html2rss 0.12.0 → 0.13.0

data/lib/html2rss/utils.rb

@@ -31,12 +31,12 @@ module Html2rss
     ##
     # Removes any space, parses and normalizes the given url.
     # @param url [String]
-    # @return [String, nil] sanitized and normalized URL, or nil if input is empty
+    # @return [Addressable::URI, nil] normalized URL, or nil if input is empty
     def self.sanitize_url(url)
       url = url.to_s.gsub(/\s+/, ' ').strip
       return if url.empty?
 
-      Addressable::URI.parse(url).normalize.to_s
+      Addressable::URI.parse(url).normalize
     end
 
     ##
@@ -71,18 +71,13 @@ module Html2rss
 
     ##
     # @param url [String, Addressable::URI]
-    # @param convert_json_to_xml [true, false] Should JSON be converted to XML
     # @param headers [Hash] additional HTTP request headers to use for the request
-    # @return [String] body of the HTTP response
-    def self.request_body_from_url(url, convert_json_to_xml: false, headers: {})
-      response = Faraday.new(url:, headers:) do |faraday|
+    # @return [Faraday::Response] body of the HTTP response
+    def self.request_url(url, headers: {})
+      Faraday.new(url:, headers:) do |faraday|
         faraday.use Faraday::FollowRedirects::Middleware
         faraday.adapter Faraday.default_adapter
       end.get
-
-      body = response.body
-
-      convert_json_to_xml ? ObjectToXmlConverter.new(JSON.parse(body)).call : body
     end
 
     ##

data/lib/html2rss/version.rb

@@ -3,6 +3,6 @@
 ##
 # The Html2rss namespace.
 module Html2rss
-  VERSION = '0.12.0'
+  VERSION = '0.13.0'
   public_constant :VERSION
 end

data/lib/html2rss.rb

@@ -6,10 +6,21 @@ loader = Zeitwerk::Loader.for_gem
 loader.setup
 
 require 'yaml'
+require 'logger'
 
 ##
 # The Html2rss namespace.
 module Html2rss
+  ##
+  # The logger instance.
+  Log = Logger.new($stdout)
+
+  Log.level = ENV.fetch('LOG_LEVEL', :warn).upcase.to_sym
+
+  Log.formatter = proc do |severity, datetime, _progname, msg|
+    "#{datetime} [#{severity}] #{msg}\n"
+  end
+
   ##
   # The Html2rss::Error base class.
   class Error < StandardError; end
@@ -91,5 +102,15 @@ module Html2rss
     end
   end
 
+  ##
+  # Scrapes the provided URL and returns an RSS object.
+  # No need for a "feed config".
+  #
+  # @param url [String] the URL to automatically source the feed from
+  # @return [RSS::Rss]
+  def self.auto_source(url)
+    Html2rss::AutoSource.new(url).build
+  end
+
   private_class_method :load_yaml, :find_feed_config
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html2rss
 version: !ruby/object:Gem::Version
-  version: 0.12.0
+  version: 0.13.0
 platform: ruby
 authors:
 - Gil Desmarais
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2024-08-10 00:00:00.000000000 Z
+date: 2024-08-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
@@ -106,6 +106,20 @@ dependencies:
     - - "<"
       - !ruby/object:Gem::Version
         version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: parallel
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: regexp_parser
   requirement: !ruby/object:Gem::Requirement
@@ -230,6 +244,18 @@ files:
 - lib/html2rss/attribute_post_processors/sanitize_html.rb
 - lib/html2rss/attribute_post_processors/substring.rb
 - lib/html2rss/attribute_post_processors/template.rb
+- lib/html2rss/auto_source.rb
+- lib/html2rss/auto_source/article.rb
+- lib/html2rss/auto_source/channel.rb
+- lib/html2rss/auto_source/cleanup.rb
+- lib/html2rss/auto_source/reducer.rb
+- lib/html2rss/auto_source/rss_builder.rb
+- lib/html2rss/auto_source/scraper.rb
+- lib/html2rss/auto_source/scraper/schema.rb
+- lib/html2rss/auto_source/scraper/schema/base.rb
+- lib/html2rss/auto_source/scraper/semantic_html.rb
+- lib/html2rss/auto_source/scraper/semantic_html/extractor.rb
+- lib/html2rss/auto_source/scraper/semantic_html/image.rb
 - lib/html2rss/cli.rb
 - lib/html2rss/config.rb
 - lib/html2rss/config/channel.rb
@@ -253,7 +279,7 @@ licenses:
 - MIT
 metadata:
   allowed_push_host: https://rubygems.org
-  changelog_uri: https://github.com/html2rss/html2rss/releases/tag/v0.12.0
+  changelog_uri: https://github.com/html2rss/html2rss/releases/tag/v0.13.0
   rubygems_mfa_required: 'true'
 post_install_message: 
 rdoc_options: []