muck-feedbag 0.1.0 → 0.5.100

data/README.markdown

@@ -1,6 +1,7 @@
 Feedbag
 =======
-Forked version of feedback that returns title and url.
+> Do you want me to drag my sack across your face?
+>                                 - Glenn Quagmire
 
 Feedbag is a feed auto-discovery Ruby library. You don't need to know more about it. It is said to be:
 

data/lib/feedbag.rb

@@ -20,7 +20,6 @@ require "rubygems"
 require "hpricot"
 require "open-uri"
 require "net/http"
-require 'timeout'
 
 module Feedbag
   Feed = Struct.new(:url, :title)
@@ -66,8 +65,6 @@ module Feedbag
 		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
     unless args[:narrow]
       begin
@@ -87,38 +84,36 @@ module Feedbag
     end
 
 		begin
-      Timeout::timeout(10) do
-        open(url) do |f|
-          if @content_types.include?(f.content_type.downcase)
-            return self.add_feed(url, nil)
-          end
-
-          doc = Hpricot(f.read)
-
-          if doc.at("base") and doc.at("base")["href"]
-            $base_uri = doc.at("base")["href"]
-          else
-            $base_uri = nil
-          end
-
-          # first with links
-          (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, l["title"])
-            end
-          end
-
-          unless args[:narrow]
-            (doc/"a").each do |a|
-              next unless a["href"]
-              if self.looks_like_feed?(a["href"])
-                self.add_feed(a["href"], url, $base_uri, a["title"] || a.inner_html || a['alt']) # multiple fallbacks, first title, then the tag content, then the alt tag (in case of image)
-              end
-            end
-          end
+			open(url) do |f|
+				if @content_types.include?(f.content_type.downcase)
+					return self.add_feed(url, nil)
+				end
+
+				doc = Hpricot(f.read)
+
+				if doc.at("base") and doc.at("base")["href"]
+					$base_uri = doc.at("base")["href"]
+				else
+					$base_uri = nil
+				end
+
+				# first with links
+				(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, l["title"])
+					end
+				end
+
+        unless args[:narrow]
+	  			(doc/"a").each do |a|
+		  			next unless a["href"]
+			  		if self.looks_like_feed?(a["href"])
+				  		self.add_feed(a["href"], url, $base_uri, a["title"] || a.inner_html || a['alt']) # multiple fallbacks, first title, then the tag content, then the alt tag (in case of image)
+					  end
+  				end
         end
-      end
+			end
 		rescue Timeout::Error => err
 			$stderr.puts "Timeout error ocurred with `#{url}: #{err}'"
 		rescue OpenURI::HTTPError => the_error
@@ -133,7 +128,7 @@ module Feedbag
 	end
 
 	def self.looks_like_feed?(url)
-		if url =~ /((\.|\/)(rdf|xml|rdf|rss)$|feed=(rss|atom)|(atom|feed)\/?$)/i
+		if url =~ /(\.(rdf|xml|rdf|rss)$|feed=(rss|atom)|(atom|feed)\/?$)/i
 			true
 		else
 			false

metadata

@@ -1,57 +1,48 @@
 --- !ruby/object:Gem::Specification 
 name: muck-feedbag
 version: !ruby/object:Gem::Version 
-  version: 0.1.0
+  version: 0.5.100
 platform: ruby
 authors: 
-- Joel Duffin
-- Justin Ball
+- Axiombox
+- David Moreno
 autorequire: 
 bindir: bin
 cert_chain: []
 
-date: 2009-11-10 00:00:00 -07:00
+date: 2009-02-10 00:00:00 -08:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
-  name: shoulda
-  type: :development
+  name: hpricot
+  type: :runtime
   version_requirement: 
   version_requirements: !ruby/object:Gem::Requirement 
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: "0"
+        version: "0.6"
     version: 
-description: This gem will return title and url for each feed discovered at a given url
-email: justin@tatemae.com
+description: Ruby's favorite feed auto-discoverty tool
+email: david@axiombox.com
 executables: []
 
 extensions: []
 
 extra_rdoc_files: 
-- ChangeLog
 - README.markdown
-files: 
-- .gitignore
 - COPYING
-- ChangeLog
-- README.markdown
-- TODO
-- VERSION
-- benchmark/rfeedfinder_benchmark.rb
-- feedbag.gemspec
-- index.html
+files: 
 - lib/feedbag.rb
-- rails/init.rb
-- test/atom_autodiscovery_test.rb
+- benchmark/rfeedfinder_benchmark.rb
+- README.markdown
+- COPYING
 has_rdoc: true
-homepage: http://github.com/tatemae/muck-feedbag
-licenses: []
-
+homepage: http://axiombox.com/feedbag
 post_install_message: 
 rdoc_options: 
-- --charset=UTF-8
+- --main
+- README.markdown
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
@@ -69,9 +60,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.5
+rubygems_version: 1.2.0
 signing_key: 
-specification_version: 3
-summary: Fork of the feedbag gem.
-test_files: 
-- test/atom_autodiscovery_test.rb
+specification_version: 2
+summary: Ruby's favorite feed auto-discovery tool
+test_files: []
+

data/.gitignore

@@ -1,30 +0,0 @@
-*.swp
-**/*.pid
-log/*.log
-log/*.pid
-tmp
-.DS_Store
-public/cache/**/*
-public/system/**/*
-doc/**/*
-db/*.sqlite3
-.project
-.loadpath
-nbproject/
-.idea
-testjour.log
-*.so
-*.o
-Makefile
-mkmf.log
-*.bundle
-conftest
-content/
-.idea
-*.sw?
-.DS_Store
-coverage
-rdoc
-pkg
-pkg/*
-log/*

data/ChangeLog

@@ -1,20 +0,0 @@
-* 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/TODO

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

data/VERSION

@@ -1 +0,0 @@
-0.1.0

data/feedbag.gemspec

@@ -1,20 +0,0 @@
-# -*- encoding: utf-8 -*-
- 
-Gem::Specification.new do |s|
-  s.name = %q{feedbag}
-  s.version = "0.5.103"
-  s.homepage = "http://axiombox.com/feedbag"
-  #s.rubyforge_project = "feedbag"
- 
-  s.authors = ["Axiombox", "David Moreno"]
-  s.date = %q{2009-02-10}
-  s.description = %q{Ruby's favorite feed auto-discoverty tool}
-  s.email = %q{david@axiombox.com}
-  s.extra_rdoc_files = ["README.markdown", "COPYING"]
-  s.files = ["lib/feedbag.rb", "benchmark/rfeedfinder_benchmark.rb"]
-  s.has_rdoc = true
-  s.rdoc_options = ["--main", "README.markdown"]
-  s.summary = %q{Ruby's favorite feed auto-discovery tool}
-	s.add_dependency("hpricot", '>= 0.6') 
-end
-

data/index.html

@@ -1,115 +0,0 @@
-<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/rails/init.rb

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

data/test/atom_autodiscovery_test.rb

@@ -1,46 +0,0 @@
-#!/usr/bin/ruby
-
-require "#{File.dirname(__FILE__)}/../feedbag"
-require "test/unit"
-require "open-uri"
-require "hpricot"
-require "pp"
-
-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