Set spotlight searchable content scraped from web to FinderComment for webloc

webloc-spotlight.rb

#!/usr/bin/ruby

require 'tempfile'
require 'open-uri'
require 'rubygems'
require 'sanitize'
require 'nokogiri'

webloc = ARGV[0]

tf = Tempfile.new('webloc-spotlight')
tf.write(File.read(webloc))
tf.close
system 'plutil', '-convert', 'xml1', tf.path
f = tf.open
doc = Nokogiri::XML(f)
tf.close(true)

url = doc.xpath('/plist/dict/string').text

html = open(url).read

sanitized_html = Sanitize.clean html, :remove_contents => %w(script style)

tf = Tempfile.new('webloc-spotlight')
tf.write(<<EOL)
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<string>#{sanitized_html}</string>
</plist>
EOL
tf.close
system 'plutil', '-convert', 'binary1', tf.path
attr = `xxd -ps #{tf.path}`
tf.close(true)

exec 'xattr', '-wx', 'com.apple.metadata:kMDItemFinderComment', attr, webloc

worked on Mac OS only. ;-)