gistfile1.rb

require "nokogiri"

BASE_DIR = "../support_vector_machine/data/female_blogs"
TARGET_DIR = "../support_vector_machine/data/female_posts"

Dir["#{BASE_DIR}/*"].each do |path|
  blog = Nokogiri::XML(File.open(path))
  posts = blog.xpath("//post")

  extension = File.extname(path)
  basename  = File.basename(path, extension)

  posts.each_with_index do |post, index|
    new_path = File.join(TARGET_DIR, basename + "_" + index.to_s + extension)
    File.write(new_path, post.text)
  end 
end