Quick little script to fetch all the meta tags from a website and export them to excel

meta-fetcher.rb

#!/usr/bin/ruby -w
require 'rubygems'
require 'hpricot'
require 'open-uri'
require 'spreadsheet'

class MetaReader 
  attr_reader :url, :outFile, :links, :book, :sheet1, :rownum
  attr_accessor :url, :outFile, :links, :book, :sheet1, :rownum

  def initialize(url, outFile)
    @url = url
    @outFile = outFile
    @links = {}
    @rownum = 0
    @book = Spreadsheet::Workbook.new
    @sheet1 = book.create_worksheet
  end

  def writeMeta(tempurl)
    fullurl = "#{url}#{tempurl}"
    puts tempurl
    outFile.puts "#{tempurl}\n\n"
    keywords = ''
    desc = ''
    begin
      doc = Hpricot(open(tempurl)) # open web page
      doc.search('meta').each do |meta|
        if meta.attributes['name'] =~ /keywords|description/
          outFile.puts "#{meta.attributes['name']}: #{meta.attributes['content']}"
          if meta.attributes['name'] == 'keywords'
            keywords = meta.attributes['content']
          else
            desc = meta.attributes['content']
          end
        end
      end
      sheet1.row(rownum).push tempurl, keywords, desc
      @rownum += 1
      
      doc.search("a[@href]").each do |param| # for every link do
        param_string = param.to_s
        href = param.attributes['href']
        unless (href =~ /\.pdf|\.jpg|\.mp3|\.flv|\.jpeg|\.flv|\.swf|netreturns|staywellsolutions|javascript\:|mailto/i)
          href = param.attributes['href']
          href = href.gsub(/\.\./,'')
          if(href =~ /http|www/ )
            if (!links["#{href}"] && href =~/nch\.org/)
              links["#{href}"] = 1
              writeMeta("#{href}")
            end
          elsif href=~/^\//
            href = href.gsub(/\/\//,'')
            unless (links["#{url}#{href}"])
              links["#{url}#{href}"] = 1
              writeMeta("#{url}#{href}") 
            end
          else
            href = href.gsub(/\/\//,'')
            unless (links["#{url}/#{href}"])
              links["#{url}/#{href}"] = 1
              writeMeta("#{url}/#{href}") 
            end
          end
        end
      end
      book.write "links.xls"
    rescue OpenURI::HTTPError => e
      puts "The '#{tempurl}' page is not accessible, error #{e}"
      sheet1.row(rownum).push tempurl, '', '', "#{e}"
      @rownum += 1
    rescue SocketError => e
      puts "The '#{tempurl}' page is not accessible, error #{e}"
      sheet1.row(rownum).push tempurl, '', '', "#{e}"
      @rownum += 1
    rescue ECONNRESET => e
      puts "The '#{tempurl}' page is not accessible, error #{e}"
      sheet1.row(rownum).push tempurl, '', '', "#{e}"
      @rownum += 1
    end
  end
end

myfile = File.new('links.html', 'w') # the output file
MetaReader.new("http://www.example.com", myfile).writeMeta('http://www.example.com')