wpxml_parser 0.0.1

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2010 Maxim Chernyak
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,51 @@
+wpxml_parser
+============
+
+WordPress (version 3.x and I think there's a plugin for 2.x) can export xml with all your blog posts, comments, etc. This tool can parse the xml file and give you a convenient access to all your posts, comments, categories, etc in a ruby script that _you have to write_.
+
+The cool thing is — you don't even need to have access to your own WordPress database, all you need is to download the xml file from your admin panel.
+
+### Let me demonstrate
+
+    require 'wpxml_parser'
+    include WpxmlParser
+    
+    # Blog
+    blog = Blog.new('dump_of_your_blog.xml')
+    blog.posts.size # => 51
+    post = blog.posts.first # => <Post>
+    
+    # Post
+    post.title # => "Title of your post"
+    post.categories # => ["ruby", "rails"]
+    post.date # => <Time>
+    post.slug # => "title-of-your-post"
+    post.body # => "...shitload of text..."
+    post.post_id # => 27
+    
+    # Comments
+    post.comments # => [<Comment>, <Comment>, ...]
+    comment = post.comments.first
+    
+    comment.author # => 'dude'
+    comment.date # => <Time>
+    
+    # Comments have parent and children
+    comment.parent_id # => 32
+    comment.parent # => <Comment>
+    comment.children # => [<Comment>, <Comment>]
+
+    # Conveniences
+    # You can quickly find a post or a comment by post_id or comment_id respectively
+    blog.find_post(27) # => <Post>
+    post.find_comment(32) # => <Comment>
+    
+    # For more info and more accessible properties check out the source code, it's pretty straightforward.
+
+### A note on posts
+
+Currently only published posts are included. Drafts, private, etc are skipped. This was done on purpose, since I didn't really use those wordpress features.
+
+### A note on comments
+
+Currently only approved comments are included. This was done on purpose, since I didn't need spam.

data/lib/wpxml_parser.rb

@@ -0,0 +1,4 @@
+require 'wpxml_parser/blog'
+require 'wpxml_parser/entity'
+require 'wpxml_parser/comment'
+require 'wpxml_parser/post'

data/lib/wpxml_parser/blog.rb

@@ -0,0 +1,28 @@
+require 'nokogiri'
+require File.dirname(__FILE__) + '/post'
+
+module WpxmlParser
+  class Blog
+    def initialize(xml_filename)
+      File.open(xml_filename) do |xml_file|
+        @xml = Nokogiri::XML(xml_file)
+      end
+    end
+    
+    def posts
+      @xml.xpath('//item').map do |item|
+        Post.new(item)
+      end.select{|p| p.post_type == 'post' && p.status == 'publish'}
+    end
+
+    def find_post(post_id)
+      posts.find{|p| p.post_id == post_id}
+    end
+
+    def attachments
+      @xml.xpath('//item').map do |item|
+        Post.new(item)
+      end.select{|p| p.post_type == 'attachment'}
+    end
+  end
+end

data/lib/wpxml_parser/comment.rb

@@ -0,0 +1,56 @@
+require 'time'
+require File.dirname(__FILE__) + '/entity'
+
+module WpxmlParser
+  class Comment < Entity
+    def initialize(entity, post)
+      super(entity)
+      @post = post
+    end
+    
+    def self.method_element_map
+      { :comment_id => 'wp:comment_id',
+        :author     => 'wp:comment_author',
+        :email      => 'wp:comment_author_email',
+        :url        => 'wp:comment_author_url',
+        :ip         => 'wp:comment_author_ip',
+        :date       => 'wp:comment_date',
+        :date_gmt   => 'wp:comment_date_gmt',
+        :body       => 'wp:comment_content',
+        :approved   => 'wp:comment_approved',
+        :parent_id  => 'wp:comment_parent' }
+    end
+
+    def parent
+      @post.comments.find{|c| c.comment_id == parent_id }
+    end
+
+    def children
+      @post.comments.select{|c| c.parent_id == comment_id}
+    end
+
+    def approved?
+      approved == '1'
+    end
+
+    def process_comment_id(comment_id)
+      comment_id.to_i
+    end
+    
+    def process_parent_id(parent_id)
+      parent_id.to_i
+    end
+
+    def process_comment_id(comment_id)
+      comment_id.to_i
+    end
+
+    def process_date(date)
+      Time.parse(date)
+    end
+
+    def process_date_gmt(date)
+      Time.parse(date)
+    end
+  end
+end

data/lib/wpxml_parser/entity.rb

@@ -0,0 +1,19 @@
+module WpxmlParser
+  class Entity
+    def initialize(entity)
+      @entity = entity
+    end
+
+    def method_missing(meth, *args, &blk)
+      if self.class.method_element_map.keys.include?(meth)
+        if (public_methods - Object.public_methods).include?("process_#{meth}")
+          send("process_#{meth}", @entity.xpath(self.class.method_element_map[meth]).first.content)
+        else
+          @entity.xpath(self.class.method_element_map[meth]).first.content
+        end
+      else
+        super
+      end
+    end
+  end
+end

data/lib/wpxml_parser/post.rb

@@ -0,0 +1,40 @@
+require File.dirname(__FILE__) + '/entity'
+require File.dirname(__FILE__) + '/comment'
+
+module WpxmlParser
+  class Post < Entity
+    def self.method_element_map
+      { :title     => 'title',
+        :link      => 'link',
+        :date      => 'pubDate',
+        :author    => 'dc:creator',
+        :body      => 'content:encoded',
+        :post_id   => 'wp:post_id',
+        :slug      => 'wp:post_name',
+        :status    => 'wp:status',
+        :post_type => 'wp:post_type' }
+    end
+
+    def categories
+      @entity.xpath('category').map(&:content).uniq
+    end
+  
+    def comments
+      @entity.xpath('wp:comment').map do |comment|
+        Comment.new(comment, self)
+      end.select(&:approved?)
+    end
+    
+    def find_comment(comment_id)
+      comments.find{|c| c.comment_id == comment_id}
+    end
+    
+    def process_date(date)
+      Time.parse(date)
+    end
+
+    def process_post_id(post_id)
+      post_id.to_i
+    end
+  end
+end

metadata

@@ -0,0 +1,88 @@
+--- !ruby/object:Gem::Specification 
+name: wpxml_parser
+version: !ruby/object:Gem::Version 
+  hash: 29
+  prerelease: false
+  segments: 
+  - 0
+  - 0
+  - 1
+  version: 0.0.1
+platform: ruby
+authors: 
+- Maxim Chernyak
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-08-14 00:00:00 -04:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: nokogiri
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :runtime
+  version_requirements: *id001
+description: Convenient parser that provides a clean way to interact with wordpress's XML dump file in your ruby scripts, to make it easy to migrate away from WordPress anywhere else.
+email: max@bitsonnet.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- lib/wpxml_parser/blog.rb
+- lib/wpxml_parser/comment.rb
+- lib/wpxml_parser/entity.rb
+- lib/wpxml_parser/post.rb
+- lib/wpxml_parser.rb
+- LICENSE
+- README.md
+has_rdoc: true
+homepage: http://github.com/maxim/wpxml_parser
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 19
+      segments: 
+      - 1
+      - 3
+      - 4
+      version: 1.3.4
+requirements: []
+
+rubyforge_project: wpxml_parser
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: Convenient WordPress XML dump parser.
+test_files: []
+