weneedfeed 0.6.1 → 0.9.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c580b642b78a2c26bf06d840fad6a745d498630779c670784deba389d9b28f1a
-  data.tar.gz: e29a86399e141b1c650a064cf6c45066149d93dee722b70fa657366519015f7b
+  metadata.gz: 3b2041bae9e09565e1b72a4799f8a57034ad73c139de460dc0d187a5b94dbbe2
+  data.tar.gz: 292b45f698fb86f8cd5632687210ab6c09cd74a6d6ad340bb6eb7b989ffc4e3a
 SHA512:
-  metadata.gz: 3293b7dbba14a24988a77bb2070adfef0a4c4f343197d5633076c497747d6f66d9642b89e37ec11f9d2c51a0f91b18c8dfd614cf053339adfc3c7b4390702774
-  data.tar.gz: f9549a610dec4b77e9e6f86829890bc31928f086652480cbe2c501b1c9fda479a1a0d549ec6efb3a40d1f8ea4fcdb4cc4ccc198403c57ab0a2dbf3c9010ea27f
+  metadata.gz: 8dc45d743eb961d6a18983b8c20340b1e4c2085c7ed1c348332bddb51c211aa2c5067211e789f9cdd192eb3b161602d63f304adc8421ade49210ce11396a0031
+  data.tar.gz: 60f284ba462f92130a3de4702e33ae3d73418a3057459b40656e75f0a27e8ad9bc8b67946b1137b590f38250d5dec695cdfe41cad58f96947cf0dc0885c2839b

data/.github/workflows/test.yml

@@ -7,16 +7,24 @@ on:
       - master
 
 jobs:
-  build:
-    runs-on: ubuntu-18.04
+  rspec:
+    runs-on: ubuntu-20.04
     steps:
       - uses: actions/checkout@v2
+      - uses: ruby/setup-ruby@v1
+        with:
+          bundler-cache: true
+          ruby-version: 2.7.2
+      - run: bundle exec rspec --force-color
+  rubocop:
+    runs-on: ubuntu-20.04
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          ref: ${{ github.event.pull_request.head.sha }}
       - uses: ruby/setup-ruby@v1
         with:
           bundler-cache: true
           ruby-version: 2.7.2
       - uses: r7kamura/rubocop-problem-matchers-action@v1
       - run: bundle exec rubocop --parallel
-      - run: bundle exec rspec --force-color
-
-

data/.rubocop.yml

@@ -1,4 +1,8 @@
+require:
+  - rubocop-rspec
+
 AllCops:
+  NewCops: enable
   TargetRubyVersion: 2.5
 
 Lint/SuppressedException:
@@ -7,8 +11,20 @@ Lint/SuppressedException:
 Metrics:
   Enabled: false
 
+RSpec/ImplicitSubject:
+  Enabled: false
+
+RSpec/MultipleExpectations:
+  Enabled: false
+
+RSpec/NamedSubject:
+  Enabled: false
+
 Style/Documentation:
   Enabled: false
 
 Style/TrailingCommaInArguments:
   Enabled: false
+
+Style/TrailingCommaInHashLiteral:
+  Enabled: false

data/CHANGELOG.md

@@ -7,6 +7,44 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## Unreleased
 
+## 0.9.0 - 2020-12-03
+
+### Added
+
+- Add item_image_selector.
+
+## 0.8.0 - 2020-11-25
+
+### Added
+
+- Add page description for writing channel description.
+
+### Changed
+
+- Change channel link content from feeds index URL to page URL.
+
+## 0.7.2 - 2020-11-25
+
+### Fixed
+
+- Fix time parse error by HTML entities handling.
+
+## 0.7.1 - 2020-11-25
+
+### Fixed
+
+- Fix error when no title element found.
+
+## 0.7.0 - 2020-11-23
+
+### Added
+
+- Convert JSON response into XML.
+
+### Fixed
+
+- Fix bug that item_description_selector is not used.
+
 ## 0.6.1 - 2020-11-15
 
 ### Changed

data/Gemfile

@@ -9,4 +9,5 @@ gem 'rack-test'
 gem 'rake', '~> 12.0'
 gem 'rspec'
 gem 'rubocop'
+gem 'rubocop-rspec'
 gem 'webmock'

data/Gemfile.lock

@@ -1,9 +1,13 @@
 PATH
   remote: .
   specs:
-    weneedfeed (0.6.1)
+    weneedfeed (0.9.0)
+      activesupport
+      builder
       faraday
+      faraday_middleware
       hibana (>= 0.2)
+      mimemagic
       nokogiri
       rack-capture (>= 0.4.0)
       thor
@@ -11,14 +15,24 @@ PATH
 GEM
   remote: https://rubygems.org/
   specs:
+    activesupport (6.0.3.4)
+      concurrent-ruby (~> 1.0, >= 1.0.2)
+      i18n (>= 0.7, < 2)
+      minitest (~> 5.1)
+      tzinfo (~> 1.1)
+      zeitwerk (~> 2.2, >= 2.2.2)
     addressable (2.7.0)
       public_suffix (>= 2.0.2, < 5.0)
     ast (2.4.1)
+    builder (3.2.4)
+    concurrent-ruby (1.1.7)
     crack (0.4.4)
     diff-lcs (1.4.4)
     faraday (1.1.0)
       multipart-post (>= 1.2, < 3)
       ruby2_keywords
+    faraday_middleware (1.0.0)
+      faraday (~> 1.0)
     hanami-router (2.0.0.alpha3)
       mustermann (~> 1.0)
       mustermann-contrib (~> 1.0)
@@ -29,7 +43,11 @@ GEM
       hanami-router (>= 2.0.0.alpha3)
       rack
       tilt
+    i18n (1.8.5)
+      concurrent-ruby (~> 1.0)
+    mimemagic (0.3.5)
     mini_portile2 (2.4.0)
+    minitest (5.14.2)
     multipart-post (2.1.1)
     mustermann (1.1.1)
       ruby2_keywords (~> 0.0.1)
@@ -38,7 +56,7 @@ GEM
       mustermann (= 1.1.1)
     nokogiri (1.10.10)
       mini_portile2 (~> 2.4.0)
-    parallel (1.19.2)
+    parallel (1.20.1)
     parser (2.7.2.0)
       ast (~> 2.4.1)
     public_suffix (4.0.6)
@@ -64,26 +82,33 @@ GEM
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.9.0)
     rspec-support (3.9.4)
-    rubocop (1.0.0)
+    rubocop (1.4.0)
       parallel (~> 1.10)
       parser (>= 2.7.1.5)
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 1.8)
       rexml
-      rubocop-ast (>= 0.6.0)
+      rubocop-ast (>= 1.1.1)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 1.4.0, < 2.0)
-    rubocop-ast (1.1.0)
+    rubocop-ast (1.1.1)
       parser (>= 2.7.1.5)
+    rubocop-rspec (2.0.0)
+      rubocop (~> 1.0)
+      rubocop-ast (>= 1.1.0)
     ruby-progressbar (1.10.1)
     ruby2_keywords (0.0.2)
     thor (1.0.1)
+    thread_safe (0.3.6)
     tilt (2.0.10)
+    tzinfo (1.2.8)
+      thread_safe (~> 0.1)
     unicode-display_width (1.7.0)
     webmock (3.9.3)
       addressable (>= 2.3.6)
       crack (>= 0.3.2)
       hashdiff (>= 0.4.0, < 2.0.0)
+    zeitwerk (2.4.2)
 
 PLATFORMS
   ruby
@@ -93,6 +118,7 @@ DEPENDENCIES
   rake (~> 12.0)
   rspec
   rubocop
+  rubocop-rspec
   webmock
   weneedfeed!
 

data/README.md

@@ -27,24 +27,28 @@ gem install weneedfeed
 
 ## Schema
 
-You need to write a schema file named with `weneedfeed.yml` to use this gem.
+Weneedfeed requires `weneedfeed.yml` that describes URLs and selectors.
 
 ### Example
 
 ```yaml
 pages:
   - id: example1
-    title: Example feed with CSS Selector
+    title: Example 1
+    description: Example feed with CSS Selector
     url: http://example.com/1
     item_selector: li
     item_description_selector: p:nth-child(3)
+    item_image_selector: img
     item_link_selector: a
     item_time_selector: time
     item_title_selector: p:nth-child(2)
   - id: example2
-    title: Example feed with XPath
+    title: Example 2
+    description: Example feed with XPath
     url: http://example.com/2
     item_selector: //li
+    item_image_selector: .//img
     item_description_selector: .//p[3]
     item_link_selector: .//a
     item_time_selector: .//time
@@ -56,7 +60,7 @@ pages:
 Feed ID.
 
 - required
-- Used for feed URL.
+- Used for feed URL and `<link>` element in `<channel>` element.
 
 ### `title`
 
@@ -65,6 +69,13 @@ Feed title.
 - required
 - Used for RSS `<title>` element in `<channel>` element.
 
+### `description`
+
+Feed description.
+
+- optional
+- Used for RSS `<description>` element in `<channel>` element.
+
 ### `url`
 
 HTML source URL.
@@ -100,6 +111,13 @@ CSS or XPath selector to find element with description information in each item.
 - optional
 - Used for `<description>` in `<item>`.
 
+### `item_image_selector`
+
+CSS or XPath selector to find `<img>`element in each item.
+
+- optional
+- Used for `<enclosure>` in `<item>`.
+
 ### `item_time_selector`
 
 CSS or XPath selector to find element with datetime information in each item.

data/lib/weneedfeed.rb

@@ -7,6 +7,7 @@ module Weneedfeed
   autoload :Capture, 'weneedfeed/capture'
   autoload :Command, 'weneedfeed/command'
   autoload :Controllers, 'weneedfeed/controllers'
+  autoload :FaradayResponseMiddleware, 'weneedfeed/faraday_response_middleware'
   autoload :Helpers, 'weneedfeed/helpers'
   autoload :Item, 'weneedfeed/item'
   autoload :Page, 'weneedfeed/page'

data/lib/weneedfeed/controllers/show_feed.rb

@@ -11,7 +11,9 @@ module Weneedfeed
         end
 
         scraping = ::Weneedfeed::Scraping.new(
+          description: page_schema.description,
           item_description_selector: page_schema.item_description_selector,
+          item_image_selector: page_schema.item_image_selector,
           item_link_selector: page_schema.item_link_selector,
           item_time_selector: page_schema.item_time_selector,
           item_title_selector: page_schema.item_title_selector,

data/lib/weneedfeed/faraday_response_middleware.rb

@@ -0,0 +1,23 @@
+# frozen_string_literal: true
+
+require 'active_support/core_ext/array/conversions'
+require 'active_support/core_ext/hash/conversions'
+require 'faraday'
+require 'faraday_middleware/response_middleware'
+require 'json'
+
+module Weneedfeed
+  class FaradayResponseMiddleware < ::FaradayMiddleware::ResponseMiddleware
+    define_parser do |body, options|
+      options ||= {}
+      options = { dasherize: false }.merge(options)
+      object = ::JSON.parse(body)
+      object.to_xml(options)
+    end
+
+    # @note Overriding.
+    def parse_response?(env)
+      env.response.headers['Content-Type'].to_s.include?('application/json')
+    end
+  end
+end

data/lib/weneedfeed/item.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+require 'mimemagic'
+
 module Weneedfeed
   class Item
     class << self
@@ -16,6 +18,7 @@ module Weneedfeed
     end
 
     # @param [String, nil] description_selector
+    # @param [String, nil] image_selector
     # @param [String, nil] link_selector
     # @param [Nokogiri::Node] node
     # @param [String] time_selector
@@ -23,6 +26,7 @@ module Weneedfeed
     # @param [String] url
     def initialize(
       description_selector:,
+      image_selector:,
       link_selector:,
       node:,
       time_selector:,
@@ -30,6 +34,7 @@ module Weneedfeed
       url:
     )
       @description_selector = description_selector
+      @image_selector = image_selector
       @link_selector = link_selector
       @node = node
       @time_selector = time_selector
@@ -44,14 +49,48 @@ module Weneedfeed
       @node.at(@description_selector)&.inner_html
     end
 
+    # @return [String, nil]
+    def image_mime_type
+      return unless image_url
+
+      ::MimeMagic.by_path(image_url)&.type
+    end
+
+    # @return [String, nil]
+    def image_path_or_url
+      return unless @image_selector
+
+      @node.at(@image_selector)&.[]('src')
+    end
+
+    def image_url
+      return unless image_path_or_url
+
+      ::URI.join(
+        @url,
+        image_path_or_url
+      ).to_s
+    end
+
     # @return [String]
     def link
       ::URI.join(
         @url,
-        @node.at(@link_selector)['href']
+        link_path_or_url
       ).to_s
     end
 
+    # @return [Nokogiri::Node, nil]
+    def link_node
+      @node.at(@link_selector)
+    end
+
+    # @return [String, nil]
+    def link_path_or_url
+      node = link_node
+      node['href'] || node.inner_text
+    end
+
     # @return [Time, nil]
     def time
       return unless @time_selector
@@ -62,9 +101,9 @@ module Weneedfeed
       self.class.parse_time(string)
     end
 
-    # @return [String]
+    # @return [String, nil]
     def title
-      @node.at(@title_selector).inner_text
+      @node.at(@title_selector)&.inner_text
     end
 
     private
@@ -79,7 +118,7 @@ module Weneedfeed
       node = time_node
       return unless node
 
-      node['datetime'] || node.inner_html
+      node['datetime'] || node.inner_text
     end
   end
 end

data/lib/weneedfeed/page.rb

@@ -2,13 +2,18 @@
 
 module Weneedfeed
   class Page
+    # @return [String, nil]
+    attr_reader :description
+
     # @return [String]
     attr_reader :title
 
     # @return [String]
     attr_reader :url
 
+    # @param [String, nil] description
     # @param [String, nil] item_description_selector
+    # @param [String, nil] item_image_selector
     # @param [String] item_link_selector
     # @param [String, nil] item_time_selector
     # @param [String] item_title_selector
@@ -17,7 +22,9 @@ module Weneedfeed
     # @param [String] title
     # @param [String] url
     def initialize(
+      description:,
       item_description_selector:,
+      item_image_selector:,
       item_link_selector:,
       item_time_selector:,
       item_title_selector:,
@@ -26,7 +33,9 @@ module Weneedfeed
       title:,
       url:
     )
+      @description = description
       @item_description_selector = item_description_selector
+      @item_image_selector = item_image_selector
       @item_link_selector = item_link_selector
       @item_time_selector = item_time_selector
       @item_title_selector = item_title_selector
@@ -41,6 +50,7 @@ module Weneedfeed
       @node.search(@item_selector).map do |node|
         ::Weneedfeed::Item.new(
           description_selector: @item_description_selector,
+          image_selector: @item_image_selector,
           link_selector: @item_link_selector,
           node: node,
           time_selector: @item_time_selector,

data/lib/weneedfeed/page_schema.rb

@@ -2,8 +2,10 @@
 
 module Weneedfeed
   PageSchema = Struct.new(
+    :description,
     :id,
     :item_description_selector,
+    :item_image_selector,
     :item_link_selector,
     :item_time_selector,
     :item_title_selector,

data/lib/weneedfeed/schema.rb

@@ -24,7 +24,10 @@ module Weneedfeed
     def page_schemata
       @raw['pages'].map do |hash|
         ::Weneedfeed::PageSchema.new(
+          description: hash['description'],
           id: hash['id'],
+          item_description_selector: hash['item_description_selector'],
+          item_image_selector: hash['item_image_selector'],
           item_link_selector: hash['item_link_selector'],
           item_time_selector: hash['item_time_selector'],
           item_title_selector: hash['item_title_selector'],

data/lib/weneedfeed/scraping.rb

@@ -5,7 +5,18 @@ require 'nokogiri'
 
 module Weneedfeed
   class Scraping
+    class << self
+      # @return [Faraday::Connection]
+      def faraday_connection
+        @faraday_connection ||= ::Faraday.new do |connection|
+          connection.use ::Weneedfeed::FaradayResponseMiddleware
+        end
+      end
+    end
+
+    # @param [String, nil] description
     # @param [String, nil] item_description_selector
+    # @param [String, nil] item_image_selector
     # @param [String] item_link_selector
     # @param [String, nil] item_time_selector
     # @param [String] item_title_selector
@@ -13,7 +24,9 @@ module Weneedfeed
     # @param [String] title
     # @param [String] url
     def initialize(
+      description:,
       item_description_selector:,
+      item_image_selector:,
       item_link_selector:,
       item_time_selector:,
       item_title_selector:,
@@ -21,7 +34,9 @@ module Weneedfeed
       title:,
       url:
     )
+      @description = description
       @item_description_selector = item_description_selector
+      @item_image_selector = item_image_selector
       @item_link_selector = item_link_selector
       @item_time_selector = item_time_selector
       @item_title_selector = item_title_selector
@@ -33,8 +48,10 @@ module Weneedfeed
     # @return [Weneedfeed::Page]
     def call
       ::Weneedfeed::Page.new(
+        description: @description,
         node: parsed_body,
         item_description_selector: @item_description_selector,
+        item_image_selector: @item_image_selector,
         item_selector: @item_selector,
         item_link_selector: @item_link_selector,
         item_time_selector: @item_time_selector,
@@ -48,12 +65,12 @@ module Weneedfeed
 
     # @return [Nokogiri::Node]
     def parsed_body
-      ::Nokogiri::HTML.parse(response.body)
+      ::Nokogiri::XML.parse(response.body)
     end
 
     # @return [Faraday::Response]
     def response
-      ::Faraday.get(@url)
+      self.class.faraday_connection.get(@url)
     end
   end
 end

data/lib/weneedfeed/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Weneedfeed
-  VERSION = '0.6.1'
+  VERSION = '0.9.0'
 end

data/templates/show_feed.xml.erb

@@ -4,9 +4,9 @@
   xmlns:content="http://purl.org/rss/1.0/modules/content/">
   <channel>
     <title><![CDATA[<%= @page.title %>]]></title>
-    <link><%= "#{request.base_url}#{top_page_path}" %></link>
+    <link><%= "#{@page.url}" %></link>
     <atom:link href="<%= "#{request.base_url}#{request.path}" %>" rel="self"/>
-    <description><![CDATA[Recent content on <%= @page.title %>]]></description>
+    <description><![CDATA[<%= @page.description %>]]></description>
     <lastBuildDate><%= Time.now.rfc822 %></lastBuildDate>
     <% items.each do |item| %>
     <item>
@@ -18,6 +18,9 @@
       <description><![CDATA[<%= item.description %>]]></description>
       <content:encoded><![CDATA[<%= item.description %>]]></content:encoded>
       <guid isPermaLink="true"><%= item.link %></guid>
+      <% if item.image_url %>
+        <enclosure url="<%= item.image_url %>" length="0" type="<%= item.image_mime_type %>"/>
+      <% end %>
     </item>
     <% end %>
   </channel>

data/weneedfeed.gemspec

@@ -25,8 +25,12 @@ Gem::Specification.new do |spec|
   spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ['lib']
 
+  spec.add_runtime_dependency 'activesupport'
+  spec.add_runtime_dependency 'builder'
   spec.add_runtime_dependency 'faraday'
+  spec.add_runtime_dependency 'faraday_middleware'
   spec.add_runtime_dependency 'hibana', '>= 0.2'
+  spec.add_runtime_dependency 'mimemagic'
   spec.add_runtime_dependency 'nokogiri'
   spec.add_runtime_dependency 'rack-capture', '>= 0.4.0'
   spec.add_runtime_dependency 'thor'

metadata

@@ -1,15 +1,43 @@
 --- !ruby/object:Gem::Specification
 name: weneedfeed
 version: !ruby/object:Gem::Version
-  version: 0.6.1
+  version: 0.9.0
 platform: ruby
 authors:
 - Ryo Nakamura
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-11-15 00:00:00.000000000 Z
+date: 2020-12-02 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: activesupport
+  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: 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
@@ -24,6 +52,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: faraday_middleware
+  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: hibana
   requirement: !ruby/object:Gem::Requirement
@@ -38,6 +80,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0.2'
+- !ruby/object:Gem::Dependency
+  name: mimemagic
+  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: nokogiri
   requirement: !ruby/object:Gem::Requirement
@@ -109,6 +165,7 @@ files:
 - lib/weneedfeed/controllers/base.rb
 - lib/weneedfeed/controllers/show_feed.rb
 - lib/weneedfeed/controllers/show_top_page.rb
+- lib/weneedfeed/faraday_response_middleware.rb
 - lib/weneedfeed/helpers.rb
 - lib/weneedfeed/helpers/parameters.rb
 - lib/weneedfeed/item.rb