Fetch a sitemaps.org-compatible sitemap file and output all of its URLs on the command-line

sitemap.rb

#!/usr/bin/env ruby
#
# sitemap
#
# Author: Rob Miller <rob@bigfish.co.uk>
#
# Fetches and parses a sitemaps.org-compatible sitemap file, outputting
# all of the URLs stored in it; useful to start a spidering process, or
# to generate a list of URLs to later redirect.
#
# It works with nested sitemap files as well as ordinary ones.
#
# Usage:
#
#   $ sitemap https://example.com/sitemap.xml
#
# Requirements:
#
#   - Ruby >1.9.2
#   - The sitemap-parser gem:
#
#       $ gem install sitemap-parser

gem "sitemap-parser", "~> 0.4.0"
require "sitemap-parser"

url = ARGV[0]
unless url
  abort "Usage: sitemap URL"
end

begin
  sitemap = SitemapParser.new(url, recurse: true)

  sitemap.to_a.each do |url|
    puts url
  end
rescue Exception => e
  abort "Something terrible went wrong: #{e.message}"
end