html2rss 0.4.0 → 0.4.1

data/docs/top-level-namespace.html

@@ -100,7 +100,7 @@
 </div>
 
       <div id="footer">
-  Generated on Sun Jul 14 19:35:05 2019 by
+  Generated on Wed Sep 18 12:52:16 2019 by
   <a href="http://yardoc.org" title="Yay! A Ruby Documentation Tool" target="_parent">yard</a>
   0.9.20 (ruby-2.6.3).
 </div>

data/html2rss.gemspec

@@ -32,6 +32,7 @@ Gem::Specification.new do |spec|
   spec.add_dependency 'faraday_middleware', '~> 0.13'
   spec.add_dependency 'hashie', '~> 3.6'
   spec.add_dependency 'nokogiri', '>= 1.10', '< 2.0'
+  spec.add_dependency 'reverse_markdown', '~> 1.3'
   spec.add_dependency 'sanitize', '~> 5.0'
   spec.add_development_dependency 'bundler', '~> 1.16'
   spec.add_development_dependency 'byebug'

data/lib/html2rss/attribute_post_processors.rb

@@ -1,3 +1,4 @@
+require_relative 'attribute_post_processors/html_to_markdown'
 require_relative 'attribute_post_processors/parse_time'
 require_relative 'attribute_post_processors/parse_uri'
 require_relative 'attribute_post_processors/sanitize_html'

data/lib/html2rss/attribute_post_processors/html_to_markdown.rb

@@ -0,0 +1,39 @@
+require 'reverse_markdown'
+
+module Html2rss
+  module AttributePostProcessors
+    ##
+    # Returns HTML code as Markdown formatted String.
+    # Before converting to markdown, the HTML is sanitized with SanitizeHtml.
+    # Imagine this HTML structure:
+    #
+    #     <section>
+    #       Lorem <b>ipsum</b> dolor...
+    #       <iframe src="https://evil.corp/miner"></iframe>
+    #       <script>alert();</script>
+    #     </section>
+    #
+    # YAML usage example:
+    #
+    #    selectors:
+    #      description:
+    #        selector: section
+    #        extractor: html
+    #        post_process:
+    #          name: html_to_markdown
+    #
+    # Would return:
+    #    'Lorem **ipsum** dolor'
+    class HtmlToMarkdown
+      def initialize(value, env)
+        @value = SanitizeHtml.new(value, env).get
+      end
+
+      ##
+      # @return [String] formatted in Markdown
+      def get
+        ReverseMarkdown.convert @value
+      end
+    end
+  end
+end

data/lib/html2rss/utils.rb

@@ -14,11 +14,10 @@ module Html2rss
 
       return url if url.absolute?
 
-      path, query = url.to_s.split('?')
-
       URI(channel_url).tap do |uri|
-        uri.path = path.to_s.start_with?('/') ? path : "/#{path}"
-        uri.query = query
+        uri.path = url.path.to_s.start_with?('/') ? url.path : "/#{url.path}"
+        uri.query = url.query
+        uri.fragment = url.fragment if url.fragment
       end
     end
   end

data/lib/html2rss/version.rb

@@ -1,3 +1,3 @@
 module Html2rss
-  VERSION = '0.4.0'.freeze
+  VERSION = '0.4.1'.freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html2rss
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.4.1
 platform: ruby
 authors:
 - Gil Desmarais
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-09-07 00:00:00.000000000 Z
+date: 2019-09-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -86,6 +86,20 @@ 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: '1.3'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
 - !ruby/object:Gem::Dependency
   name: sanitize
   requirement: !ruby/object:Gem::Requirement
@@ -234,7 +248,6 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- ".changelogrc"
 - ".gitignore"
 - ".rspec"
 - ".rubocop.yml"
@@ -249,6 +262,7 @@ files:
 - bin/setup
 - docs/Html2rss.html
 - docs/Html2rss/AttributePostProcessors.html
+- docs/Html2rss/AttributePostProcessors/HtmlToMarkdown.html
 - docs/Html2rss/AttributePostProcessors/ParseTime.html
 - docs/Html2rss/AttributePostProcessors/ParseUri.html
 - docs/Html2rss/AttributePostProcessors/SanitizeHtml.html
@@ -283,6 +297,7 @@ files:
 - html2rss.gemspec
 - lib/html2rss.rb
 - lib/html2rss/attribute_post_processors.rb
+- lib/html2rss/attribute_post_processors/html_to_markdown.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
@@ -321,8 +336,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.7
+rubygems_version: 3.0.6
 signing_key: 
 specification_version: 4
 summary: Returns an RSS::Rss object by scraping a URL.

data/.changelogrc

@@ -1,19 +0,0 @@
-{
-  "app_name": "html2rss",
-  "logo": "https://github.com/gildesmarais/html2rss/raw/master/support/logo.png",
-  "intro": "Generate RSS feeds by scraping websites by providing a config.",
-  "debug": "true",
-  "template": "support/changelog.md",
-  "sections": [
-    { "title": "Bugfixes",             "grep": "^fix" },
-    { "title": "Features",             "grep": "^feat" },
-    { "title": "Documentation",        "grep": "^docs" },
-    { "title": "Breaking changes",     "grep": "BREAKING" },
-    { "title": "Refactorings",         "grep": "^refactor" },
-    { "title": "Code style",           "grep": "^style" },
-    { "title": "Test",                 "grep": "^spec" },
-    { "title": "Chore",                "grep": "^chore" },
-    { "title": "Branches merged",      "grep": "^Merge branch" },
-    { "title": "Pull requests merged", "grep": "^Merge pull request" }
-  ]
-}