htmls_to_pdf 0.0.4

data/.gitignore

@@ -0,0 +1,5 @@
+*.gem
+*.swp
+*.html
+*.css
+*.pdf

data/README.markdown

@@ -0,0 +1,104 @@
+# HtmlsToPdf
+
+## DESCRIPTION
+
+HtmlsToPdf enables you to package one or more (ordered) HTML pages as a PDF.
+
+## REQUIREMENTS
+
+HtmlsToPdf uses the PDFKit gem, which itself uses the [wkhtmltopdf](http://madalgo.au.dk/~jakobt/wkhtmltoxdoc/wkhtmltopdf-0.9.9-doc.html) program, which uses qtwebkit.
+
+Dependence chain summary: HtmlsToPdf -> PDFKit -> wkhtmltopdf -> qtwebkit -> webkit
+
+For information on qtwebkit:
+
+- [Installing on Linux](http://trac.webkit.org/wiki/BuildingQtOnLinux)
+
+- [Installing on MacOS](http://trac.webkit.org/wiki/BuildingQtOnOSX)
+
+- [Installing on Windows](http://trac.webkit.org/wiki/BuildingQtOnWindows)
+
+For information on wkhtmltopdf:
+
+- [Installation guide from PDFKit author](https://github.com/jdpace/PDFKit/wiki/Installing-WKHTMLTOPDF)
+
+- [code.google.com](http://code.google.com/p/wkhtmltopdf/)
+
+For information on PDFKit:
+
+- [Github](https://github.com/jdpace/PDFKit)
+
+- [Railscasts](http://railscasts.com/episodes/220-pdfkit)
+
+## BASIC USAGE
+
+You will find six example scripts in the /examples directory.
+
+After you install HtmlsToPdf and its dependencies, you can write an ordinary Ruby script with the following features:
+
+### EXAMPLE 1
+
+Annotated version of /examples/get_rubygems_user_guide.rb:
+
+    # require the gem
+    require 'rubygems'
+    require 'htmls_to_pdf'
+
+    # Get 'RubyGems User Guide' as pdf file
+    # Source: 'http://docs.rubygems.org/read/book/1'
+
+    # create an empty hash to hold your configuration options
+    config = {}
+
+    # set a :urls key with a value of an array containing all the 
+    # urls you want in your PDF (in the order you want them)
+    config[:urls] = ['http://docs.rubygems.org/read/book/1']
+    # I have no idea why these chapters are numbered as they are!
+    [1,2,3,4,16,7,5,6,21].each do |val|
+      config[:urls] << 'http://docs.rubygems.org/read/chapter/' + val.to_s
+    end
+
+    # set a :savedir key with a string value indicating the directory to create
+    # your PDF file in. If the directory does not exist, it will be created
+    config[:savedir] = '~/Tech/Ruby/GEMS/DOCUMENTATION'
+
+    # set a :savename key with a string value indicating the name of the PDF file
+    config[:savename] = 'RubyGems_User_Guide.pdf'
+
+    # create a new HtmlsToPdf object, passing in your hash, and then call create_pdf
+    # on the new object
+    HtmlsToPdf.new(config).create_pdf
+
+### EXAMPLE 2
+
+Annotated version of /examples/get_coffeescript_meet_backbone.rb:
+
+  require 'rubygems'
+  require 'htmls_to_pdf'
+
+  # Get 'CoffeeScript, Meet Backbone.js' as pdf file
+  # Source: 'http://adamjspooner.github.com/coffeescript-meet-backbonejs/'
+
+  config = {}
+  config[:urls] = ['http://adamjspooner.github.com/coffeescript-meet-backbonejs/']
+  (1..5).each do |val|
+    config[:urls] << 'http://adamjspooner.github.com/coffeescript-meet-backbonejs/0' + val.to_s + '/docs/script.html'
+  end
+  config[:savedir] = '~/Tech/Javascript/COFFEESCRIPT/BACKBONE.JS'
+  config[:savename] = 'CoffeeScript_Meet_Backbone.js.pdf'
+
+  # If a :css key is given with an array value, the CSS files in the array will be used to generate
+  # the PDF document. This allows you to modify the CSS file(s) to, for example, hide HTML headers,
+  # sidebars and footers you do not wish to appear in your PDF.
+  config[:css] = ['http://adamjspooner.github.com/coffeescript-meet-backbonejs/05/docs/docco.css']
+
+  # If a :options key is passed with a hash value, that hash will be passed to wkhtmltopdf.
+  # Many options are available through wkhtmltopdf; see: [the wkhtmltopdf documentation](http://madalgo.au.dk/~jakobt/wkhtmltoxdoc/wkhtmltopdf-0.9.9-doc.html).
+  config[:options] = {:page_size => 'Letter', :orientation => 'Landscape'}
+
+  HtmlsToPdf.new(config).create_pdf
+
+## LEGAL DISCLAIMER
+
+Please use at your own risk. I do not guarantee anything about this program.
+

data/examples/get_coffeescript.rb

@@ -0,0 +1,14 @@
+require 'rubygems'
+require 'htmls_to_pdf'
+
+# Get 'CoffeeScript_documentation' as pdf file
+# Source: 'http://jashkenas.github.com/coffee-script/'
+
+config = {}
+config[:urls] = ['http://jashkenas.github.com/coffee-script/']
+config[:savedir] = '~/Tech/Javascript/COFFEESCRIPT/DOCUMENTATION'
+config[:savename] = 'CoffeeScript_documentation.pdf'
+config[:css] = ['http://jashkenas.github.com/coffee-script/documentation/css/docs.css',
+       'http://jashkenas.github.com/coffee-script/documentation/css/idle.css']
+
+HtmlsToPdf.new(config).create_pdf

data/examples/get_coffeescript_meet_backbone.rb

@@ -0,0 +1,17 @@
+require 'rubygems'
+require 'htmls_to_pdf'
+
+# Get 'CoffeeScript, Meet Backbone.js' as pdf file
+# Source: 'http://adamjspooner.github.com/coffeescript-meet-backbonejs/'
+
+config = {}
+config[:urls] = ['http://adamjspooner.github.com/coffeescript-meet-backbonejs/']
+(1..5).each do |val|
+  config[:urls] << 'http://adamjspooner.github.com/coffeescript-meet-backbonejs/0' + val.to_s + '/docs/script.html'
+end
+config[:savedir] = '~/Tech/Javascript/COFFEESCRIPT/BACKBONE.JS'
+config[:savename] = 'CoffeeScript_Meet_Backbone.js.pdf'
+config[:css] = ['http://adamjspooner.github.com/coffeescript-meet-backbonejs/05/docs/docco.css']
+config[:options] = {:page_size => 'Letter', :orientation => 'Landscape'}
+
+HtmlsToPdf.new(config).create_pdf

data/examples/get_exploring_coffeescript.rb

@@ -0,0 +1,17 @@
+require 'rubygems'
+require 'htmls_to_pdf'
+
+# Get 'Exploring CoffeeScript' as pdf file
+# Source: 'http://elegantcode.com'
+
+config = {}
+config[:urls] = ['http://elegantcode.com/2011/06/21/exploring-coffeescript-part-1-and-then-there-was-coffee/',
+        'http://elegantcode.com/2011/06/30/exploring-coffeescript-part-2-variables-and-functions/',
+        'http://elegantcode.com/2011/07/13/exploring-coffeescript-part-3-more-on-functions/',
+        'http://elegantcode.com/2011/07/26/exploring-coffeescript-part-4-objects-and-classes/',
+        'http://elegantcode.com/2011/08/02/exploring-coffeescript-part-5-ranges-loops-and-comprehensions/',
+        'http://elegantcode.com/2011/08/09/exploring-coffeescript-part-6-show-me-the-goodies/']
+config[:savedir] = '~/Tech/Javascript/COFFEESCRIPT/DOCUMENTATION/Exploring_CoffeeScript'
+config[:savename] = 'Exploring_CoffeeScript.pdf'
+
+HtmlsToPdf.new(config).create_pdf

data/examples/get_python_book.rb

@@ -0,0 +1,23 @@
+require 'rubygems'
+require 'htmls_to_pdf'
+
+# Get 'Learn Python the Hard Way' as pdf file
+# Source: 'http://learnpythonthehardway.org/book/'
+
+def python_hard_way_urls
+  urls = ['http://learnpythonthehardway.org/book/intro.html']
+  (0..52).each do |val|
+    urls << 'http://learnpythonthehardway.org/book/ex' + val.to_s + '.html'
+  end
+  urls << 'http://learnpythonthehardway.org/book/next.html'
+  urls << 'http://learnpythonthehardway.org/book/advice.html'
+  urls
+end
+
+config[:savedir] = '~/Tech/Python/Learn_Python_the_Hard_Way'
+config[:savename] = 'Learn_Python_the_Hard_Way.pdf'
+config[:urls] = python_hard_way_urls
+config[:css] = ['http://learnpythonthehardway.org/book/_static/basic.css']
+config[:remove_temp_files] = false
+
+HtmlsToPdf.new(config).create_pdf

data/examples/get_ruby_book.rb

@@ -0,0 +1,23 @@
+require 'rubygems'
+require 'htmls_to_pdf'
+
+# Get 'Learn Ruby the Hard Way' as a pdf
+# Source: 'http://ruby.learncodethehardway.org/book/'
+
+def ruby_hard_way_urls
+  urls = ['http://ruby.learncodethehardway.org/book/intro.html']
+  (1..52).each do |val|
+    urls << 'http://ruby.learncodethehardway.org/book/ex' + val.to_s.rjust(2,'0') + '.html'
+  end
+  urls << 'http://ruby.learncodethehardway.org/book/next.html'
+  urls << 'http://ruby.learncodethehardway.org/book/advice.html'
+  urls
+end
+
+config[:savedir] = '~/Ruby_programs/Learn_Ruby_the_Hard_Way'
+config[:savename] = 'Learn_Ruby_the_Hard_Way.pdf'
+config[:urls] = ruby_hard_way_urls
+config[:css] = ['http://ruby.learncodethehardway.org/book/css/syntax.css']
+config[:remove_temp_files] = false
+
+html_files = HtmlsToPdf.new(config).create_pdf

data/examples/get_rubygems_user_guide.rb

@@ -0,0 +1,17 @@
+require 'rubygems'
+require 'htmls_to_pdf'
+
+# Get 'RubyGems User Guide' as pdf file
+# Source: 'http://docs.rubygems.org/read/book/1'
+
+config = {}
+config[:urls] = ['http://docs.rubygems.org/read/book/1']
+# I have no idea why these chapters are numbered as they are!
+[1,2,3,4,16,7,5,6,21].each do |val|
+  config[:urls] << 'http://docs.rubygems.org/read/chapter/' + val.to_s
+end
+
+config[:savedir] = '~/Tech/Ruby/GEMS/DOCUMENTATION'
+config[:savename] = 'RubyGems_User_Guide.pdf'
+
+HtmlsToPdf.new(config).create_pdf

data/htmls_to_pdf.gemspec

@@ -0,0 +1,18 @@
+$:.push File.expand_path("../lib", __FILE__)
+require 'htmls_to_pdf/version'
+
+Gem::Specification.new do |s|
+  s.name            = 'htmls_to_pdf'
+  s.version         = HtmlsToPdf::VERSION
+  s.platform        = Gem::Platform::RUBY
+  s.authors         = ['James Lavin']
+  s.email           = ['htmls_to_pdf@futureresearch.com']
+  s.summary         = %q{Creates single PDF file from 1+ HTML pages}
+  s.description     = %q{Creates single PDF file from 1+ HTML pages using PDFKit}
+  s.add_runtime_dependency 'pdfkit', '~> 0.5', '>= 0.5.2'
+  s.add_development_dependency 'rspec'
+  s.require_paths   = ['lib']
+  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) }
+end

data/lib/htmls_to_pdf/htmls_to_pdf.rb

@@ -0,0 +1,144 @@
+require 'rubygems'
+require 'fileutils'
+require 'pdfkit'
+require 'uri'
+include URI
+
+class HtmlsToPdf
+
+  attr_reader :htmlarray, :pdfarray, :cssarray, :urls, :savedir, :savename, :remove_temp_files
+
+  TMP_HTML_PREFIX = 'tmp_html_file_'
+  TMP_PDF_PREFIX = 'tmp_pdf_file_'
+
+  def initialize(in_config = {})
+    config = {
+      :css => [],
+      :remove_temp_files => true,
+      :options => {}
+    }.merge(in_config)
+    set_dir(config[:savedir])
+    @savename = config[:savename]
+    exit_if_pdf_exists
+    @urls = clean_urls(config[:urls])
+    @pdfarray = create_pdfarray
+    @cssarray = config[:css]
+    @remove_temp_files = config[:remove_temp_files]
+    @options = config[:options]
+  end
+
+  def get_htmlarray
+    everything_after_last_slash(@urls)
+  end
+
+  def clean_urls(urls)
+    if !urls.is_a?(Array)
+      urls = Array(urls) if Array(urls).is_a?(Array)
+    else
+      raise "config[:urls] must be an array" unless urls.is_a?(Array)
+    end
+    remove_trailing_url_slashes(urls)
+  end
+
+  def remove_trailing_url_slashes(urls)
+    urls.map { |url| url.match(/\/$/) ? url.sub(/\/$/,'') : url }
+  end
+
+  def everything_after_last_slash(urls)
+    urls.map { |url| url.match(/([^\/]+)$/)[0] }
+  end
+
+  def add_dot_html(urls)
+    urls.map { |url| url.match(/\.html?$/) ? url : url + '.html' }
+  end
+
+  def create_pdfarray
+    outarray = []
+    (0...@urls.length).each do |idx|
+      outarray << TMP_PDF_PREFIX + idx.to_s
+    end
+    outarray
+  end
+
+  def exit_if_pdf_exists
+    if File.exists?(@savename)
+      puts "File #{@savename} already exists. Please rename or delete and re-run this program."
+      exit
+    end
+  end
+
+  def set_dir(savedir)
+    @savedir = savedir
+    save_to = File.expand_path(savedir)
+    FileUtils.mkdir_p(save_to)
+    Dir.chdir(save_to)
+  end
+
+  #def add_css(css_file)
+  #  @cssarray << css_file
+  #end
+
+  def download_files
+    download_html_files
+    download_css_files
+  end
+
+  def download_html_files
+    existing_files = Dir.entries(".")
+    @htmlarray = []
+    @urls.each_with_index do |url,idx|
+      savename = TMP_HTML_PREFIX + idx.to_s
+      unless existing_files.include?(savename)
+        `wget #{url} -O #{savename}`
+      end
+      @htmlarray << savename
+    end
+  end
+
+  def download_css_files
+    existing_files = Dir.entries(".")
+    @cssarray.each do |css_url|
+      `wget #{css_url}` unless existing_files.include?(File.basename(css_url))
+    end
+  end
+
+  def generate_pdfs
+    @urls.each_with_index { |url,i| html_to_pdf(TMP_HTML_PREFIX + i.to_s,@pdfarray[i]) }
+  end
+
+  def html_to_pdf(html_file,pdf_file)
+    puts "creating #{pdf_file} from #{html_file}"
+    html = nil
+    unless Dir.entries(".").include?(pdf_file)
+      File.open(html_file, 'r') { |inf| html = inf.read }
+      #kit = PDFKit.new(html, :page_size => 'Letter', :orientation => 'Landscape')
+      kit = PDFKit.new(html, @options)
+      @cssarray.each { |cssfile| kit.stylesheets << File.basename(cssfile) }
+      kit.to_file(pdf_file)
+    end
+  end
+
+  def join_pdfs
+    unless File.exists?(@savename)
+      pdfs_string = @pdfarray.join(" ")
+      `pdftk #{pdfs_string} output #{@savename}`
+    end
+  end
+
+  def delete_temp_files
+    @pdfarray.each { |pdffile| File.delete(pdffile) }
+    @htmlarray.each { |htmlfile| File.delete(htmlfile) }
+    @cssarray.each { |cssfile| File.delete(File.basename(cssfile)) }
+  end
+
+  def create_pdf
+    download_files
+    generate_pdfs
+    join_pdfs
+    delete_temp_files if @remove_temp_files
+  end
+
+end
+
+
+

data/lib/htmls_to_pdf/pdfkit_config.rb

@@ -0,0 +1,6 @@
+require 'pdfkit'
+
+PDFKit.configure do |config|
+  config.wkhtmltopdf = '/usr/bin/wkhtmltopdf'
+end
+

data/lib/htmls_to_pdf/version.rb

@@ -0,0 +1,3 @@
+module HtmlsToPdf
+  VERSION = "0.0.4"
+end

data/lib/htmls_to_pdf.rb

@@ -0,0 +1,2 @@
+require 'htmls_to_pdf/pdfkit_config'
+require 'htmls_to_pdf/htmls_to_pdf'

metadata

@@ -0,0 +1,114 @@
+--- !ruby/object:Gem::Specification 
+name: htmls_to_pdf
+version: !ruby/object:Gem::Version 
+  hash: 23
+  prerelease: 
+  segments: 
+  - 0
+  - 0
+  - 4
+  version: 0.0.4
+platform: ruby
+authors: 
+- James Lavin
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2011-10-07 00:00:00 Z
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: pdfkit
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 1
+        segments: 
+        - 0
+        - 5
+        version: "0.5"
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 15
+        segments: 
+        - 0
+        - 5
+        - 2
+        version: 0.5.2
+  type: :runtime
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: rspec
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id002
+description: Creates single PDF file from 1+ HTML pages using PDFKit
+email: 
+- htmls_to_pdf@futureresearch.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- .gitignore
+- README.markdown
+- examples/get_coffeescript.rb
+- examples/get_coffeescript_meet_backbone.rb
+- examples/get_exploring_coffeescript.rb
+- examples/get_python_book.rb
+- examples/get_ruby_book.rb
+- examples/get_rubygems_user_guide.rb
+- htmls_to_pdf.gemspec
+- lib/htmls_to_pdf.rb
+- lib/htmls_to_pdf/htmls_to_pdf.rb
+- lib/htmls_to_pdf/pdfkit_config.rb
+- lib/htmls_to_pdf/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 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.8.7
+signing_key: 
+specification_version: 3
+summary: Creates single PDF file from 1+ HTML pages
+test_files: []
+