Convert Wordpress xml export to Jekyll format using Markdown

wordpressxml2jekyll.rb

#!/usr/bin/env ruby

# Input: WordPress XML export file.
# Outputs: a series of Markdown files ready to be included in a Jekyll site,
# and comments.yml which contains all approved comments with metadata which
# can be used for a Disqus import.
# Changes from the original gist: http://gist.github.com/268428
# 1. Handles titles containing special characters. Those have to be YAML escaped
# 2. Use the original permalinks in wordpress.

require 'rubygems'
require 'hpricot'
require 'html2markdown'
require 'time'
require 'yaml'
require 'fileutils'
require 'uri'

WORDPRESS_XML_FILE_PATH = File.join(File.dirname(__FILE__), ARGV[0])
OUTPUT_PATH = File.join(File.dirname(__FILE__), "/_posts")
ORIGINAL_DOMAIN = "http://rubenlaguna.com"

class Post
  attr_accessor :title, :post_date, :created_at, :slug, :post_id, :content, :markdown_content
  attr_accessor :hpricot_element, :permalink, :categories

  def initialize(item)
    @hpricot_element = item

    @title = item.search("title").first.inner_text
    @permalink = item.at("link2").inner_text.gsub(/^#{ORIGINAL_DOMAIN}/,'').gsub(/\/$/,"/index.html")
    @permalink = URI.unescape(@permalink)
    puts "permalink #{@permalink}"

    @post_date = item.search("wp:post_date").first.inner_text
    @created_at = Date.parse(post_date)

    @slug = item.search("wp:post_name").first.inner_text

    @categories = []
    item.search("category").each { |cat|
      @categories << cat.inner_text
    }
    @categories.uniq!

    p @categories

    @post_id = item.at("wp:post_id").inner_text

    @content = item.search("content:encoded").first.inner_text
    text = HTMLPage.new :contents => content
    @markdown_content = text.markdown
  end

  def to_jekyll
    buf = ""
    buf << "---\n"
    buf << "layout: post\n"
    buf << "title: #{title}\n" #escape character in title
    buf << "permalink: #{permalink}\n"
    buf << "post_id: #{post_id}\n"
    buf << "categories: #{categories.to_yaml.gsub(/^---/,'').chomp}\n"
    buf << "---\n\n"
    buf << markdown_content
  end

  def save(root_path)
    File.open("#{root_path}/#{created_at}-#{slug}.md", "w") { |file| file.write self.to_jekyll }
    self
  end

  def save_comments(path)
    comment_elements = @hpricot_element.search("wp:comment").reject do |c|
      c.search("wp:comment_approved").inner_text != "1"
    end

    File.open("#{path}/comments.yml", "a") do |yaml_file|
      comment_elements.collect { |el| Comment.new(self, el) }.each { |comment| comment.write_to yaml_file }
    end
  end

  class << self
    def parse(element, path)
      return nil unless element.is_a?(Hpricot::Elem)
      post = Post.new(element)
      puts "saving post: #{post.title}"
      post.save(path)
    end
  end
end

class Comment
  attr_accessor :author_name, :author_email, :author_url, :content, :post

  def initialize(post, element)
    @post_id = post.post_id
    @post_title = post.title
    @author_name = element.search("wp:comment_author").first.inner_text
    @author_email = element.search("wp:comment_author_email").first.inner_text
    @author_url = element.search("wp:comment_author_url").first.inner_text
    @content = element.search("wp:comment_content").first.inner_text || ""

    comment_date = element.search("wp:comment_date_gmt").first.inner_text
    @created_at = Time.parse("#{comment_date} GMT")
  end

  def write_to(file)
    file.write self.to_yaml + "\n" unless @content.size == 0
  end
end

# main

file = File.open(WORDPRESS_XML_FILE_PATH,"rb");
contents = file.read
# Hpricot will destroy <link> contents as it expecting a <link href="">
# so we change link to link2 and Hpricot will leave it alone.
contents.gsub!(/link>/, "link2>")



doc = Hpricot(contents)

FileUtils.mkdir_p OUTPUT_PATH
File.open("#{OUTPUT_PATH}/comments.yml", "w") { |f| }

(doc / "item").each do |item|
  next unless item.search("wp:status").first.inner_text == "publish"
  post = Post.parse(item, OUTPUT_PATH)
  post.save_comments(OUTPUT_PATH)
end

yamlcomments2disqus.rb

#!/usr/bin/env ruby

# Takes comments.yml generated by wordpressxml2jekyll.rb and posts them to your Disqus forum.
# uses original WordPress post id as disqus_identifier 
# the user key for Disqus must be stored on API-KEY file
# Disqus ruby api http://disqus.rubyforge.org/
# sudo gem install disqus

require 'rubygems'
require 'disqus'
require 'disqus/api'
require 'yaml'


COMMENTS_YAML_FILE = "#{ENV['PWD']}/export/_posts/comments.yml"

file = File.open("API-KEY", "rb")
apikey = file.read
p "Using API-KEY: #{apikey}"
Disqus::defaults[:api_key] = apikey

forum_id = Disqus::Api.get_forum_list["message"].first["id"]
fak = Disqus::Api.get_forum_api_key(:forum_id => forum_id)["message"]

File.open(COMMENTS_YAML_FILE) do |yf|
  YAML.each_document( yf ) do |c|
    post_id = c.ivars["post_id"]
    post_title =  c.ivars["post_title"]
    
    puts "post_id:     #{post_id}"
    puts "post_title:  #{post_title}"
    
    thread = Disqus::Api.thread_by_identifier(:forum_api_key => fak, :title => post_title, :identifier => post_id)
    
    puts "======= thread_by_identifier result BEGIN ====="
    thread.each { |k,v| puts "#{k} => #{v}" }
    puts "======= thread_by_identifier result END ====="

    thread_id = thread["message"]["thread"]["id"]
    p "thread id:   #{thread_id}\n\n" 
    comment = Disqus::Api.create_post(:forum_api_key => fak,
                            :thread_id => thread_id,
                            :message => c.ivars["content"],
                            :author_name => c.ivars["author_name"],
                            :author_email => c.ivars["author_email"],
                            :author_url => c.ivars["author_url"],
                            :created_at => Time.parse(c.ivars["created_at"].to_s).strftime("%Y-%m-%dT%H:%M"))
    puts "======= create_post result BEGIN ====="
    comment.each { |k,v| puts "#{k} => #{v}" }
    puts "======= create_post result END ====="
  end
end