Quick Way to make Minified HTML readable

html_clenser.rb

#!/usr/bin/env ruby

SOURCE_PAGE="http://google.com/"
DEST_FILE="formatted-google-homepage.html"

require "nokogiri"
require "open-uri"

pretty_print_xsl = <<-EOS
<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
  <xsl:output method="xml" encoding="ISO-8859-1"/>
  <xsl:param name="indent-increment" select="'   '"/>
  
  <xsl:template name="newline">
    <xsl:text disable-output-escaping="yes">
</xsl:text>
  </xsl:template>
  
  <xsl:template match="comment() | processing-instruction()">
    <xsl:param name="indent" select="''"/>
    <xsl:call-template name="newline"/>    
    <xsl:value-of select="$indent"/>
    <xsl:copy />
  </xsl:template>
  
  <xsl:template match="text()">
    <xsl:param name="indent" select="''"/>
    <xsl:call-template name="newline"/>    
    <xsl:value-of select="$indent"/>
    <xsl:value-of select="normalize-space(.)"/>
  </xsl:template>
    
  <xsl:template match="text()[normalize-space(.)='']"/>
  
  <xsl:template match="*">
    <xsl:param name="indent" select="''"/>
    <xsl:call-template name="newline"/>    
    <xsl:value-of select="$indent"/>
      <xsl:choose>
       <xsl:when test="count(child::*) > 0">
        <xsl:copy>
         <xsl:copy-of select="@*"/>
         <xsl:apply-templates select="*|text()">
           <xsl:with-param name="indent" select="concat ($indent, $indent-increment)"/>
         </xsl:apply-templates>
         <xsl:call-template name="newline"/>
         <xsl:value-of select="$indent"/>
        </xsl:copy>
       </xsl:when>       
       <xsl:otherwise>
        <xsl:copy-of select="."/>
       </xsl:otherwise>
     </xsl:choose>
  </xsl:template>    
</xsl:stylesheet>
EOS

source_html = open(SOURCE_PAGE) { |f| f.read }
xsl = Nokogiri::XSLT(pretty_print_xsl)
html = Nokogiri(source_html)

File.open(DEST_FILE, 'w') { |f| f << xsl.apply_to(html).to_s }