kindler 0.0.7 → 0.1.0

data/Gemfile

@@ -13,8 +13,7 @@ group :development, :test do
   end
 end
 
-gem "ruby-readability",:git=>'https://github.com/iterationlabs/ruby-readability.git', :require => 'readability'
-gem 'mini_magick'
+gem "nokogiri"
 
 # Specify your gem's dependencies in kindler.gemspec
 gemspec

data/Readme.md

@@ -1,5 +1,6 @@
-### Todo
-support magzine like format
+### Prerequisite
+#### 1.kindlegen execute file from amazon
+#### 2.that's all
 
 
 ### Installation
@@ -15,22 +16,21 @@ gem 'kindler',:git=>'git@github.com:29decibel/kindler.git'
 ### 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 -t my_book
-
-outputs : my_book.mobi
-
-### Api use
+### Usage
 ```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'
+title = 'my_first_mobi_book'
+book = Kindler::Book.new :title=>title,:author=>'mike'
+book.add_page :title=>'page1',:author=>'mike1',:content=>'this is the page 1',:wrap=>true,:section => 'love'
+book.add_page :title=>'page2',:author=>'mike1',:content=>'this is the page 2',:wrap=>true,:section => 'hate'
+book.add_page :title=>'page_with_image',:author=>'mike1',:content=>'<img src="http://media2.glamour-sales.com.cn/media/catalog/category/Stroili_banner_02.jpg"></img>this is the page 3',:wrap=>true,:section=>'hate'
+# you will get my_first_mobi_book.mobi file
+book.generate 
+
+#or you can just generate simple mobi book
+book.mobi_type = :flat
+book.generate
 ```
 
-
 Hope you love it !
 
 

data/kindler.gemspec

@@ -4,13 +4,13 @@ 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{kindler is a rubygem allow you to generate kindle mobi book from urls very easily}
-  gem.summary       = %q{kindler is a rubygem allow you to generate kindle mobi book from urls very easily}
+  gem.description   = %q{kindler is a rubygem allow you to generate kindle mobi book very easily}
+  gem.summary       = %q{kindler is a rubygem allow you to generate kindle mobi book very easily}
   gem.homepage      = "https://github.com/29decibel/kindler"
 
 	gem.rubyforge_project = "kindler"
-	gem.add_dependency 'mini_magick'
-	gem.add_dependency 'ruby-readability'	
+
+	gem.add_dependency 'nokogiri'
 
   gem.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
   gem.files         = `git ls-files`.split("\n")

data/lib/kindler/version.rb

@@ -1,3 +1,3 @@
 module Kindler
-  VERSION = "0.0.7"
+  VERSION = "0.1.0"
 end

data/lib/kindler.rb

@@ -1,7 +1,7 @@
 #encoding: utf-8
 require 'rubygems'
-require "readability"
 require "open-uri"
+require "nokogiri"
 # require 'mini_magick'
 require_relative 'kindler/railtie' if defined?(Rails)
 require_relative "kindler/version"
@@ -9,52 +9,48 @@ require_relative "kindler/version"
 module Kindler
 	class Book
 		class KindlerError < StandardError;end
-		attr_accessor :urls,:title,:author,:doc_infos
+		attr_accessor :title,:author,:pages,:local_images,:mobi_type
 		TMP_DIR = 'kindler_generated_mobi'
+		DEFAULT_SECTION = "All Pages"
+		PAGE_ATTRIBUTES = %w(wrap title author content section)
 
 		# availabel options
 		# @param options [Hash]
-		# @option urls [Array] urls to generate
 		# @option title [String] book title
 		# @option output_dir [String] directory want to generate
 		# @option debug [Boolean] whether puts debug infos
 		# @option keep_image [Boolean] whether keep images, default to true
 		def initialize(options={})
-			@urls = options[:urls] || {}
-			@title = options[:title] || ''
 			@output_dir = options[:output_dir] || './'
 			@keep_image = options[:keep_image] || true
 			@debug = options[:debug]
-			raise KindlerError.new("urls option could not be empty") if @urls.empty?
+			@title = options[:title] || ''
 			@author = options[:author] || ''
-			@images = []
-			@doc_infos = {}
-			# init doc infos by url
-			@urls.each {|url| @doc_infos[url]= {} }
+			@mobi_type = options[:mobi_type] || :magzine
+			@pages = []
+			@local_images = []
+			raise KindlerError.new("must provide the book title ") unless title
 		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] = {}
+		def add_page(options={})
+			raise KindlerError.new('must provide title when add page') unless options[:title]
+			page = options.reject{|k,v| PAGE_ATTRIBUTES.include?(k)}
+			page[:wrap] ||= true
+			page[:section] ||= DEFAULT_SECTION
+			page[:count] = pages.count + 1
+			page[:file_name] = "#{page[:count].to_s.rjust(3,'0')}.html"
+			pages << page
+			debug pages
 		end
 
-		# generate books by given urls
-		def generate(title='')
+		def generate
 			make_generated_dirs
-			# generate
-			generate_html
-			localize_images
+			localize_images if @keep_image
 			generate_toc
 			generate_opf
 			generate_ncx
 			write_to_disk
 			kindlegen
-			# clear
 		end
 
 		# check mobi file is generated already
@@ -83,8 +79,8 @@ module Kindler
 						<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>"
+			pages.each do |page|
+				contents << "<li><a href='#{files_count.to_s.rjust(3,'0')}.html'>#{page[:title]}</a></li>"
 				files_count += 1
 			end
 			# append footer
@@ -100,60 +96,124 @@ module Kindler
 				<!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: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>
+						<text>#{title}</text>
 					</docTitle>
 					<docAuthor>
-						<text>#{@author}</text>
+						<text>#{author}</text>
 					</docAuthor>
 					<navMap>
 			NCX
+			contents << (magzine? ? magzine_ncx : flat_ncx)
+			contents << "</navMap></ncx>"
+			@ncx = contents
+		end
+
+		def flat_ncx
+			contents = ''
 			files_count = 2
-			@doc_infos.each do |url,infos|
+			pages.each do |page|
 				nav_point = <<-NAV
 					<navPoint id="navpoint-#{files_count}" playOrder="#{files_count}">
-						<navLabel><text>#{infos[:title]}</text></navLabel>
+						<navLabel><text>#{page[: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>"
-			@ncx = contents
+			contents
+		end
+
+		def magzine_ncx
+			contents = ''
+			pages_by_section = {}
+			pages.each do |page|
+				pages_by_section[page[:title]] ||= []
+				pages_by_section[page[:title]] << page
+			end
+			contents << <<-MAG
+			<navPoint playOrder="0" class="periodical" id="periodical">
+				<navLabel>
+					<text>Table of Contents</text>
+				</navLabel>
+				<content src="contents.html"/>
+
+			MAG
+
+			play_order = 1
+			pages_by_section.each do |section,pages|
+				next if pages.count==0
+				# add section header
+				contents << <<-SECHEADER
+					<navPoint playOrder="#{play_order}" class="section" id="#{section}">
+								 <navLabel>
+									 <text>#{section}</text>
+								 </navLabel>
+								 <content src="#{pages.first[:file_name]}"/>
+				SECHEADER
+
+				play_order += 1
+				# add pages nav
+				pages.each do |page|
+					contents << <<-PAGE
+					 <navPoint playOrder="#{play_order}" class="article" id="item-#{page[:count].to_s.rjust(3,'0')}">
+						 <navLabel>
+							 <text>#{page[:title]}</text>
+						 </navLabel>
+						 <content src="#{page[:file_name]}"/>
+						 <mbp:meta name="description">#{page[:title]}</mbp:meta>
+						 <mbp:meta name="author">#{page[:author]}</mbp:meta>
+					 </navPoint>
+					PAGE
+					play_order += 1
+				end
+				# add section footer
+				contents << "</navPoint>"
+			end
+			contents << "</navPoint>"
+		end
+
+		def magzine_meta
+			<<-META
+    		<x-metadata>
+      		<output content-type="application/x-mobipocket-subscription-magazine" encoding="utf-8"/>
+    		</x-metadata>
+			META
+		end
+
+		def magzine?
+			@mobi_type == :magzine
 		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}">
+				<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: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:identifier id="#{title}">#{title}</dc:identifier>
 							<dc:date>#{Time.now.to_date}/dc:date>
 							<dc:description>Kindler generated book</dc:description>
 						</dc-metadata>
+						#{magzine? ? magzine_meta : ''}
 					</metadata>
 					<manifest>
 			HTML
 			files_count = 1
-			@doc_infos.each do |url,infos|
+			pages.each do |page|
 				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
@@ -164,7 +224,7 @@ module Kindler
 			contents << "<spine toc='nav-contents'>"
 			contents << "<itemref idref='contents'/>"
 			files_count = 1
-			@doc_infos.each do |url,infos|
+			pages.each do |page|
 				contents << "<itemref idref='#{files_count.to_s.rjust(3,'0')}'/>"
 				files_count += 1
 			end
@@ -172,27 +232,10 @@ module Kindler
 			@opf = contents
 		end
 
-		# generate every url to article in readable format
-		def generate_html
-			@doc_infos.each do |url,infos|
-				article = readable_article(url)
-				if article
-					begin
-						# puts article.images
-						infos[:content] = html_wrap(article.title,article.content)
-						infos[:title] = article.title
-					rescue Exception => e
-						debug "error when get contents from article, #{e}"
-					end
-				end
-			end
-			@doc_infos = @doc_infos.reject{|url,infos| infos[:content]==nil or infos[:title]==nil }
-		end
-
 		def localize_images
 			images_count = 1
-			@doc_infos.each do |url,infos|
-				article = Nokogiri::HTML(infos[:content])
+			pages.each do |page|
+				article = Nokogiri::HTML(page[:content])
 				article.css('img').each do |img|
 					begin
 						image_remote_address = img.attr('src')
@@ -209,9 +252,9 @@ module Kindler
 						debug 'Image saved'
 						# replace local url address
 						img.attributes['src'].value = "#{images_count}#{File.extname(image_remote_address)}"
-						infos[:content] = article.inner_html
+						page[:content] = article.inner_html
 						# add to manifest
-						@images << "#{images_count}#{File.extname(image_remote_address)}"
+						local_images << "#{images_count}#{File.extname(image_remote_address)}"
 						images_count += 1 
 					rescue Exception => e
 						debug "got error when fetch and save image: #{e}"
@@ -236,22 +279,6 @@ module Kindler
 			result << '</body></html>'
 		end
 
-		# get readable document by url, using ruby-readability here
-		def readable_article(url)
-			debug "begin fetch url : #{url}"
-			begin
-				source = open(url).read
-			rescue Exception => e
-				debug "got some erros,#{e}"
-				return nil
-			end
-			if @keep_image
-				Readability::Document.new(source,:tags=>%w(div p img a),:attributes => %w[src href],:remove_empty_nodes => false)
-			else
-				Readability::Document.new(source)
-			end
-		end
-
 		# the dir path to generated files
 		def tmp_dir
 			File.join @output_dir,"#{TMP_DIR}_#{@title.gsub(' ','_')}"
@@ -266,24 +293,21 @@ module Kindler
 		def write_to_disk
 			File.open("#{tmp_dir}/nav-contents.ncx",'wb') { |f| f.write @ncx }
 			File.open(file_path('contents'),'wb') {|f| f.write @toc }
-			File.open("#{tmp_dir}/#{@title}.opf",'wb') {|f| f.write @opf}
+			File.open("#{tmp_dir}/#{title}.opf",'wb') {|f| f.write @opf}
 			# make html files
 			files_count = 1
-			@doc_infos.each do |url,infos|
+			pages.each do |page|
 				File.open(file_path(files_count.to_s.rjust(3,'0')),'wb') do |f|
-					f.write infos[:content]
+					content_to_write = page[:wrap] ? html_wrap(page[:title],page[:content]) : page[:content]
+					debug "here is the page #{page[:title]} need to write"
+					debug content_to_write
+					f.write content_to_write
 				end
 				files_count += 1
 			end
 
 		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
-
 		def debug(str)
 			return unless @debug
 			Rails.logger.info(str) if defined?(Rails)

data/spec/cases/generator_spec.rb

@@ -1,47 +1,32 @@
 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',:debug=>true})
-	# 	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',:debug=>true
-	# 	book.generate 
-	# 	File.exist?(mobi_book_path(title)).should == true
-	# end
+	it "should not generate a mobi book" do
+		title = 'good_book'
+		book = Kindler::Book.new :title=>title,:author=>'mike',:debug=>true
+		book.add_page :title=>'page1',:author=>'mike1',:content=>'this is the page 1',:wrap=>true
+		book.add_page :title=>'page2',:author=>'mike1',:content=>'this is the page 2',:wrap=>true
+		book.add_page :title=>'page3',:author=>'mike1',:content=>'this is the page 3',:wrap=>true
+		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',:debug=>true
-	# 	book.generate 
-	# 	File.exist?(mobi_book_path(title,'/Users/lidongbin/projects')).should == true
-	# end
+	it "should generate book contains images" do
+		title = 'book_with_image'
+		book = Kindler::Book.new :title=>title,:author=>'mike',:debug=>true
+		book.add_page :title=>'page1',:author=>'mike1',:content=>'this is the page 1',:wrap=>true
+		book.add_page :title=>'page2',:author=>'mike1',:content=>'this is the page 2',:wrap=>true
+		book.add_page :title=>'page3',:author=>'mike1',:content=>'<img src="http://media2.glamour-sales.com.cn/media/catalog/category/Stroili_banner_02.jpg"></img>this is the page 3',:wrap=>true
+		book.generate 
+		File.exist?(mobi_book_path(title)).should == true
+	end
 
-	it "should not say error when got redirect page" do
-		title = 'good_book'
-		urls = []
-		urls << "http://droplr.com"
-		urls << "http://www.mysenz.com/?p=3692"
-		book = Kindler::Book.new :urls=>urls,:title=>title,:author=>'mike',:debug=>true
+	it "should generate book with sections" do
+		title = 'first_section_book'
+		book = Kindler::Book.new :title=>title,:author=>'mike',:debug=>true
+		book.add_page :title=>'page1',:author=>'mike1',:content=>'this is the page 1',:wrap=>true,:section => 'love'
+		book.add_page :title=>'page2',:author=>'mike1',:content=>'this is the page 2',:wrap=>true,:section => 'hate'
+		book.add_page :title=>'page3',:author=>'mike1',:content=>'<img src="http://media2.glamour-sales.com.cn/media/catalog/category/Stroili_banner_02.jpg"></img>this is the page 3',:wrap=>true,:section=>'hate'
 		book.generate 
 		File.exist?(mobi_book_path(title)).should == true
 	end
@@ -50,35 +35,4 @@ describe "Mobi html file generator" do
 		File.join(output_dir,"kindler_generated_mobi_#{title}/#{title}.mobi")
 	end
 
-
-			# 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>
-			# ####################################################################################
-
-
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: kindler
 version: !ruby/object:Gem::Version
-  version: 0.0.7
+  version: 0.1.0
   prerelease: 
 platform: ruby
 authors:
@@ -12,8 +12,8 @@ cert_chain: []
 date: 2012-02-04 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: mini_magick
-  requirement: &2155014640 !ruby/object:Gem::Requirement
+  name: nokogiri
+  requirement: &2156313120 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,24 +21,11 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2155014640
-- !ruby/object:Gem::Dependency
-  name: ruby-readability
-  requirement: &2155014220 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *2155014220
-description: kindler is a rubygem allow you to generate kindle mobi book from urls
-  very easily
+  version_requirements: *2156313120
+description: kindler is a rubygem allow you to generate kindle mobi book very easily
 email:
 - mike.d.1984@gmail.com
-executables:
-- kindler
+executables: []
 extensions: []
 extra_rdoc_files: []
 files:
@@ -47,7 +34,6 @@ files:
 - Guardfile
 - Rakefile
 - Readme.md
-- bin/kindler
 - kindler.gemspec
 - lib/kindler.rb
 - lib/kindler/railtie.rb
@@ -77,8 +63,7 @@ rubyforge_project: kindler
 rubygems_version: 1.8.11
 signing_key: 
 specification_version: 3
-summary: kindler is a rubygem allow you to generate kindle mobi book from urls very
-  easily
+summary: kindler is a rubygem allow you to generate kindle mobi book very easily
 test_files:
 - spec/cases/generator_spec.rb
 - spec/spec_helper.rb

data/bin/kindler

@@ -1,29 +0,0 @@
-#!/usr/bin/env ruby
-require 'rubygems'
-require 'optparse'
-require 'open-uri'
-require File.dirname(__FILE__) + "/../lib/kindler"
-# get options
-options = {:title=>'kindler_ebook',:urls=>ARGV}
-option_parser = OptionParser.new do |opts|
-	opts.banner = "Usage kindler url1 url2 url3 [-t my_book] [-d]"
-
-	opts.on("-d",'--debug','show debug infos') do |d|
-		options[:debug] = d
-	end
-
-	opts.on("-t",'--title','title of book') do |t|
-		options[:title] = t
-	end
-
-	opts.on_tail('-h','--help','show this message') do
-		puts opts
-		exit
-	end
-	
-end
-
-exit unless ARGV.length > 0
-book = Kindler::Book.new(options)
-book.generate
-