html2rss 0.9.0 → 0.11.0

data/lib/html2rss.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require 'zeitwerk'
 
 loader = Zeitwerk::Loader.for_gem
@@ -7,35 +9,39 @@ require 'yaml'
 
 ##
 # The Html2rss namespace.
-# Request HTML from an URL and transform it to a RSS 2.0 object.
 module Html2rss
   ##
-  # Returns a RSS object which is generated from the provided file.
-  #
-  # `file_path`: a File object of a YAML file
-  # `name`: the of the feed
+  # The Html2rss::Error base class.
+  class Error < StandardError; end
+
+  ##
+  # Key for the feeds configuration in the YAML file.
+  CONFIG_KEY_FEEDS = :feeds
+
+  ##
+  # Returns an RSS object generated from the provided YAML file configuration.
   #
   # Example:
   #
   #    feed = Html2rss.feed_from_yaml_config(File.join(['spec', 'config.test.yml']), 'nuxt-releases')
   #    # => #<RSS::Rss:0x00007fb2f6331228
-  # @return [RSS:Rss]
-  def self.feed_from_yaml_config(file, name)
-    # rubocop:disable Security/YAMLLoad
-    yaml = YAML.load(File.open(file))
-    # rubocop:enable Security/YAMLLoad
+  #
+  # @param file [String] Path to the YAML file.
+  # @param name [String, Symbol, nil] Name of the feed in the YAML file.
+  # @param global_config [Hash] Global options (e.g., HTTP headers).
+  # @param params [Hash] Dynamic parameters for the feed configuration.
+  # @return [RSS::Rss] RSS object generated from the configuration.
+  def self.feed_from_yaml_config(file, name = nil, global_config: {}, params: {})
+    yaml = load_yaml(file)
+    feeds = yaml[CONFIG_KEY_FEEDS] || {}
 
-    feed_config = yaml['feeds'][name]
-    global_config = yaml.reject { |key| key == 'feeds' }
+    feed_config = find_feed_config(yaml, feeds, name, global_config)
 
-    config = Config.new(feed_config, global_config)
-    feed(config)
+    feed(Config.new(feed_config, global_config, params))
   end
 
   ##
-  # Returns a RSS object which is generated from the provided config.
-  #
-  # `config`: can be a Hash or an instance of Html2rss::Config.
+  # Returns an RSS object generated from the provided configuration.
   #
   # Example:
   #
@@ -48,11 +54,42 @@ module Html2rss
   #      }
   #    )
   #    # => #<RSS::Rss:0x00007fb2f48d14a0 ...>
-  # @return [RSS:Rss]
+  #
+  # @param config [Hash<Symbol, Object>, Html2rss::Config] Feed configuration.
+  # @return [RSS::Rss] RSS object generated from the configuration.
   def self.feed(config)
     config = Config.new(config) unless config.is_a?(Config)
+    RssBuilder.build(config)
+  end
 
-    feed = FeedBuilder.new config
-    feed.rss
+  ##
+  # Loads and parses the YAML file.
+  #
+  # @param file [String] Path to the YAML file.
+  # @return [Hash] Parsed YAML content.
+  def self.load_yaml(file)
+    YAML.safe_load_file(file, symbolize_names: true)
   end
+
+  ##
+  # Builds the feed configuration based on the provided parameters.
+  #
+  # @param yaml [Hash] Parsed YAML content.
+  # @param feeds [Hash] Feeds from the YAML content.
+  # @param feed_name [String, Symbol, nil] Name of the feed in the YAML file.
+  # @param global_config [Hash] Global options (e.g., HTTP headers).
+  # @return [Hash] Feed configuration.
+  def self.find_feed_config(yaml, feeds, feed_name, global_config)
+    return yaml unless feed_name
+
+    feed_name = feed_name.to_sym
+    if feeds.key?(feed_name)
+      global_config.merge!(yaml.reject { |key| key == CONFIG_KEY_FEEDS })
+      feeds[feed_name]
+    else
+      yaml
+    end
+  end
+
+  private_class_method :load_yaml, :find_feed_config
 end

metadata

@@ -1,35 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: html2rss
 version: !ruby/object:Gem::Version
-  version: 0.9.0
+  version: 0.11.0
 platform: ruby
 authors:
 - Gil Desmarais
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-06-19 00:00:00.000000000 Z
+date: 2024-08-09 00:00:00.000000000 Z
 dependencies:
-- !ruby/object:Gem::Dependency
-  name: activesupport
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '5'
-    - - "<"
-      - !ruby/object:Gem::Version
-        version: '7'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '5'
-    - - "<"
-      - !ruby/object:Gem::Version
-        version: '7'
 - !ruby/object:Gem::Dependency
   name: addressable
   requirement: !ruby/object:Gem::Requirement
@@ -44,36 +24,28 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '2.7'
-- !ruby/object:Gem::Dependency
-  name: builder
-  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: faraday
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">"
+      - !ruby/object:Gem::Version
+        version: 2.0.1
+    - - "<"
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: '3.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">"
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: 2.0.1
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '3.0'
 - !ruby/object:Gem::Dependency
-  name: faraday_middleware
+  name: faraday-follow_redirects
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -135,35 +107,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '2.0'
 - !ruby/object:Gem::Dependency
-  name: reverse_markdown
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.0'
-- !ruby/object:Gem::Dependency
-  name: sanitize
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '5.0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '5.0'
-- !ruby/object:Gem::Dependency
-  name: to_regexp
+  name: regexp_parser
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -177,41 +121,27 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: zeitwerk
+  name: reverse_markdown
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '2.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: bundler
-  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'
+        version: '2.0'
 - !ruby/object:Gem::Dependency
-  name: byebug
+  name: rss
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  type: :development
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
@@ -219,69 +149,27 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: rspec
+  name: sanitize
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.0'
-  type: :development
+        version: '6.0'
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '6.0'
 - !ruby/object:Gem::Dependency
-  name: rubocop
+  name: thor
   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: rubocop-performance
-  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: rubocop-rspec
-  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: simplecov
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
@@ -289,13 +177,13 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: vcr
+  name: tzinfo
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  type: :development
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
@@ -303,69 +191,69 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: yard
+  name: zeitwerk
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  type: :development
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-description: Give the URL to scrape and some CSS selectors. Get a RSS::Rss instance
-  in return.
+description: Supports JSON content, custom HTTP headers, and post-processing of extracted
+  content.
 email:
 - html2rss@desmarais.de
-executables: []
+executables:
+- html2rss
 extensions: []
 extra_rdoc_files: []
 files:
-- ".gitignore"
-- ".rspec"
-- ".rubocop.yml"
-- ".travis.yml"
-- ".yardopts"
-- CHANGELOG.md
-- Gemfile
-- Gemfile.lock
 - LICENSE
 - README.md
-- bin/console
-- bin/setup
+- exe/html2rss
 - html2rss.gemspec
 - lib/html2rss.rb
 - lib/html2rss/attribute_post_processors.rb
 - lib/html2rss/attribute_post_processors/gsub.rb
 - lib/html2rss/attribute_post_processors/html_to_markdown.rb
+- lib/html2rss/attribute_post_processors/html_transformers/transform_urls_to_absolute_ones.rb
+- lib/html2rss/attribute_post_processors/html_transformers/wrap_img_in_a.rb
 - lib/html2rss/attribute_post_processors/markdown_to_html.rb
 - lib/html2rss/attribute_post_processors/parse_time.rb
 - lib/html2rss/attribute_post_processors/parse_uri.rb
 - lib/html2rss/attribute_post_processors/sanitize_html.rb
 - lib/html2rss/attribute_post_processors/substring.rb
 - lib/html2rss/attribute_post_processors/template.rb
+- lib/html2rss/cli.rb
 - lib/html2rss/config.rb
-- lib/html2rss/feed_builder.rb
+- lib/html2rss/config/channel.rb
+- lib/html2rss/config/selectors.rb
 - lib/html2rss/item.rb
 - lib/html2rss/item_extractors.rb
 - lib/html2rss/item_extractors/attribute.rb
-- lib/html2rss/item_extractors/current_time.rb
 - lib/html2rss/item_extractors/href.rb
 - lib/html2rss/item_extractors/html.rb
 - lib/html2rss/item_extractors/static.rb
 - lib/html2rss/item_extractors/text.rb
+- lib/html2rss/object_to_xml_converter.rb
+- lib/html2rss/rss_builder.rb
+- lib/html2rss/rss_builder/channel.rb
+- lib/html2rss/rss_builder/item.rb
+- lib/html2rss/rss_builder/stylesheet.rb
 - lib/html2rss/utils.rb
 - lib/html2rss/version.rb
-- support/logo.png
-homepage: https://github.com/gildesmarais/html2rss
+homepage: https://github.com/html2rss/html2rss
 licenses:
 - MIT
 metadata:
   allowed_push_host: https://rubygems.org
-  changelog_uri: https://github.com/gildesmarais/html2rss/blob/master/CHANGELOG.md
+  changelog_uri: https://github.com/html2rss/html2rss/releases/tag/v0.11.0
+  rubygems_mfa_required: 'true'
 post_install_message: 
 rdoc_options: []
 require_paths:
@@ -374,16 +262,16 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.5.0
+      version: '3.1'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.7
+rubygems_version: 3.5.11
 signing_key: 
 specification_version: 4
-summary: Returns an RSS::Rss object by scraping a URL.
+summary: Generates RSS feeds from websites by scraping a URL and using CSS selectors
+  to extract item.
 test_files: []

data/.gitignore

@@ -1,12 +0,0 @@
-/.bundle/
-/.yardoc
-/_yardoc/
-/coverage/
-/doc/
-/pkg/
-/spec/reports/
-/tmp/
-
-# rspec failure tracking
-.rspec_status
-coverage

data/.rspec

@@ -1,4 +0,0 @@
---format documentation
---color
---order random
---require spec_helper

data/.rubocop.yml

@@ -1,164 +0,0 @@
-require:
-  - rubocop-performance
-  - rubocop-rspec
-
-AllCops:
-  TargetRubyVersion: 2.5
-  DisplayCopNames: true
-
-Metrics/BlockLength:
-  Exclude:
-    - "**/*_spec.rb"
-    - html2rss.gemspec
-
-Metrics/ModuleLength:
-  Exclude:
-    - "**/*_spec.rb"
-
-Layout/ClassStructure:
-  Enabled: true
-
-Layout/HeredocArgumentClosingParenthesis:
-  Enabled: true
-
-Layout/LineLength:
-  Max: 110
-
-Layout/MultilineArrayLineBreaks:
-  Enabled: true
-
-Layout/MultilineHashKeyLineBreaks:
-  Enabled: true
-
-Layout/SpaceInsideParens:
-  Enabled: true
-
-Layout/EmptyLinesAroundAttributeAccessor:
-  Enabled: true
-
-Layout/SpaceAroundMethodCallOperator:
-  Enabled: true
-
-Lint/HeredocMethodCallPosition:
-  Enabled: true
-
-Lint/NumberConversion:
-  Enabled: false
-
-Lint/DeprecatedOpenSSLConstant:
-  Enabled: true
-
-Lint/MixedRegexpCaptureTypes:
-  Enabled: true
-
-Lint/RaiseException:
-  Enabled: true
-
-Lint/StructNewOverride:
-  Enabled: true
-
-
-Performance/CaseWhenSplat:
-  Enabled: true
-
-Performance/ChainArrayAllocation:
-  Enabled: true
-
-Performance/OpenStruct:
-  Enabled: true
-
-
-RSpec/NestedGroups:
-  Exclude:
-    - spec/html2rss_spec.rb
-
-
-Style/AsciiComments:
-  Enabled: false
-
-Style/AutoResourceCleanup:
-  Enabled: true
-
-Style/BlockDelimiters:
-  Enabled: true
-  Exclude:
-    - '**/*_spec.rb'
-
-Style/HashEachMethods:
-  Enabled: true
-
-Style/HashTransformKeys:
-  Enabled: true
-
-Style/HashTransformValues:
-  Enabled: true
-
-Style/CollectionMethods:
-  Enabled: true
-
-Style/ConstantVisibility:
-  Enabled: true
-
-Style/DateTime:
-  Enabled: true
-
-Style/Documentation:
-  Exclude:
-    - lib/html2rss/version.rb
-
-Style/DocumentationMethod:
-  Enabled: false
-
-Style/FormatStringToken:
-  Enabled: false
-
-Style/FrozenStringLiteralComment:
-  Enabled: false
-
-Style/HashSyntax:
-  Enabled: true
-
-Style/InlineComment:
-  Enabled: true
-
-Style/IpAddresses:
-  Enabled: true
-
-Style/MethodCallWithArgsParentheses:
-  Enabled: false
-
-Style/MethodCalledOnDoEndBlock:
-  Enabled: true
-
-Style/MissingElse:
-  Enabled: true
-
-Style/MultilineMethodSignature:
-  Enabled: true
-
-Style/OptionHash:
-  Enabled: true
-
-Style/ReturnNil:
-  Enabled: true
-
-Style/SingleLineBlockParams:
-  Enabled: true
-
-Style/StderrPuts:
-  Enabled: true
-
-Style/StringMethods:
-  Enabled: true
-
-Style/ExponentialNotation:
-  Enabled: true
-
-Style/RedundantRegexpCharacterClass:
-  Enabled: true
-
-Style/RedundantRegexpEscape:
-  Enabled: true
-
-Style/SlicingWithRange:
-  Enabled: true

data/.travis.yml

@@ -1,25 +0,0 @@
-sudo: false
-language: ruby
-cache: bundler
-
-before_install:
-  - gem update --system
-  - gem install bundler
-
-bundler_args: "--jobs=3 --retry=3"
-
-rvm:
-  - 2.5.8
-  - 2.6.6
-  - 2.7.1
-
-script:
-  - bundle exec rubocop -F
-  - bundle exec rspec
-
-deploy:
-  provider: rubygems
-  api_key:
-    secure: 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
-  on:
-    tags: true

data/.yardopts

@@ -1,6 +0,0 @@
---readme README.md
---charset utf-8
---no-private
---exclude /coverage
---exclude /support
---output-dir docs/