download slideshare slide as PDF

slideshare.rb

#!/usr/bin/env ruby

require 'nokogiri'
require 'open-uri'
require 'prawn'

url = "http://www.slideshare.net/nippondanji/db-engineerstudyanim"

charset = nil
html = open(url) do |f|
  charset = f.charset
  f.read
end

doc = Nokogiri::HTML.parse(html,nil,charset)

item = doc.xpath('/html/head/meta[@name="thumbnail"]').first
thumbnail_url = item.attributes["content"].value

xml_url = thumbnail_url.gsub(/phpapp(\d+)?(.+)$/,'phpapp\1').gsub(/ss_thumbnails\//,'') + ".xml"
xml = open(xml_url) do |f|
  f.read
end

xml_doc = Nokogiri::XML(xml)
slide_count = xml_doc.xpath("/Show/Slide").count
slide_name = tthumbnail_url.match(/ss_thumbnails\/(.+phpapp\d+)/)[1]

pdf_name = "#{slide_name}.pdf"
pdf_file = Tempfile.new(pdf_name)

Dir.mktmpdir do |dir|
  Dir.chdir(dir) do
    
    slide_count.times do |i|
      path = "http://image.slidesharecdn.com/#{slide_name}/95/slide-#{i+1}-1024.jpg"
      puts "downloading #{path} ..."
      filename = File.basename(path)
      open(filename, 'wb') do |out|
        open(path) do |data|
          out.write(data.read)
        end
      end
    end
    images = Dir.glob("slide-*.jpg")
    images = images.sort_by{|str| str[/\d+/].to_i}

    puts "generating #{pdf_file.path} ..."

    Prawn::Document.generate(
      pdf_file.path,
      page_size:[1024,768],
      margin:0
    ) do
      images.each do |img|
        image(
          img,
          fit:[1024,768]
        )
        start_new_page
      end
    end
  end
end

puts pdf_file.path

new_name = pdf_file.path.gsub(/\.pdf(.+)$/,'.pdf')
File.rename(pdf_file.path, new_name)

FileUtils.copy(new_name, "./")

pdf_file.unlink