Dan-Q/bbc-news-rss-filter-sport-out.rb

## bbc-news-rss-filter-sport-out.rb
#!/usr/bin/env ruby
require 'bundler/inline'

# # Sample crontab:
# # Every twenty minutes, run the script and log the results
# */20 * * * * ~/bbc-news-rss-filter-sport-out.rb > ~/bbc-news-rss-filter-sport-out.log 2>>&1

# Dependencies:
# * open-uri - load remote URL content easily
# * nokogiri - parse/filter XML
gemfile do
  source 'https://rubygems.org'
  gem 'nokogiri'
end
require 'open-uri'

# Regular expression describing the GUIDs to reject from the resulting RSS feed
# We want to drop everything from the "sport" section of the website, also any iPlayer/Sounds/Ideas links
REJECT_GUIDS_MATCHING = /^https:\/\/www\.bbc\.co\.uk\/(sport|iplayer|sounds|ideas)\//

# Load and filter the original RSS
rss = Nokogiri::XML(open('https://feeds.bbci.co.uk/news/rss.xml?edition=uk'))
rss.css('item').select{|item| item.css('guid').text =~ REJECT_GUIDS_MATCHING }.each(&:unlink)

# Strip the anchors off the <guid>s: BBC News "republishes" stories by using guids with #0, #1, #2 etc, which results in duplicates in feed readers
rss.css('guid').each{|g|g.content=g.content.gsub(/#.*$/,'')}

File.open( '/www/bbc-news-no-sport.xml', 'w' ){ |f| f.puts(rss.to_s) }
	#!/usr/bin/env ruby
	require 'bundler/inline'

	# # Sample crontab:
	# # Every twenty minutes, run the script and log the results
	# /20 * * * ~/bbc-news-rss-filter-sport-out.rb > ~/bbc-news-rss-filter-sport-out.log 2>>&1

	# Dependencies:
	# * open-uri - load remote URL content easily
	# * nokogiri - parse/filter XML
	gemfile do
	source 'https://rubygems.org'
	gem 'nokogiri'
	end
	require 'open-uri'

	# Regular expression describing the GUIDs to reject from the resulting RSS feed
	# We want to drop everything from the "sport" section of the website, also any iPlayer/Sounds/Ideas links
	REJECT_GUIDS_MATCHING = /^https:\/\/www\.bbc\.co\.uk\/(sport\|iplayer\|sounds\|ideas)\//

	# Load and filter the original RSS
	rss = Nokogiri::XML(open('https://feeds.bbci.co.uk/news/rss.xml?edition=uk'))
	rss.css('item').select{\|item\| item.css('guid').text =~ REJECT_GUIDS_MATCHING }.each(&:unlink)

	# Strip the anchors off the <guid>s: BBC News "republishes" stories by using guids with #0, #1, #2 etc, which results in duplicates in feed readers
	rss.css('guid').each{\|g\|g.content=g.content.gsub(/#.*$/,'')}

	File.open( '/www/bbc-news-no-sport.xml', 'w' ){ \|f\| f.puts(rss.to_s) }