feat(html2rss): add initial version of the html2rss gem

.gitignore

@@ -0,0 +1,11 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# rspec failure tracking
+.rspec_status

.rspec

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

Gemfile

@@ -0,0 +1,6 @@
+source 'https://rubygems.org'
+
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in html2rss.gemspec
+gemspec

Gemfile.lock

@@ -0,0 +1,53 @@
+PATH
+  remote: .
+  specs:
+    html2rss (0.1.0)
+      faraday (~> 0.15)
+      nokogiri (~> 1.8)
+      sanitize (~> 4.6)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    byebug (10.0.2)
+    crass (1.0.4)
+    diff-lcs (1.3)
+    faraday (0.15.2)
+      multipart-post (>= 1.2, < 3)
+    mini_portile2 (2.3.0)
+    multipart-post (2.0.0)
+    nokogiri (1.8.2)
+      mini_portile2 (~> 2.3.0)
+    nokogumbo (1.5.0)
+      nokogiri
+    rspec (3.7.0)
+      rspec-core (~> 3.7.0)
+      rspec-expectations (~> 3.7.0)
+      rspec-mocks (~> 3.7.0)
+    rspec-core (3.7.1)
+      rspec-support (~> 3.7.0)
+    rspec-expectations (3.7.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.7.0)
+    rspec-mocks (3.7.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.7.0)
+    rspec-support (3.7.1)
+    sanitize (4.6.5)
+      crass (~> 1.0.2)
+      nokogiri (>= 1.4.4)
+      nokogumbo (~> 1.4)
+    vcr (4.0.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.16)
+  byebug
+  html2rss!
+  rspec (~> 3.0)
+  vcr (~> 4.0)
+
+BUNDLED WITH
+   1.16.2

README.md

@@ -0,0 +1,45 @@
+# Html2rss
+
+Requests and convert an HTML document to an RSS feed via a config object.
+The config contains the URL to scrape and the selectors needed to extract
+the required information. This gem provides some extractors (e.g. extract 
+the information from an HTML attribute).
+
+Please always check the website's Terms of Service before if its allowed to
+scrape their content!
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'html2rss'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install html2rss
+
+## Usage example with a YAML file
+
+Create a YAML config file. Find an example at `rspec/config.test.yml`.
+
+`Html2rss.feed_from_yaml_config(File.join(['spec', 'config.test.yml']), 'nuxt-releases')` returns
+
+an `RSS:Rss` object.
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/gildesmarais/html2rss.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).

bin/console

@@ -0,0 +1,15 @@
+#!/usr/bin/env ruby
+
+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__)

bin/setup

@@ -0,0 +1,8 @@
+#!/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

html2rss.gemspec

@@ -0,0 +1,40 @@
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'html2rss/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'html2rss'
+  spec.version       = Html2rss::VERSION
+  spec.authors       = ['Gil Desmarais']
+  spec.email         = ['html2rss@desmarais.de']
+
+  spec.summary       = 'Generate RSS feeds by scraping websites by providing a config.'
+  spec.description   = 'Create your config object, include the url to scrape,
+                        some selectors and get a RSS2 feed in return.'
+  spec.homepage      = 'https://github.com/gildesmarais/html2rss'
+  spec.license       = 'MIT'
+
+  # Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
+  # to allow pushing to a single host or delete this section to allow pushing to any host.
+  if spec.respond_to?(:metadata)
+    spec.metadata['allowed_push_host'] = "TODO: Set to 'http://mygemserver.com'"
+  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)/})
+  end
+  spec.bindir        = 'exe'
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ['lib']
+
+  spec.add_dependency 'nokogiri', '~> 1.8'
+  spec.add_dependency 'sanitize', '~> 4.6'
+  spec.add_dependency 'faraday', '~> 0.15'
+  spec.add_development_dependency 'bundler', '~> 1.16'
+  spec.add_development_dependency 'rspec', '~> 3.0'
+  spec.add_development_dependency 'vcr', '~> 4.0'
+  spec.add_development_dependency 'byebug'
+end

lib/html2rss.rb

@@ -0,0 +1,16 @@
+require 'html2rss/config'
+require 'html2rss/feed_builder'
+require 'html2rss/version'
+require 'yaml'
+
+module Html2rss
+  def self.feed_from_yaml_config(file, name)
+    config = Config.new(YAML.load(File.open(file))['feeds'].freeze, name)
+    feed(config)
+  end
+
+  def self.feed(config)
+    feed = FeedBuilder.new config
+    feed.rss
+  end
+end

lib/html2rss/config.rb

@@ -0,0 +1,54 @@
+module Html2rss
+  class Config
+    attr_reader :feed_config, :channel_config
+
+    def initialize(config, name)
+      @config = config
+      @feed_config = @config['feeds'][name.to_s]
+      @channel_config = @feed_config['channel']
+    end
+
+    def author
+      channel_config.fetch 'author', 'html2rss'
+    end
+
+    def ttl
+      (channel_config.fetch 'ttl').to_i || nil
+    end
+
+    def title
+      channel_config.fetch 'title', 'html2rss generated title'
+    end
+
+    def language
+      channel_config.fetch 'language', 'en'
+    end
+
+    def description
+      channel_config.fetch 'description', 'A description of my html2rss feed.'
+    end
+
+    def url
+      channel_config.dig 'url'
+    end
+    alias link url
+
+    def headers
+      @config.fetch('headers', {})
+    end
+
+    def options(name)
+      feed_config.dig('selectors', name).merge('channel' => channel_config)
+    end
+
+    def selector(name)
+      feed_config.dig('selectors', name, 'selector')
+    end
+
+    def attribute_names
+      attribute_names = feed_config.fetch('selectors', {}).keys.map(&:to_sym)
+      attribute_names.delete(:items)
+      attribute_names
+    end
+  end
+end

lib/html2rss/feed_builder.rb

@@ -0,0 +1,47 @@
+require 'rss'
+require_relative 'item'
+
+module Html2rss
+  class FeedBuilder
+    attr_reader :config
+
+    def initialize(feed_config)
+      @config = feed_config
+    end
+
+    def rss
+      RSS::Maker.make('2.0') do |maker|
+        add_channel_to_maker(maker)
+
+        feed_items.map do |feed_item|
+          add_item_to_items(feed_item, maker.items)
+        end
+      end
+    end
+
+    private
+
+    def add_channel_to_maker(maker)
+      [:language, :author, :title, :description, :link, :ttl].each do |attribute_name|
+        maker.channel.send("#{attribute_name}=".to_sym, config.send(attribute_name))
+      end
+
+      maker.channel.generator = "html2rss V. #{::Html2rss::VERSION}"
+      maker.channel.lastBuildDate = Time.now.to_s
+    end
+
+    def feed_items
+      Item.from_url config.url, config
+    end
+
+    def add_item_to_items(feed_item, items)
+      items.new_item do |rss_item|
+        config.attribute_names.each do |attribute_name|
+          rss_item.send("#{attribute_name}=".to_sym, feed_item.send(attribute_name))
+
+          rss_item.guid.content = Digest::SHA1.hexdigest(feed_item.title)
+        end
+      end
+    end
+  end
+end

lib/html2rss/item.rb

@@ -0,0 +1,49 @@
+require 'faraday'
+require 'open-uri'
+require 'nokogiri'
+require_relative 'item_extractor'
+
+module Html2rss
+  class Item
+    attr_reader :xml, :config
+
+    def initialize(xml, config)
+      @xml = xml
+      @config = config
+    end
+
+    def respond_to_missing?(method_name, _include_private = false)
+      config.attribute_names.include?(method_name) || super
+    end
+
+    def method_missing(method_name, *_args)
+      attribute_config = config.options(method_name.to_s)
+      return super unless attribute_config
+
+      extractor = attribute_config['extractor'] || 'text'
+      proc = ItemExtractor.const_get extractor.upcase.to_sym
+      value = proc.call(xml, attribute_config)
+
+      post_process(method_name, value)
+    end
+
+    def post_process(method_name, value)
+      case method_name
+      when :link
+        URI(value)
+      when :updated
+        Time.parse(value).to_s
+      else
+        value
+      end
+    end
+
+    def self.from_url(url, config)
+      connection = Faraday.new(url: url, headers: config.headers)
+      page = Nokogiri::HTML(connection.get.body)
+      page.css(config.selector('items')).map { |xml_item|
+        new xml_item, config
+      }
+    end
+  end
+end

lib/html2rss/item_extractor.rb

@@ -0,0 +1,25 @@
+require 'sanitize'
+
+module Html2rss
+  module ItemExtractor
+    TEXT = proc { |xml, options| xml.css(options['selector'])&.text }
+    ATTRIBUTE = proc { |xml, options| xml.css(options['selector']).attr(options['attribute']) }
+
+    HREF = proc { |xml, options|
+      uri = URI(options['channel']['url'])
+      uri.path = xml.css(options['selector']).attr('href')
+      uri
+    }
+
+    HTML = proc { |xml, options|
+      html = xml.css(options['selector']).to_s
+
+      Sanitize.fragment(html, Sanitize::Config.merge(
+                                Sanitize::Config::RELAXED,
+                                add_attributes: {
+                                  'a' => { 'rel' => 'nofollow noopener noreferrer' }
+                                }
+      ))
+    }
+  end
+end

lib/html2rss/version.rb

@@ -0,0 +1,3 @@
+module Html2rss
+  VERSION = '0.0.1'.freeze
+end