Last active
December 15, 2015 04:39
-
-
Save i09158knct/5203145 to your computer and use it in GitHub Desktop.
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 'nokogiri' | |
require 'json' | |
def parse_rss_xml(file_name) | |
file = File.read file_name | |
doc = Nokogiri.XML file | |
to_info = -> rss { | |
title = rss.attr 'title' | |
html_url = rss.attr 'htmlUrl' | |
xml_url = rss.attr 'xmlUrl' | |
{title: title, html_url: html_url, xml_url: xml_url} | |
} | |
root_elements = doc.css 'body > outline' | |
groups = root_elements.group_by {|elm| elm.attr('type') == 'rss' } | |
categories = groups[false] | |
rss_table = categories.each_with_object({}) { |categorie_root, acc| | |
name = categorie_root.attr 'title' | |
rss_list = categorie_root.css('outline[type=rss]') | |
acc[name] = rss_list.map &to_info | |
} | |
uncategorized_rss_list = groups[true] | |
rss_table['__uncategorized-rss-list'] = uncategorized_rss_list.map &to_info | |
rss_table | |
end | |
file = File.read 'subscriptions.xml' | |
if __FILE__ == $0 | |
file_name = ARGV[0] || 'subscriptions.xml' | |
rss_table = parse_rss_xml file_name | |
puts rss_table.to_json( | |
indent: ' ', | |
object_nl: "\n", | |
space: ' ', | |
) | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment