feed_detector 0.0.1

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in feed_detector.gemspec
+gemspec

data/LICENSE

@@ -0,0 +1,22 @@
+Copyright (c) 2012 Bettina Steger
+
+MIT License
+
+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/README.md

@@ -0,0 +1,29 @@
+# FeedDetector
+
+TODO: Write a gem description
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'feed_detector'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install feed_detector
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Added some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,2 @@
+#!/usr/bin/env rake
+require "bundler/gem_tasks"

data/feed_detector.gemspec

@@ -0,0 +1,17 @@
+# -*- encoding: utf-8 -*-
+require File.expand_path('../lib/feed_detector/version', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.authors       = ["Bettina Steger"]
+  gem.email         = ["bettina_steger@gmx.at"]
+  gem.description   = %q{A ruby gem based on code from Dominiek's post (http://synaptify.com/?p=93) on detecting feeds. }
+  gem.summary       = %q{A ruby gem based on code from Dominiek's post (http://synaptify.com/?p=93) on detecting feeds. }
+  gem.homepage      = ""
+
+  gem.files         = `git ls-files`.split($\)
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.name          = "feed_detector"
+  gem.require_paths = ["lib"]
+  gem.version       = FeedDetector::VERSION
+end

data/lib/feed_detector/version.rb

@@ -0,0 +1,3 @@
+module FeedDetector
+  VERSION = "0.0.1"
+end

data/lib/feed_detector.rb

@@ -0,0 +1,76 @@
+require "feed_detector/version"
+require "net/http"
+require "uri"
+
+module FeedDetector
+  
+  # return the feed url for a url
+  # for example: http://blog.dominiek.com/ => http://blog.dominiek.com/feed/atom.xml
+  # only_detect can force detection of :rss or :atom
+  # if nil is returned the has no discernible feed url -- perhaps because it's the feed url
+  def self.url_from_string(url)
+    if url =~ /^http:\/\//
+      url
+    else
+      "http://#{url}"
+    end
+  end
+
+  ## converts relative urls to absolute urls
+  def self.to_absolute_url(page_url,feed_url)
+    if feed_url =~ /^http:\/\// ## if its absolute
+      feed_url
+    elsif feed_url =~ /^\//  ## relative to the host root ## '/some_dir_from_root/feed.xml'
+      "http://#{URI.parse(page_url).host.to_s + feed_url}"
+    else  ## relative to the page path ## 'feed.xml'
+      feed_path = page_url.scan(/^(http:\/\/[^\/]+)((?:\/[^\/]+)+(?=\/))?\/?(?:[^\/]+)?$/i).to_s
+      feed_path +'/'+ feed_url
+    end
+  end
+  
+  def self.fetch_feed_urls(page_url, only_detect=nil)
+    retries = 3 ## default retries
+    html = ""
+    begin
+      response = Net::HTTP.get_response(URI.parse(page_url)) # sends get request
+      html = response.body
+    rescue
+      retries -= 1
+      if retries > 0
+        sleep 0.42 and retry
+      else
+        raise
+      end
+    end
+
+    feed_urls = self.get_feed_paths(html, only_detect)
+    feed_urls.map { |feed_url| self.to_absolute_url(page_url, feed_url) }
+  end
+
+  ##
+  # get the feed href from an HTML document
+  # for example:
+  # ...
+  # <link href="/feed/atom.xml" rel="alternate" type="application/atom+xml" />
+  # ...
+  # => /feed/atom.xml
+  # only_detect can force detection of :rss or :atom
+  def self.get_feed_paths(html, only_detect=nil)
+    matches =[]
+
+    unless only_detect && only_detect != :atom
+      matches |= html.scan(/<link.*href=['"]*([^\s'"]+)['"]*.*application\/atom\+xml.*>/)
+      matches |= html.scan(/<link.*application\/atom\+xml.*href=['"]*([^\s'"]+)['"]*.*>/)
+      #matches |=  atom_feed
+    end
+    
+    unless only_detect && only_detect != :rss  
+      matches |= html.scan(/<link.*href=['"]*([^\s'"]+)['"]*.*application\/rss\+xml.*>/)
+      matches |= html.scan(/<link.*application\/rss\+xml.*href=['"]*([^\s'"]+)['"]*.*>/)
+    #  matches |= rss_feed
+    end
+
+    flattened_matches = matches.flatten
+    flattened_matches
+  end
+end

data/test/feed_detector_test.rb

@@ -0,0 +1,144 @@
+require 'test/unit'
+$LOAD_PATH << File.join(File.dirname(__FILE__), '..', 'lib')
+require 'feed_detector'
+
+class FeedDetectorTest < Test::Unit::TestCase
+  def setup
+    @body = []
+    
+    @wordpress_atom_url = 'http://bettysteger.com/feed/' # the link says it's RSS, the XML is really ATOM
+    @wordpress_single_feed_page_url = 'http://9gag.com/'
+    @wordpress_several_feed_page_url = 'http://bettysteger.com/'  
+    
+    @blogger_atom_url = 'http://ethandraws.blogspot.com/feeds/posts/default'
+    @blogger_other_atom_url = 'http://www.blogger.com/feeds/21351008/posts/default'
+    @blogger_rss_url = 'http://ethandraws.blogspot.com/feeds/posts/default?alt=rss'
+    @blogger_page_url = 'http://ethandraws.blogspot.com/'    
+  end
+  
+  def test_get_feed_path
+    # page containing no feeds
+    html = make_html(nil_feed_html).join("\n")
+    feed_paths = FeedDetector.get_feed_paths(html)
+    assert_equal([], feed_paths)
+    
+    # page containing a single atom feed
+    html = make_html(single_atom_feed_html).join("\n")
+    feed_paths = FeedDetector.get_feed_paths(html)
+    assert_equal(['/feed/atom.xml'], feed_paths)
+    
+    # page containing a single rss feed
+    html = make_html(single_rss_feed_html).join("\n")
+    feed_paths = FeedDetector.get_feed_paths(html)
+    assert_equal(['/feed/blog.xml'], feed_paths)
+
+    # page containing several feeds
+    html = make_html(multi_feed_html).join("\n")
+    feed_paths = FeedDetector.get_feed_paths(html)
+    assert_equal(["/feed/blog.xml",
+                  "http://ethandraws.blogspot.com/feeds/posts/default",
+                  "http://ethandraws.blogspot.com/feeds/posts/default?alt=rss",
+                  "http://giftedslacker.com/feed/",
+                  "http://www.blogger.com/feeds/21351008/posts/default"], feed_paths.sort)
+  end
+  
+  def test_get_feed_paths_with_only_detect
+    # page containing no feeds w/rss
+    html = make_html(nil_feed_html).join("\n")
+    feed_paths = FeedDetector.get_feed_paths(html, :rss)
+    assert_equal([], feed_paths)
+    
+    # page containing no feeds w/atom
+    html = make_html(nil_feed_html).join("\n")
+    feed_paths = FeedDetector.get_feed_paths(html, :atom)
+    assert_equal([], feed_paths)
+    
+    # page containing a single feed w/rss
+    html = make_html(single_rss_feed_html).join("\n")
+    feed_paths = FeedDetector.get_feed_paths(html, :rss)
+    assert_equal(['/feed/blog.xml'], feed_paths)
+    
+    # page containing a single feed w/atom
+    html = make_html(single_atom_feed_html).join("\n")
+    feed_paths = FeedDetector.get_feed_paths(html, :atom)
+    assert_equal(['/feed/atom.xml'], feed_paths)
+
+    # page containing several feeds w/rss
+    html = make_html(multi_feed_html(:rss)).join("\n")
+    feed_paths = FeedDetector.get_feed_paths(html, :rss)    
+    assert_equal(["/feed/blog.xml",
+                  "http://ethandraws.blogspot.com/feeds/posts/default?alt=rss",
+                  "http://giftedslacker.com/feed/"], feed_paths.sort)
+                  
+    # page containing several feeds w/atom
+    html = make_html(multi_feed_html(:atom)).join("\n")
+    feed_paths = FeedDetector.get_feed_paths(html, :atom)    
+    assert_equal(["/feed/atom.xml",
+                  "http://ethandraws.blogspot.com/feeds/posts/default",
+                  "http://www.blogger.com/feeds/21351008/posts/default"], feed_paths.sort)
+  end
+  
+  def test_fetch_feed_urls
+    # page containing a single feed pointer
+    result = ["http://9gag.com/rss/site/feed.rss"]
+    feed_paths = FeedDetector.fetch_feed_urls(@wordpress_single_feed_page_url)
+    assert_equal(result, feed_paths)
+    feed_paths = FeedDetector.fetch_feed_urls(@wordpress_single_feed_page_url, :rss)
+    assert_equal(result, feed_paths)
+    feed_paths = FeedDetector.fetch_feed_urls(@wordpress_single_feed_page_url, :atom)
+    assert_equal([], feed_paths)
+    
+    # page containing several feed pointers
+    result = [@wordpress_atom_url, "http://bettysteger.com/comments/feed/"]  
+    feed_paths = FeedDetector.fetch_feed_urls(@wordpress_several_feed_page_url)
+    assert_equal(result, feed_paths)
+    # feed_paths = FeedDetector.fetch_feed_urls(@wordpress_several_feed_page_url, :rss)
+    # assert_equal(["http://www.hasmanydevelopers.com/rss.xml"], feed_paths)
+    # feed_paths = FeedDetector.fetch_feed_urls(@wordpress_several_feed_page_url, :atom)
+    # assert_equal(["http://www.hasmanydevelopers.com/atom.xml"], feed_paths)
+  end
+  
+  #TODO: add tests for malformed urls
+
+private  
+  def multi_feed_html(spec=:rss)
+    body = []
+    body << '   <link rel="alternate" type="application/atom+xml" title="Ethan Draws - Atom" href="http://ethandraws.blogspot.com/feeds/posts/default" />'
+    body << '   <link rel="service.post" type="application/atom+xml" title="Ethan Draws - Atom" href="http://www.blogger.com/feeds/21351008/posts/default" />'    
+    body << '   <link rel="alternate" type="application/rss+xml" title="Ethan Draws - RSS" href="http://ethandraws.blogspot.com/feeds/posts/default?alt=rss" />'
+    body << '   <link rel="alternate" type="application/rss+xml" title="Gifted Slacker RSS Feed" href="http://giftedslacker.com/feed/" />'
+    if spec == :rss
+      body << '   <link href="/feed/blog.xml" rel="alternate" type="application/rss+xml" />'
+    else
+      body << '   <link href="/feed/atom.xml" rel="alternate" type="application/atom+xml" />'    
+    end
+    body
+  end
+  
+  def single_atom_feed_html
+    body = []
+    body << '   <link href="/feed/atom.xml" rel="alternate" type="application/atom+xml" />'
+    body
+  end
+  
+  def single_rss_feed_html
+    body = []
+    body << '   <link href="/feed/blog.xml" rel="alternate" type="application/rss+xml" />'
+    body
+  end
+  
+  def nil_feed_html
+    []
+  end
+  
+  def make_html(lines)
+    @body = []
+    @body << ' <html>'
+    @body << '  <head>'
+    @body << '   <link href="/super.css" rel="alternate" type="text/css"/>'
+    lines.each { |line| @body << line }
+    @body << '  </head>'
+    @body << ' </html>'
+  end
+  
+end

metadata

@@ -0,0 +1,58 @@
+--- !ruby/object:Gem::Specification
+name: feed_detector
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Bettina Steger
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-04-27 00:00:00.000000000 Z
+dependencies: []
+description: ! 'A ruby gem based on code from Dominiek''s post (http://synaptify.com/?p=93)
+  on detecting feeds. '
+email:
+- bettina_steger@gmx.at
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- feed_detector.gemspec
+- lib/feed_detector.rb
+- lib/feed_detector/version.rb
+- test/feed_detector_test.rb
+homepage: ''
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.11
+signing_key: 
+specification_version: 3
+summary: A ruby gem based on code from Dominiek's post (http://synaptify.com/?p=93)
+  on detecting feeds.
+test_files:
+- test/feed_detector_test.rb
+has_rdoc: