curation 1.6 → 1.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f059bacdf3a2deedf5363721c8186af8a62d5b69709022b3d076f725433be26f
-  data.tar.gz: ac36789448e1b3a58161f98362dbed1d889537612939f86d4a2db31b935811c3
+  metadata.gz: e68898021d1c54927e120e46d2b1282535aec94a4daa0c552d9edeb4d6dc1d88
+  data.tar.gz: d6ba0ccabe71d10efb60fb0a5806f94f3fdd42f7e49fe39f00d64c427455d450
 SHA512:
-  metadata.gz: 311113b9b172cfb54f917b694ca5a8f2bb17184c38fc99c8930592f73de9219c9ecda9217562180ef0e17def15682f56255b5f7e671555071d32b9149479cc2b
-  data.tar.gz: bbbe41e2fce674677dac3f3d7c5b724c6bbde6e8941f8be79f8d695ce722578046cb061d7c25fcac771ecb1bb57223d4c88748f36c85c0d6d08cac354ecb6a40
+  metadata.gz: 88310bda3ba8221af689f5848c24af2dfd48668caaf875b55f05626e09dbf072747b877e779b93a91c4e602b39cd23e61dc602662bb2b34e8b0e095c6cd9c488
+  data.tar.gz: c750a811383b541beefd3214accbdacda85ab7552ded3863734101cf1ffa42ec963b455c83f817e6176a2e31dc8d57a07ce14fac0f2567a54fd353c42f26d7fb

data/.gitignore

@@ -6,3 +6,4 @@
 /pkg/
 /spec/reports/
 /tmp/
+.byebug_history

data/Gemfile

@@ -3,4 +3,7 @@ source "https://rubygems.org"
 # Specify your gem's dependencies in curation.gemspec
 gemspec
 
-gem "rake", "~> 12.0"
+gem 'rake', '~> 12.0'
+gem 'minitest'
+gem 'minitest-reporters'
+gem 'byebug'

data/Gemfile.lock

@@ -1,57 +1,96 @@
 PATH
   remote: .
   specs:
-    curation (1.6)
+    curation (1.9)
+      htmlentities
       metainspector
       nokogiri
 
 GEM
   remote: https://rubygems.org/
   specs:
-    addressable (2.7.0)
+    addressable (2.8.0)
       public_suffix (>= 2.0.2, < 5.0)
+    ansi (1.5.0)
+    builder (3.2.4)
+    byebug (11.1.3)
     domain_name (0.5.20190701)
       unf (>= 0.0.5, < 1.0.0)
-    faraday (1.0.1)
-      multipart-post (>= 1.2, < 3)
-    faraday-cookie_jar (0.0.6)
-      faraday (>= 0.7.4)
+    faraday (1.10.0)
+      faraday-em_http (~> 1.0)
+      faraday-em_synchrony (~> 1.0)
+      faraday-excon (~> 1.1)
+      faraday-httpclient (~> 1.0)
+      faraday-multipart (~> 1.0)
+      faraday-net_http (~> 1.0)
+      faraday-net_http_persistent (~> 1.0)
+      faraday-patron (~> 1.0)
+      faraday-rack (~> 1.0)
+      faraday-retry (~> 1.0)
+      ruby2_keywords (>= 0.0.4)
+    faraday-cookie_jar (0.0.7)
+      faraday (>= 0.8.0)
       http-cookie (~> 1.0.0)
+    faraday-em_http (1.0.0)
+    faraday-em_synchrony (1.0.0)
     faraday-encoding (0.0.5)
       faraday
+    faraday-excon (1.1.0)
     faraday-http-cache (2.2.0)
       faraday (>= 0.8)
-    faraday_middleware (1.0.0)
+    faraday-httpclient (1.0.1)
+    faraday-multipart (1.0.3)
+      multipart-post (>= 1.2, < 3)
+    faraday-net_http (1.0.1)
+    faraday-net_http_persistent (1.2.0)
+    faraday-patron (1.0.0)
+    faraday-rack (1.0.0)
+    faraday-retry (1.0.3)
+    faraday_middleware (1.2.0)
       faraday (~> 1.0)
-    fastimage (2.1.7)
-    http-cookie (1.0.3)
+    fastimage (2.2.6)
+    htmlentities (4.3.4)
+    http-cookie (1.0.4)
       domain_name (~> 0.5)
-    metainspector (5.10.1)
-      addressable (~> 2.7.0)
-      faraday (~> 1.0.0)
-      faraday-cookie_jar (~> 0.0.6)
-      faraday-encoding (~> 0.0.5)
-      faraday-http-cache (~> 2.2.0)
-      faraday_middleware (~> 1.0.0)
-      fastimage (~> 2.1.7)
-      nesty (~> 1.0.2)
-      nokogiri (~> 1.10.9)
-    mini_portile2 (2.4.0)
+    metainspector (5.12.1)
+      addressable (~> 2.7)
+      faraday (>= 1.4, < 3.0)
+      faraday-cookie_jar (~> 0.0)
+      faraday-encoding (~> 0.0)
+      faraday-http-cache (~> 2.2)
+      faraday_middleware (~> 1.0)
+      fastimage (~> 2.2)
+      nesty (~> 1.0)
+      nokogiri (~> 1.11)
+    mini_portile2 (2.8.0)
+    minitest (5.15.0)
+    minitest-reporters (1.5.0)
+      ansi
+      builder
+      minitest (>= 5.0)
+      ruby-progressbar
     multipart-post (2.1.1)
     nesty (1.0.2)
-    nokogiri (1.10.10)
-      mini_portile2 (~> 2.4.0)
-    public_suffix (4.0.5)
+    nokogiri (1.13.6)
+      mini_portile2 (~> 2.8.0)
+      racc (~> 1.4)
+    public_suffix (4.0.7)
+    racc (1.6.0)
     rake (12.3.3)
+    ruby-progressbar (1.11.0)
+    ruby2_keywords (0.0.5)
     unf (0.1.4)
       unf_ext
-    unf_ext (0.0.7.7)
+    unf_ext (0.0.8.1)
 
 PLATFORMS
   ruby
 
 DEPENDENCIES
+  byebug
   curation!
+  minitest
+  minitest-reporters
   rake (~> 12.0)
 
 BUNDLED WITH

data/Rakefile

@@ -1,2 +1,10 @@
 require "bundler/gem_tasks"
-task :default => :spec
+require "rake/testtask"
+
+Rake::TestTask.new do |t|
+  t.libs << "test"
+  t.test_files = FileList["test/**/*_spec.rb"]
+  t.warning = false
+end
+
+task default: :test

data/curation.gemspec

@@ -23,4 +23,5 @@ Gem::Specification.new do |spec|
   spec.require_paths = ["lib"]
   spec.add_dependency "metainspector"
   spec.add_dependency "nokogiri"
+  spec.add_dependency "htmlentities"
 end

data/lib/curation/version.rb

@@ -1,3 +1,3 @@
 module Curation
-  VERSION = "1.6"
+  VERSION = "1.9"
 end

data/lib/curation.rb

@@ -1,12 +1,13 @@
 require "curation/version"
 require "metainspector"
 require "open-uri"
+require "htmlentities"
 
 module Curation
   class Error < StandardError; end
 
   class Page
-    attr_reader :url, :title, :text, :image
+    attr_reader :url
 
     BLACKLIST = [
       'head', 'script', 'style', 'iframe', 'nav', 'noscript', 'header', 'footer', 'aside',
@@ -20,46 +21,38 @@ module Curation
     ]
 
     def initialize(url, html = nil)
-      @url = url
+      @url = url.to_s.gsub('http://', 'https://')
       @html = html
     end
 
     def title
-      @title = find_title
+      @title ||= find_title
     end
 
     def image
-      @image = find_image
-      @image = @image.to_s.gsub('http://', 'https://')
+      unless @image
+        @image = find_image
+        @image = @image.to_s.gsub('http://', 'https://')
+      end
       @image
     end
 
     def text
-      if json_ld.any?
-        json_ld.each do |ld|
-          next unless ld['@type'] == 'NewsArticle'
-          return ld['text'] if ld.has_key? 'text'
-          return ld['articleBody'] if ld.has_key? 'articleBody'
-        end
-      end
-      h = nokogiri.dup
-      BLACKLIST.each do |tag|
-        h.css(tag).remove
-      end
-      nodes = h.css('p')
-      nodes.xpath('//style').remove
-      text = nodes.to_html
-      text.gsub!('<br><br>', '<br>')
-      text
+      # require 'byebug'; byebug
+      @text ||= find_text
+    end
+
+    def date
+      @date ||= find_date
     end
 
     protected
 
     def find_title
       if json_ld.any?
-        # Some sites have tables in tables
-        json_ld.flatten!
         json_ld.each do |ld|
+          # require 'byebug'; byebug
+          ld = ld.first if ld.is_a?(Array)
           return ld['headline'] if ld.has_key? 'headline'
         end
       end
@@ -70,7 +63,7 @@ module Curation
           nokogiri.css('[itemprop="headline"]')&.first&.inner_text,
           nokogiri.css('title')&.first&.inner_text
         ].each do |possibility|
-          return possibility unless possibility.blank?
+          return possibility unless possibility.to_s.empty?
         end
       rescue
         puts 'Curation::Page find_title error'
@@ -81,6 +74,7 @@ module Curation
     def find_image
       if json_ld.any?
         json_ld.each do |ld|
+          ld = ld.first if ld.is_a?(Array)
           if ld.has_key? 'image'
             image_data = ld['image']
             return image_data if image_data.is_a? String
@@ -98,7 +92,7 @@ module Curation
           metainspector.images.best,
           nokogiri.css('[property="og:image"]').first&.attributes['content'].value
         ].each do |possibility|
-            return possibility unless possibility.blank?
+          return possibility unless possibility.to_s.empty?
         end
       rescue
         puts 'Curation::Page find_image error'
@@ -106,16 +100,84 @@ module Curation
       return ''
     end
 
+    def find_text
+      text = find_text_with_json_ld || find_text_with_nokogiri
+      text.to_s.gsub!('<br><br>', '<br>')
+      # require 'byebug'; byebug
+      text = clean_encoding text
+      text
+    end
+
+    def find_text_with_json_ld
+      if json_ld.any?
+        json_ld.each do |ld|
+          next unless ['NewsArticle', 'ReportageNewsArticle'].include? ld['@type']
+          return ld['text'] if ld.has_key? 'text'
+          return ld['articleBody'] if ld.has_key? 'articleBody'
+        end
+      end
+      nil
+    end
+
+    def find_text_with_nokogiri
+      h = nokogiri.dup
+      BLACKLIST.each do |tag|
+        h.css(tag).remove
+      end
+      nodes = h.css('p')
+      nodes.xpath('//style').remove
+      text = nodes.to_html
+      text
+    end
+
+    def find_date
+      if json_ld.any?
+        json_ld.each do |ld|
+          next unless ['NewsArticle', 'ReportageNewsArticle'].include? ld['@type']
+          return Date.parse ld['datePublished'] if ld.has_key? 'datePublished'
+        end
+      end
+      return Date.parse metatags['date'] rescue nil
+      return Date.parse metatags['pubdate'] rescue nil
+      return Date.parse nokogiri.css('meta[property="article:published"]').first['content'] rescue nil
+      return Date.parse nokogiri.css('meta[property="article:published_time"]').first['content'] rescue nil
+      return Date.parse nokogiri.css('meta[property="og:article:published_time"]').first['content'] rescue nil
+      chunks = html.split('DisplayDate')
+      if chunks.count > 1
+        value = chunks[1]
+        value = value.split(',').first
+        value = value.gsub('"', '')
+        value = value[1..-1] if value[0] == ':'
+        return Date.parse value rescue nil
+      end
+      begin
+        value = nokogiri.css('.postDate').first
+        value = value.inner_text
+        value = value.gsub(' — ', '')
+        return Date.parse value
+      rescue
+      end
+      begin
+        value = nokogiri.css('.gta_post_date').first
+        value = value.inner_text
+        return Date.parse value
+      rescue
+      end
+    end
+
+    private
+
     def json_ld
-      unless @json_ld
+      unless defined?(@json_ld)
         @json_ld = []
         begin
           options = nokogiri.css('[type="application/ld+json"]')
           options.each do |option|
-            string = option.inner_text
-            hash = JSON.parse(string)
-            @json_ld << hash
+            @json_ld << json_ld_from_object(option)
           end
+          # Some sites have tables in tables
+          @json_ld.flatten!
+          # require 'byebug'; byebug
         rescue
           puts 'Curation::Page json_ld error'
         end
@@ -123,22 +185,79 @@ module Curation
       @json_ld
     end
 
+    def json_ld_from_object(object)
+      JSON.parse object.inner_text
+    rescue
+      {}
+    end
+
+    def file
+      @file ||= URI.open url, 'User-Agent' => "Mozilla/5.0"
+    rescue
+      puts "Curation::Page file error with url #{url}"
+    end
+
     def html
-      @html ||= URI.open url
+      unless @html
+        file.rewind
+        @html = file.read
+        file.rewind
+      end
+      @html
     rescue
-      puts "Impossible to open #{url}"
+      puts "Curation::Page html error"
     end
 
     def nokogiri
-      @nokogiri ||= Nokogiri::HTML html
+      unless @nokogiri
+        if file.nil?
+          @nokogiri = metainspector.parsed
+        else
+          file.rewind
+          @nokogiri = Nokogiri::HTML file
+          file.rewind
+        end
+      end
+      @nokogiri
     rescue
       puts 'Curation::Page nokogiri error'
     end
 
     def metainspector
-      @metainspector ||= MetaInspector.new url, document: html
+      unless @metainspector
+        @metainspector = html.nil?  ? MetaInspector.new(url)
+                                    : MetaInspector.new(url, document: html)
+      end
+      @metainspector
     rescue
       puts 'Curation::Page metainspector error'
     end
+
+    def metatags
+      @metatags ||= metainspector.meta_tag['name']
+    rescue
+      puts 'Curation::Page metatags error'
+    end
+
+    # r&Atilde;&copy;forme -> réforme
+    def clean_encoding(text)
+      clean_text = HTMLEntities.new.decode text
+      double_encoding = false
+      [
+        'é', # é
+        'è', # è
+        'î', # î
+        'ê', # ê
+      ].each do |string|
+        # require 'byebug'; byebug
+        double_encoding = true if clean_text.include? string
+      end
+      if double_encoding
+        clean_text.encode('iso-8859-1', undef: :replace)
+                  .force_encoding('utf-8')
+      else
+        text
+      end
+    end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: curation
 version: !ruby/object:Gem::Version
-  version: '1.6'
+  version: '1.9'
 platform: ruby
 authors:
 - Arnaud Levy
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2020-07-22 00:00:00.000000000 Z
+date: 2022-05-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: metainspector
@@ -38,6 +38,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: htmlentities
+  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'
 description: When you build content curation tools, you need to extract the content
   of pages (title, text, image...). This requires different strategies and some fine
   tuning to work efficiently.
@@ -65,7 +79,7 @@ licenses:
 metadata:
   homepage_uri: https://github.com/arnaudlevy/curation
   source_code_uri: https://github.com/arnaudlevy/curation
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -80,8 +94,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
-signing_key: 
+rubygems_version: 3.1.6
+signing_key:
 specification_version: 4
 summary: Curation of content
 test_files: []