rss_feed_plus 0.1.0 → 0.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ec579256585d8f4a9ddf84497d214779d61c605cbf443bd1e55e4f094204cdc5
-  data.tar.gz: 0bf2827e8bfab1aa2806578303ff04a570991c97a61673dc0edd8c9bb82c57e1
+  metadata.gz: ed3bccb810245ef55c8098543c200b38d82a3e42db7c7740a7a330c15729c518
+  data.tar.gz: 4ffdfd85aedd999af87a4053064a2c50a76ff93772c4910ca83ef802518be77e
 SHA512:
-  metadata.gz: 566a7978173b0d7527a6413d80f6f0a2245633c51b7dc2950346e0b1b81ba10d465f906887f5e0b1fa5b06870c657e7426f47a3ac7e1bd989aa739daf3dfac7f
-  data.tar.gz: 1f0c46d97d326cbb2aa65dced535beee715b58b9570e7ced3f2d4cb36d5d876ac25c8d16cd17884b383171cdcd0dae34927c90d20e40cc1f1952b17c4bba3f23
+  metadata.gz: 7a0c323043a3d4c014e9f840f364a9db8ab27c14c231a157496ea2e824b614e9f0121318ba400e891c111c89e89ac990b8d381d8d03b19739c093a48717e8611
+  data.tar.gz: a1c4dcb037b7d3c43e20a1d4403e239238cbb94d192a31a81270f7e498fd80b50ca2cd1ef081973d3bc7a7b742d5373941d6613c8ed7bc38f81b1b00957a45be

data/README.md

@@ -49,7 +49,10 @@ parser = RssFeed::Parser.new(feed_urls, xml_parser: xml_parser, uri_parser: uri_
 # or 
 parser = RssFeed::Parser.new(feed_urls)
 # Parse the RSS feeds
-parsed_data = parser.parse_as_object
+parsed_data = parser.parse_as_object 
+
+# OR  Parse the RSS feed as a JSON
+parsed_data = parser.parse
 
 # Process the parsed data
 puts parsed_data.inspect

data/lib/rss_feed/feed/base.rb

@@ -18,8 +18,6 @@ module RssFeed
         raise NotImplementedError
       end
 
-      private
-
       # Detects the type of the feed based on the root element of the XML document.
       #
       # @return [String] The name of the root element.

data/lib/rss_feed/feed/channel.rb

@@ -17,7 +17,8 @@ module RssFeed
         image logo icon rating
         rights copyright
         textInput feedburner:browserFriendly
-        itunes:author itunes:category
+        itunes:author itunes:category category itunes:explicit itunes:image itunes:keywords itunes:owner itunes:subtitle
+        itunes:summary
       ].freeze
 
       # XPath expression for selecting the RSS channel.
@@ -31,7 +32,7 @@ module RssFeed
       def atom
         return nil if document.blank?
 
-        '//feed'
+        '//xmlns:feed'
       end
 
       alias feed atom

data/lib/rss_feed/feed/item.rb

@@ -27,7 +27,7 @@ module RssFeed
 
       # XPath expression for selecting the Atom entry.
       def atom
-        '//entry'
+        '//xmlns:entry'
       end
 
       alias feed atom

data/lib/rss_feed/feed/namespace.rb

@@ -12,7 +12,9 @@ module RssFeed
         'feedburner' => 'http://rssnamespace.org/feedburner/ext/1.0',
         'content' => 'http://purl.org/rss/1.0/modules/content/',
         'trackback' => 'http://example.com/trackback',
-        'media' => 'http://search.yahoo.com/mrss/'
+        'media' => 'http://search.yahoo.com/mrss/',
+        'atom' => 'http://www.w3.org/2005/Atom',
+        'xmlns' => 'http://www.w3.org/2005/Atom'
       }.freeze
 
       class << self
@@ -21,8 +23,9 @@ module RssFeed
         # @param tag [String] The XML tag to access.
         # @param doc [Nokogiri::XML::Document] The XML document.
         # @return [Hash] The tag data including text, nested elements flag, nested attributes flag, and the document.
-        def access_tag(tag, doc)
-          doc = doc.xpath(tag, namespace(tag))
+        def access_tag(tag, doc, feed)
+          feed_tag = %w[atom feed].include?(feed.detect_feed_type) && namespace(tag).blank? ? "xmlns:#{tag}" : tag
+          doc = doc.xpath(feed_tag, namespace(tag))
           nested_elements = nested_elements?(doc)
           { text: doc.to_s, nested_elements: nested_elements, nested_attributes: nested_attributes?(doc), docs: doc }
         end
@@ -33,7 +36,7 @@ module RssFeed
         # @return [Hash] The namespace declaration.
         def namespace(tag)
           namespace_key = tag.split(':').first
-          { namespace_key.to_s => NAMESPACES[namespace_key] }.compact
+          NAMESPACES[namespace_key].blank? ? nil : { namespace_key.to_s => NAMESPACES[namespace_key] }.compact
         end
 
         # Removes HTML tags from the given content.

data/lib/rss_feed/parser.rb

@@ -93,7 +93,7 @@ module RssFeed
       item_data = {}
 
       feed.class::TAGS.each do |tag|
-        tag_data = extract_tag_data(tag, feed_parse)
+        tag_data = extract_tag_data(tag, feed_parse, feed)
         next if skip_extraction?(tag_data)
 
         items = extract_items(tag_data)
@@ -136,8 +136,8 @@ module RssFeed
     # @param tag [String] The tag to extract.
     # @param feed_parse [Hash] The parsed XML data.
     # @return [Hash] The extracted tag data.
-    def extract_tag_data(tag, feed_parse)
-      value = RssFeed::Feed::Namespace.access_tag(tag, feed_parse)
+    def extract_tag_data(tag, feed_parse, feed)
+      value = RssFeed::Feed::Namespace.access_tag(tag, feed_parse, feed)
       value[:attributes] = extract_attributes(value[:docs]) if value[:nested_attributes]
       value
     end

data/lib/rss_feed/version.rb

@@ -1,3 +1,3 @@
 module RssFeed
-  VERSION = '0.1.0'.freeze
+  VERSION = '0.1.1'.freeze
 end

data/parser.rb

@@ -1,7 +1,7 @@
 require 'rss_feed'
 require 'nokogiri'
 
-# require 'open-uri'
+require 'open-uri'
 #
 # # url = 'https://feeds.nbcnews.com/nbcnews/public/news'
 # # url = 'https://abcnews.go.com/abcnews/usheadlines'
@@ -11,7 +11,9 @@ require 'nokogiri'
 # p rss
 
 # Define your custom options
-feed_urls = 'https://feeds.nbcnews.com/nbcnews/public/news'
+# feed_urls = 'https://rubygems.org/gems/rss_feed_plus/versions.atom'
+feed_urls = 'http://dev.fyicenter.com/atom_xml.php'
+# feed_urls = 'https://feeds.nbcnews.com/nbcnews/public/news'
 xml_parser = Nokogiri
 uri_parser = URI
 timeout = 10
@@ -19,11 +21,45 @@ timeout = 10
 # Initialize the Parser class with custom options
 parser = RssFeed::Parser.new(feed_urls, xml_parser: xml_parser, uri_parser: uri_parser, timeout: timeout)
 
-# Parse the RSS feeds
-# parsed_data = parser.parse
 
-# Process the parsed data
-# puts parsed_data.inspect
-
-parsed_data = parser.parse_as_object
+parsed_data = parser.parse
 puts parsed_data.inspect
+
+# xml = URI.parse(feed_urls).open
+# doc = Nokogiri::XML(xml)
+# namespaces = doc.root.namespaces
+# spaces = {}
+# namespaces.each do |prefix, uri|
+#   puts "Namespace Prefix: #{prefix}"
+#   puts "Namespace URI: #{uri}"
+#   spaces[prefix] = uri
+# end
+# title = doc.xpath("//xmlns:entry").map { |entry| entry.at_xpath("dc:date", 'dc' => 'http://purl.org/dc/elements/1.1/') }
+# title = doc.xpath('//xmlns:entry').map { |entry| entry.xpath('//xmlns:title', 'xmlns' => 'http://www.w3.org/2005/Atom').text }
+
+# p title
+# tags = doc.xpath('//*[not(self::text() or self::comment())]').map(&:name).uniq
+# feed_tags = doc.xpath('/rss/channel/*').map(&:name).uniq
+#
+# # Get tags under <item> (entry)
+# entry_tags = doc.xpath('/rss/channel/item/*').map(&:name).uniq
+#
+# # Print tags under <channel> (feed)
+# puts "Tags under <channel> (feed):"
+# puts feed_tags
+#
+# puts "\nTags under <item> (entry):"
+# puts entry_tags
+
+# feed_tags = doc.xpath('/xmlns:feed/*').map(&:name).uniq
+#
+# # Get tags under <entry>
+# entry_tags = doc.xpath('/xmlns:feed/xmlns:entry/*').map(&:name).uniq
+#
+# # Print tags under <feed>
+# puts "Tags under <feed> (channel):"
+# puts feed_tags
+#
+# # Print tags under <entry>
+# puts "\nTags under <entry>:"
+# puts entry_tags

data/sig/rss_feed/feed/base.rbs

@@ -7,8 +7,6 @@ module RssFeed
 
       def parser: -> Nokogiri::XML::Document
 
-      private
-
       def detect_feed_type: -> String
 
 

data/sig/rss_feed/feed/namespace.rbs

@@ -5,7 +5,7 @@ module RssFeed
 
       def self.access_tag: (tag: String, doc: Nokogiri::XML::NodeSet)-> Hash[Symbol, bool | String | Nokogiri::XML::Document ]
 
-      def self.namespace: (tag: String)-> Hash[String, String]
+      def self.namespace: (tag: String)-> Hash[String, String] | nil
 
       def self.nested_attributes?:  (node: Nokogiri::XML::NodeSet) -> bool
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rss_feed_plus
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
 platform: ruby
 authors:
 - talaatmagdyx