feedalize_bbc_stuff.rb

require 'rubygems'
require 'feedalizer'

def six_music_hub
  url = "http://www.bbc.co.uk/6music/events/hub/index.shtml"
  f = feedalize(url) do
    feed.title = "BBC 6 Music Hub Sessions"
    feed.description = "Live sessions on BBC 6 Music"
    
    scrape_items("a.watch") do |rss_item, html_element|
      next if html_element.inner_html=='Watch the session and see the pictures'
      link = "http://www.bbc.co.uk#{html_element.attributes['href']}"
      rss_item.title = "#{html_element.inner_html} 6 Music Hub Session"
      rss_item.link = link
      rss_item.guid.isPermaLink = true
      rss_item.guid.content = link
    end
  end
  f.output
end

def six_music_news
  url = "http://www.bbc.co.uk/6music/news/index.shtml"
  f = feedalize(url) do
    feed.title = "BBC 6 Music News"
    feed.description = "News from BBC 6 Music"
    
    links_parsed = []
    scrape_items("a", 100) do |rss_item, html_element|
      link = "http://www.bbc.co.uk#{html_element.attributes['href']}"
      next unless link =~ %r[/6music/news/\d+]
      next if links_parsed.include?(link)
      links_parsed << link
      rss_item.title = (html_element/"//img").first.attributes['alt']
      rss_item.link = link
      rss_item.guid.isPermaLink = true
    end
    @source = grab_page("http://www.bbc.co.uk/6music/news/archive.shtml")
    scrape_items("a", 100) do |rss_item, html_element|
      link = "http://www.bbc.co.uk#{html_element.attributes['href']}"
      next unless link =~ %r[/6music/news/\d+]
      next if links_parsed.include?(link)
      links_parsed << link 
      rss_item.title = (html_element/"//img").first.attributes['alt']
      rss_item.link = link
      rss_item.guid.isPermaLink = true
    end
  end
  f.output
end

def live_lounge
  url = "http://www.bbc.co.uk/radio1/livelounge/"
  f = feedalize(url) do
    feed.title = "BBC Radio 1 Live Lounge Hub Sessions"
    feed.description = "Latest from the live lounge"
    
    links_parsed = []
    scrape_items("//div.radio1_promo") do |rss_item, html_element|
      link = "http://www.bbc.co.uk#{(html_element/"//a").first.attributes['href']}"
      next if links_parsed.include?(link)
      links_parsed << link
      rss_item.title = "#{(html_element/"//img").first.attributes['alt']} - Live Lounge Session"
      rss_item.link = link
      rss_item.guid.isPermaLink = true
      rss_item.guid.content = link      
    end
    scrape_items("//td/div:eq(5)[@class='rh-links-rm']/ul/li/a") do |rss_item, html_element|
      link = "http://www.bbc.co.uk#{html_element.attributes['href']}"
      next if links_parsed.include?(link)
      links_parsed << link
      rss_item.title = "#{html_element.inner_html} - Live Lounge Session"
      rss_item.link = link
      rss_item.guid.isPermaLink = true
      rss_item.guid.content = link
    end
  end
  f.output
end

File.open(File.join(File.dirname(__FILE__),'bbc_feeds','6music_hub.rss'), 'w') { |f| f.puts(six_music_hub) }
File.open(File.join(File.dirname(__FILE__),'bbc_feeds','live_lounge.rss'), 'w') { |f| f.puts(live_lounge) }
File.open(File.join(File.dirname(__FILE__),'bbc_feeds','6music_music_news.rss'), 'w') { |f| f.puts(six_music_news) }