Created
May 18, 2017 14:39
-
-
Save manton/03a41efd6ebb1afa4ff3c482b83d1097 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
# run with: ruby jsonfeed_convert_rss.rb "http://therecord.co/xml/rss.xml" | |
# also make sure to "gem install simple-rss" first | |
require 'rubygems' | |
require 'simple-rss' | |
require 'open-uri' | |
require 'json' | |
rss_url = ARGV[0] | |
SimpleRSS.item_tags << :"enclosure#url" | |
SimpleRSS.item_tags << :"enclosure#type" | |
SimpleRSS.item_tags << :"enclosure#length" | |
rss = SimpleRSS.parse(open(rss_url)) | |
json_feed = { | |
version: "https://jsonfeed.org/version/1", | |
title: rss.channel.title, | |
home_page_url: rss.channel.link, | |
items: [] | |
} | |
for rss_item in rss.items | |
json_item = { | |
id: rss_item.link, | |
url: rss_item.link, | |
title: rss_item.title.force_encoding('UTF-8'), | |
date_published: rss_item.pubDate.iso8601 | |
} | |
if rss_item.description.to_s.length > 0 | |
json_item[:content_text] = CGI.unescapeHTML(rss_item.description.force_encoding('UTF-8')) | |
end | |
if rss_item.content_encoded.to_s.length > 0 | |
json_item[:content_html] = CGI.unescapeHTML(rss_item.content_encoded.force_encoding('UTF-8')) | |
elsif rss_item.content.to_s.length > 0 | |
json_item[:content_html] = CGI.unescapeHTML(rss_item.content.force_encoding('UTF-8')) | |
end | |
if rss_item.enclosure_url | |
json_item[:attachments] = [ | |
{ | |
url: rss_item.enclosure_url, | |
mime_type: rss_item.enclosure_type, | |
size_in_bytes: rss_item.enclosure_length.to_i | |
} | |
] | |
end | |
json_feed[:items] << json_item | |
end | |
puts JSON.pretty_generate(json_feed) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment