Created
April 5, 2011 01:12
-
-
Save ayosec/902825 to your computer and use it in GitHub Desktop.
Downloader for TED
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
# Use | |
# ruby download.rb http://www.ted.com/search?q=any+query | |
require 'rubygems' | |
require 'mechanize' | |
agent = Mechanize.new { |agent| agent.user_agent_alias = 'Linux Firefox' } | |
pages = ARGV | |
loaded = [] | |
class DummyObject | |
def method_missing(*a) | |
end | |
end | |
class <<agent | |
def absolute_url(uri) | |
hash = { :uri => uri, :referer => current_page } | |
Mechanize::Chain::URIResolver.new(@scheme_handlers).tap {|o| o.chain = DummyObject.new }.handle(nil, hash) | |
hash[:uri].to_s | |
end | |
end | |
while not pages.empty? | |
current_url = pages.shift | |
next if loaded.include?(current_url) | |
loaded << current_url | |
puts "Loading #{current_url}..." | |
current_page = agent.get(current_url) | |
download_links = current_page.search(".downloads a") | |
if not download_links.empty? | |
Process.wait(fork do | |
video_link = download_links.last[:href] | |
dest_file = current_url.split("/").last.sub(/\.html$/i, "") + ".mp4" | |
if File.exist?(dest_file) | |
puts "#{dest_file} exists" | |
else | |
exec "wget", "-O", dest_file, agent.absolute_url(video_link) | |
end | |
end) | |
else | |
current_page.search("dt a").each do |next_link| | |
pages << next_link[:href] | |
end | |
if next_page = current_page.at("li.next a") | |
pages << next_page[:ref] | |
end | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment