Created
August 9, 2011 01:56
-
-
Save zanshin/1133266 to your computer and use it in GitHub Desktop.
WordPress to Markdown ruby script. Parses existing WP categories into discreet list of categories. Also identifies link-style postings and sets a YAML attribute to identify those entries. Finally forces all content to be UTF-8.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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| | |
post = e.elements | |
slug = post['wp:post_name'].text | |
date = DateTime.parse(post['wp:post_date'].text) | |
name = "%02d-%02d-%02d-%s.markdown" % [date.year, date.month, date.day, slug] | |
date_string = date.year.to_s + "-" + date.month.to_s + '-' + date.day.to_s | |
# clean up years of category randomness in one fell swoop. | |
case post['category'].text | |
when "diversions", | |
"elsewhere", | |
"family", | |
"health", | |
"life", | |
"meme", | |
"nerdliness", | |
"photography", | |
"random", | |
"relationships", | |
"social issues" | |
category_string = post['category'].text | |
link_string = false | |
when "links" | |
category_string = post['category'].text | |
link_string = true | |
else | |
category_string = "life" | |
link_string = false | |
end | |
content_text = post['content:encoded'].text | |
content = content_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 %}') | |
(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' => category_string, | |
'link' => link_string | |
}.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 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment