html2rss 0.16.0 → 0.17.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3a33d49918c1e75268b3b314908305986dd863ccf31dbe1b6ace8202d3a652de
-  data.tar.gz: 7121a463570c62ffdddb85b9c0d7ba098bdc784ad6649b6bb34b232125a9bf49
+  metadata.gz: bb6b3eb69655bdbb4511f74db9e1bcc766a98aa55d7afc2561a176c6973bda4f
+  data.tar.gz: 45193122489ba965b489c981696f71508030dc80f156e5b0f077932fc55caec3
 SHA512:
-  metadata.gz: e77faa7bd81f63894f0001157a81e858a67eae502f5a5f3ecd41790f48c630b3ab94cd281531cb0a8cf0a7693fa03c7d6176edde04d063804f69f15d4b7469f3
-  data.tar.gz: d84a132a76997336f840c7b5e9261ab304ecfb302628b10d839350fbe3de92919bdc3321b5f374231c703202560d7b392da51cfbcb66ae8e18debdcd69d9e3d0
+  metadata.gz: 294529cd8cb1d289e969f94c32757656d12c864a92c438fceb73ba9dbddd85cca822b146898cdeff928aeefcba75652b91c0a56ded66241bcf23014fea299196
+  data.tar.gz: a2b50e52a7f6ad7768a7092fcdf04c7000dd43d190ee12461f6773fe4b324e43be7b411c7aff69b3af1266aeca3fbb4678e5c43e3bac2b0c2a49d86589869b38

data/README.md

@@ -681,7 +681,6 @@ To submit changes:
 ## Development Helpers
 
 1. `bin/setup`: installs dependencies and sets up the development environment.
-2. `bin/guard`: automatically runs rspec, rubocop and reek when a file changes.
-3. for a modern Ruby development experience: install [`ruby-lsp`](https://github.com/Shopify/ruby-lsp) and integrate it to your IDE.
+2. for a modern Ruby development experience: install [`ruby-lsp`](https://github.com/Shopify/ruby-lsp) and integrate it to your IDE.
 
 For example: [Ruby in Visual Studio Code](https://code.visualstudio.com/docs/languages/ruby).

data/html2rss.gemspec

@@ -14,7 +14,7 @@ Gem::Specification.new do |spec|
   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'
+  spec.required_ruby_version = '>= 3.2'
 
   if spec.respond_to?(:metadata)
     spec.metadata['allowed_push_host'] = 'https://rubygems.org'
@@ -46,5 +46,5 @@ Gem::Specification.new do |spec|
   spec.add_dependency 'sanitize', '~> 6.0'
   spec.add_dependency 'thor'
   spec.add_dependency 'tzinfo'
-  spec.add_dependency 'zeitwerk', '~> 2.6.0'
+  spec.add_dependency 'zeitwerk'
 end

data/lib/html2rss/attribute_post_processors/sanitize_html.rb

@@ -77,10 +77,17 @@ module Html2rss
         )
       end
 
+      ##
+      # @return [Hash]
+      # @see https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Referrer-Policy
       def add_attributes
         {
           'a' => { 'rel' => 'nofollow noopener noreferrer', 'target' => '_blank' },
-          'img' => { 'referrer-policy' => 'no-referrer' }
+          'area' => { 'rel' => 'nofollow noopener noreferrer', 'target' => '_blank' },
+          'img' => { 'referrerpolicy' => 'no-referrer' },
+          'iframe' => { 'referrerpolicy' => 'no-referrer' },
+          'video' => { 'referrerpolicy' => 'no-referrer' },
+          'audio' => { 'referrerpolicy' => 'no-referrer' }
         }
       end
 

data/lib/html2rss/auto_source/scraper/html.rb

@@ -1,7 +1,6 @@
 # frozen_string_literal: true
 
 require 'nokogiri'
-require 'set'
 
 module Html2rss
   class AutoSource
@@ -50,9 +49,10 @@ module Html2rss
           frequent_selectors.each do |selector|
             parsed_body.xpath(selector).each do |selected_tag|
               article_tag = self.class.parent_until_condition(selected_tag, method(:article_condition))
-              article_hash = SemanticHtml::Extractor.new(article_tag, url: @url).call
 
-              yield article_hash if article_hash
+              if article_tag && (article_hash = SemanticHtml::Extractor.new(article_tag, url: @url).call)
+                yield article_hash
+              end
             end
           end
         end

data/lib/html2rss/auto_source/scraper/schema.rb

@@ -2,7 +2,6 @@
 
 require 'json'
 require 'nokogiri'
-require 'set'
 
 module Html2rss
   class AutoSource

data/lib/html2rss/auto_source/scraper/semantic_html/extractor.rb

@@ -1,7 +1,5 @@
 # frozen_string_literal: true
 
-require 'set'
-
 module Html2rss
   class AutoSource
     module Scraper
@@ -33,6 +31,8 @@ module Html2rss
           end
 
           def initialize(article_tag, url:)
+            raise ArgumentError, 'article_tag is required' unless article_tag
+
             @article_tag = article_tag
             @url = url
           end

data/lib/html2rss/auto_source/scraper/semantic_html/image.rb

@@ -28,14 +28,14 @@ module Html2rss
           # @see <https://developer.mozilla.org/en-US/docs/Web/HTML/Element/picture>
           def self.from_source(article_tag) # rubocop:disable Metrics/AbcSize
             hash = article_tag.css('img[srcset], picture > source[srcset]')
-                              .flat_map { |source| source['srcset'].to_s.split(',') }
-                              .filter_map do |line|
-              width, url = line.split.reverse
-              next if url.nil? || url.start_with?('data:')
+                              .flat_map do |source|
+              source['srcset'].to_s.scan(/(\S+)\s+(\d+w|\d+h)/).map do |url, width|
+                next if url.nil? || url.start_with?('data:')
 
-              width_value = width.to_i.zero? ? 0 : width.scan(/\d+/).first.to_i
+                width_value = width.to_i.zero? ? 0 : width.scan(/\d+/).first.to_i
 
-              [width_value, url.strip]
+                [width_value, url.strip]
+              end
             end.to_h
 
             hash[hash.keys.max]

data/lib/html2rss/auto_source/scraper/semantic_html.rb

@@ -106,9 +106,10 @@ module Html2rss
           SemanticHtml.anchor_tag_selector_pairs.each do |tag_name, selector|
             parsed_body.css(selector).each do |selected_tag|
               article_tag = SemanticHtml.find_tag_in_ancestors(selected_tag, tag_name)
-              article_hash = Extractor.new(article_tag, url: @url).call
 
-              yield article_hash if article_hash
+              if article_tag && (article_hash = Extractor.new(article_tag, url: @url).call)
+                yield article_hash
+              end
             end
           end
         end

data/lib/html2rss/version.rb

@@ -3,6 +3,6 @@
 ##
 # The Html2rss namespace.
 module Html2rss
-  VERSION = '0.16.0'
+  VERSION = '0.17.0'
   public_constant :VERSION
 end

metadata

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: html2rss
 version: !ruby/object:Gem::Version
-  version: 0.16.0
+  version: 0.17.0
 platform: ruby
 authors:
 - Gil Desmarais
-autorequire: 
 bindir: exe
 cert_chain: []
-date: 2024-12-24 00:00:00.000000000 Z
+date: 2025-01-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
@@ -222,16 +221,16 @@ dependencies:
   name: zeitwerk
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 2.6.0
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 2.6.0
+        version: '0'
 description: Supports JSON content, custom HTTP headers, and post-processing of extracted
   content.
 email:
@@ -303,9 +302,8 @@ licenses:
 - MIT
 metadata:
   allowed_push_host: https://rubygems.org
-  changelog_uri: https://github.com/html2rss/html2rss/releases/tag/v0.16.0
+  changelog_uri: https://github.com/html2rss/html2rss/releases/tag/v0.17.0
   rubygems_mfa_required: 'true'
-post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -313,15 +311,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '3.1'
+      version: '3.2'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.22
-signing_key: 
+rubygems_version: 3.6.2
 specification_version: 4
 summary: Generates RSS feeds from websites by scraping a URL and using CSS selectors
   to extract item.