
+	end
+end

data/lib/kindler/version.rb

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

data/lib/kindler.rb

@@ -0,0 +1,254 @@
+require "kindler/version"
+require "readability"
+require "open-uri"
+# require 'mini_magick'
+require 'kindler/railtie' if defined?(Rails)
+
+module Kindler
+	class Book
+		class KindlerError < StandardError;end
+		attr_accessor :urls,:title,:author
+		TMP_DIR = 'kindler_generated_mobi'
+
+		# availabel options
+		# @param options [Hash]
+		# @option urls [Array] urls to generate
+		# @option title [String] book title
+		# @option output_dir [String] directory want to generate
+		def initialize(options={})
+			@urls = options[:urls] || {}
+			@title = options[:title] || ''
+			@output_dir = options[:output_dir] || './'
+			raise KindlerError.new("urls option could not be empty") if @urls.empty?
+			@author = options[:author] || ''
+			@doc_infos = {}
+			# init doc infos by url
+			@urls.each {|url| @doc_infos[url]= {} }
+		end
+
+		# add url to book
+		# @param url [String] url to add to book
+		# @param options [Hash]
+		# @option section [Symbol] indicate which section the url belongs to,if not empty the book will be generated with magzine style
+		def add_url(url,options={})
+			return if @doc_infos[url]
+			@urls << url
+			@doc_infos[url] = {}
+		end
+
+		# generate books by given urls
+		def generate(title='')
+			make_generated_dirs
+			# generate
+			generate_html
+			generate_toc
+			generate_opf
+			generate_ncx
+			kindlegen
+			# clear
+		end
+
+		# check mobi file is generated already
+		def mobi_generated?
+			File.exist? "#{tmp_dir}/#{@title}.mobi"
+		end
+
+		private
+		# make sure kindlegen is installed
+		# you can use "sudo brew install " to install it
+		def kindlegen
+			puts 'begin generate mobi'
+			system("kindlegen #{tmp_dir}/#{@title}.opf ")
+		end
+
+		def generate_toc
+			contents = <<-CODE
+				<html>
+					<head>
+						<meta content="text/html; charset=utf-8" http-equiv="Content-Type"/>
+						<title>Table of Contents</title>
+					</head>
+					<body>
+						<h1>Contents</h1>
+						<h4>Main section</h4>
+						<ul>
+			CODE
+			files_count = 1
+			@doc_infos.each do |url,infos|
+				contents << "<li><a href='#{files_count.to_s.rjust(3,'0')}.html'>#{infos[:title]}</a></li>"
+				files_count += 1
+			end
+			# append footer
+			contents << "</ul></body></html>"
+			File.open(file_path('contents'),'w') do |f|
+				f.puts contents
+			end
+		end
+
+		# generate ncx , which is navigation
+		def generate_ncx
+			contents = <<-NCX
+				<?xml version="1.0" encoding="UTF-8"?>
+				<!DOCTYPE ncx PUBLIC "-//NISO//DTD ncx 2005-1//EN" "http://www.daisy.org/z3986/2005/ncx-2005-1.dtd">
+				<ncx xmlns="http://www.daisy.org/z3986/2005/ncx/" version="2005-1" xml:lang="en-US">
+					<head>
+						<meta name="dtb:uid" content="#{@title}"/>
+						<meta name="dtb:depth" content="1"/>
+						<meta name="dtb:totalPageCount" content="0"/>
+						<meta name="dtb:maxPageNumber" content="0"/>
+					</head>
+					<docTitle>
+						<text>#{@title}</text>
+					</docTitle>
+					<docAuthor>
+						<text>#{@author}</text>
+					</docAuthor>
+					<navMap>
+			NCX
+			# this navPoint seems not useful
+			# contents << <<-NAV
+			# <navPoint id="navpoint-1" playOrder="1">
+			# 	<navLabel><text>Table Of Contents</text></navLabel>
+			# 	<content src="contents.html"/>
+			# </navPoint>
+			# NAV
+			####################### periodocal , magzine like format #########################
+			# <navPoint playOrder="0" class="periodical" id="periodical">
+			#			<mbp:meta-img src="masthead.gif" name="mastheadImage"/>
+			#			<navLabel>
+			#				<text>Table of Contents</text>
+			#			</navLabel>
+			#			<content src="contents.html"/>
+			#			<navPoint playOrder="1" class="section" id="Main-section">
+			#				<navLabel>
+			#					<text>Main section</text>
+			#				</navLabel>
+			#				<content src="001.html"/>
+			#				<navPoint playOrder="2" class="article" id="item-001">
+			#					<navLabel>
+			#						<text>Nick Clegg and David Cameron agree key changes on NHS plans</text>
+			#					</navLabel>
+			#					<content src="001.html"/>
+			#					<mbp:meta name="description">Deputy PM tells Andrew Marr show that GPs should not be forced to sign up to new commissioning consortiums</mbp:meta>
+			#					<mbp:meta name="author">Nicholas Watt and Denis Campbell</mbp:meta>
+			#				</navPoint>
+			# ####################################################################################
+			files_count = 2
+			@doc_infos.each do |url,infos|
+				nav_point = <<-NAV
+					<navPoint id="navpoint-#{files_count}" playOrder="#{files_count}">
+						<navLabel><text>#{infos[:title]}</text></navLabel>
+						<content src="#{(files_count-1).to_s.rjust(3,'0')}.html"/>
+					</navPoint>
+				NAV
+				contents << nav_point
+				files_count += 1
+			end
+			contents << "</navMap></ncx>"
+			File.open("#{tmp_dir}/nav-contents.ncx",'w') { |f| f.puts contents }
+		end
+
+		# generate the opf, manifest of book,including all articles and images and css
+		def generate_opf
+			# mark mobi as magzine format
+			# <x-metadata>
+			#	 <output content-type="application/x-mobipocket-subscription-magazine" encoding="utf-8"/>
+			# </x-metadata>
+			contents = <<-HTML
+				<?xml version='1.0' encoding='utf-8'?>
+				<package xmlns="http://www.idpf.org/2007/opf" version="2.0" unique-identifier="#{@title}">
+					<metadata>
+						<dc-metadata xmlns:dc="http://purl.org/dc/elements/1.1/">
+							<dc:title>#{@title}</dc:title>
+							<dc:language>en-gb</dc:language>
+							<meta content="cover-image" name="cover"/>
+							<dc:creator>Kindler- 29decibel</dc:creator>
+							<dc:publisher>Kindler- 29decibel</dc:publisher>
+							<dc:subject>News</dc:subject>
+							<dc:identifier id="#{@title}">#{@title}</dc:identifier>
+							<dc:date>#{Time.now.to_date}/dc:date>
+							<dc:description>Kindler generated book</dc:description>
+						</dc-metadata>
+					</metadata>
+					<manifest>
+			HTML
+			files_count = 1
+			@doc_infos.each do |url,infos|
+				doc_id = files_count.to_s.rjust(3,'0')
+				contents << "<item href='#{doc_id}.html' media-type='application/xhtml+xml' id='#{doc_id}'/>"
+				files_count += 1
+			end
+			contents << "<item href='contents.html' media-type='application/xhtml+xml' id='contents'/>"
+			contents << "<item href='nav-contents.ncx' media-type='application/x-dtbncx+xml' id='nav-contents'/>"
+			contents << "</manifest>"
+			contents << "<spine toc='nav-contents'>"
+			contents << "<itemref idref='contents'/>"
+			files_count = 1
+			@doc_infos.each do |url,infos|
+				contents << "<itemref idref='#{files_count.to_s.rjust(3,'0')}'/>"
+				files_count += 1
+			end
+			contents << "</spine><guide><reference href='contents.html' type='toc' title='Table of Contents'/></guide></package>"
+			File.open("#{tmp_dir}/#{@title}.opf",'w') {|f| f.puts contents}
+		end
+
+		# generate every url to article in readable format
+		def generate_html
+			@doc_infos.each do |url,infos|
+				article = readable_article(url)
+				# puts article.images
+				infos[:content] = html_wrap(article.title,article.content)
+				infos[:title] = article.title
+			end
+			# make html files
+			files_count = 1
+			@doc_infos.each do |url,infos|
+				File.open(file_path(files_count.to_s.rjust(3,'0')),'w') do |f|
+					f.puts infos[:content]
+				end
+				files_count += 1
+			end
+		end
+
+		# html file path
+		def file_path(file_name)
+			"#{tmp_dir}/#{file_name}.html"
+		end
+
+		# wrap readable contents with in html format
+		def html_wrap(title,content)
+			result = ''
+			result << '<html><head>'
+			result << "<meta content='text/html; charset=utf-8' http-equiv='Content-Type'/>"
+			result << '</head><body>'
+			result << "<h3>#{title}</h3>"
+			result << content
+			result << '</body></html>'
+		end
+
+		# get readable document by url, using ruby-readability here
+		def readable_article(url)
+			puts "begin fetch url : #{url}"
+			source = open(url).read
+			Readability::Document.new(source)
+		end
+
+		# the dir path to generated files
+		def tmp_dir
+			File.join @output_dir,"#{TMP_DIR}_#{@title.gsub(' ','_')}"
+		end
+
+		# create dirs of generated files
+		def make_generated_dirs
+			FileUtils.rm_rf tmp_dir if File.exist?(tmp_dir)
+			FileUtils.mkdir_p tmp_dir unless File.exist?(tmp_dir)
+		end
+
+		# exist to clear tmp files such as ncx,opf or html other than mobi file
+		# keep them right now
+		def clear_tmp_dirs
+			
+		end
+
+	end
+end

data/spec/cases/generator_spec.rb

@@ -0,0 +1,43 @@
+require 'spec_helper'
+describe "Mobi html file generator" do
+
+	it "should generate html files by urls" do
+		title = "Test_book"
+		book = Kindler::Book.new ({:urls=>["http://blog.farmostwood.net/643.html",
+															"http://www.ifanr.com/69878","http://www.oneplus.info/archives/455"],
+															:title=>title,:author=>'mike'})
+		book.generate
+		File.exist?(mobi_book_path(title)).should == true
+	end
+
+
+	it "should generate hacker news book" do
+		title = 'haker_news'
+		urls = []
+		urls << "http://jseliger.com/2010/09/26/how-universities-work-or-what-i-wish-i%E2%80%99d-known-freshman-year-a-guide-to-american-university-life-for-the-uninitiated/"
+		urls << "http://randykepple.com/photoblog/2010/10/8-bad-habits-that-crush-your-creativity-and-stifle-your-success/"
+		urls << "http://nathanmarz.com/blog/how-to-get-a-job-at-a-kick-ass-startup-for-programmers.html"
+		urls << "http://tumblr.intranation.com/post/766290565/how-set-up-your-own-private-git-server-linux"
+		urls << "http://antirez.com/post/what-is-wrong-with-2006-programming.html"
+		urls << "http://fak3r.com/2009/09/14/howto-build-your-own-open-source-dropbox-clone/"
+		book = Kindler::Book.new :urls=>urls,:title=>title,:author=>'mike'
+		book.generate 
+		File.exist?(mobi_book_path(title)).should == true
+	end
+
+	it "should generate book and infos on output_dir" do
+		title = 'my_dir_book'
+		urls = []
+		urls << "http://www.wowsai.com/home/space.php?uid=1&do=blog&id=4362&classid=2"
+		urls << "http://www.honeykennedy.com/2012/01/miss-moss-love-letters/"
+		urls << "http://www.mysenz.com/?p=3692"
+		book = Kindler::Book.new :urls=>urls,:title=>title,:author=>'mike',:output_dir=>'/Users/lidongbin/projects'
+		book.generate 
+		File.exist?(mobi_book_path(title,'/Users/lidongbin/projects')).should == true
+	end
+
+	def mobi_book_path(title,output_dir='.')
+		File.join(output_dir,"kindler_generated_mobi_#{title}/#{title}.mobi")
+	end
+
+end

data/spec/spec_helper.rb

@@ -0,0 +1,7 @@
+begin
+  require 'bundler/setup'
+rescue LoadError
+  puts 'Although not required, bundler is recommended for running the tests.'
+end
+
+require 'kindler'

metadata

@@ -0,0 +1,83 @@
+--- !ruby/object:Gem::Specification
+name: kindler
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- dongbin.li
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-01-30 00:00:00.000000000Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: mini_magick
+  requirement: &2162549440 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *2162549440
+- !ruby/object:Gem::Dependency
+  name: ruby-readability
+  requirement: &2162549020 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *2162549020
+description: a simple gem to generate kindle mobi book
+email:
+- mike.d.1984@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Guardfile
+- Rakefile
+- Readme.md
+- kindler.gemspec
+- lib/kindler.rb
+- lib/kindler/html_generator.rb
+- lib/kindler/railtie.rb
+- lib/kindler/toc_generator.rb
+- lib/kindler/version.rb
+- spec/cases/generator_spec.rb
+- spec/spec_helper.rb
+homepage: https://github.com/29decibel/kindler
+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: kindler
+rubygems_version: 1.8.11
+signing_key: 
+specification_version: 3
+summary: a simple gem to generate kindle mobi book
+test_files:
+- spec/cases/generator_spec.rb
+- spec/spec_helper.rb
+has_rdoc: