href-preview 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: a67ef243d53323e6ece890b63a587c0b6a298db3
+  data.tar.gz: 4843646e829511658a361df0fe24a81fea30d512
+SHA512:
+  metadata.gz: bd3ea4180c61cab25a689adecc200cded13d3747bcefa1ab6061cbd13dc014e77be8fd2b3cca8cedc17ca4d15a5d9b998cb9a2f83d1e4abc6950de98fe3b9389
+  data.tar.gz: 88b207d8bcc1b6a5574e0987bd717257d1b90c98b48277f09d53ae282cfcbd17f8c34db9d783e35322569048901546387e4179d46e447d545e97a40b839163e1

data/CHANGELOG

@@ -0,0 +1,3 @@
+== 0.1.0
+
+* initial release

data/Gemfile

@@ -0,0 +1,15 @@
+source 'https://rubygems.org'
+
+# dependencies go here
+
+group :development do
+  gem 'launchy', '>= 2.1.1'
+  gem 'yard'
+  gem 'kramdown'
+end
+
+group :test, :development do
+  gem 'rake', '>= 0.9.0'
+  gem 'rspec', '>= 2.11.0'
+  gem 'rcov', '>= 0.9.9', :platform => :mri_18
+end

data/LICENSE

@@ -0,0 +1,202 @@
+
+                              Apache License
+                        Version 2.0, January 2004
+                     http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+   "License" shall mean the terms and conditions for use, reproduction,
+   and distribution as defined by Sections 1 through 9 of this document.
+
+   "Licensor" shall mean the copyright owner or entity authorized by
+   the copyright owner that is granting the License.
+
+   "Legal Entity" shall mean the union of the acting entity and all
+   other entities that control, are controlled by, or are under common
+   control with that entity. For the purposes of this definition,
+   "control" means (i) the power, direct or indirect, to cause the
+   direction or management of such entity, whether by contract or
+   otherwise, or (ii) ownership of fifty percent (50%) or more of the
+   outstanding shares, or (iii) beneficial ownership of such entity.
+
+   "You" (or "Your") shall mean an individual or Legal Entity
+   exercising permissions granted by this License.
+
+   "Source" form shall mean the preferred form for making modifications,
+   including but not limited to software source code, documentation
+   source, and configuration files.
+
+   "Object" form shall mean any form resulting from mechanical
+   transformation or translation of a Source form, including but
+   not limited to compiled object code, generated documentation,
+   and conversions to other media types.
+
+   "Work" shall mean the work of authorship, whether in Source or
+   Object form, made available under the License, as indicated by a
+   copyright notice that is included in or attached to the work
+   (an example is provided in the Appendix below).
+
+   "Derivative Works" shall mean any work, whether in Source or Object
+   form, that is based on (or derived from) the Work and for which the
+   editorial revisions, annotations, elaborations, or other modifications
+   represent, as a whole, an original work of authorship. For the purposes
+   of this License, Derivative Works shall not include works that remain
+   separable from, or merely link (or bind by name) to the interfaces of,
+   the Work and Derivative Works thereof.
+
+   "Contribution" shall mean any work of authorship, including
+   the original version of the Work and any modifications or additions
+   to that Work or Derivative Works thereof, that is intentionally
+   submitted to Licensor for inclusion in the Work by the copyright owner
+   or by an individual or Legal Entity authorized to submit on behalf of
+   the copyright owner. For the purposes of this definition, "submitted"
+   means any form of electronic, verbal, or written communication sent
+   to the Licensor or its representatives, including but not limited to
+   communication on electronic mailing lists, source code control systems,
+   and issue tracking systems that are managed by, or on behalf of, the
+   Licensor for the purpose of discussing and improving the Work, but
+   excluding communication that is conspicuously marked or otherwise
+   designated in writing by the copyright owner as "Not a Contribution."
+
+   "Contributor" shall mean Licensor and any individual or Legal Entity
+   on behalf of whom a Contribution has been received by Licensor and
+   subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of
+   this License, each Contributor hereby grants to You a perpetual,
+   worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+   copyright license to reproduce, prepare Derivative Works of,
+   publicly display, publicly perform, sublicense, and distribute the
+   Work and such Derivative Works in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of
+   this License, each Contributor hereby grants to You a perpetual,
+   worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+   (except as stated in this section) patent license to make, have made,
+   use, offer to sell, sell, import, and otherwise transfer the Work,
+   where such license applies only to those patent claims licensable
+   by such Contributor that are necessarily infringed by their
+   Contribution(s) alone or by combination of their Contribution(s)
+   with the Work to which such Contribution(s) was submitted. If You
+   institute patent litigation against any entity (including a
+   cross-claim or counterclaim in a lawsuit) alleging that the Work
+   or a Contribution incorporated within the Work constitutes direct
+   or contributory patent infringement, then any patent licenses
+   granted to You under this License for that Work shall terminate
+   as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the
+   Work or Derivative Works thereof in any medium, with or without
+   modifications, and in Source or Object form, provided that You
+   meet the following conditions:
+
+   (a) You must give any other recipients of the Work or
+       Derivative Works a copy of this License; and
+
+   (b) You must cause any modified files to carry prominent notices
+       stating that You changed the files; and
+
+   (c) You must retain, in the Source form of any Derivative Works
+       that You distribute, all copyright, patent, trademark, and
+       attribution notices from the Source form of the Work,
+       excluding those notices that do not pertain to any part of
+       the Derivative Works; and
+
+   (d) If the Work includes a "NOTICE" text file as part of its
+       distribution, then any Derivative Works that You distribute must
+       include a readable copy of the attribution notices contained
+       within such NOTICE file, excluding those notices that do not
+       pertain to any part of the Derivative Works, in at least one
+       of the following places: within a NOTICE text file distributed
+       as part of the Derivative Works; within the Source form or
+       documentation, if provided along with the Derivative Works; or,
+       within a display generated by the Derivative Works, if and
+       wherever such third-party notices normally appear. The contents
+       of the NOTICE file are for informational purposes only and
+       do not modify the License. You may add Your own attribution
+       notices within Derivative Works that You distribute, alongside
+       or as an addendum to the NOTICE text from the Work, provided
+       that such additional attribution notices cannot be construed
+       as modifying the License.
+
+   You may add Your own copyright statement to Your modifications and
+   may provide additional or different license terms and conditions
+   for use, reproduction, or distribution of Your modifications, or
+   for any such Derivative Works as a whole, provided Your use,
+   reproduction, and distribution of the Work otherwise complies with
+   the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise,
+   any Contribution intentionally submitted for inclusion in the Work
+   by You to the Licensor shall be under the terms and conditions of
+   this License, without any additional terms or conditions.
+   Notwithstanding the above, nothing herein shall supersede or modify
+   the terms of any separate license agreement you may have executed
+   with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade
+   names, trademarks, service marks, or product names of the Licensor,
+   except as required for reasonable and customary use in describing the
+   origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or
+   agreed to in writing, Licensor provides the Work (and each
+   Contributor provides its Contributions) on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+   implied, including, without limitation, any warranties or conditions
+   of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+   PARTICULAR PURPOSE. You are solely responsible for determining the
+   appropriateness of using or redistributing the Work and assume any
+   risks associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory,
+   whether in tort (including negligence), contract, or otherwise,
+   unless required by applicable law (such as deliberate and grossly
+   negligent acts) or agreed to in writing, shall any Contributor be
+   liable to You for damages, including any direct, indirect, special,
+   incidental, or consequential damages of any character arising as a
+   result of this License or out of the use or inability to use the
+   Work (including but not limited to damages for loss of goodwill,
+   work stoppage, computer failure or malfunction, or any and all
+   other commercial damages or losses), even if such Contributor
+   has been advised of the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing
+   the Work or Derivative Works thereof, You may choose to offer,
+   and charge a fee for, acceptance of support, warranty, indemnity,
+   or other liability obligations and/or rights consistent with this
+   License. However, in accepting such obligations, You may act only
+   on Your own behalf and on Your sole responsibility, not on behalf
+   of any other Contributor, and only if You agree to indemnify,
+   defend, and hold each Contributor harmless for any liability
+   incurred by, or claims asserted against, such Contributor by reason
+   of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS
+
+APPENDIX: How to apply the Apache License to your work.
+
+   To apply the Apache License to your work, attach the following
+   boilerplate notice, with the fields enclosed by brackets "[]"
+   replaced with your own identifying information. (Don't include
+   the brackets!)  The text should be enclosed in the appropriate
+   comment syntax for the file format. We also recommend that a
+   file or class name and description of purpose be included on the
+   same "printed page" as the copyright notice for easier
+   identification within third-party archives.
+
+Copyright [yyyy] [name of copyright owner]
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

data/README.md

@@ -0,0 +1,39 @@
+# HREF Preview
+
+<dl>
+  <dt>Homepage</dt><dd><a href="https://github.com/sporkmonger/href-preview">https://github.com/sporkmonger/href-preview</a></dd>
+  <dt>Author</dt><dd><a href="mailto:bob@sporkmonger.com">Bob Aman</a></dd>
+  <dt>Copyright</dt><dd>Copyright © 2014 Bob Aman</dd>
+  <dt>License</dt><dd>Apache 2.0</dd>
+</dl>
+
+# Description
+
+A comprehensive library for efficiently previewing links.
+
+# Features
+
+Capable of detecting:
+* OpenGraph metadata
+* Twitter metadata
+* Microdata metadata
+* Assorted microformat metadata
+* RDFa metadata
+* rel="canonical" links
+
+# Example Usage
+
+    require 'href_preview'
+    p = HRefPreview.open('http://nyti.ms/1c1zNtX')
+    p.title
+    # => "A Successor to Sagan Reboots ‘Cosmos’"
+    p.description
+    # =>
+    p.article_html
+    p.article_text
+    p.published
+    p.canonical_uri
+
+# Install
+
+* gem install href-preview

data/Rakefile

@@ -0,0 +1,42 @@
+lib_dir = File.expand_path(File.join(File.dirname(__FILE__), 'lib'))
+$:.unshift(lib_dir)
+$:.uniq!
+
+require 'rubygems'
+require 'rake'
+
+require File.join(File.dirname(__FILE__), 'lib/href_preview', 'version')
+
+PKG_DISPLAY_NAME   = 'HREF Preview'
+PKG_NAME           = PKG_DISPLAY_NAME.gsub(/ /, '-').downcase
+PKG_VERSION        = HRefPreview::VERSION::STRING
+PKG_FILE_NAME      = "#{PKG_NAME}-#{PKG_VERSION}"
+
+RELEASE_NAME       = "REL #{PKG_VERSION}"
+GIT_HUB_URL        = "https://github.com/sporkmonger/href-preview"
+
+PKG_AUTHOR         = 'Bob Aman'
+PKG_AUTHOR_EMAIL   = 'bob@sporkmonger.com'
+PKG_HOMEPAGE       = GIT_HUB_URL
+PKG_SUMMARY        = 'Package Summary'
+PKG_DESCRIPTION    = <<-TEXT
+A simple library for efficiently previewing links.
+TEXT
+
+PKG_FILES = FileList[
+    'lib/**/*', 'spec/**/*', 'vendor/**/*',
+    'tasks/**/*', 'website/**/*',
+    '[A-Z]*', 'Rakefile'
+].exclude(/database\.yml/).exclude(/[_\.]git$/).exclude(/Gemfile\.lock/)
+
+RCOV_ENABLED = (RUBY_PLATFORM != 'java' && RUBY_VERSION =~ /^1\.8/)
+if RCOV_ENABLED
+  task :default => 'spec:rcov'
+else
+  task :default => 'spec'
+end
+
+WINDOWS = (RUBY_PLATFORM =~ /mswin|win32|mingw|bccwin|cygwin/) rescue false
+SUDO = WINDOWS ? '' : ('sudo' unless ENV['SUDOLESS'])
+
+Dir['tasks/**/*.rake'].each { |rake| load rake }

data/lib/href-preview.rb

@@ -0,0 +1,17 @@
+# Copyright 2014 Bob Aman
+#
+#    Licensed under the Apache License, Version 2.0 (the "License");
+#    you may not use this file except in compliance with the License.
+#    You may obtain a copy of the License at
+#
+#        http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS,
+#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#    See the License for the specific language governing permissions and
+#    limitations under the License.
+
+
+# Just a require alias.
+require 'href_preview'

data/lib/href_preview.rb

@@ -0,0 +1,34 @@
+# Copyright 2014 Bob Aman
+#
+#    Licensed under the Apache License, Version 2.0 (the "License");
+#    you may not use this file except in compliance with the License.
+#    You may obtain a copy of the License at
+#
+#        http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS,
+#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#    See the License for the specific language governing permissions and
+#    limitations under the License.
+
+
+require 'addressable/uri'
+require 'faraday'
+require 'faraday_middleware'
+require 'href_preview/version'
+require 'href_preview/preview'
+require 'href_preview/faraday_common_request'
+
+module HRefPreview
+  DEFAULT_CONNECTION = Faraday.new do |connection|
+    connection.use FaradayMiddleware::FollowRedirects, {:limit => 5}
+    connection.use Faraday::CommonRequest
+    connection.adapter :httpclient
+  end
+
+  def self.open(uri, connection=DEFAULT_CONNECTION)
+    response = connection.get(Addressable::URI.parse(uri))
+    return HRefPreview::Preview.new(response, connection)
+  end
+end

data/lib/href_preview/faraday_common_request.rb

@@ -0,0 +1,40 @@
+# Copyright 2014 Bob Aman
+#
+#    Licensed under the Apache License, Version 2.0 (the "License");
+#    you may not use this file except in compliance with the License.
+#    You may obtain a copy of the License at
+#
+#        http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS,
+#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#    See the License for the specific language governing permissions and
+#    limitations under the License.
+
+
+module Faraday
+  class CommonRequest < Faraday::Middleware
+    def initialize(app, *args)
+      @app = app
+      @options = args.shift || {}
+      @options.merge!(
+        :user_agent => (
+          "Mozilla/5.0 (compatible; " +
+          "HRefPreview/#{HRefPreview::VERSION::STRING}; " +
+          "+https://github.com/sporkmonger/href-preview)"
+        ),
+        :accept => "*/*"
+      )
+      @user_agent = @options[:user_agent]
+      @accept = @options[:accept]
+    end
+
+    def call(env)
+      env[:request_headers].merge!('User-Agent' => @user_agent)
+      env[:request_headers].merge!('Accept' => @accept)
+      response = @app.call env
+      response
+    end
+  end
+end

data/lib/href_preview/fastimage_uri.rb

@@ -0,0 +1,20 @@
+# Copyright 2014 Bob Aman
+#
+#    Licensed under the Apache License, Version 2.0 (the "License");
+#    you may not use this file except in compliance with the License.
+#    You may obtain a copy of the License at
+#
+#        http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS,
+#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#    See the License for the specific language governing permissions and
+#    limitations under the License.
+
+
+require 'fastimage'
+
+class FastImage
+  attr_reader :uri
+end

data/lib/href_preview/preview.rb

@@ -0,0 +1,451 @@
+# Copyright 2014 Bob Aman
+#
+#    Licensed under the Apache License, Version 2.0 (the "License");
+#    you may not use this file except in compliance with the License.
+#    You may obtain a copy of the License at
+#
+#        http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS,
+#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#    See the License for the specific language governing permissions and
+#    limitations under the License.
+
+
+require 'mime/types'
+require 'faraday'
+require 'nokogiri'
+require 'sanitize'
+require 'fastimage'
+require 'href_preview/fastimage_uri'
+require 'time'
+
+module HRefPreview
+  class Preview
+    ##
+    # Initializes a `Preview` from an HTTP response.
+    def initialize(response, connection=DEFAULT_CONNECTION)
+      @response = response
+      @connection = connection
+    end
+
+    attr_reader :response
+
+    ##
+    # Returns the MIME type declared in the HTTP headers or HTML meta
+    # tags.
+    #
+    # @return [MIME::Type] The MIME type of the HTTP response.
+    def mime_type
+      @mime_type ||= (begin
+        MIME::Types[response.headers['Content-Type']].first or
+        begin
+          node = dom.xpath("//*/meta[@http-equiv='Content-Type']/@content").first
+          MIME::Types[node.value].first if node && node.value
+        end or
+        begin
+          node = dom.xpath("//*/meta[@name='dc.format']/@content").first
+          MIME::Types[node.value].first if node && node.value
+        end
+      end)
+    end
+
+    ##
+    # Returns the charset declared in the HTTP headers or HTML meta
+    # tags.
+    #
+    # @return [String] The charset of the HTTP response.
+    def charset
+      @charset ||= (begin
+        charset = response.headers['Content-Type'].to_s[/;\s*charset=([^;,]*)/, 1] or
+        begin
+          node = dom.xpath("//*/meta[@http-equiv='Content-Type']/@content").first
+          node.value.to_s[/;\s*charset=([^;,]*)/, 1] if node
+        end or
+        begin
+          node = dom.xpath("//*/meta/@charset").first
+          node.value if node
+        end
+        charset.strip if charset
+      end)
+    end
+
+    ##
+    # @returns [String] The two-letter language code for the content.
+    def language
+      @language ||= (begin
+        language = response.headers['Content-Language'] or
+        begin
+          node = dom.xpath("//*/meta[@http-equiv='Content-Language']/@content").first
+          node.value if node
+        end or
+        begin
+          node = dom.xpath("//*/meta[@name='dc.language']/@content").first
+          node.value if node
+        end
+        if language
+          # Strip the irrelevant '-US' from 'en-US' if it appears.
+          language[/^([a-z]{2})/, 1].to_s.downcase
+        end
+      end)
+    end
+
+    ##
+    # Returns true if the response had a 2xx HTTP code and the mime type
+    # is either HTML or XHTML.
+    #
+    # @return [true, false] Whether successful HTML response or not.
+    def is_html?
+      return (
+        response.status >= 200 && response.status < 300 &&
+        mime_type && mime_type.sub_type =~ /^x?html/
+      )
+    end
+
+    ##
+    # The DOM for the response body.
+    #
+    # @return [Nokogiri::HTML::Document]
+    #   The DOM, as generated by Nokogiri.
+    def dom
+      @dom ||= Nokogiri::HTML(response.body)
+    end
+
+    ##
+    # @return [String] The title of the page.
+    def title
+      @title ||= (begin
+        if is_html?
+          title = begin
+            node = dom.xpath("//*/meta[@property='og:title']/@content").first
+            node.value if node
+          end or
+          begin
+            node = dom.xpath("//*/meta[@name='dc.title']/@content").first
+            node.value if node
+          end or
+          begin
+            if article_node
+              node = article_node.xpath("*[@itemprop='headline']").first
+              node.text if node
+            end
+          end or
+          begin
+            node = dom.xpath("//*/*[(self::h1 or self::h2) and @itemprop='headline']").first
+            node.text if node
+          end or
+          begin
+            node = dom.xpath("//*/head/title").first
+            node.text if node
+          end or
+          begin
+            # Unlikely to ever happen
+            node = dom.xpath("//*/meta[@name='twitter:title']/@content").first
+            node.value if node
+          end or
+          begin
+            # Unlikely to ever happen
+            node = dom.xpath("//*/meta[@name='sailthru.title']/@content").first
+            node.value if node
+          end
+          if title
+            title.gsub!(/&nbsp;/, ' ')
+            title.gsub!(/^#{site_name}[\s\|\-\:]*/, '')
+            title.gsub!(/[\s\|\-\:]*#{site_name}$/, '')
+            title.strip
+          end
+        end
+      end)
+    end
+
+    def description
+      @description ||= (begin
+        if is_html?
+          description = begin
+            node = dom.xpath("//*/meta[@property='og:description']/@content").first
+            node.value if node
+          end or
+          begin
+            node = dom.xpath("//*/meta[@name='dc.description']/@content").first
+            node.value if node
+          end or
+          begin
+            node = dom.xpath("//*/meta[@itemprop='description']/@content").first
+            node.value if node
+          end or
+          begin
+            node = dom.xpath("//*/meta[@name='description']/@content").first
+            node.value if node
+          end or
+          begin
+            node = dom.xpath("//*/meta[@name='dcterms.abstract']/@content").first
+            node.value if node
+          end or
+          begin
+            # Unlikely to ever happen
+            node = dom.xpath("//*/meta[@name='twitter:description']/@content").first
+            node.value if node
+          end or
+          begin
+            # Unlikely to ever happen
+            node = dom.xpath("//*/meta[@name='sailthru.description']/@content").first
+            node.value if node
+          end
+          if description
+            description.gsub!(/&nbsp;/, ' ')
+            description.strip
+          end
+        end
+      end)
+    end
+
+    def canonical_uri
+      @canonical_uri ||= (if is_html?
+        begin
+          node = dom.xpath("//*/link[@rel='canonical']/@href").first
+          Addressable::URI.parse(node.value) if node && node.value && node.value != ''
+        end or
+        begin
+          node = dom.xpath("//*/meta[@property='og:url']/@content").first
+          Addressable::URI.parse(node.value) if node && node.value && node.value != ''
+        end or
+        Addressable::URI.parse(response.env.url.to_s)
+      else
+        Addressable::URI.parse(response.env.url.to_s)
+      end)
+    end
+
+    def shortlink_uri
+      @shortlink_uri ||= (if is_html?
+        begin
+          node = dom.xpath("//*/link[@rel='shortlink']/@href").first
+          Addressable::URI.parse(node.value) if node && node.value && node.value != ''
+        end or
+        begin
+          node = dom.xpath("//*[@class='story-short-url']/a/@href").first
+          Addressable::URI.parse(node.value) if node && node.value && node.value != ''
+        end
+      end)
+    end
+
+    def image_uri
+      @image_uri ||= (images.first ? Addressable::URI.parse(images.first.uri) : nil)
+    end
+
+    def images
+      @images ||= (begin
+        image_uris = []
+        if is_html?
+          nodes = dom.xpath("//*/meta[@property='og:image']/@content")
+          nodes.each do |node|
+            if node && node.value && node.value != ''
+              image_uris << Addressable::URI.parse(node.value)
+            end
+          end
+          if article_node
+            nodes = article_node.xpath("meta[@itemprop='thumbnailurl']/@content")
+            nodes.each do |node|
+              if node && node.value && node.value != ''
+                image_uris << Addressable::URI.parse(node.value)
+              end
+            end
+          end
+        elsif mime_type && mime_type.media_type == 'image'
+          image_uris << canonical_uri
+        end
+        image_uris.uniq.map { |uri| FastImage.new(uri, :timeout => 0.5) }
+      end)
+    end
+
+    def item_type
+      @item_type ||= (if is_html?
+        begin
+          node = dom.xpath("//*/meta[@property='og:type']/@content").first
+          node.value if node
+        end or
+        if dom.xpath("//*[@itemtype='http://schema.org/NewsArticle']").first != nil
+          'article'
+        end
+      end)
+    end
+
+    def site_name
+      @site_name ||= (if is_html?
+        begin
+          node = dom.xpath("//*/meta[@property='og:site_name']/@content").first
+          node.value if node
+        end or
+        begin
+          node = dom.xpath("//*/meta[@name='dc.publisher']/@content").first
+          node.value if node
+        end
+      end)
+    end
+
+    ##
+    # @return [String] The Twitter handle used by the site.
+    def twitter
+      @twitter ||= (if is_html?
+        begin
+          node = dom.xpath("//*/meta[@name='twitter:site']/@content").first
+          node.value if node && node.value && node.value =~ /^@/
+        end
+      end)
+    end
+
+    def article_node
+      @article_node ||= (if is_html?
+        begin
+          nodes = dom.xpath("/html[@itemtype='http://schema.org/NewsArticle']//article[@id='story']")
+          nodes.first if nodes.size == 1
+        end or
+        begin
+          nodes = dom.xpath("//*/*[@itemtype='http://schema.org/NewsArticle']")
+          nodes.first if nodes.size == 1
+        end or
+        begin
+          nodes = dom.xpath("//*/*[@itemprop='articleBody']")
+          nodes.first if nodes.size == 1
+        end or
+        begin
+          nodes = dom.css("article div.article-entry")
+          nodes.first if nodes.size == 1
+        end or
+        begin
+          nodes = dom.css("article.post div.entry-content")
+          nodes.first if nodes.size == 1
+        end or
+        begin
+          nodes = dom.css("div.post div.postBody")
+          nodes.first if nodes.size == 1
+        end or
+        begin
+          nodes = dom.css(".pg_story div#leftcolumn div.body")
+          nodes.first if nodes.size == 1
+        end
+      end)
+    end
+
+    options = Sanitize::Config::RELAXED.merge(
+      :remove_contents => true,
+      :elements => %w[
+        a abbr address b bdi bdo blockquote br caption cite code col colgroup dd
+        del dfn dl dt em figcaption figure h1 h2 h3 h4 h5 h6 hgroup hr i img ins
+        kbd li mark ol p pre q rp rt ruby s samp small span strike strong sub
+        summary sup table tbody td tfoot th thead time tr u ul var wbr
+      ]
+    )
+    options[:attributes]['span'] = []
+    SANITIZE_OPTIONS = options
+
+    def article_html
+      @article_html ||= (if is_html?
+        begin
+          html = nil
+          if article_node
+            html = article_node.children.reject do |child|
+              next unless child.attribute('class')
+              [
+                'related_links_inline',
+                'inline-share-btn-label',
+                'inline-share-btn'
+              ].include?(child.attribute('class').value)
+            end.map(&:to_s).join('')
+          end
+          if html
+            html = Sanitize.clean(html, SANITIZE_OPTIONS)
+            html.gsub!("\r\n", "\n")
+            html.gsub!("\t", "  ")
+            html.gsub!(/ *\n */, "\n")
+            html.gsub!(/\n\n+/, "\n\n")
+            html.gsub!(/<p>\n+/, "<p>\n")
+            html.gsub!(/\n+<\/p>/, "\n</p>")
+            html.gsub!(/<\/p>\n+/, "</p>\n")
+            html.strip!
+
+            # Excise empty elements
+            reparsed = Nokogiri::HTML.fragment(html)
+            excise_empty = lambda do |node|
+              if node.respond_to?(:name) && node.name == "script"
+                node.unlink
+              else
+                node.children.each do |node|
+                  excise_empty.call(node) if node.element?
+                end
+                if node.respond_to?(:attribute_nodes) && node.respond_to?(:text)
+                  if node.attribute_nodes.size == 0 && node.text.to_s.strip =~ /^\s*$/ &&
+                      node.children.all? { |child| child.text? }
+                    node.unlink
+                  end
+                end
+              end
+            end
+            excise_empty.call(reparsed)
+            html = reparsed.to_s
+          end
+          html
+        end
+      end)
+    end
+
+    def article_text
+      @article_text ||= is_html? ? Sanitize.clean(article_html) : nil
+    end
+
+    def published
+      @published ||= (begin
+        # Check under the article node first, otherwise search all
+        begin
+          node = dom.xpath("//*/meta[@property='article:published_time']/@content").first
+          Time.parse(node.value) if node && node.value && node.value != ''
+        end or
+        if article_node
+          node = article_node.xpath("meta[@itemprop='datepublished']/@content").first
+          Time.parse(node.value) if node && node.value && node.value != ''
+        end or
+        begin
+          node = dom.xpath("//*/meta[@itemprop='datepublished']/@content").first
+          Time.parse(node.value) if node && node.value && node.value != ''
+        end or
+        begin
+          node = dom.xpath("//*/meta[@name='dcterms.created']/@content").first
+          Time.parse(node.value) if node && node.value && node.value != ''
+        end or
+        begin
+          # Only a date, not a time, and not particularly specific,
+          # so this is a fallback at best.
+          node = dom.xpath("//*/meta[@name='dc.date']/@content").first
+          Time.parse(node.value) if node && node.value && node.value != ''
+        end
+      end)
+    end
+
+    def updated
+      @updated ||= (begin
+        # Check under the article node first, otherwise search all
+        begin
+          node = dom.xpath("//*/meta[@property='article:modified_time']/@content").first
+          Time.parse(node.value) if node && node.value && node.value != ''
+        end or
+        if article_node
+          node = article_node.xpath("meta[@itemprop='datemodified']/@content").first
+          Time.parse(node.value) if node && node.value && node.value != ''
+        end or
+        begin
+          node = dom.xpath("meta[@itemprop='datemodified']/@content").first
+          Time.parse(node.value) if node && node.value && node.value != ''
+        end or
+        begin
+          node = dom.xpath("//*/meta[@name='dcterms.modified']/@content").first
+          Time.parse(node.value) if node && node.value && node.value != ''
+        end
+      end)
+    end
+
+    def inspect
+      addr = '0x' + ('%x' % (object_id << 1)).rjust(14, '0')
+      "#<HRefPreview::Preview:#{addr} TITLE=#{title.inspect}>"
+    end
+  end
+end