report.rb

#!/usr/bin/env ruby -wKU
# Create an XML report of all html files in a folder or any of its children
require 'rubygems'
require 'fileutils'
gem 'nokogiri'
require 'nokogiri'
#map the current folder
here = File.dirname(__FILE__)
#the URL to prepend to all filenames in this folder
base = 'http://example.com'
puts 'Deleting previous report' if ( File::exists?( File.join( here, 'report.xml' ) ) )
FileUtils::rm_rf( File.join( here, 'report.xml' ) )
builder = Nokogiri::XML::Builder.new(:encoding => 'UTF-8') do |xml|
  xml.links {
    Dir.glob( File.join(here, '**/*.html') ).each do | filename |
      relative_path = filename.sub( here, '' )
      doc = Nokogiri::HTML( File.read( filename ) )
      xml.link{
        xml.title( doc.at_css('title') ? doc.at_css('title').content : 'No title found' )
        xml.url( base + relative_path )
      }
    end
  }
end
# this next part is just to "pretty-print" the XML
xsl = Nokogiri::XSLT('<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
  <xsl:output method="xml" encoding="UTF-8"/>
  <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>')
report_output = File.open( File.join( here, 'report.xml' ),'wb', 0664 )
#apply the pretty-printer
report_output.print xsl.apply_to( builder.doc ).to_s
report_output.close
puts 'Report generated!!!'