feed_detector 0.0.1 → 0.0.2

data/README.md

@@ -1,6 +1,10 @@
 # FeedDetector
 
-TODO: Write a gem description
+Detecting RSS feeds: When you use a proper browser like Mozilla Firefox you will see a syndication icon every time you visit a website that has RSS feeds:
+
+It does this by reading certain HTML tags.
+
+After a quick search I couldn’t find any code to do this in my own project, so I wrote a little piece of code for it with a RubyOnRails integration test.
 
 ## Installation
 
@@ -18,7 +22,27 @@ Or install it yourself as:
 
 ## Usage
 
-TODO: Write usage instructions here
+    FeedDetector.fetch_feed_urls('http://www.rubycorner.com')
+    => ["http://www.rubycorner.com/feeds/updated/atom10", "http://www.rubycorner.com/feeds/updated/rss20"]
+
+    FeedDetector.fetch_feed_urls('http://blog.dominiek.com/')
+     => ["http://blog.dominiek.com/feed/atom.xml"]
+
+    FeedDetector.fetch_feed_urls('http://blog.dominiek.com/feed/atom.xml')
+    => ["http://blog.dominiek.com/feed/atom.xml"]
+
+    FeedDetector.fetch_feed_urls('http://www.flickr.com/photos/dominiekterheide/', :rss)
+    => ["http://api.flickr.com/services/feeds/photos_public.gne?id=71386598@N00&lang=en-us&format=rss_200"]
+
+alternatively you can parse HTML with 
+    
+    FeedDetector.get_feed_paths(html_data)
+
+see integration test for more examples
+
+## TODO
+* Decouple parsing and retrieving data.
+* Tests should not depend on data retrieved from the web taking a particular form.
 
 ## Contributing
 

data/lib/feed_detector/version.rb

@@ -1,3 +1,3 @@
 module FeedDetector
-  VERSION = "0.0.1"
+  VERSION = "0.0.2"
 end

data/lib/feed_detector.rb

@@ -1,35 +1,16 @@
 require "feed_detector/version"
 require "net/http"
 require "uri"
+require "nokogiri"
 
 module FeedDetector
   
-  # return the feed url for a url
+  # returns all feed urls from one 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
-  
+  # if nil is returned no feeds were detected - perhaps because it's the feed url
   def self.fetch_feed_urls(page_url, only_detect=nil)
-    retries = 3 ## default retries
+    retries = 3 # default retries
     html = ""
     begin
       response = Net::HTTP.get_response(URI.parse(page_url)) # sends get request
@@ -47,30 +28,42 @@ module FeedDetector
     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 =[]
+    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
+    # parse html with nokogiri to find all link tags (see self.get_link_href)
+    doc = Nokogiri::HTML.parse(html)
+
+    unless only_detect
+      ["rss", "atom"].each do |type|
+        matches << get_link_href(doc, type)
+      end
+    else
+      matches << get_link_href(doc, only_detect.to_s)
     end
 
-    flattened_matches = matches.flatten
-    flattened_matches
+    matches.flatten
+  end
+
+  private
+
+  # finding all link tags and get the attribute href
+  # types: rss or atom
+  def self.get_link_href doc, type
+    doc.css('link[type="application/'+type+'+xml"]').map { |link| link['href'] }
   end
+
+  # converts relative urls to absolute urls
+  def self.to_absolute_url(page_url,feed_url)
+    return feed_url if feed_url =~ /^http:\/\// # already absolute
+    File.join(page_url, feed_url)
+  end
+
+
 end

data/test/feed_detector_test.rb

@@ -7,7 +7,7 @@ class FeedDetectorTest < Test::Unit::TestCase
     @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_single_feed_page_url = 'http://showmaniac.org'
     @wordpress_several_feed_page_url = 'http://bettysteger.com/'  
     
     @blogger_atom_url = 'http://ethandraws.blogspot.com/feeds/posts/default'
@@ -80,12 +80,12 @@ class FeedDetectorTest < Test::Unit::TestCase
   
   def test_fetch_feed_urls
     # page containing a single feed pointer
-    result = ["http://9gag.com/rss/site/feed.rss"]
+    result = ["http://showmaniac.org/feed"]
     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(result, feed_paths)
+    feed_paths = FeedDetector.fetch_feed_urls(@wordpress_single_feed_page_url, :rss)
     assert_equal([], feed_paths)
     
     # page containing several feed pointers

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: feed_detector
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
   prerelease: 
 platform: ruby
 authors: