scrapers/staatsoperette/scrape.rb

60 lines
1.1 KiB
Ruby

#!/usr/bin/env ruby
# coding: utf-8
require 'open-uri'
require 'json'
require 'nokogiri'
require 'erb'
events = []
url = "https://www.staatsoperette.de/spielplan/"
STDERR.puts "GET #{url}"
doc = Nokogiri::HTML URI.open(url)
doc.css(".performance").each do |content|
event_link = URI::join url, content.css("h2 a").attr("href")
ical_link = URI.join url, content.css("a[href$='.ics']").attr('href')
event_line = false
has_url = false
STDERR.puts "GET #{ical_link}"
ical = URI.open(ical_link).read
events.push ical.lines.collect { |line|
case line.chomp
when "BEGIN:VEVENT"
event_line = true
line
when "END:VEVENT"
event_line = false
if has_url
line
else
["URL:#{event_link}\n", line]
end
when /URL:/
if event_line
has_url = true
line
else
[]
end
else
event_line ? line : []
end
}.flatten.join
end
ical = ERB::new <<~EOF
BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
X-WR-TIMEZONE;VALUE=TEXT:Europe/Berlin
<%= events.join "\n" %>
END:VCALENDAR
EOF
puts ical.result