RailsCasts: get a list of links to MP4 Version of the Episodes

railscasts-episodes-list.rb

#!/usr/bin/env /Users/nikhilgupta/.rvm/wrappers/ruby-1.9.3-p0@tools/ruby

# a tiny script that crawls 'railscasts.com' and stores the path to MP4 versions
# of the episodes in the file: 'downloads.txt'
# currently, set to track only the last 3 pages of the site's free section.
# you can then run: $(for tut in `cat downloads.txt`; do wget --continue $tut; done) to download them.

require 'rubygems'
require 'nokogiri'
require 'open-uri'

def get_railscasts_episodes(pages, file)
	pages = pages.to_i
	raise "Not a valid integer" if pages.nil?
	downloads = File.readlines(file)
	while pages > 0 do
		puts "Searching for Episodes on Page ##{pages} on RailsCasts.com"
		doc = Nokogiri::HTML(open("http://railscasts.com/?type=free&page=#{pages}"))
		doc.css('.episodes .main h2 a').each do |episode|
			epidoc = Nokogiri::HTML(open("http://railscasts.com#{episode.attribute('href')}"))
			epidoc.css('ul.downloads li a').each do |link|
				link.attribute('href').to_s.scan(/.*\.mp4/) do | mp4link |
					if downloads.include?("#{mp4link}\n")
						puts "Already added: #{mp4link}"
					else
						File.open(file, 'a+') { |f1|  f1.write("#{mp4link}\n") }
						puts "New Download: #{mp4link}"
					end
				end
			end
		end
		pages -= 1
	end
end

get_railscasts_episodes 3, "downloads.txt"

http://www.anleger.blog