html2rss 0.10.0 → 0.11.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8d51b095228dec5d98a1ff66ee7329171d2297bad67ca27a7930afe296b589e8
-  data.tar.gz: 32bf56a05ed45a1bb8c3341f228f41d1441e65243c6a5d55908e90d002f8880b
+  metadata.gz: 3c8df87caea7cc1dd9855993e9dd4fcb4285b37a5c1f87fb48a3d85e75ce0a51
+  data.tar.gz: 8ab432f13d76f45e30ea65316669c324bcba46b5234a082a6f0670cc445a6958
 SHA512:
-  metadata.gz: 0cbe761521ec3cd43bd25565f6425e6ced445814c30706d50d52c008ce6e3905a6f95b9f6d9dfa2faf90baf4bc2fbeb43741af5bc185e1488d31b55b9ffa3c75
-  data.tar.gz: 353e1586ddde92858ea95a2eecda6d752975585038acc29e6d09ff97363e5429d15966a005e1f9c4a41e9ad83b972973cfadd9c840160849d530166e7dd84298
+  metadata.gz: 7115ee36e47ac65d19b13bb0f2ef0b19ebdb387d2e6fa53128e804b8d22d6a834517b88642f5c3e31e8850e344a2f94b6cb0de6619504603cfeacae52e47f3e2
+  data.tar.gz: b2c9f342cff237d9cafd4817f2570d18803fa9ba844ab306681ac02d12fb7cf147f3b40117ab21c78937325d80623ad27e25c6df4c8f8150fe81be2a07d12817

data/README.md

@@ -1,6 +1,6 @@
 ![html2rss logo](https://github.com/html2rss/html2rss/raw/master/support/logo.png)
 
-[![Gem Version](https://badge.fury.io/rb/html2rss.svg)](http://rubygems.org/gems/html2rss/) [![Yard Docs](http://img.shields.io/badge/yard-docs-blue.svg)](https://www.rubydoc.info/gems/html2rss) ![Retro Badge: valid RSS](https://validator.w3.org/feed/images/valid-rss-rogers.png) [![](http://img.shields.io/liberapay/goal/gildesmarais.svg?logo=liberapa)](https://liberapay.com/gildesmarais/donate)
+[![Gem Version](https://badge.fury.io/rb/html2rss.svg)](http://rubygems.org/gems/html2rss/) [![Yard Docs](http://img.shields.io/badge/yard-docs-blue.svg)](https://www.rubydoc.info/gems/html2rss) ![Retro Badge: valid RSS](https://validator.w3.org/feed/images/valid-rss-rogers.png)
 
 `html2rss` is a Ruby gem that generates RSS 2.0 feeds from a _feed config_.
 

data/html2rss.gemspec

@@ -10,23 +10,23 @@ Gem::Specification.new do |spec|
   spec.authors       = ['Gil Desmarais']
   spec.email         = ['html2rss@desmarais.de']
 
-  spec.summary       = 'Returns an RSS::Rss object by scraping a URL.'
-  spec.description   = 'Give the URL to scrape and some CSS selectors. Get a RSS::Rss instance in return.'
+  spec.summary       = 'Generates RSS feeds from websites by scraping a URL and using CSS selectors to extract item.'
+  spec.description   = 'Supports JSON content, custom HTTP headers, and post-processing of extracted content.'
   spec.homepage      = 'https://github.com/html2rss/html2rss'
   spec.license       = 'MIT'
   spec.required_ruby_version = '>= 3.1'
 
   if spec.respond_to?(:metadata)
     spec.metadata['allowed_push_host'] = 'https://rubygems.org'
-    spec.metadata['changelog_uri'] = 'https://github.com/html2rss/html2rss/releases'
+    spec.metadata['changelog_uri'] = "#{spec.homepage}/releases/tag/v#{spec.version}"
     spec.metadata['rubygems_mfa_required'] = 'true'
   else
     raise 'RubyGems 2.0 or newer is required to protect against ' \
           'public gem pushes.'
   end
 
-  spec.files = `git ls-files -z`.split("\x0").reject do |f|
-    f.match(%r{^(test|spec|features|support|docs|.github|.yardoc)/})
+  spec.files = `git ls-files -z`.split("\x0").select do |f|
+    f.match(%r{^(lib/|exe/|README.md|LICENSE|html2rss.gemspec)})
   end
   spec.bindir        = 'exe'
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }

data/lib/html2rss/attribute_post_processors.rb

@@ -6,7 +6,7 @@ module Html2rss
   module AttributePostProcessors
     ##
     # Error raised when an unknown post processor name is requested.
-    class UnknownPostProcessorName < StandardError; end
+    class UnknownPostProcessorName < Html2rss::Error; end
 
     ##
     # Maps the post processor name to the class implementing the post processor.

data/lib/html2rss/config/channel.rb

@@ -11,6 +11,15 @@ module Html2rss
     # 1. the RSS channel attributes
     # 2. html2rss options like json or custom HTTP-headers for the request
     class Channel
+      ##
+      # @param config [Hash<Symbol, Object>]
+      # @return [Set<String>] the required parameter names
+      def self.required_params_for_config(config)
+        config.each_with_object(Set.new) do |(_, value), required_params|
+          required_params.merge(value.scan(/%<([\w_\d]+)>/).flatten) if value.is_a?(String)
+        end
+      end
+
       ##
       # @param channel [Hash<Symbol, Object>]
       # @param params [Hash]
@@ -77,15 +86,6 @@ module Html2rss
         config.fetch(:json, false)
       end
 
-      ##
-      # @param config [Hash<Symbol, Object>]
-      # @return [Set<String>] the required parameter names
-      def self.required_params_for_config(config)
-        config.each_with_object(Set.new) do |(_, value), required_params|
-          required_params.merge(value.scan(/%<([\w_\d]+)>/).flatten) if value.is_a?(String)
-        end
-      end
-
       private
 
       # @return [Hash<Symbol, Object>]

data/lib/html2rss/config.rb

@@ -12,11 +12,11 @@ module Html2rss
     ##
     # The Error class to be thrown when a feed config requires params, but none
     # were passed to Config.
-    class ParamsMissing < StandardError; end
+    class ParamsMissing < Html2rss::Error; end
 
     ##
     # Thrown when the feed config does not contain a value at `:channel`.
-    class ChannelMissing < StandardError; end
+    class ChannelMissing < Html2rss::Error; end
 
     # Struct to store XML Stylesheet attributes
     Stylesheet = Struct.new(:href, :type, :media, keyword_init: true)

data/lib/html2rss/item.rb

@@ -16,6 +16,21 @@ module Html2rss
     # Class to keep an Item's <enclosure>.
     Enclosure = Struct.new('Enclosure', :type, :bits_length, :url, keyword_init: true)
 
+    ##
+    # Fetches items from a given URL using configuration settings.
+    #
+    # @param url [String] URL to fetch items from.
+    # @param config [Html2rss::Config] Configuration object.
+    # @return [Array<Html2rss::Item>] list of items fetched.
+    def self.from_url(url, config)
+      body = Utils.request_body_from_url(url, convert_json_to_xml: config.json?, headers: config.headers)
+
+      Nokogiri.HTML(body)
+              .css(config.selector_string(Config::Selectors::ITEMS_SELECTOR_NAME))
+              .map { |xml| new(xml, config) }
+              .select(&:valid?)
+    end
+
     ##
     # @param xml [Nokogiri::XML::Element]
     # @param config [Html2rss::Config]
@@ -122,21 +137,6 @@ module Html2rss
       )
     end
 
-    ##
-    # Fetches items from a given URL using configuration settings.
-    #
-    # @param url [String] URL to fetch items from.
-    # @param config [Html2rss::Config] Configuration object.
-    # @return [Array<Html2rss::Item>] list of items fetched.
-    def self.from_url(url, config)
-      body = Utils.request_body_from_url(url, convert_json_to_xml: config.json?, headers: config.headers)
-
-      Nokogiri.HTML(body)
-              .css(config.selector_string(Config::Selectors::ITEMS_SELECTOR_NAME))
-              .map { |xml| new(xml, config) }
-              .select(&:valid?)
-    end
-
     private
 
     # @return [Nokogiri::XML::Element] XML element representing the item.

data/lib/html2rss/item_extractors.rb

@@ -6,7 +6,7 @@ module Html2rss
   module ItemExtractors
     ##
     # The Error class to be thrown when an unknown extractor name is requested.
-    class UnknownExtractorName < StandardError; end
+    class UnknownExtractorName < Html2rss::Error; end
 
     ##
     # Maps the extractor name to the class implementing the extractor.

data/lib/html2rss/version.rb

@@ -3,6 +3,6 @@
 ##
 # The Html2rss namespace.
 module Html2rss
-  VERSION = '0.10.0'
+  VERSION = '0.11.0'
   public_constant :VERSION
 end

data/lib/html2rss.rb

@@ -10,6 +10,12 @@ require 'yaml'
 ##
 # The Html2rss namespace.
 module Html2rss
+  ##
+  # The Html2rss::Error base class.
+  class Error < StandardError; end
+
+  ##
+  # Key for the feeds configuration in the YAML file.
   CONFIG_KEY_FEEDS = :feeds
 
   ##

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html2rss
 version: !ruby/object:Gem::Version
-  version: 0.10.0
+  version: 0.11.0
 platform: ruby
 authors:
 - Gil Desmarais
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2024-07-30 00:00:00.000000000 Z
+date: 2024-08-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
@@ -204,8 +204,8 @@ dependencies:
     - - ">="
       - !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:
@@ -213,17 +213,8 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
-- ".gitignore"
-- ".mergify.yml"
-- ".rspec"
-- ".rubocop.yml"
-- ".yardopts"
-- Gemfile
-- Gemfile.lock
 - LICENSE
 - README.md
-- bin/console
-- bin/setup
 - exe/html2rss
 - html2rss.gemspec
 - lib/html2rss.rb
@@ -256,13 +247,12 @@ files:
 - lib/html2rss/rss_builder/stylesheet.rb
 - lib/html2rss/utils.rb
 - lib/html2rss/version.rb
-- rakefile.rb
 homepage: https://github.com/html2rss/html2rss
 licenses:
 - MIT
 metadata:
   allowed_push_host: https://rubygems.org
-  changelog_uri: https://github.com/html2rss/html2rss/releases
+  changelog_uri: https://github.com/html2rss/html2rss/releases/tag/v0.11.0
   rubygems_mfa_required: 'true'
 post_install_message: 
 rdoc_options: []
@@ -282,5 +272,6 @@ requirements: []
 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
-docs/

data/.mergify.yml

@@ -1,15 +0,0 @@
-queue_rules:
-  - name: dependabot
-    conditions:
-      - author=dependabot[bot]
-      - status-success=test
-      - base=master
-
-pull_request_rules:
-  - name: automatic merge for Dependabot pull requests
-    conditions:
-      - author=dependabot[bot]
-    actions:
-      queue:
-        method: squash
-        name: dependabot

data/.rspec

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

data/.rubocop.yml

@@ -1,30 +0,0 @@
-require:
-  - rubocop-performance
-  - rubocop-rspec
-  - rubocop-md
-  - rubocop-rake
-
-AllCops:
-  DisplayCopNames: true
-  NewCops: enable
-  Exclude:
-    - vendor/**/*
-
-Metrics/BlockLength:
-  Exclude:
-    - "spec/**/*_spec.rb"
-    - html2rss.gemspec
-
-RSpec/NestedGroups:
-  Exclude:
-    - spec/html2rss_spec.rb
-
-RSpec/DescribeClass:
-  Exclude:
-    - spec/exe/**/*_spec.rb
-
-RSpec/NamedSubject:
-  Enabled: false
-
-Naming/RescuedExceptionsVariableName:
-  PreferredName: error

data/.yardopts

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

data/Gemfile

@@ -1,25 +0,0 @@
-# frozen_string_literal: true
-
-source 'https://rubygems.org'
-
-git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
-
-# Specify your gem's dependencies in html2rss.gemspec
-gemspec
-
-group :development, :test do
-  gem 'byebug'
-  gem 'rake'
-  gem 'rspec', '~> 3.0'
-  gem 'rubocop'
-  gem 'rubocop-md'
-  gem 'rubocop-performance'
-  gem 'rubocop-rake'
-  gem 'rubocop-rspec'
-  gem 'vcr'
-  gem 'yard'
-end
-
-group :test do
-  gem 'simplecov', require: false
-end

data/Gemfile.lock

@@ -1,153 +0,0 @@
-PATH
-  remote: .
-  specs:
-    html2rss (0.10.0)
-      addressable (~> 2.7)
-      faraday (> 2.0.1, < 3.0)
-      faraday-follow_redirects
-      kramdown
-      mime-types (> 3.0)
-      nokogiri (>= 1.10, < 2.0)
-      regexp_parser
-      reverse_markdown (~> 2.0)
-      rss
-      sanitize (~> 6.0)
-      thor
-      tzinfo
-      zeitwerk
-
-GEM
-  remote: https://rubygems.org/
-  specs:
-    addressable (2.8.6)
-      public_suffix (>= 2.0.2, < 6.0)
-    ast (2.4.2)
-    byebug (11.1.3)
-    concurrent-ruby (1.2.3)
-    crass (1.0.6)
-    diff-lcs (1.5.1)
-    docile (1.4.0)
-    faraday (2.9.0)
-      faraday-net_http (>= 2.0, < 3.2)
-    faraday-follow_redirects (0.3.0)
-      faraday (>= 1, < 3)
-    faraday-net_http (3.1.0)
-      net-http
-    json (2.7.2)
-    kramdown (2.4.0)
-      rexml
-    language_server-protocol (3.17.0.3)
-    mime-types (3.5.2)
-      mime-types-data (~> 3.2015)
-    mime-types-data (3.2024.0305)
-    mini_portile2 (2.8.6)
-    net-http (0.4.1)
-      uri
-    nokogiri (1.16.5)
-      mini_portile2 (~> 2.8.2)
-      racc (~> 1.4)
-    nokogiri (1.16.5-x86_64-darwin)
-      racc (~> 1.4)
-    nokogiri (1.16.5-x86_64-linux)
-      racc (~> 1.4)
-    parallel (1.24.0)
-    parser (3.3.1.0)
-      ast (~> 2.4.1)
-      racc
-    public_suffix (5.0.5)
-    racc (1.7.3)
-    rainbow (3.1.1)
-    rake (13.2.1)
-    regexp_parser (2.9.0)
-    reverse_markdown (2.1.1)
-      nokogiri
-    rexml (3.3.2)
-      strscan
-    rspec (3.13.0)
-      rspec-core (~> 3.13.0)
-      rspec-expectations (~> 3.13.0)
-      rspec-mocks (~> 3.13.0)
-    rspec-core (3.13.0)
-      rspec-support (~> 3.13.0)
-    rspec-expectations (3.13.0)
-      diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.13.0)
-    rspec-mocks (3.13.0)
-      diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.13.0)
-    rspec-support (3.13.1)
-    rss (0.3.0)
-      rexml
-    rubocop (1.63.4)
-      json (~> 2.3)
-      language_server-protocol (>= 3.17.0)
-      parallel (~> 1.10)
-      parser (>= 3.3.0.2)
-      rainbow (>= 2.2.2, < 4.0)
-      regexp_parser (>= 1.8, < 3.0)
-      rexml (>= 3.2.5, < 4.0)
-      rubocop-ast (>= 1.31.1, < 2.0)
-      ruby-progressbar (~> 1.7)
-      unicode-display_width (>= 2.4.0, < 3.0)
-    rubocop-ast (1.31.3)
-      parser (>= 3.3.1.0)
-    rubocop-capybara (2.20.0)
-      rubocop (~> 1.41)
-    rubocop-factory_bot (2.25.1)
-      rubocop (~> 1.41)
-    rubocop-md (1.2.2)
-      rubocop (>= 1.0)
-    rubocop-performance (1.21.0)
-      rubocop (>= 1.48.1, < 2.0)
-      rubocop-ast (>= 1.31.1, < 2.0)
-    rubocop-rake (0.6.0)
-      rubocop (~> 1.0)
-    rubocop-rspec (2.29.1)
-      rubocop (~> 1.40)
-      rubocop-capybara (~> 2.17)
-      rubocop-factory_bot (~> 2.22)
-      rubocop-rspec_rails (~> 2.28)
-    rubocop-rspec_rails (2.28.3)
-      rubocop (~> 1.40)
-    ruby-progressbar (1.13.0)
-    sanitize (6.1.0)
-      crass (~> 1.0.2)
-      nokogiri (>= 1.12.0)
-    simplecov (0.22.0)
-      docile (~> 1.1)
-      simplecov-html (~> 0.11)
-      simplecov_json_formatter (~> 0.1)
-    simplecov-html (0.12.3)
-    simplecov_json_formatter (0.1.4)
-    strscan (3.1.0)
-    thor (1.3.1)
-    tzinfo (2.0.6)
-      concurrent-ruby (~> 1.0)
-    unicode-display_width (2.5.0)
-    uri (0.13.0)
-    vcr (6.2.0)
-    yard (0.9.36)
-    zeitwerk (2.6.13)
-
-PLATFORMS
-  ruby
-  x86_64-darwin
-  x86_64-darwin-20
-  x86_64-linux
-
-DEPENDENCIES
-  byebug
-  html2rss!
-  rake
-  rspec (~> 3.0)
-  rubocop
-  rubocop-md
-  rubocop-performance
-  rubocop-rake
-  rubocop-rspec
-  simplecov
-  vcr
-  yard
-
-BUNDLED WITH
-   2.4.1

data/bin/console

@@ -1,16 +0,0 @@
-#!/usr/bin/env ruby
-# frozen_string_literal: true
-
-require 'bundler/setup'
-require 'html2rss'
-require 'byebug'
-
-# You can add fixtures and/or initialization code here to make experimenting
-# with your gem easier. You can also use a different console, if you like.
-
-# (If you use this, don't forget to add pry to your Gemfile!)
-# require "pry"
-# Pry.start
-
-require 'irb'
-IRB.start(__FILE__)

data/bin/setup

@@ -1,8 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-IFS=$'\n\t'
-set -vx
-
-bundle install
-
-# Do any other automated setup that you need to do here

data/rakefile.rb

@@ -1,16 +0,0 @@
-# frozen_string_literal: true
-
-require 'bundler'
-require 'rake'
-require 'rspec'
-require 'rspec/core/rake_task'
-
-Bundler.setup
-Bundler::GemHelper.install_tasks
-
-task default: [:spec]
-
-desc 'Run all examples'
-RSpec::Core::RakeTask.new(:spec) do |t|
-  t.ruby_opts = %w[-w]
-end