feedbagtoo 0.7.2

data/COPYING

@@ -0,0 +1,20 @@
+Copyright (C) 2012 David Moreno <david@axiombox.com>
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/ChangeLog

@@ -0,0 +1,29 @@
+* 0.9 - Fri Mar 16 10:59:00 EDT 2012
+  - Changed license to MIT.
+
+* 0.6 - Fri Mar  5 20:10:33 EST 2010
+  - Added bin/feedbag.
+  - Removed the args[:narrow] option, not really needed.
+  - Handle case where feed URLs contain GET parameters; add tests
+    by Patrick Reagan <patrick.reagan@viget.com>.
+
+* 0.5.99 - Tue May 12 12:52:22 EDT 2009
+  - Added rails/init.rb to load easily on a Rails app.
+
+* 0.5.13.1 - Wed Apr 22 11:16:19 EDT 2009
+  - Changed args on find() from nil to {}
+
+* 0.5.13 - Wed Apr 22 11:12:40 EDT 2009
+  - Added :narrow option so find() skips feed_validate and A links.
+
+* 0.5.12 - Fri Mar 20 12:34:48 EDT 2009
+	- Added support for "feed://" URLs
+
+* 0.5.11 - Sat Mar  7 17:22:30 EST 2009
+	- Benchmark against Rfeedfinder added.
+
+* 0.5.10 - Wed Mar  4 13:32:33 EST 2009
+  - Feeds whose URLs contained query string arguments were not being
+    auto-discovered -- fixed
+
+** For previous changes, see the git log

data/Gemfile

@@ -0,0 +1,22 @@
+# Clean up if needed
+# rm -rf ~/.bundle/ ~/.gem/; rm -rf $GEM_HOME/bundler/ $GEM_HOME/cache/bundler/; rm -rf .bundle/; rm -rf vendor/cache/; rm -rf Gemfile.lock
+
+source "http://rubygems.org"
+
+
+# Add dependencies to develop your gem here.
+# Include everything needed to run rake, tests, features, etc.
+group :development, :test do
+  gem 'growl'
+  gem "rdoc", "~> 3.12"
+  gem "bundler", ">=1.0.0"
+  gem "jeweler", "~> 1.8.3"
+  gem "active_support"
+  gem "mocha"
+  gem "hpricot"
+  if RUBY_VERSION < '1.9'
+    gem "ruby-debug"
+  else
+    gem 'debugger', '~> 1.1.4'
+  end
+end

data/Gemfile.lock

@@ -0,0 +1,43 @@
+GEM
+  remote: http://rubygems.org/
+  specs:
+    active_support (3.0.0)
+      activesupport (= 3.0.0)
+    activesupport (3.0.0)
+    columnize (0.3.6)
+    git (1.2.5)
+    growl (1.0.3)
+    hpricot (0.8.6)
+    jeweler (1.8.4)
+      bundler (~> 1.0)
+      git (>= 1.2.5)
+      rake
+      rdoc
+    json (1.7.3)
+    linecache (0.46)
+      rbx-require-relative (> 0.0.4)
+    metaclass (0.0.1)
+    mocha (0.12.0)
+      metaclass (~> 0.0.1)
+    rake (0.9.2.2)
+    rbx-require-relative (0.0.9)
+    rdoc (3.12)
+      json (~> 1.4)
+    ruby-debug (0.10.4)
+      columnize (>= 0.1)
+      ruby-debug-base (~> 0.10.4.0)
+    ruby-debug-base (0.10.4)
+      linecache (>= 0.3)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  active_support
+  bundler (>= 1.0.0)
+  growl
+  hpricot
+  jeweler (~> 1.8.3)
+  mocha
+  rdoc (~> 3.12)
+  ruby-debug

data/README.markdown

@@ -0,0 +1,101 @@
+Feedbag
+=======
+Forked version of feedbag that returns title, description and url.
+
+Feedbag is a feed auto-discovery Ruby library. You don't need to know more about it. It is said to be:
+
+> Ruby's favorite auto-discovery tool/library!
+
+### Quick synopsis
+
+	>> require "rubygems"
+	=> true
+	>> require "feedbag"
+ 	=> true
+ 	>> Feedbag.find "log.damog.net"
+ 	=> ["http://feeds.feedburner.com/TeoremaDelCerdoInfinito", "http://log.damog.net/comments/feed/"]
+	>> Feedbag.feed?("google.com")
+	=> false
+	>> Feedbag.feed?("http://planet.debian.org/rss20.xml")
+	=> true
+
+### Installation
+
+	$ sudo gem install damog-feedbag -s http://gems.github.com/
+
+Or just grab feedbag.rb and use it on your own project:
+
+	$ wget http://github.com/damog/feedbag/raw/master/lib/feedbag.rb
+
+## Tutorial
+
+So you want to know more about it.
+
+OK, if the URL passed to the find method is a feed itself, that only feed URL will be returned.
+
+	>> Feedbag.find "github.com/damog.atom"
+	=> ["http://github.com/damog.atom"]
+	>> 
+
+Otherwise, it will always return LINK feeds first, A (anchor tags) feeds later. Between A feeds, the ones hosted on the same URL's host, will have larger priority:
+
+	>> Feedbag.find "http://ve.planetalinux.org"
+	=> ["http://feedproxy.google.com/PlanetaLinuxVenezuela", "http://rendergraf.wordpress.com/feed/", "http://rootweiller.wordpress.com/feed/", "http://skatox.com/blog/feed/", "http://kodegeek.com/atom.xml", "http://blog.0x29.com.ve/?feed=rss2&cat=8"]
+	>> 
+
+On your application you should only take the very first element of the array, most of the times:
+
+	>> Feedbag.find("planet.debian.org").first(3)
+	=> ["http://planet.debian.org/rss10.xml", "http://planet.debian.org/rss20.xml", "http://planet.debian.org/atom.xml"]
+	>> 
+
+(Try running that same example without the "first" method. That example's host is a blog aggregator, so it has hundreds of feed URLs:)
+
+	>> Feedbag.find("planet.debian.org").size
+	=> 104
+	>> 
+
+Feedbag will find them all, but it will return the most important ones on the first elements on the array returned.
+
+	>> Feedbag.find("cnn.com")
+	=> ["http://rss.cnn.com/rss/cnn_topstories.rss", "http://rss.cnn.com/rss/cnn_latest.rss", "http://rss.cnn.com/services/podcasting/robinmeade/rss.xml"]
+	>> 
+
+### Why should you use it?
+
+- Because it's cool.
+- Because it only uses [Hpricot](https://code.whytheluckystiff.net/hpricot/) as dependency.
+- Because it follows modern feed filename conventions (like those ones used by WordPress blogs, or Blogger, etc).
+- Because it's a single file you can embed easily in your application.
+- Because it passes most of the Mark Pilgrim's [Atom auto-discovery test suite](http://diveintomark.org/tests/client/autodiscovery/). It doesn't pass them all because some of those tests are	broken (citation needed).
+
+### Why did I build it?
+
+- Because I liked Benjamin Trott's [Feed::Find](http://search.cpan.org/~btrott/Feed-Find-0.06/lib/Feed/Find.pm).
+- Because I thought it would be good to have Feed::Find's functionality in Ruby.
+- Because I thought it was going to be easy to maintain.
+- Because I was going to use it on [rFeed](http://github.com/damog/rfeed).
+- And finally, because I didn't know [rfeedfinder](http://rfeedfinder.rubyforge.org/) existed :-)
+
+### Bugs
+
+Please, report bugs to [rt@support.axiombox.com](rt@support.axiombox.com) or directly to the author.
+
+### Contribute
+
+> git clone git://github.com/damog/feedbag.git
+
+...patch, build, hack and make pull requests. I'll be glad.
+
+### Author
+
+[David Moreno](http://damog.net/) <[david@axiombox.com](mailto:david@axiombox.com)>.
+
+### Copyright
+
+This is free software. See [COPYING](http://github.com/damog/feedbag/master/COPYING) for more information.
+
+### Thanks
+
+[Raquel](http://maggit.net), for making [Axiombox](http://axiombox.com) and most of my dreams possible. Also, [GitHub](http://github.com) for making a nice code sharing service that doesn't suck.
+

data/Rakefile

@@ -0,0 +1,33 @@
+# encoding: utf-8
+
+require 'rubygems'
+require 'bundler'
+require 'rake/testtask'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  gem.name = "feedbagtoo"
+  gem.summary = "Fork of the feedbag gem that returns title along with url."
+  gem.description = "This gem will return title and url for each feed discovered at a given url"
+  gem.email = "justin@tatemae.com"
+  gem.homepage = "http://github.com/tatemae/feedbagtoo"
+  gem.authors = ["Axiombox", "David Moreno", "Joel Duffin", "Justin Ball", "Fabien Penso"]
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+
+task :default => :test
+
+Rake::TestTask.new do |t|
+  t.libs << 'test'
+  t.test_files = FileList["test/feedbag_test.rb"]
+  t.verbose = true
+end

data/TODO

@@ -0,0 +1 @@
+- Document Feedbag.feed?

data/VERSION

@@ -0,0 +1 @@
+0.7.2

data/benchmark/rfeedfinder_benchmark.rb

@@ -0,0 +1,30 @@
+require "benchmark"
+require "rubygems"
+
+sites = [
+	"log.damog.net",
+	"http://cnn.com",
+	"scripting.com",
+	"mx.planetalinux.org",
+	"http://feedproxy.google.com/UniversoPlanetaLinux",
+]
+
+Benchmark.bm do |x|
+	sites.each do |site|
+		puts "#{site}:"
+
+		puts " feedbag"
+		x.report {
+			require 'feedbag'
+			Feedbag.find(site)
+		}
+
+		puts "  rfeedfinder"
+		x.report {
+			require 'rfeedfinder'
+			Rfeedfinder.feed(site)
+		}
+
+	end
+end
+

data/bin/feedbag

@@ -0,0 +1,28 @@
+#!/usr/bin/env ruby
+
+require "rubygems"
+require "feedbag"
+
+def usage
+  %Q{
+    #{$0} <url 1> [<url 2> <url 3> ... <url n>]
+  }
+end
+
+if ARGV.empty?
+  puts usage
+  exit 1
+end
+
+ARGV.each do |url|
+  puts "== #{url}:"
+  feeds = Feedbag.find url
+  if feeds.empty?
+    puts "   no feeds found!"
+  else
+    feeds.each do |f|
+      puts " - #{f}"
+    end
+  end
+end
+

data/feedbagtoo.gemspec

@@ -0,0 +1,80 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{feedbagtoo}
+  s.version = "0.7.2"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Axiombox", "David Moreno", "Joel Duffin", "Justin Ball", "Fabien Penso"]
+  s.date = %q{2012-07-18}
+  s.default_executable = %q{feedbag}
+  s.description = %q{This gem will return title and url for each feed discovered at a given url}
+  s.email = %q{justin@tatemae.com}
+  s.executables = ["feedbag"]
+  s.extra_rdoc_files = [
+    "ChangeLog",
+    "README.markdown",
+    "TODO"
+  ]
+  s.files = [
+    "COPYING",
+    "ChangeLog",
+    "Gemfile",
+    "Gemfile.lock",
+    "README.markdown",
+    "Rakefile",
+    "TODO",
+    "VERSION",
+    "benchmark/rfeedfinder_benchmark.rb",
+    "bin/feedbag",
+    "feedbagtoo.gemspec",
+    "index.html",
+    "lib/feedbag.rb",
+    "lib/feedbagtoo.rb",
+    "rails/init.rb",
+    "test/atom_autodiscovery_test.rb",
+    "test/feedbag_test.rb",
+    "test/test_helper.rb"
+  ]
+  s.homepage = %q{http://github.com/tatemae/feedbagtoo}
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.6.2}
+  s.summary = %q{Fork of the feedbag gem that returns title along with url.}
+
+  if s.respond_to? :specification_version then
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_development_dependency(%q<growl>, [">= 0"])
+      s.add_development_dependency(%q<rdoc>, ["~> 3.12"])
+      s.add_development_dependency(%q<bundler>, [">= 1.0.0"])
+      s.add_development_dependency(%q<jeweler>, ["~> 1.8.3"])
+      s.add_development_dependency(%q<active_support>, [">= 0"])
+      s.add_development_dependency(%q<mocha>, [">= 0"])
+      s.add_development_dependency(%q<hpricot>, [">= 0"])
+      s.add_development_dependency(%q<ruby-debug>, [">= 0"])
+    else
+      s.add_dependency(%q<growl>, [">= 0"])
+      s.add_dependency(%q<rdoc>, ["~> 3.12"])
+      s.add_dependency(%q<bundler>, [">= 1.0.0"])
+      s.add_dependency(%q<jeweler>, ["~> 1.8.3"])
+      s.add_dependency(%q<active_support>, [">= 0"])
+      s.add_dependency(%q<mocha>, [">= 0"])
+      s.add_dependency(%q<hpricot>, [">= 0"])
+      s.add_dependency(%q<ruby-debug>, [">= 0"])
+    end
+  else
+    s.add_dependency(%q<growl>, [">= 0"])
+    s.add_dependency(%q<rdoc>, ["~> 3.12"])
+    s.add_dependency(%q<bundler>, [">= 1.0.0"])
+    s.add_dependency(%q<jeweler>, ["~> 1.8.3"])
+    s.add_dependency(%q<active_support>, [">= 0"])
+    s.add_dependency(%q<mocha>, [">= 0"])
+    s.add_dependency(%q<hpricot>, [">= 0"])
+    s.add_dependency(%q<ruby-debug>, [">= 0"])
+  end
+end
+

data/index.html

@@ -0,0 +1,115 @@
+<h1>Feedbag</h1>
+
+<blockquote>
+  <p>Do you want me to drag my sack across your face?
+                                - Glenn Quagmire</p>
+</blockquote>
+
+<p>Feedbag is a feed auto-discovery Ruby library. You don't need to know more about it. It is said to be:</p>
+
+<blockquote>
+  <p>Ruby's favorite auto-discovery tool/library!</p>
+</blockquote>
+
+<h3>Quick synopsis</h3>
+
+<pre><code>&gt;&gt; require "rubygems"
+=&gt; true
+&gt;&gt; require "feedbag"
+=&gt; true
+&gt;&gt; Feedbag.find "log.damog.net"
+=&gt; ["http://feeds.feedburner.com/TeoremaDelCerdoInfinito", "http://log.damog.net/comments/feed/"]
+</code></pre>
+
+<h3>Installation</h3>
+
+<pre><code>$ sudo gem install damog-feedbag -s http://gems.github.com/
+</code></pre>
+
+<p>Or just grab feedbag.rb and use it on your own project:</p>
+
+<pre><code>$ wget http://github.com/damog/feedbag/raw/master/lib/feedbag.rb
+</code></pre>
+
+<h2>Tutorial</h2>
+
+<p>So you want to know more about it.</p>
+
+<p>OK, if the URL passed to the find method is a feed itself, that only feed URL will be returned.</p>
+
+<pre><code>&gt;&gt; Feedbag.find "github.com/damog.atom"
+=&gt; ["http://github.com/damog.atom"]
+&gt;&gt;
+</code></pre>
+
+<p>Otherwise, it will always return LINK feeds first, A (anchor tags) feeds later. Between A feeds, the ones hosted on the same URL's host, will have larger priority:</p>
+
+<pre><code>&gt;&gt; Feedbag.find "http://ve.planetalinux.org"
+=&gt; ["http://feedproxy.google.com/PlanetaLinuxVenezuela", "http://rendergraf.wordpress.com/feed/", "http://rootweiller.wordpress.com/feed/", "http://skatox.com/blog/feed/", "http://kodegeek.com/atom.xml", "http://blog.0x29.com.ve/?feed=rss2&amp;cat=8"]
+&gt;&gt;
+</code></pre>
+
+<p>On your application you should only take the very first element of the array, most of the times:</p>
+
+<pre><code>&gt;&gt; Feedbag.find("planet.debian.org").first(3)
+=&gt; ["http://planet.debian.org/rss10.xml", "http://planet.debian.org/rss20.xml", "http://planet.debian.org/atom.xml"]
+&gt;&gt;
+</code></pre>
+
+<p>(Try running that same example without the "first" method. That example's host is a blog aggregator, so it has hundreds of feed URLs:)</p>
+
+<pre><code>&gt;&gt; Feedbag.find("planet.debian.org").size
+=&gt; 104
+&gt;&gt;
+</code></pre>
+
+<p>Feedbag will find them all, but it will return the most important ones on the first elements on the array returned.</p>
+
+<pre><code>&gt;&gt; Feedbag.find("cnn.com")
+=&gt; ["http://rss.cnn.com/rss/cnn_topstories.rss", "http://rss.cnn.com/rss/cnn_latest.rss", "http://rss.cnn.com/services/podcasting/robinmeade/rss.xml"]
+&gt;&gt;
+</code></pre>
+
+<h3>Why should you use it?</h3>
+
+<ul>
+<li>Because it's cool.</li>
+<li>Because it only uses <a href="https://code.whytheluckystiff.net/hpricot/">Hpricot</a> as dependency.</li>
+<li>Because it follows modern feed filename conventions (like those ones used by WordPress blogs, or Blogger, etc).</li>
+<li>Because it's a single file you can embed easily in your application.</li>
+<li>Because it passes most of the Mark Pilgrim's <a href="http://diveintomark.org/tests/client/autodiscovery/">Atom auto-discovery test suite</a>. It doesn't pass them all because some of those tests are  broken (citation needed).</li>
+</ul>
+
+<h3>Why did I build it?</h3>
+
+<ul>
+<li>Because I liked Benjamin Trott's <a href="http://search.cpan.org/~btrott/Feed-Find-0.06/lib/Feed/Find.pm">Feed::Find</a>.</li>
+<li>Because I thought it would be good to have Feed::Find's functionality in Ruby.</li>
+<li>Because I thought it was going to be easy to maintain.</li>
+<li>Because I was going to use it on <a href="http://github.com/damog/rfeed">rFeed</a>.</li>
+<li>And finally, because I didn't know <a href="http://rfeedfinder.rubyforge.org/">rfeedfinder</a> existed :-)</li>
+</ul>
+
+<h3>Bugs</h3>
+
+<p>Please, report bugs to <a href="rt@support.axiombox.com">rt@support.axiombox.com</a> or directly to the author.</p>
+
+<h3>Contribute</h3>
+
+<blockquote>
+  <p>git clone git://github.com/damog/feedbag.git</p>
+</blockquote>
+
+<p>...patch, build, hack and make pull requests. I'll be glad.</p>
+
+<h3>Author</h3>
+
+<p><a href="http://damog.net/">David Moreno</a> &lt;<a href="mailto:david@axiombox.com">david@axiombox.com</a>>.</p>
+
+<h3>Copyright</h3>
+
+<p>This is free software. See <a href="http://github.com/damog/feedbag/master/COPYING">COPYING</a> for more information.</p>
+
+<h3>Thanks</h3>
+
+<p><a href="http://maggit.net">Raquel</a>, for making <a href="http://axiombox.com">Axiombox</a> and most of my dreams possible. Also, <a href="http://github.com">GitHub</a> for making a nice code sharing service that doesn't suck.</p>

data/lib/feedbag.rb

@@ -0,0 +1,226 @@
+#!/usr/bin/ruby
+
+# Copyright (c) 2012 David Moreno <david@axiombox.com>
+#
+# Permission is hereby granted, free of charge, to any person obtaining
+# a copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to
+# permit persons to whom the Software is furnished to do so, subject to
+# the following conditions:
+# 
+# The above copyright notice and this permission notice shall be
+# included in all copies or substantial portions of the Software.
+# 
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+# LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+# OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+# WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+require "rubygems"
+require "hpricot"
+require "open-uri"
+require "net/http"
+require 'timeout'
+require 'iconv' if RUBY_VERSION < '1.9'
+
+module Feedbag
+  Feed = Struct.new(:url, :title, :human_url, :description)
+
+	@content_types = [
+		'application/x.atom+xml',
+		'application/atom+xml',
+		'application/xml',
+		'text/xml',
+		'application/rss+xml',
+		'application/rdf+xml',
+	]
+
+	$feeds = []
+	$base_uri = nil
+
+	def self.feed?(url)
+		# use LWR::Simple.normalize some time
+		url_uri = URI.parse(url)
+		url = "#{url_uri.scheme or 'http'}://#{url_uri.host}#{url_uri.path}"
+		url << "?#{url_uri.query}" if url_uri.query
+		
+		# hack:
+		url.sub!(/^feed:\/\//, 'http://')
+
+		res = self.find(url)
+		if res.size == 1 and res.first == url
+			return true
+		else
+			return false
+		end
+	end
+
+	def self.find(url, args = {})
+		$feeds = []
+
+		url_uri = URI.parse(url)
+		url = nil
+		if url_uri.scheme.nil?
+		  url = "http://#{url_uri.to_s}"
+		elsif url_uri.scheme == "feed"
+		  return self.add_feed(url_uri.to_s.sub(/^feed:\/\//, 'http://'), nil)
+		else
+		  url = url_uri.to_s
+		end
+		#url = "#{url_uri.scheme or 'http'}://#{url_uri.host}#{url_uri.path}"
+
+    #return self.add_feed(url, nil) if looks_like_feed? url
+
+		# check if feed_valid is avail
+    begin
+  		require "feed_validator"
+	  	v = W3C::FeedValidator.new
+		  v.validate_url(url)
+			return self.add_feed(url, nil) if v.valid?
+  	rescue LoadError
+	  	# scoo
+		rescue REXML::ParseException
+  	  # usually indicates timeout
+	    # TODO: actually find out timeout. use Terminator?
+	    # $stderr.puts "Feed looked like feed but might not have passed validation or timed out"
+    rescue => ex
+  		$stderr.puts "#{ex.class} error ocurred with: `#{url}': #{ex.message}"
+	  end
+
+		begin
+			Timeout::timeout(15) do
+				html = open(url) do |f|
+					content_type = f.content_type.downcase
+					if content_type == "application/octet-stream" # open failed
+					  content_type = f.meta["content-type"].gsub(/;.*$/, '')
+					end
+					if @content_types.include?(content_type)
+						return self.add_feed(url, nil)
+					end
+
+					if RUBY_VERSION < '1.9'
+						ic = Iconv.new('UTF-8//IGNORE', f.charset)
+          	doc = Hpricot(ic.iconv(f.read))
+          else
+          	doc = Hpricot(f.read)
+          end
+
+					if doc.at("base") and doc.at("base")["href"]
+						$base_uri = doc.at("base")["href"]
+					else
+						$base_uri = nil
+					end
+
+					title = (doc/:title).first
+					title = title.innerHTML if title
+
+					description = (doc/:description).first
+					description = description.innerHTML if description
+
+					# first with links
+	        (doc/"atom:link").each do |l|
+						next unless l["rel"]
+						if l["type"] and @content_types.include?(l["type"].downcase.strip) and l["rel"].downcase == "self"
+							self.add_feed(l["href"], url, $base_uri, title, description || title)
+						end
+					end
+
+					(doc/"link").each do |l|
+						next unless l["rel"]
+						if l["type"] and @content_types.include?(l["type"].downcase.strip) and (l["rel"].downcase =~ /alternate/i or l["rel"] == "service.feed")
+							self.add_feed(l["href"], url, $base_uri, title, description || title)
+						end
+					end
+
+					(doc/"a").each do |a|
+	  				next unless a["href"]
+		  			if self.looks_like_feed?(a["href"]) and (a["href"] =~ /\// or a["href"] =~ /#{url_uri.host}/)
+		  				title = a["title"] || a.inner_html || a['alt'] || title
+			  			self.add_feed(a["href"], url, $base_uri, title, description || title)
+				  	end
+					end
+
+	  			(doc/"a").each do |a|
+		  			next unless a["href"]
+			  		if self.looks_like_feed?(a["href"])
+			  			title = a["title"] || a.inner_html || a['alt'] || title
+				  		self.add_feed(a["href"], url, $base_uri, title, description || title)
+					  end
+					end
+
+	        # Added support for feeds like http://tabtimes.com/tbfeed/mashable/full.xml
+	        if url.match(/.xml$/) and doc.root and doc.root["xml:base"] and doc.root["xml:base"].strip == url.strip
+						self.add_feed(url, url, $base_uri, title, description)
+	        end
+				end
+			end
+		rescue Timeout::Error => err
+			$stderr.puts "Timeout error ocurred with `#{url}: #{err}'"
+		rescue OpenURI::HTTPError => the_error
+			$stderr.puts "Error ocurred with `#{url}': #{the_error}"
+		rescue SocketError => err
+			$stderr.puts "Socket error ocurred with: `#{url}': #{err}"
+		rescue => ex
+			$stderr.puts "#{ex.class} error ocurred with: `#{url}': #{ex.message}"
+		ensure
+			return $feeds
+		end
+	end
+
+	def self.looks_like_feed?(url)
+		if url =~ /((\.|\/)(rdf|xml|rdf|rss)$|feed=(rss|atom)|(atom|feed)\/?$)/i
+			true
+		else
+			false
+		end
+	end
+
+	def self.add_feed(feed_url, orig_url, base_uri = nil, title = "", description = "")
+		# puts "#{feed_url} - #{orig_url}"
+		url = feed_url.sub(/^feed:/, '').strip
+
+		if base_uri
+			#	url = base_uri + feed_url
+			url = URI.parse(base_uri).merge(feed_url).to_s
+		end
+
+		begin
+			uri = URI.parse(url)
+		rescue
+			puts "Error with `#{url}'"
+			exit 1
+		end
+		unless uri.absolute?
+			orig = URI.parse(orig_url)
+			url = orig.merge(url).to_s
+		end
+
+		# verify url is really valid
+		$feeds.push(Feed.new(url, title, orig_url, description)) unless $feeds.any? { |f| f.url == url }# if self._is_http_valid(URI.parse(url), orig_url)
+	end
+
+	# not used. yet.
+	def self._is_http_valid(uri, orig_url)
+		req = Net::HTTP.get_response(uri)
+		orig_uri = URI.parse(orig_url)
+		case req
+			when Net::HTTPSuccess then
+				return true
+			else
+				return false
+		end
+	end
+end
+
+if __FILE__ == $0
+  if ARGV.size == 0
+    puts 'usage: feedbag url'
+  else
+    puts Feedbag.find ARGV.first
+  end
+end

data/lib/feedbagtoo.rb

@@ -0,0 +1 @@
+require 'feedbag'

data/rails/init.rb

@@ -0,0 +1 @@
+require File.join File.dirname(__FILE__), "..", "lib", "feedbag"

data/test/atom_autodiscovery_test.rb

@@ -0,0 +1,40 @@
+require File.dirname(__FILE__) + '/test_helper'
+
+class AtomAutoDiscoveryTest < Test::Unit::TestCase
+	def test_autodisc
+		base_url = "http://diveintomark.org/tests/client/autodiscovery/"
+		url = base_url + "html4-001.html"
+
+		i = 1
+		puts "trying now with #{url}"
+		while(i)
+			puts
+			i = 0 # unless otherwise found
+
+			f = Feedbag.find url
+
+			assert_instance_of Array, f
+			assert f.size == 1, "Feedbag didn't find a feed on #{url} or found more than one"
+
+			puts " found #{f[0]}"
+			feed = Hpricot(open(f[0]))
+	
+			(feed/"link").each do |l|
+				next unless l["rel"] == "alternate"
+				assert_equal l["href"], url
+			end
+
+			# ahora me voy al siguiente
+			html = Hpricot(open(url))
+			(html/"link").each do |l|
+				next unless l["rel"] == "next"
+				url = URI.parse(base_url).merge(l["href"]).to_s
+				puts "trying now with #{url}"
+				i = 1
+			end
+		
+		end	
+	end
+
+
+end

data/test/feedbag_test.rb

@@ -0,0 +1,47 @@
+require File.dirname(__FILE__) + '/test_helper'
+class FeedbagTest < ActiveSupport::TestCase
+
+  test "Feedbag.feed? should know that an RSS url is a feed" do
+    rss_url = 'http://example.com/rss/'
+    Feedbag.stubs(:find).with(rss_url).returns([rss_url])
+
+    assert Feedbag.feed?(rss_url)
+  end
+
+  test "Feedbag.feed? should know that an RSS url with parameters is a feed" do
+    rss_url = "http://example.com/data?format=rss"
+    Feedbag.stubs(:find).with(rss_url).returns([rss_url])
+
+    assert Feedbag.feed?(rss_url)
+  end
+
+  test "Feedbag find should discover feeds containing atom:link" do
+    feeds = []
+    feeds << 'http://www.psfk.com/feeds/mashable'
+    feeds << 'http://jenniferlynch.wordpress.com/feed'
+    feeds << 'http://lurenbijdeburen.wordpress.com/feed'
+
+    feeds.each do |url|
+      assert_equal url, Feedbag.find(url).first.url
+    end
+  end
+
+  test "Feedbag find should discover feeds from site" do
+    feeds = []
+    feeds << 'http://www.justinball.com/'
+
+    feeds.each do |url|
+      assert_equal 'http://www.justinball.com/feed/', Feedbag.find(url).first.url
+    end
+  end
+
+  test "Feedbag find should discover feeds from xml" do
+    feeds = []
+    feeds << 'http://tabtimes.com/tbfeed/mashable/full.xml'
+
+    feeds.each do |url|
+      assert_equal url, Feedbag.find(url).first.url
+    end
+  end
+
+end

data/test/test_helper.rb

@@ -0,0 +1,17 @@
+require 'rubygems'
+
+require 'test/unit'
+
+
+require 'active_support'
+require 'active_support/test_case'
+
+require 'mocha'
+
+require File.dirname(__FILE__) + '/../lib/feedbag'
+
+if RUBY_VERSION < '1.9'
+  require 'ruby-debug'
+else
+  require 'debugger'
+end

metadata

@@ -0,0 +1,206 @@
+--- !ruby/object:Gem::Specification 
+name: feedbagtoo
+version: !ruby/object:Gem::Version 
+  hash: 7
+  prerelease: 
+  segments: 
+  - 0
+  - 7
+  - 2
+  version: 0.7.2
+platform: ruby
+authors: 
+- Axiombox
+- David Moreno
+- Joel Duffin
+- Justin Ball
+- Fabien Penso
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2012-07-18 00:00:00 -06:00
+default_executable: feedbag
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  prerelease: false
+  type: :development
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  name: growl
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  prerelease: false
+  type: :development
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 31
+        segments: 
+        - 3
+        - 12
+        version: "3.12"
+  name: rdoc
+  version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  prerelease: false
+  type: :development
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 23
+        segments: 
+        - 1
+        - 0
+        - 0
+        version: 1.0.0
+  name: bundler
+  version_requirements: *id003
+- !ruby/object:Gem::Dependency 
+  prerelease: false
+  type: :development
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 49
+        segments: 
+        - 1
+        - 8
+        - 3
+        version: 1.8.3
+  name: jeweler
+  version_requirements: *id004
+- !ruby/object:Gem::Dependency 
+  prerelease: false
+  type: :development
+  requirement: &id005 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  name: active_support
+  version_requirements: *id005
+- !ruby/object:Gem::Dependency 
+  prerelease: false
+  type: :development
+  requirement: &id006 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  name: mocha
+  version_requirements: *id006
+- !ruby/object:Gem::Dependency 
+  prerelease: false
+  type: :development
+  requirement: &id007 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  name: hpricot
+  version_requirements: *id007
+- !ruby/object:Gem::Dependency 
+  prerelease: false
+  type: :development
+  requirement: &id008 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  name: ruby-debug
+  version_requirements: *id008
+description: This gem will return title and url for each feed discovered at a given url
+email: justin@tatemae.com
+executables: 
+- feedbag
+extensions: []
+
+extra_rdoc_files: 
+- ChangeLog
+- README.markdown
+- TODO
+files: 
+- COPYING
+- ChangeLog
+- Gemfile
+- Gemfile.lock
+- README.markdown
+- Rakefile
+- TODO
+- VERSION
+- benchmark/rfeedfinder_benchmark.rb
+- bin/feedbag
+- feedbagtoo.gemspec
+- index.html
+- lib/feedbag.rb
+- lib/feedbagtoo.rb
+- rails/init.rb
+- test/atom_autodiscovery_test.rb
+- test/feedbag_test.rb
+- test/test_helper.rb
+has_rdoc: true
+homepage: http://github.com/tatemae/feedbagtoo
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.6.2
+signing_key: 
+specification_version: 3
+summary: Fork of the feedbag gem that returns title along with url.
+test_files: []
+