Týden vědy 2015 Praha v CSV

tydenvedy-2015-praha.csv

tydenvedy-to-csv.rb

#!/usr/bin/env ruby
#
# This is free and unencumbered software released into the public domain.
#
# Anyone is free to copy, modify, publish, use, compile, sell, or
# distribute this software, either in source code form or as a compiled
# binary, for any purpose, commercial or non-commercial, and by any
# means.

###############################################################################
# Quick & dirty script to extract events from http://www.tydenvedy.cz to CSV. #
#                                                                             #
# Usage:                                                                      #
#   gem install active_support httparty oga                                   #
#   ruby tydenvedy-to-csv.rb Praha output.csv                                 #
###############################################################################

require 'active_support/core_ext/object'
require 'httparty'
require 'oga'
require 'ostruct'

LOCATION = ARGV[0] || 'Praha'
CSV_FILE = ARGV[1] || "tydenvedy-#{YEAR}-#{LOCATION}.csv"
YEAR = 2015

BASE_URL = 'http://www.tydenvedy.cz'
PAGE_LIMIT = 2000
SEARCH_URL = "#{BASE_URL}/sys/search.jsp?fulltext_search_all_words=#{LOCATION}\
&fulltext_search_pager_number_of_pages=#{PAGE_LIMIT}&search=Hledat&fulltext_search_file_formats=anytype\
&fulltext_search_date=anytime&order_asc=true&order_title=true&q1=#{LOCATION}&searchFields=keywords"

fetch_html = ->(url) do
  Oga.parse_html(HTTParty.get(url).body)
end

parse_event_page = ->(doc) do
  OpenStruct.new(
    title:        doc.at_css('h1').text.strip,
    date:         (doc.at_css('.bluebox').try(:text) || '').gsub("\n", ' ').strip,
    location:     doc.at_css('#m2-event-detail a').text.gsub("\n", ' ').strip,
    location_url: doc.at_css('#m2-event-detail a').get('href'),
    types:        doc.css('.event-keyw1').map(&:text),
    topics:       doc.css('.event-keyw2').map(&:text),
    booking:      !!doc.at_css('#rezervuj'),
    info_url:     BASE_URL + doc.at_css('form input[type="hidden"]').get('value')
  )
end

puts "Fetching events in #{LOCATION} (this may take few minutes) ..."

events = fetch_html.(SEARCH_URL).css('.record').lazy
  .map { |record| BASE_URL + record.at_css('h3 a').get('href') }
  .map(&fetch_html)
  .map(&parse_event_page)

CSV.open(CSV_FILE, 'w', force_quotes: true) do |csv|
  csv << %w{title date location types topics booking location_url info_url}
  events.each do |e|
    csv << [e.title, e.date, e.location, e.types.join(', '), e.topics.join(', '), e.booking, e.location_url, e.info_url]
  end
end