Koupaliště Petynka - teplota vzduchu, vody a počet návštěvníků bez otvírání webového prohlížeče (Crystal)

petynka.cr

# coding: utf-8
# petynka.cr
#
# Extracts temperature and count of visitors from the website
# of Koupaliste Petynka, Prague

require "http/client"
require "http/headers"
require "option_parser"

def strip_xml_tags(str : String)
  str.gsub(/<.+?>/, "").gsub(/\s+/, ' ')
end

options = {
  :only_visitors => false,
  :url => "https://www.koupalistepetynka.cz/",
}
OptionParser.parse! do |parser|
  parser.on("-V", "--visitors", "Print visitor count only") do
    options[:only_visitors] = true
  end
  parser.on("-u URL", "--url=URL", "URL of the page to scrape (mostly for debugging purposes)") do |url|
    options[:url] = url
  end
end

headers = HTTP::Headers.new.add "User-Agent", "petynka.cr https://gist.github.com/igneus/3ea0627a515951a509c7"
response = HTTP::Client.get options[:url].as(String), headers
page = response.body

searched = [
  /<h1>(.+?)<\/h1>\s*<div class="description">teplota vody<\/div>/i,
  /<h1>(.+?)<\/h1>\s*<div class="description">teplota vzduchu<\/div>/i,
  /<h1>(.+?)<\/h1>\s*<div class="description text-uppercase">návštěvní(k|ci|ků)<\/div>/i,
]

if options[:only_visitors]
  match = page.match searched.last
  if match.nil?
    puts "?"
  else
    puts match[1]
  end
else
  puts Time::Format.new("%H:%M").format Time.now.to_local
  searched.each do |term|
    m = page.match(term)

    puts strip_xml_tags(m[0]) unless m.nil?
  end
end