WordPress to Textile Ruby script (I used a Textile plugin for WP). Parses all existing WP categories and tags into discreet list of categories. Finally forces all content to be UTF-8.

wp-xml-import.rb

require 'fileutils'
require 'date'
require 'yaml'
require 'rexml/document'

include REXML

doc = Document.new(File.new(ARGV[0]))

FileUtils.mkdir_p "_posts"

doc.elements.each("rss/channel/item[wp:status = 'publish' and wp:post_type = 'post']") do |e|
  p e.elements['wp:post_name'].text
  post = e.elements
  slug = post['wp:post_name'].text
  date = DateTime.parse(post['wp:post_date'].text)
  name = "%02d-%02d-%02d-%s.textile" % [date.year, date.month, date.day, slug]
  date_string = "#{date.year}-#{date.month}-#{date.day}"

  # convert all tags and categories into categories
  categories = []
  post.each('category') do |cat|
    categories << cat.text
  end

  content = post['content:encoded'].text.encode("UTF-8")

  # convert <code></code> blocks to {% codeblock %}{% encodebloc %}
  #content = content.gsub(/<code>(.*?)<\/code>/, '`\1`')
  content = content.gsub(/<code>/, '{% codeblock %}')
  content = content.gsub(/<\/code>/, '{% endcodeblock %}')

  # convert <pre></pre> blocks to {% codeblock %}{% encodebloc %}
  #content = content.gsub(/<pre lang="([^"]*)">(.*?)<\/pre>/m, '`\1`')
  content = content.gsub(/<pre>/, '{% codeblock %}')
  content = content.gsub(/<pre lang="([^"]*)">/, '{% codeblock %}')
  content = content.gsub(/<\/pre>/m, '{% endcodeblock %}')

  # convert headers
  (1..3).each do |i|
    content = content.gsub(/<h#{i}>([^<]*)<\/h#{i}>/, ('#'*i) + ' \1')
  end

  puts "Converting: #{name}"

  data = {
    'layout' => 'post',
    'title' => post['title'].text,
    'date' => date_string,
    'comments' => true,
    'categories' => categories,
  }.delete_if { |k,v| v.nil? || v == ''}.to_yaml

  File.open("_posts/#{name}", "w") do |f|
    f.puts data
    f.puts "---"
    f.puts content
  end

end