damog-feedbag 0.2

data/README

@@ -0,0 +1,76 @@
+Feedbag 
+--------------------------------------------------------
+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.
+
+Quick synopsis
+--------------
+ ~/axiombox/feedbag :master $ irb
+ >> require "feedbag"
+ => true
+ >> Feedbag.find "http://log.damog.net/"
+ => ["http://feeds.feedburner.com/TeoremaDelCerdoInfinito", "http://log.damog.net/comments/feed/"]
+ >> 
+
+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 you should use it?
+----------------------
+- Because it's cool.
+- Because it only uses 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. It doesn't pass them all because some of those tests are
+	broken (citation needed).
+
+Why did you build it?
+---------------------
+- Because I liked Benjamin Trott's Feed::Finder.
+- Because I thought it would be good to have Feed::Finder's functionality
+  in Ruby.
+- Because I thought it was going to be easy to maintain.
+- Because I was going to use it on rFeed.
+

data/feedbag.rb

@@ -0,0 +1,137 @@
+#!/usr/bin/ruby
+
+# Copyright  Axiombox (c) 2008
+#            David Moreno <david@axiombox.com> (c) 2008
+
+#    This program is free software: you can redistribute it and/or modify
+#    it under the terms of the GNU General Public License as published by
+#    the Free Software Foundation, either version 3 of the License, or
+#    (at your option) any later version.
+#
+#    This program is distributed in the hope that it will be useful,
+#    but WITHOUT ANY WARRANTY; without even the implied warranty of
+#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#    GNU General Public License for more details.
+#
+#    You should have received a copy of the GNU General Public License
+#    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+
+# Originally wrote by David Moreno <david@axiombox.com>
+#  mainly based on Benjamin Trott's Feed::Find
+
+require "rubygems"
+require "hpricot"
+require "open-uri"
+require "net/http"
+
+module Feedbag
+
+	@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.find(url)
+		$feeds = []
+
+		url_uri = URI.parse(url)
+		url = "#{url_uri.scheme or 'http'}://#{url_uri.host}#{url_uri.path}"
+
+		begin
+			html = 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)
+					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}/)
+						self.add_feed(a["href"], url, $base_uri)
+					end
+				end
+
+				(doc/"a").each do |a|
+					next unless a["href"]
+					if self.looks_like_feed?(a["href"])
+						self.add_feed(a["href"], url, $base_uri)
+					end
+				end
+
+			end
+		rescue OpenURI::HTTPError => the_error
+			puts "Error ocurred with `#{url}': #{the_error}"
+		rescue SocketError => err
+			puts "Socket error ocurred with: `#{url}': #{err}"
+		end
+		
+		$feeds
+	end
+
+	def self.looks_like_feed?(url)
+		if url =~ /(\.(rdf|xml|rdf)$|feed=(rss|atom)|(atom|feed)\/$)/i
+			true
+		else
+			false
+		end
+	end
+
+	def self.add_feed(feed_url, orig_url, base_uri = nil)
+		# 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(url) unless $feeds.include?(url)# if self._is_http_valid(URI.parse(url), orig_url)
+	end
+
+	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
+

metadata

@@ -0,0 +1,64 @@
+--- !ruby/object:Gem::Specification 
+name: damog-feedbag
+version: !ruby/object:Gem::Version 
+  version: "0.2"
+platform: ruby
+authors: 
+- Axiombox
+- David Moreno
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2008-12-25 00:00:00 -08:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: hpricot
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+    version: 
+description: Ruby's favorite feed auto-discoverty tool
+email: david@axiombox.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- README
+files: 
+- feedbag.rb
+- README
+has_rdoc: true
+homepage: http://axiombox.com/feedbag
+post_install_message: 
+rdoc_options: 
+- --main
+- README
+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: feedbag
+rubygems_version: 1.2.0
+signing_key: 
+specification_version: 2
+summary: Ruby's favorite feed auto-discovery tool
+test_files: []
+