panchira 0.2.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f2715a3395e43d5ad43f35bedae84dbfe25a4cd533f964cbcc4cdaf953bc0c4b
-  data.tar.gz: '059e23e1ca4831bc58c62a4a7ccd4ed87010fee75b7e8997560fe49f43486f01'
+  metadata.gz: e0715fad65f1b2f6654761d9d1132217ce644c49b621a94aff1f0a6372dd327b
+  data.tar.gz: 265c9ab995d2c2913465e0dd17e69c008389c1c06e3b8fbeb798e24dcdced89d
 SHA512:
-  metadata.gz: e5ed936514fec2e05dfcaeb727189d1bcc6328e1a27559bd925acba7dc3037c26c57c99fece2c88bad95c7d0d7ae7ffd6840f9e33dde58aef81db81ae600d829
-  data.tar.gz: 8383db6bdc9c78e2e845651e7206d702f5a8566475b8161c9e464364da7b6aa9c5f9886125771c636e0465e8eec7f1ee1dda3c0865a1f0d478131510451c4a74
+  metadata.gz: 231b3b600e88c20f3479943c93efd3b8d720c7052c45c26301818b88a860ac8387610fdd7006c2c6211ecf482a76b24389e4e409290c8817869a3a19af0b0966
+  data.tar.gz: a69dfa20c85d5ef15c12d825dd791450835c7ac9edf511a2b3b5592621706ba0c80d94cf258fd513dc8568e5972270fd5e7271a3c7219c0a3ad8724e4a9a0b23

data/CHANGELOG.md

@@ -4,6 +4,15 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/)
 and this project adheres to [Semantic Versioning](http://semver.org/).
 
+## 0.3.0 - 2020-06-04
+### Added
+- You can now register and use your own Resolver with this gem. (see Panchira::Extensions#register)
+- Added support for new Twitter UI.
+
+### Changed
+- Panchira::fetch now returns an instance of PanchiraResult instead of a hash.
+- Changed default User-Agent slightly.
+
 ## 0.2.0 - 2020-05-18
 ### Added
 - Added support for Shousetsuka Ni Narou (novel18.syosetu.com).
@@ -18,6 +27,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/).
 ### Added
 - Released Panchira gem. At this time we can parse only 5 websites.
 
+[0.3.0]: https://github.com/nuita/panchira/releases/tag/v0.3.0
 [0.2.0]: https://github.com/nuita/panchira/releases/tag/v0.2.0
 [0.1.1]: https://github.com/nuita/panchira/releases/tag/v0.1.1
 [0.1.0]: https://github.com/nuita/panchira/releases/tag/v0.1.0

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    panchira (0.2.0)
+    panchira (0.3.0)
       fastimage (~> 2.1.7)
       nokogiri (~> 1.10.9)
 

data/lib/panchira.rb

@@ -6,6 +6,7 @@ require 'fastimage'
 require 'json'
 
 require_relative 'panchira/version'
+require_relative 'panchira/panchira_result'
 require_relative 'panchira/resolvers/resolver'
 require_relative 'panchira/extensions'
 
@@ -13,9 +14,10 @@ project_root = File.dirname(File.absolute_path(__FILE__))
 Dir.glob(project_root + '/panchira/resolvers/*_resolver.rb').sort.each { |file| require file }
 
 # Main Panchira code goes here.
+# If you simply want to get data from your URL, then ::Panchira::fetch() will do.
 module Panchira
   class << self
-    # Fetch the given URL and returns a hash that contains attributes of hentai.
+    # Return a PanchiraResult that contains the attributes of given url.
     def fetch(url)
       resolver = select_resolver(url)
 

data/lib/panchira/extensions.rb

@@ -1,15 +1,18 @@
 # frozen_string_literal: true
 
 module Panchira
+  # This Module manages Resolver classes.
+  # To enable your own Resolver, you need to call Extensions::register().
   module Extensions
     @resolvers = []
 
     class << self
-      # Register a resolver class which extends Panchira::Resolver.
+      # Register a given Resolver to Extensions::Resolvers.
       def register(resolver)
         @resolvers.push(resolver) unless @resolvers.include?(resolver)
       end
 
+      # Panchira::fetch will find a correct Resolver based on this list.
       attr_reader :resolvers
     end
   end

data/lib/panchira/panchira_result.rb

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+
+module Panchira
+  # Image attributes in PanchiraResult.
+  class PanchiraImage
+    attr_accessor :url, :width, :height
+  end
+
+  # Result class for Panchira.fetch.
+  class PanchiraResult
+    attr_accessor :canonical_url, :title, :description, :image
+  end
+end

data/lib/panchira/resolvers/komiflo_resolver.rb

@@ -30,7 +30,7 @@ module Panchira
 
       parent = @json['content']['parents'][0]['data']['title']
       description = '著: ' + author if author
-      description += " / #{parent}" if parent
+      description + " / #{parent}" if parent
     end
 
     def parse_canonical_url

data/lib/panchira/resolvers/resolver.rb

@@ -1,39 +1,42 @@
 # frozen_string_literal: true
 
-# Resolver is a class that actually GET url and resolve attributes.
-# This class is the default resolver for pages,
-# and is inherited by the other resolvers.
 module Panchira
+  # Resolver is a class that actually get attributes by fetching designated url.
+  # This class is the default resolver for pages. <br>
+  # To create your own resolver, first you make a class that extends Resolver,
+  # and then register it by ::Panchira::Extensions::register().
+  # Then ::Panchira::fetch will pick up your resolver when Resolver::applicable?() is true.
   class Resolver
-    # The URL pattern that this resolver tries to resolve.
-    # Should be redefined in subclasses.
+    # URL pattern that a resolver tries to resolve.
+    # You must override this in subclasses to limit which urls to resolve.
     URL_REGEXP = URI::DEFAULT_PARSER.make_regexp
 
-    USER_AGENT = "Mozilla/5.0 (compatible; Panchira/#{VERSION}; +https://github.com/nuita/panchira)"
+    USER_AGENT = "Mozilla/5.0 (compatible; PanchiraBot/#{VERSION}; +https://github.com/nuita/panchira)"
 
     def initialize(url)
       @url = url
     end
 
+    # This function is called right after this Resolver instance is made.
+    # Fetch page from @url and return PanchiraResult.
     def fetch
-      attributes = {}
+      result = PanchiraResult.new
 
       @page = fetch_page(@url)
-      attributes[:canonical_url] = parse_canonical_url
+      result.canonical_url = parse_canonical_url
 
-      if @url != attributes[:canonical_url]
-        @page = fetch_page(attributes[:canonical_url])
-      end
+      @page = fetch_page(result.canonical_url) if @url != result.canonical_url
 
-      attributes[:title] = parse_title
-      attributes[:description] = parse_description
-      attributes[:image] = parse_image
+      result.title = parse_title
+      result.description = parse_description
+      result.image = parse_image
 
-      attributes
+      result
     end
 
     class << self
       # Tell whether the url is applicable for this resolver.
+      # ::Panchira::fetch uses this method to choose a Resolver for a URL.
       def applicable?(url)
         url =~ self::URL_REGEXP
       end
@@ -42,16 +45,28 @@ module Panchira
     private
 
     def fetch_page(url)
-      raw_page = URI.parse(url).read('User-Agent' => USER_AGENT)
+      raw_page = URI.parse(url).read('User-Agent' => self.class::USER_AGENT)
       charset = raw_page.charset
       Nokogiri::HTML.parse(raw_page, url, charset)
     end
 
     def parse_canonical_url
-      if (canonical_url = @page.css('//link[rel="canonical"]/@href')).any?
-        canonical_url.to_s
-      else
-        @url
+      history = []
+
+      # fetch page and refresh canonical_url until canonical_url converges.
+      loop do
+        url_in_res = @page.css('//link[rel="canonical"]/@href').to_s
+
+        if url_in_res.empty?
+          return history.last || @url
+        else
+          if history.include?(url_in_res) || history.length > 5
+            return url_in_res
+          else
+            history.push(url_in_res)
+            @page = fetch_page(url_in_res)
+          end
+        end
       end
     end
 
@@ -72,9 +87,9 @@ module Panchira
     end
 
     def parse_image
-      image = {}
-      image[:url] = parse_image_url
-      image[:width], image[:height] = FastImage.size(image[:url])
+      image = PanchiraImage.new
+      image.url = parse_image_url
+      image.width, image.height = FastImage.size(image.url)
 
       image
     end

data/lib/panchira/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Panchira
-  VERSION = '0.2.0'
+  VERSION = '0.3.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: panchira
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors:
 - kyp
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-05-18 00:00:00.000000000 Z
+date: 2020-06-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -101,6 +101,7 @@ files:
 - bin/setup
 - lib/panchira.rb
 - lib/panchira/extensions.rb
+- lib/panchira/panchira_result.rb
 - lib/panchira/resolvers/dlsite_resolver.rb
 - lib/panchira/resolvers/komiflo_resolver.rb
 - lib/panchira/resolvers/melonbooks_resolver.rb