Created
September 20, 2017 14:35
-
-
Save sinsoku/9db4084e1e21c89333d4ff7eac005ab8 to your computer and use it in GitHub Desktop.
RubyKaigi のスポンサーを取得するスクリプト
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env ruby | |
# frozen_string_literal: true | |
require 'nokogiri' | |
require 'open-uri' | |
Sponsor = Struct.new("Sponsor", :name, :url, :year) | |
RUBYKAIGI_URL = "http://rubykaigi.org/" | |
sponsors = [] | |
def search_sponsors(doc, year) | |
query = year < 2015 ? "#sponsors .name a" : ".sponsor__name a" | |
doc.css(query).map { |el| Sponsor.new(el.text, el["href"], year) } | |
end | |
(2013..2017).reverse_each do |year| | |
url = "#{RUBYKAIGI_URL}/#{year}/sponsors" | |
puts "#{url}: Now scraping..." | |
doc = Nokogiri::HTML(open(url)) | |
sponsors += search_sponsors(doc, year) | |
end | |
puts "Generate ranking" | |
ranking = sponsors.map do |sponsor| | |
years = sponsors.select { |obj| obj.name == sponsor.name || obj.url == sponsor.url }.map(&:year) | |
[sponsor, years.sort] | |
end.sort_by { |_, years| [years.size, years.join(", ")] } | |
puts "-" * 30 | |
output = [] | |
ranking.reverse_each do |sponsor, years| | |
next if [sponsor.name, sponsor.url].any? { |x| output.include?(x) } | |
puts "#{years.size}: #{sponsor.name} - #{sponsor.url} (#{years.join(", ")})" | |
output += [sponsor.name, sponsor.url] | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment