Created
June 11, 2014 13:13
-
-
Save phil/cb13bebf6ff8473ba705 to your computer and use it in GitHub Desktop.
EventMachine scraping Hackernews
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
require "eventmachine" | |
require "em-http-request" | |
require 'nokogiri' | |
EventMachine.run do | |
http_hackernews = EM::HttpRequest.new("https://news.ycombinator.com").get | |
http_hackernews.callback do | |
links = Nokogiri::HTML.parse(http_hackernews.response).css("td.title a") | |
links.each do |link| | |
next unless link | |
href = link.attribute("href").to_s | |
unless href.match(/http.*/) | |
links.delete(link) and next | |
end | |
http_site = EventMachine::HttpRequest.new(href).get | |
http_site.callback do | |
links.delete(link) | |
begin | |
title = Nokogiri.HTML(http_site.response).css("head>title").inner_text | |
puts "#{href} - #{http_site.response_header.status} - #{title}" | |
rescue | |
puts "#{href} - BOOM" | |
end | |
EventMachine.stop if links.empty? | |
end | |
http_site.errback do | |
puts "#{href} - Error - #{http_site.error.inspect}" | |
end | |
end | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment