#!/usr/bin/ruby
 
require 'open-uri'
require 'time'
 
class Comment
  attr_accessor :author, :datewritten, :comment
  def initialize (author, datewritten, comment)
      @author, @datewritten, @comment = author, datewritten, comment
  end
end
 
class Post
  attr_accessor :author, :title, :datewritten, :body, :comments
  def initialize (author, title, datewritten, body)
    @author, @title, @datewritten, @body = author, title, datewritten, body
    @comments = []
  end
  def addcomment (author, datewritten, comment)
    @comments.push(Comment.new(author, datewritten, comment))
  end
end
 
class Ripper
  def initialize  
    @pages = []
    @posts = Array.new
  end
  def get (uri)
    connection = open(uri)  
    content = connection.read
    return content
  end
 
  def parse (uri)
    content = get(uri)
    #blogContentInfo points to links to posts
    links = content.scan(/class="blogContentInfo">.*?<a href=".*?">/m)
    links.each do |link|
        #Strip out the bullshit amazon links
        unless link =~ /amazon/
            #Pull the URL out of the link
            link = (/.*<a href="(.*)">/m).match(link)[1]
            @pages.push(link)
        end
    end
    #Checking if there are any older pages with a hyperlink
    if content =~ /\[.*?<a href="(.*?)">Older<\/a>/
      #If so, call itself recursively to pull out the rest
      #Myspace breaks the URI standard.  Replace the spaces with real escapes
      parse($1.gsub(/\s/, "%20"))
    else
      #Edge case to break out of the loop for when there aren't any more older
      parsepages()
    end
  end
 
  def parsepages()
    @pages.each do |uri|
      #Replace with yourself, if you want
      author = "Ryan"
      content = get(uri)
      #Pull out the fields I want
      title = (/blogSubject">(.*?)\n/m).match(content)[1]
      body = (/blogContent">(.*?)<table/m).match(content)[1]
      datewritten = (/blogTimeStamp">(.*?)<\/p>/m).match(content)[1].gsub(/(^\s+|\n+)/, "")
      time = (/blogContentInfo"><b>.*?(\d+:\d+)/m).match(content)[1]
      datewritten = datewritten + " #{time}:00"
      #Parse the time, and force it into something Wordpress can deal with
      t = Time.parse(datewritten)
      datewritten = t.strftime("%m/%d/%Y %H:%M:%S")
      puts "Title: #{title}\n"
      #Create a new Post object
      post = Post.new(author, title, datewritten, body)
      #Pull out an array of all the comment blocks
      comments = content.scan(/id="blogComments.*?commentSpacer/m)
      #Pass off the post object along with the list of comments
      parsecomments(comments, post)
    end
  end
 
  def parsecomments(comments, post)
    comments.each do |com|
      author = (/profileLinks">(.*?)</m).match(com)[1]
      puts "Author: #{author}\n"
      #MySpace decided to make the CSS ids identical here, except that the
      #actual comment doesn't have "Posted" after the closing tag
      #Filter it as such
      comment = (/blogCommentsContent">(.*?)<\/p>/m).match(com)[1]
      datewritten = (/blogCommentsContent">Posted by.*?> on(.*?)<b/m).match(com)[1].gsub(/\n|\t|\r/, "")
      t = Time.parse(datewritten)
      #The same datetime munging as before
      datewritten = t.strftime("%m/%d/%Y %H:%M:%S")
      #Commit each commment to our post object
      post.addcomment(author, datewritten, comment)
    end
  #Push them all into our class array
  @posts.push(post)
  end
 
  def print(file)
    @posts.each do |post|
      #Using Movable Type's export syntax, so I don't need to mess with XML
      #It's documented here: http://www.sixapart.com/moveabletype/docs/mtimport#example
      #Basically, 5 hyphens separates the categories
      #Eight hyphens separate each post
      file.puts "TITLE: #{post.title}"
      file.puts "AUTHOR: #{post.author}"
      file.puts "DATE: #{post.datewritten}"
      #Change this, too, if you want
      file.puts "CATEGORY: MySpace"
      file.puts "-----"
      #Get rid of empty lines and fucking Windows ^M newlines, plus convert &nbsp; to " "
      file.puts "BODY:\n#{post.body.gsub(/^(\s+|\t+|\n+)$/, "").gsub(/\015/, "").gsub(/&nbsp;/, " ")}"
      file.puts "-----"
      post.comments.each do |com|
        #More stuff is possible here, but isn't necessary
        file.puts "COMMENT:"
        file.puts "AUTHOR: #{com.author}"
        file.puts "DATE: #{com.datewritten}"
        file.puts "#{com.comment}"
        file.puts "-----"
      end
      file.puts "--------"
    end
  end
end
 
#Instantiate it
ripper = Ripper.new
#Parse my blog (substitute whatever yours is here)
ripper.parse("http://blog.myspace.com/lykurgos")
#Output it
 
output = File.open("posts.txt", "a")
ripper.print(output)
puts "Done!\n"
#Import into Wordpress!