From bab178d9f8502e6941e75dbba1631d26f246fab4 Mon Sep 17 00:00:00 2001 From: Stephen McDonald Date: Thu, 29 Dec 2011 11:37:46 +1100 Subject: [PATCH] Strip HTML from any caption-based titles. --- lib/jekyll/migrators/tumblr.rb | 2 ++ 1 file changed, 2 insertions(+) diff --git a/lib/jekyll/migrators/tumblr.rb b/lib/jekyll/migrators/tumblr.rb index cc318ca0..d1df9678 100644 --- a/lib/jekyll/migrators/tumblr.rb +++ b/lib/jekyll/migrators/tumblr.rb @@ -1,6 +1,7 @@ require 'rubygems' require 'open-uri' require 'fileutils' +require 'nokogiri' require 'date' require 'json' require 'uri' @@ -89,6 +90,7 @@ module Jekyll end end date = Date.parse(post['date']).to_s + title = Nokogiri::HTML(title).text slug = title.downcase.strip.gsub(' ', '-').gsub(/[^\w-]/, '') { :name => "#{date}-#{slug}.#{format}",