Last active
December 15, 2015 09:39
-
-
Save mpasternacki/5240054 to your computer and use it in GitHub Desktop.
Download lolcats from your soup.io while it's up! Needs Ruby (used with MRI - "the regular ruby" - 1.9.3, should work with 1.9.2 or 2.0.0; 1.8.7 is a "maybe") and the Nokogiri gem (http://nokogiri.org).
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 'fileutils' | |
require 'open-uri' | |
require 'yaml' | |
require 'rubygems' | |
require 'nokogiri' | |
FileUtils.mkdir_p 'items' | |
feed = Nokogiri::XML(File.open('3fc1319c496ea1aacde451cecbdc17e3.rss')) | |
items = feed.xpath('/rss/channel/item') | |
n = items.length | |
errors = 0 | |
begin | |
items.each_with_index do |item, i| | |
guid = item.xpath('guid').text.sub /^urn:www-soup-io:1:/, '' | |
puts "* #{guid} #{i}/#{n} #{ '%.2f' % ((i.to_f/n)*100) }%" | |
File.open("items/#{guid}.yml", 'w') do |ymlf| | |
ymlf.puts YAML::dump( | |
'title' => item.xpath('title').text, | |
'link' => item.xpath('link').text, | |
'date' => item.xpath('pubDate').text, | |
'description' => item.xpath('description').text ) | |
end | |
item.xpath('enclosure').each do |encl| | |
url = encl['url'] | |
file = "assets/#{guid}-#{url.split('/').last}" | |
if File.size?(file) | |
puts " Exists: #{file}" | |
else | |
puts " Download: #{url} => #{file}" | |
begin | |
open(url) do |img| | |
open(file, 'wb') do |imgf| | |
imgf.write(img.read) | |
end | |
end | |
rescue => e | |
puts " `->Error: #{e}, let's try again later" | |
FileUtils.rm_f file | |
errors += 1 | |
end | |
end | |
end | |
end | |
ensure | |
puts "** #{errors} errors **" | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment