feedbag 0.9.2 → 0.9.3

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 13f1c9e29ccb4e1c9affd106d1a7dacb641ebecf
+  data.tar.gz: 0b3ed450ad3fe07bca31cc120429092809d2bbdf
+SHA512:
+  metadata.gz: 03c341cc2fca2caf681ab6086b008498622ab639f3fb751ffe12a54c5a34e04f9d1c3c2cc145dcd25681dff02f16bbbe29e8149cd690429ede6159df6fc42ac0
+  data.tar.gz: 80b23d8060a4721b904e294196a1359f6d63efdcdac73d5ba715ccd0aff250713919f03fb28e7514d13436342cec6ccf3e1c42cb29cacb94c379dbf753484ad0

data/README.markdown

@@ -14,24 +14,23 @@ Feedbag is Ruby's favorite auto-discovery tool/library!
 	>> Feedbag.feed?("http://jobs.perl.org/rss/standard.rss")
     => true
 
-You can also use an installed command line tool for quick queries, if you install the gem:
-
-    $ feedbag http://rubygems.org/profiles/damog
-    == http://rubygems.org/profiles/damog:
-     - http://feeds.feedburner.com/gemcutter-latest
-
-
 ### Installation
 
-	$ sudo gem install feedbag
+	$ gem install feedbag
 
 Or just grab feedbag.rb and use it on your own project:
 
 	$ wget http://github.com/damog/feedbag/raw/master/lib/feedbag.rb
 
+You can also use the command line tool for quick queries, if you install the gem:
+
+    $ feedbag http://rubygems.org/profiles/damog
+    == http://rubygems.org/profiles/damog:
+     - http://feeds.feedburner.com/gemcutter-latest
+
 ### Why should you use it?
 
-- Because it only uses [Hpricot](https://code.whytheluckystiff.net/hpricot/) as dependency.
+- Because it only uses [Nokogiri](http://nokogiri.org/) 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's faster than rfeedfinder.

data/lib/feedbag.rb

@@ -22,180 +22,187 @@
 # WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 require "rubygems"
-require "hpricot"
+require "nokogiri"
 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.feed?(url)
-		# use LWR::Simple.normalize some time
-		url_uri = URI.parse(url)
-		url = "#{url_uri.scheme or 'http'}://#{url_uri.host}#{url_uri.path}"
-		url << "?#{url_uri.query}" if url_uri.query
-		
-		# hack:
-		url.sub!(/^feed:\/\//, 'http://')
-
-		res = self.find(url)
-		if res.size == 1 and res.first == url
-			return true
-		else
-			return false
-		end
-	end
-
-	def self.find(url, args = {})
-		$feeds = []
-
-		url_uri = URI.parse(url)
-		url = nil
-		if url_uri.scheme.nil?
-		  url = "http://#{url_uri.to_s}"
-		elsif url_uri.scheme == "feed"
-		  return self.add_feed(url_uri.to_s.sub(/^feed:\/\//, 'http://'), nil)
-		else
-		  url = url_uri.to_s
-		end
-		#url = "#{url_uri.scheme or 'http'}://#{url_uri.host}#{url_uri.path}"
-
-		# check if feed_valid is avail
+class Feedbag
+
+  CONTENT_TYPES = [
+    'application/x.atom+xml',
+    'application/atom+xml',
+    'application/xml',
+    'text/xml',
+    'application/rss+xml',
+    'application/rdf+xml',
+  ].freeze
+
+  def self.feed?(url)
+    new.feed?(url)
+  end
+
+  def self.find(url, args = {})
+    new.find(url, args = {})
+  end
+
+  def initialize
+    @feeds = []
+  end
+
+  def feed?(url)
+    # use LWR::Simple.normalize some time
+    url_uri = URI.parse(url)
+    url = "#{url_uri.scheme or 'http'}://#{url_uri.host}#{url_uri.path}"
+    url << "?#{url_uri.query}" if url_uri.query
+
+      # hack:
+      url.sub!(/^feed:\/\//, 'http://')
+
+    res = Feedbag.find(url)
+    if res.size == 1 and res.first == url
+      return true
+    else
+      return false
+    end
+  end
+
+  def find(url, args = {})
+    url_uri = URI.parse(url)
+    url = nil
+    if url_uri.scheme.nil?
+      url = "http://#{url_uri.to_s}"
+    elsif url_uri.scheme == "feed"
+      return self.add_feed(url_uri.to_s.sub(/^feed:\/\//, 'http://'), nil)
+    else
+      url = url_uri.to_s
+    end
+    #url = "#{url_uri.scheme or 'http'}://#{url_uri.host}#{url_uri.path}"
+
+    # check if feed_valid is avail
     begin
-  		require "feed_validator"
-	  	v = W3C::FeedValidator.new
-		  v.validate_url(url)
-			return self.add_feed(url, nil) if v.valid?
-  	rescue LoadError
-	  	# scoo
-		rescue REXML::ParseException
-  	  # usually indicates timeout
-	    # TODO: actually find out timeout. use Terminator?
-	    # $stderr.puts "Feed looked like feed but might not have passed validation or timed out"
+      require "feed_validator"
+      v = W3C::FeedValidator.new
+      v.validate_url(url)
+      return self.add_feed(url, nil) if v.valid?
+    rescue LoadError
+      # scoo
+    rescue REXML::ParseException
+      # usually indicates timeout
+      # TODO: actually find out timeout. use Terminator?
+      # $stderr.puts "Feed looked like feed but might not have passed validation or timed out"
     rescue => ex
-  		$stderr.puts "#{ex.class} error ocurred with: `#{url}': #{ex.message}"
-	  end
-
-		begin
-			html = open(url) do |f|
-				content_type = f.content_type.downcase
-				if content_type == "application/octet-stream" # open failed
-				  content_type = f.meta["content-type"].gsub(/;.*$/, '')
-				end
-				if @content_types.include?(content_type)
-					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
+      $stderr.puts "#{ex.class} error occurred with: `#{url}': #{ex.message}"
+    end
+
+    begin
+      html = open(url) do |f|
+        content_type = f.content_type.downcase
+        if content_type == "application/octet-stream" # open failed
+          content_type = f.meta["content-type"].gsub(/;.*$/, '')
+        end
+        if CONTENT_TYPES.include?(content_type)
+          return self.add_feed(url, nil)
+        end
+
+        doc = Nokogiri::HTML(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/"atom:link").each do |l|
-					next unless l["rel"]
-					if l["type"] and @content_types.include?(l["type"].downcase.strip) and l["rel"].downcase == "self"
-						self.add_feed(l["href"], url, $base_uri)
-					end
-				end
-
-				(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
+          next unless l["rel"]
+          if l["type"] and CONTENT_TYPES.include?(l["type"].downcase.strip) and l["rel"].downcase == "self"
+            self.add_feed(l["href"], url, @base_uri)
+          end
+        end
+
+        (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
 
         # Added support for feeds like http://tabtimes.com/tbfeed/mashable/full.xml
         if url.match(/.xml$/) and doc.root and doc.root["xml:base"] and doc.root["xml:base"].strip == url.strip
-					self.add_feed(url, nil)
+          self.add_feed(url, nil)
         end
-			end
-		rescue Timeout::Error => err
-			$stderr.puts "Timeout error ocurred with `#{url}: #{err}'"
-		rescue OpenURI::HTTPError => the_error
-			$stderr.puts "Error ocurred with `#{url}': #{the_error}"
-		rescue SocketError => err
-			$stderr.puts "Socket error ocurred with: `#{url}': #{err}"
-		rescue => ex
-			$stderr.puts "#{ex.class} error ocurred with: `#{url}': #{ex.message}"
-		ensure
-			return $feeds
-		end
-		
-	end
-
-	def self.looks_like_feed?(url)
-		if url =~ /(\.(rdf|xml|rdf|rss)$|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
-
-	# not used. yet.
-	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
+    rescue Timeout::Error => err
+      $stderr.puts "Timeout error occurred with `#{url}: #{err}'"
+    rescue OpenURI::HTTPError => the_error
+      $stderr.puts "Error occurred with `#{url}': #{the_error}"
+    rescue SocketError => err
+      $stderr.puts "Socket error occurred with: `#{url}': #{err}"
+    rescue => ex
+      $stderr.puts "#{ex.class} error occurred with: `#{url}': #{ex.message}"
+    ensure
+      return @feeds
+    end
+
+  end
+
+  def looks_like_feed?(url)
+    if url =~ /(\.(rdf|xml|rdf|rss)$|feed=(rss|atom)|(atom|feed)\/?$)/i
+      true
+    else
+      false
+    end
+  end
+
+  def 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
+
+  # not used. yet.
+  def _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
 
 if __FILE__ == $0

metadata

@@ -1,32 +1,58 @@
 --- !ruby/object:Gem::Specification
 name: feedbag
 version: !ruby/object:Gem::Version
-  version: 0.9.2
-  prerelease: 
+  version: 0.9.3
 platform: ruby
 authors:
 - David Moreno
+- Derek Willis
 autorequire: 
 bindir: bin
 cert_chain: []
 date: 2013-12-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: hpricot
+  name: nokogiri
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '0.6'
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '0.6'
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: shoulda
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: mocha
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.12.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.12.0
 description: Ruby's favorite feed auto-discoverty tool
 email: david@axiombox.com
 executables:
@@ -36,35 +62,34 @@ extra_rdoc_files:
 - README.markdown
 - COPYING
 files:
-- lib/feedbag.rb
+- COPYING
+- README.markdown
 - benchmark/rfeedfinder_benchmark.rb
 - bin/feedbag
-- README.markdown
-- COPYING
+- lib/feedbag.rb
 homepage: http://github.com/damog/feedbag
 licenses: []
+metadata: {}
 post_install_message: 
 rdoc_options:
-- --main
+- "--main"
 - README.markdown
 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: feedbag
-rubygems_version: 1.8.23
+rubygems_version: 2.2.2
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Ruby's favorite feed auto-discovery tool
 test_files: []