Parse postdoc URIs from sitemap

postdocs.rb

require 'nokogiri'
require 'open-uri'

sitemaps = [
  'https://www.clir.org/page-sitemap1.xml',
  'https://www.clir.org/page-sitemap2.xml'
]

xml = Nokogiri::XML(URI.open(sitemaps[0]))
# urls = xml.search('url')
# puts "before: #{urls.count}"

sitemaps.drop(1).each do |sitemap|
  s = Nokogiri::XML(URI.open(sitemap))
  url = s.search('url')
  xml.at('urlset').add_child(url)
end

pages = xml.search('loc:contains("postdoc")')
pages.each do |page|
  puts page.text
end