metainspector 5.4.3 → 5.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: f6e7b6989a9d97ffd983e24718a751fb4b6bd6bf
-  data.tar.gz: 19298091068438ac8cb97955a87e6ed00eacddbe
+  metadata.gz: 2e1034aff57cb80cddd6a4c03c7e3ef92da0c6bf
+  data.tar.gz: 44ff18adc7fd7a1bfb7c17034591708eb309c5a6
 SHA512:
-  metadata.gz: 78bf72901f8c4bade41d3fe3bd4aa60a15477f187d983732d503838a1213e15788131371fb0f7e452e3654948abe91883b7d9f6b411477ed3308b29fac32ebf6
-  data.tar.gz: c032e15346a3aa542a17efbadd154adab78cce03519b8d7b4919013923b1aebef90200bd2c8d6776b4cdf4918cf14d4785c5024a47982ff2e5ada10ef098d96c
+  metadata.gz: 55a2d91009a7158d15109818d945db5133e21223da78f9ccd82c22765e6c4ae018940b50a3cd389c7d57b8d0c522ac282f5c0a3d44b4d1ddbfa4636add0add28
+  data.tar.gz: dab9bff983779b57467dc8db0ba9a0bb0c628abb2cc8fbc2aedbdd77503fd6ca5a882bb3576e951ce847ee4000afd277a94fa21e91364c5b13a72a711d4fc0de

data/README.md

@@ -81,6 +81,8 @@ page.feed                # Get rss or atom links in meta data fields as array
 ```ruby
 page.title               # title of the page from the head section, as string
 page.best_title          # best title of the page, from a selection of candidates
+page.author              # author of the page from the meta author tag
+page.best_author         # best author of the page, from a selection of candidates
 page.description         # returns the meta description
 page.best_description    # returns the first non-empty description between the following candidates: standard meta description, og:description, twitter:description, the first long paragraph
 ```

data/lib/meta_inspector/document.rb

@@ -45,7 +45,7 @@ module MetaInspector
 
     delegate [:content_type, :response]               => :@request
 
-    delegate [:parsed, :title, :best_title,
+    delegate [:parsed, :title, :best_title, :author, :best_author,
               :description, :best_description, :links,
               :images, :feed, :charset, :meta_tags,
               :meta_tag, :meta, :favicon,
@@ -60,6 +60,8 @@ module MetaInspector
         'root_url'         => root_url,
         'title'            => title,
         'best_title'       => best_title,
+        'author'           => author,
+        'best_author'      => best_author,
         'description'      => description,
         'best_description' => best_description,
         'links'            => links.to_hash,

data/lib/meta_inspector/parser.rb

@@ -21,12 +21,12 @@ module MetaInspector
     end
 
     extend Forwardable
-    delegate [:url, :scheme, :host]                                 => :@document
-    delegate [:meta_tags, :meta_tag, :meta, :charset]               => :@meta_tag_parser
-    delegate [:head_links, :stylesheets, :canonicals, :feed]        => :@head_links_parser
-    delegate [:links, :base_url]                                    => :@links_parser
-    delegate :images                                                => :@images_parser
-    delegate [:title, :best_title, :description, :best_description] => :@texts_parser
+    delegate [:url, :scheme, :host]                                                        => :@document
+    delegate [:meta_tags, :meta_tag, :meta, :charset]                                      => :@meta_tag_parser
+    delegate [:head_links, :stylesheets, :canonicals, :feed]                               => :@head_links_parser
+    delegate [:links, :base_url]                                                           => :@links_parser
+    delegate :images                                                                       => :@images_parser
+    delegate [:title, :best_title, :author, :best_author, :description, :best_description] => :@texts_parser
 
     # Returns the whole parsed document
     def parsed

data/lib/meta_inspector/parsers/texts.rb

@@ -14,6 +14,21 @@ module MetaInspector
         @best_title ||= find_best_title
       end
 
+      # Returns the meta author, if present
+      def author
+        @author ||= meta['author']
+      end
+
+      # An author getter that returns the first non-nil description
+      # from the following candidates:
+      # - the standard meta description
+      # - a link with the relational attribute "author"
+      # - address tag which may contain the author
+      # - the twitter:creator meta tag for the username
+      def best_author
+        @best_author ||= find_best_author
+      end
+
       # Returns the meta description, if present
       def description
         @description ||= meta['description']
@@ -50,6 +65,24 @@ module MetaInspector
         candidates.first
       end
 
+      def find_best_author
+        candidates = [
+          meta['author'],
+          parsed.css('a[rel="author"]').first,
+          parsed.css('address').first,
+          meta['twitter:creator']
+        ]
+        candidates.flatten!
+        candidates.compact!
+        candidates.map! { |c| (c.respond_to? :inner_text) ? c.inner_text : c }
+        candidates.map! { |c| c.strip }
+        return nil if candidates.empty?
+        candidates.map! { |c| c.gsub(/\s+/, ' ') }
+        candidates.uniq!
+        candidates.sort_by! { |t| -t.length }
+        candidates.first
+      end
+
       def find_best_description
         candidates = [
           meta['description'],

data/lib/meta_inspector/version.rb

@@ -1,3 +1,3 @@
 module MetaInspector
-  VERSION = '5.4.3'
+  VERSION = '5.5.0'
 end

data/spec/document_spec.rb

@@ -26,6 +26,8 @@ describe MetaInspector::Document do
                             "root_url"        => "http://pagerankalert.com/",
                             "title"           => "PageRankAlert.com :: Track your PageRank changes & receive alerts",
                             "best_title"      => "PageRankAlert.com :: Track your PageRank changes & receive alerts",
+                            "author"          => nil,
+                            "best_author"     => nil,
                             "description"     => "Track your PageRank(TM) changes and receive alerts by email",
                             "best_description"=> "Track your PageRank(TM) changes and receive alerts by email",
                             "favicon"         => "http://pagerankalert.com/src/favicon.ico",

data/spec/fixtures/author_in_body.response

@@ -0,0 +1,21 @@
+HTTP/1.1 200 OK
+Age: 13
+Cache-Control: max-age=120
+Content-Type: text/html
+Date: Mon, 06 Jan 2014 12:47:42 GMT
+Expires: Mon, 06 Jan 2014 12:49:28 GMT
+Server: Apache/2.2.14 (Ubuntu)
+Vary: Accept-Encoding
+Via: 1.1 varnish
+X-Powered-By: PHP/5.3.2-1ubuntu4.22
+X-Varnish: 1188792404 1188790413
+Content-Length: 265
+Connection: keep-alive
+
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml" xmlns:fb="http://www.facebook.com/2008/fbml">
+  <head></head>
+  <body>
+    <address>This author came from the address tag</address>
+  </body>
+</html>

data/spec/fixtures/author_in_link.response

@@ -0,0 +1,21 @@
+HTTP/1.1 200 OK
+Age: 13
+Cache-Control: max-age=120
+Content-Type: text/html
+Date: Mon, 06 Jan 2014 12:47:42 GMT
+Expires: Mon, 06 Jan 2014 12:49:28 GMT
+Server: Apache/2.2.14 (Ubuntu)
+Vary: Accept-Encoding
+Via: 1.1 varnish
+X-Powered-By: PHP/5.3.2-1ubuntu4.22
+X-Varnish: 1188792404 1188790413
+Content-Length: 265
+Connection: keep-alive
+
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml" xmlns:fb="http://www.facebook.com/2008/fbml">
+  <head></head>
+  <body>
+    <a rel="author">This author came from a link with the author relational attribute</a>
+  </body>
+</html>

data/spec/fixtures/author_in_meta.response

@@ -0,0 +1,23 @@
+HTTP/1.1 200 OK
+Age: 13
+Cache-Control: max-age=120
+Content-Type: text/html
+Date: Mon, 06 Jan 2014 12:47:42 GMT
+Expires: Mon, 06 Jan 2014 12:49:28 GMT
+Server: Apache/2.2.14 (Ubuntu)
+Vary: Accept-Encoding
+Via: 1.1 varnish
+X-Powered-By: PHP/5.3.2-1ubuntu4.22
+X-Varnish: 1188792404 1188790413
+Content-Length: 40571
+Connection: keep-alive
+
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml" xmlns:fb="http://www.facebook.com/2008/fbml">
+  <head>
+    <meta name="author" content="the author" />
+  </head>
+  <body>
+    <p>A sample page with author in standard meta tag</p>
+  </body>
+</html>

data/spec/fixtures/author_in_twitter.response

@@ -0,0 +1,23 @@
+HTTP/1.1 200 OK
+Age: 13
+Cache-Control: max-age=120
+Content-Type: text/html
+Date: Mon, 06 Jan 2014 12:47:42 GMT
+Expires: Mon, 06 Jan 2014 12:49:28 GMT
+Server: Apache/2.2.14 (Ubuntu)
+Vary: Accept-Encoding
+Via: 1.1 varnish
+X-Powered-By: PHP/5.3.2-1ubuntu4.22
+X-Varnish: 1188792404 1188790413
+Content-Length: 40571
+Connection: keep-alive
+
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml" xmlns:fb="http://www.facebook.com/2008/fbml">
+  <head>
+    <meta property="twitter:creator" content="This author came from the twitter creator tag" />
+</head>
+  <body>
+    <p>A sample page with author in Twitter meta tag</p>
+  </body>
+</html>

data/spec/meta_inspector/texts_spec.rb

@@ -49,6 +49,50 @@ describe MetaInspector do
     end
   end
 
+  describe '#author' do
+    it "should find author from meta author" do
+      page = MetaInspector.new('http://example.com/author_in_meta')
+
+      expect(page.author).to eq("the author")
+    end
+
+    it "should be nil if no meta author" do
+      page = MetaInspector.new('http://example.com/empty')
+
+      expect(page.author).to be(nil)
+    end
+  end
+
+  describe "#best_author" do
+    it "should return the author meta tag content if present" do
+      page = MetaInspector.new('http://example.com/author_in_meta')
+
+      expect(page.best_author).to eq("the author")
+    end
+
+    it "should find a link with the relational attribute author if standard meta tag is not present" do
+      page = MetaInspector.new('http://example.com/author_in_link')
+      expect(page.best_author).to eq("This author came from a link with the author relational attribute")
+    end
+
+    it "should find the address tag if standard meta tag and relational attribute author are not present" do
+      page = MetaInspector.new('http://example.com/author_in_body')
+      expect(page.best_author).to eq("This author came from the address tag")
+    end
+
+    it "should return the twitter creator if address tag not present" do
+      page = MetaInspector.new('http://example.com/author_in_twitter')
+
+      expect(page.best_author).to eq("This author came from the twitter creator tag")
+    end
+
+    it "should return nil if no author information present" do
+      page = MetaInspector.new('http://example.com/empty')
+
+      expect(page.best_author).to be(nil)
+    end
+  end
+
   describe '#description' do
     it "should find description from meta description" do
       page = MetaInspector.new('http://example.com/desc_in_meta')

data/spec/spec_helper.rb

@@ -44,6 +44,10 @@ RSpec.configure do |config|
     stub_request(:get, "http://example.com/title_in_head").to_return(fixture_file("title_in_head.response"))
     stub_request(:get, "http://example.com/title_in_head_with_whitespace").to_return(fixture_file("title_in_head_with_whitespace.response"))
     stub_request(:get, "http://example.com/title_not_present").to_return(fixture_file("title_not_present.response"))
+    stub_request(:get, "http://example.com/author_in_meta").to_return(fixture_file("author_in_meta.response"))
+    stub_request(:get, "http://example.com/author_in_body").to_return(fixture_file("author_in_body.response"))
+    stub_request(:get, "http://example.com/author_in_link").to_return(fixture_file("author_in_link.response"))
+    stub_request(:get, "http://example.com/author_in_twitter").to_return(fixture_file("author_in_twitter.response"))
     stub_request(:get, "http://example.com/~").to_return(fixture_file("example.response"))
     stub_request(:get, "http://facebook.com/").to_return(fixture_file("facebook.com.response"))
     stub_request(:get, "http://international.com").to_return(fixture_file("international.response"))

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: metainspector
 version: !ruby/object:Gem::Version
-  version: 5.4.3
+  version: 5.5.0
 platform: ruby
 authors:
 - Jaime Iniesta
@@ -262,6 +262,10 @@ files:
 - spec/fixtures/404.response
 - spec/fixtures/alazan.com.response
 - spec/fixtures/alazan_websolution.response
+- spec/fixtures/author_in_body.response
+- spec/fixtures/author_in_link.response
+- spec/fixtures/author_in_meta.response
+- spec/fixtures/author_in_twitter.response
 - spec/fixtures/broken_head_links.response
 - spec/fixtures/charset_000.response
 - spec/fixtures/charset_001.response