Created
February 4, 2011 17:52
-
-
Save agmcleod/811447 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'csv' | |
require 'net/http' | |
obsolete_metros = [] | |
class OldMetro | |
attr_accessor :url, :state | |
def initialize(url, state) | |
@url = url | |
@state = state | |
end | |
def to_s | |
"#{@state}/#{@url}" | |
end | |
def urls | |
urls = [] | |
['Lawn-Care', 'Outdoor-Pest-Control', 'Tree-Shrub-Care'].each do |service| | |
urls << "/#{service}/#{@state}/#{@url}" | |
end | |
urls | |
end | |
end | |
CSV.foreach('FuegoMetros.csv') do |row| | |
obsolete_metros << OldMetro.new(row[1], row[4]) if row[2].nil? || row[2] == '' | |
end | |
sem_urls = [] | |
File.open('semurls.txt', 'r+') do |file| | |
file.each_line { |line| line.gsub(/\?/, '').strip!; sem_urls << line unless sem_urls.include?(line) } | |
end | |
sem_urls.each do |url| | |
is_obsolete = false | |
obsolete_metros.each do |obs| | |
if obs.urls.include?(url) | |
is_obsolete = true | |
break | |
end | |
end | |
unless is_obsolete | |
status = Net::HTTP.get_response(URI.parse(url)).inspect | |
if status.index('404') | |
puts url | |
end | |
end | |
end | |
# File.open('redirects.csv', 'w+') do |file| | |
# file.write("URLName,RedirectURL,StatusCode\n") | |
# ['Lawn-Care', 'Outdoor-Pest-Control', 'Tree-Shrub-Care'].each do |service| | |
# obsolete_metros.each do |obs| | |
# file.write("/#{service}/#{obs.state}/#{obs.url},/#{service}/#{obs.state},302\n") | |
# end | |
# end | |
# end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment