#!/usr/bin/ruby
puts "Content-Type: text/html\n\n"
require 'net/http'
require 'uri'
require 'open-uri'
require 'date'
@@begin_time = Time.now
def check_urls(url, iterate)
puts "<h3>Checking URLS</h3>"
puts "<ul>"
iterate.times do |i|
uri_output = Net::HTTP.get(URI.parse(url[i])).scan(/\d{2}\.\d{2}\.\d{4}/)[0]
site_kind = Net::HTTP.get(URI.parse(url[i])).include? "SPECIAL"
if uri_output == nil
puts "<li>[NOTHING FOUND] <a href='" + url[i] + "' target='_blank'>" + url[i] + "</a></li>"
else
site_date = Date.strptime(uri_output, "%d.%m.%Y")
current_date = Date.today
difference = current_date - chart_date
if site_kind == true && difference > 7
puts "<li>[NOT UPDATED] #{site_date} <a href='" + url[i] + "' target='_blank'>" + url[i] + "</a></li>"
else
if site_kind == false && difference > 1
puts "<li>[NOT UPDATED] #{site_date} <a href='" + url[i] + "' target='_blank'>" + url[i] + "</a></li>"
else
puts "<li>[OK] #{site_date} <a href='" + url[i] + "' target='_blank'>" + url[i] + "</a></li>"
end
end
end
end
puts "</ul>"
puts "</ul> <strong>ALL DONE</strong>"
executed_time = Time.now - @@begin_time
to_minutes(executed_time)
end
def to_minutes(seconds)
min = (seconds/60).floor
sec = (seconds - (min * 60)).round
if min < 10
min = "0#{min}"
end
if sec < 10
sec = "0#{sec}"
end
puts "in <strong>#{min}:#{sec}</strong>"
end
websites = IO.read('websites.txt').split
number_of_lines = websites.length
check_urls(websites, number_of_lines)
Refactorings
No refactoring yet !
Adam
March 4, 2009, March 04, 2009 19:45, permalink
No rating.
Login to rate!
require 'rubygems'
require 'uri'
require 'net/http'
require 'markaby'
require 'activesupport'
require File.dirname(__FILE__) + '/lib/website.rb'
require File.dirname(__FILE__) + '/lib/website_view.rb'
require File.dirname(__FILE__) + '/lib/website_controller.rb'
if __FILE__ == $0
controller = WebsiteController.new(File.readlines('websites.txt'))
puts controller.render_results
end
class Website
attr_reader :source, :uri
def initialize(uri)
@uri = uri.is_a?(URI) ? uri : URI.parse(uri)
@source = Net::HTTP.get(@uri)
end
def success?
source
end
def last_update
Date.parse(source[/\d{2}\.\d{2}\.\d{4}/])
rescue
Date.today
end
def distance_of_last_update
Date.today - last_update
end
def special?
source.include?('SPECIAL')
end
def url
uri.to_s
end
end
module WebsiteView
def render
html do
body do
h3 'Checking URLS'
ul do
@websites.each do |website|
li do
if website.success?
if (website.special? && website.distance_of_last_update > 7) ||
(!website.special? && website.distance_of_last_update > 1)
span '[NOT UPDATED]', :class => 'status'
else
span '[OK]', :class => 'status'
end
span website.last_update, :class => 'last_update'
else
span '[FAILED]', :class => 'last_update'
end
a website.url, :href => website.url, :target => '_blank'
end
end
end
end
end
end
end
class WebsiteController
attr_reader :urls, :render_results
def initialize(urls)
@websites = urls.map { |url| Website.new(url) }
@render_results = render
end
def render(view = WebsiteView)
builder = Markaby::Builder.new
builder.extend(view)
attach_instance_variables!(builder)
builder.render
end
protected
def attach_instance_variables!(object)
instance_variables.each do |variable_name|
object.instance_variable_set(variable_name, instance_variable_get(variable_name))
end
end
end
Jonathan Parker
March 6, 2009, March 06, 2009 04:20, permalink
No rating.
Login to rate!
You will need to make the code multi-threaded in order to get any significant performance gain.
See here fore details: http://www.tutorialspoint.com/ruby/ruby_multithreading.htm
Krist0ff
March 7, 2009, March 07, 2009 00:25, permalink
No rating.
Login to rate!
#!/usr/bin/ruby
puts "Content-Type: text/html\n\n"
require 'net/http'
require 'uri'
require 'open-uri'
require 'date'
def check_urls(websites)
begin_time = Time.now
puts "<h3>Checking URLS</h3>
<ul>"
websites.each do |url|
puts "<li>#{result_for(url)}<a href='#{url}' target='_blank'>#{url}</a></li>"
end
puts "</ul>
<strong>ALL DONE</strong> in <strong>#{to_minutes(Time.now - begin_time)}</strong>"
end
def result_for(url)
output = Net::HTTP.get(URI.parse(url))
uri_output = output.scan(/\d{2}\.\d{2}\.\d{4}/)[0]
site_kind = output.include? "SPECIAL"
if uri_output.nil?
"[NOTHING FOUND]"
else
site_date = Date.strptime(uri_output, "%d.%m.%Y")
current_date = Date.today
difference = current_date - site_date
if (site_kind && difference > 7) || (!site_kind && difference > 1)
status = "[NOT UPDATED]"
else
status = "[OK]"
end
"#{status} #{site_date}"
end
end
def to_minutes(seconds)
min = (seconds/60).floor
sec = (seconds - (min * 60)).round
"#{"%02d" % min}:#{"%02d" % sec}"
end
websites = IO.read('websites.txt').split
check_urls(websites)
Hi Everyone,
I've created a ruby script that checks several (fake/local) websites whether it's up-to-date or not by just doing a comparison on the date listed on the site.
The condition is: each site must not be older then 1 day.
If however it's a "special" site (by simply looking if the text "special" is present on the site) then it shouldn't be older then 7 days.
Now the thing is, I've created a ruby script to check all of this, and it works perfectly fine though. However I really don't like the way the code looks. Also I think it's quite a bit slow, I believe it can be much faster if the code is well optimized.
As you can see in my script below it does the following things:
1. It does two regular expressions, one for the date that is on the site, and one to see wheater it's a "special" site of not.
2. It compares the date on the site with the current date (Date.today)
3. And some If and else statements to see if a site is up-to-date.
Any idea how to optimize this? Any suggestions will be very appreciated.
Many thanks in advance....