#!/usr/bin/ruby -w
# author: rgollapudi
# description: Script to fetch all your twitter favorites and write them to a csv file

require 'open-uri'
require 'rss/1.0'
require 'rss/2.0'

# For reading rss from a url:
# refer http://benwoodall.com/2010/10/ruby-rss-parser/
#

# Open a file for exporting all favorites from the rss
$i = 1
$csv = File.open('mytwitfavs.csv', 'w')
$username = 'rajeshgollapudi'

#
# gets 20 favorites from twitter rss
#
def getfavorites
  url = "http://twitter.com/favorites/#{$username}.rss"
  unless $i == 1
    url = url+"?page=#{$i}"
  end
  puts "url : " + url
  content = ''
  open(url) do |parse|
    content = parse.read
  end

  rss = RSS::Parser.parse(content, false)
  return rss
end

def writefavorites(rss)
  # Output the feeds title, URL, and number of entries
  puts "=================================="
  puts "Title: #{rss.channel.title}"
  puts "URL: #{rss.channel.link}"
  puts "Total Entries: #{rss.items.size}"
  puts "=================================="

  # Setup to read feed and parse all items
  # Change for this: parse top 5 posts, ask if more, (Y/N?), get/end

  rss.items.each do |item|
     puts "Title: #{item.title}"
     puts "Published: #{item.date}"
  #     puts "#{item.description}"
     puts "=================================="
     $csv << ["#{item.title}", "#{item.date}\n"]
  end
end
#
# => write the fetched rss to a file
#
rss = getfavorites() # => call once to initialize the loop
size = rss.items.size
writefavorites(rss)
while size > 0
  $i += 1
  rss = getfavorites()
  size = rss.items.size
  writefavorites(rss)
end

# close the file handle
$csv.close()

#!/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')

#!/usr/local/bin/ruby -w
require 'csv'
CSV.foreach("contacts.csv") do |row|
  name = row[0]
  if name.nil?
#  do nothing
  elsif name.empty?
#  do nothing
  else
    command = "google calendar add --cal \"Finelighters Birthdays\" \"#{name}'s Birthday #{row[1]}\""
    puts command
    `#{command}`
  end
end