truffle-hog 0.0.1

data/README.textile

@@ -0,0 +1,66 @@
+h1. TruffleHog
+
+"http://github.com/pauldix/truffle-hog":http://github.com/pauldix/truffle-hog
+
+If you have issues please use the "Feedzirra group":http://groups.google.com/group/feedzirra
+
+h2. Summary
+
+Finds RSS and Atom feed urls in html like a hog finds truffles. Tasty, delicious feeds... er, truffles.
+
+h2. Description
+
+This is a simple library. It doesn't GET the html for you. It doesn't use an HTML or XML parser. It just uses a little regex to find feed urls. If you want to GET the web pages, use "Typhoeus":http://github.com/pauldix/typhoeus/. If you want to fetch and parse the feeds use "Feedzirra":http://github.com/pauldix/feedzirra.
+
+h2. Installation
+
+<pre>
+  gem install truffle-hog --source http://gemcutter.org
+</pre>
+
+h2. Use
+
+<pre>
+require 'rubygems'
+require 'truffle-hog'
+
+# get atom and rss
+feed_urls = TruffleHog.parse_feed_urls(some_html)
+
+# get atom if available, otherwise rss
+feed_urls = TruffleHog.parse_feed_urls(some_html, :atom)
+
+# get rss if available, otherwise atom
+feed_urls = TruffleHog.parse_feed_urls(some_html, :rss)
+</pre>
+
+h2. Next
+
+I may want to make a fun Nokogiri backed version and test speed and stuff. This thing hasn't been benchmarked yet.
+
+h2. LICENSE
+
+(The MIT License)
+ 
+Copyright (c) 2009:
+ 
+"Paul Dix":http://pauldix.net
+ 
+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/lib/truffle-hog.rb

@@ -0,0 +1,27 @@
+module TruffleHog
+  VERSION = "0.0.1"
+  
+  def self.parse_feed_urls(html, favor = :all)
+    rss_links  = []
+    atom_links = []
+    
+    rss_links  = (scan_for_tag(html, "a", "rss") + scan_for_tag(html, "link", "rss")).flatten.uniq
+    atom_links = (scan_for_tag(html, "a", "atom") + scan_for_tag(html, "link", "atom")).flatten.uniq
+
+    case favor
+    when :all
+      (rss_links + atom_links).uniq
+    when :rss
+      rss_links.empty? ? atom_links : rss_links
+    when :atom
+      atom_links.empty? ? rss_links : atom_links
+    end
+  end
+  
+  def self.scan_for_tag(html, tag, type)
+    href_first = html.scan(/<#{tag}.*href\=['"](.*?)['"].*type\=['"]application\/#{type}\+xml['"].*?>/)
+    return href_first unless href_first.empty?
+    
+    html.scan(/<#{tag}.*type\=['"]application\/#{type}\+xml['"].*href=['"](.*?)['"].*?>/)
+  end
+end

data/spec/spec.opts

@@ -0,0 +1,2 @@
+--diff
+--color

data/spec/spec_helper.rb

@@ -0,0 +1,10 @@
+require "rubygems"
+require "spec"
+
+# gem install redgreen for colored test output
+begin require "redgreen" unless ENV['TM_CURRENT_LINE']; rescue LoadError; end
+
+path = File.expand_path(File.dirname(__FILE__) + "/../lib/")
+$LOAD_PATH.unshift(path) unless $LOAD_PATH.include?(path)
+
+require "lib/truffle-hog"

data/spec/truffle-hog_spec.rb

@@ -0,0 +1,44 @@
+require File.dirname(__FILE__) + '/spec_helper'
+
+describe "parsing html" do
+  before(:all) do
+    @html = File.read(File.dirname(__FILE__) + "/pauldix_net.html")
+  end
+  
+  it "parses all feed urls" do
+    TruffleHog.parse_feed_urls(@html).should == ["http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/rss", 
+                                                 "http://www.pauldix.net/in_head/index.rdf", "http://www.pauldix.net/in_head/rss.xml", 
+                                                 "http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/atom", 
+                                                 "http://www.pauldix.net/in_head/atom.xml"]
+  end
+  
+  it "parses rss feeds from the link tags in head" do
+    feed_urls = TruffleHog.parse_feed_urls(@html, :rss)
+    feed_urls.should include("http://www.pauldix.net/in_head/index.rdf")
+    feed_urls.should include("http://www.pauldix.net/in_head/rss.xml")
+    feed_urls.should_not include("http://www.pauldix.net/in_head/atom.xml")
+    feed_urls.should_not include("http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/atom")
+  end
+  
+  it "parses atom feeds from the link tags in head" do
+    feed_urls = TruffleHog.parse_feed_urls(@html, :atom)
+    feed_urls.should include("http://www.pauldix.net/in_head/atom.xml")
+    feed_urls.should_not include("http://www.pauldix.net/in_head/index.rdf")
+    feed_urls.should_not include("http://www.pauldix.net/in_head/rss.xml")
+  end
+  
+  it "parses rss feeds from the body" do
+    feed_urls = TruffleHog.parse_feed_urls(@html, :rss)
+    feed_urls.should include("http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/rss")
+    feed_urls.should_not include("http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/atom")
+  end
+
+  it "parses atom feeds from the body" do
+    feed_urls = TruffleHog.parse_feed_urls(@html, :atom)
+    feed_urls.should include("http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/atom")
+    feed_urls.should_not include("http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/rss")
+  end
+  
+  it "returns atom feeds if rss is favored, but none are found"
+  it "returns rss feeds if atom is favored, but none are found"
+end

metadata

@@ -0,0 +1,59 @@
+--- !ruby/object:Gem::Specification 
+name: truffle-hog
+version: !ruby/object:Gem::Version 
+  version: 0.0.1
+platform: ruby
+authors: 
+- Paul Dix
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-09-21 00:00:00 -04:00
+default_executable: 
+dependencies: []
+
+description: 
+email: paul@pauldix.net
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- lib/truffle-hog.rb
+- README.textile
+- spec/spec.opts
+- spec/spec_helper.rb
+- spec/truffle-hog_spec.rb
+has_rdoc: true
+homepage: http://github.com/pauldix/truffle-hog
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.5
+signing_key: 
+specification_version: 2
+summary: Finds RSS and Atom feed urls in html like a hog finds truffles. Tasty, delicious feeds... er, truffles.
+test_files: []
+