metainspector 4.0.0.rc3 → 4.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: bf5c2667ff165768d1a0e0c49ebd47ea5f8de28e
-  data.tar.gz: 15b2f4fb7a2f090a75fe06ab98959e35d5f97a3f
+  metadata.gz: 4fbb85a1c08f497b3c38edbdc97e0c8d96ee6c6a
+  data.tar.gz: 9ce2c80b81b1eb085037312e75fb82d1e46f4202
 SHA512:
-  metadata.gz: eeb60786169e979dd8bb257832f2bf2c0270af8b2bf63056330826677a4943373aea51269a1ddfc397ae296cb786b5285997a1721b5ae412cc006214c872af18
-  data.tar.gz: ae891af393d3746df5048a1e512e70f11718fc8357a2c8212376119afb174e8b7e0ccd180f48c252813581a4ed5671b0f01e35ca555b475efc9997238c29c952
+  metadata.gz: e12a19a7598d3a9c7d83d90c121336964490dcd8b334f72d9ceb64ea8efab67c3b269445eb1ebf46eb5385169ea04a81ef155533dbe92779614eb3e0a10c50b3
+  data.tar.gz: 555a9b35ee7f51def2c45a24e46996cc130a65d15daebda9841c7be74fda8a2c76cb0097c53a67ad763b80272db52d84f8bdb7b99ecee124929a19b3c36a6338

data/.gitignore

@@ -7,3 +7,5 @@
 Gemfile.lock
 pkg/*
 .idea/
+.rubocop_todo.yml
+.rubocop.yml

data/.rubocop.yml.example

@@ -0,0 +1,4 @@
+# Forcing the new ruby 1.9 syntax for hashes is not a requirement,
+# we still { :love => 'hashrockets' }
+Style/HashSyntax:
+  Enabled: false

data/lib/meta_inspector/document.rb

@@ -5,16 +5,18 @@ module MetaInspector
 
     include MetaInspector::Exceptionable
 
-    # Initializes a new instance of MetaInspector::Document, setting the URL to the one given
+    # Initializes a new instance of MetaInspector::Document, setting the URL
     # Options:
-    # => connection_timeout: defaults to 20 seconds
-    # => read_timeout: defaults to 20 seconds
-    # => retries: defaults to 3 times
-    # => html_content_type_only: if an exception should be raised if request content-type is not text/html. Defaults to false
-    # => allow_redirections: when true, follow HTTP redirects. Defaults to true
-    # => document: the html of the url as a string
-    # => warn_level: what to do when encountering exceptions. Can be :warn, :raise or nil
-    # => headers: object containing custom headers for the request
+    # * connection_timeout: defaults to 20 seconds
+    # * read_timeout: defaults to 20 seconds
+    # * retries: defaults to 3 times
+    # * html_content_type_only: if an exception should be raised if request
+    #   content-type is not text/html. Defaults to false.
+    # * allow_redirections: when true, follow HTTP redirects. Defaults to true
+    # * document: the html of the url as a string
+    # * warn_level: what to do when encountering exceptions.
+    #   Can be :warn, :raise or nil
+    # * headers: object containing custom headers for the request
     def initialize(initial_url, options = {})
       options             = defaults.merge(options)
       @connection_timeout = options[:connection_timeout]
@@ -37,25 +39,28 @@ module MetaInspector
     end
 
     extend Forwardable
-    def_delegators :@url,     :url, :scheme, :host, :root_url
-    def_delegators :@request, :content_type, :response
-    def_delegators :@parser,  :parsed, :respond_to?, :title, :description, :links,
-                              :images, :image, :feed, :charset, :meta_tags, :meta_tag, :meta, :favicon
+    delegate [:url, :scheme, :host, :root_url]        => :@url
+
+    delegate [:content_type, :response]               => :@request
+
+    delegate [:parsed, :title, :description, :links,
+              :images, :feed, :charset, :meta_tags,
+              :meta_tag, :meta, :favicon]             => :@parser
 
     # Returns all document data as a nested Hash
     def to_hash
       {
-        'url' => url,
-        'title' => title,
-        'links' => links.to_hash,
-        'images' => images.to_a,
-        'charset' => charset,
-        'feed' => feed,
-        'content_type' => content_type,
-        'meta_tags' => meta_tags,
-        'favicon' => images.favicon,
-        'response' => { 'status'  => response.status,
-                        'headers' => response.headers }
+        'url'           => url,
+        'title'         => title,
+        'links'         => links.to_hash,
+        'images'        => images.to_a,
+        'charset'       => charset,
+        'feed'          => feed,
+        'content_type'  => content_type,
+        'meta_tags'     => meta_tags,
+        'favicon'       => images.favicon,
+        'response'      => { 'status'  => response.status,
+                             'headers' => response.headers }
       }
     end
 
@@ -67,18 +72,21 @@ module MetaInspector
     private
 
     def defaults
-      { :timeout => 20,
-        :retries => 3,
-        :html_content_only => false,
-        :warn_level => :raise,
-        :headers => {'User-Agent' => "MetaInspector/#{MetaInspector::VERSION} (+https://github.com/jaimeiniesta/metainspector)"},
-        :allow_redirections => true
-      }
+      { :timeout            => 20,
+        :retries            => 3,
+        :html_content_only  => false,
+        :warn_level         => :raise,
+        :headers            => { 'User-Agent' => default_user_agent },
+        :allow_redirections => true }
+    end
+
+    def default_user_agent
+      "MetaInspector/#{MetaInspector::VERSION} (+https://github.com/jaimeiniesta/metainspector)"
     end
 
     def document
-      @document ||= if html_content_only && content_type != "text/html"
-                      raise "The url provided contains #{content_type} content instead of text/html content" and nil
+      @document ||= if html_content_only && content_type != 'text/html'
+                      fail "The url provided contains #{content_type} content instead of text/html content"
                     else
                       @request.read
                     end

data/lib/meta_inspector/exception_log.rb

@@ -12,7 +12,7 @@ module MetaInspector
     def <<(exception)
       case warn_level
       when :raise
-        raise exception
+        fail exception
       when :warn
         warn exception
       when :store
@@ -24,7 +24,7 @@ module MetaInspector
       if warn_level == :store
         exceptions.empty?
       else
-        warn "ExceptionLog#ok? should only be used when warn_level is :store"
+        warn 'ExceptionLog#ok? should only be used when warn_level is :store'
       end
     end
   end

data/lib/meta_inspector/exceptionable.rb

@@ -4,6 +4,6 @@ module MetaInspector
   #
   module Exceptionable
     extend Forwardable
-    def_delegators :@exception_log, :exceptions, :ok?
+    delegate [:exceptions, :ok?] => :@exception_log
   end
 end

data/lib/meta_inspector/parser.rb

@@ -20,11 +20,11 @@ module MetaInspector
     end
 
     extend Forwardable
-    def_delegators :@document,        :url, :scheme, :host
-    def_delegators :@meta_tag_parser, :meta_tags, :meta_tag, :meta, :charset
-    def_delegators :@links_parser,    :links, :feed, :base_url
-    def_delegators :@images_parser,   :images
-    def_delegators :@texts_parser,    :title, :description
+    delegate [:url, :scheme, :host]                   => :@document
+    delegate [:meta_tags, :meta_tag, :meta, :charset] => :@meta_tag_parser
+    delegate [:links, :feed, :base_url]               => :@links_parser
+    delegate :images                                  => :@images_parser
+    delegate [:title, :description]                   => :@texts_parser
 
     # Returns the whole parsed document
     def parsed

data/lib/meta_inspector/parsers/base.rb

@@ -23,7 +23,7 @@ module MetaInspector
 
       # Cleans up nokogiri search results
       def cleanup(results)
-        results.map { |_| _.value.strip }.reject { |_| _.empty? }.uniq
+        results.map { |r| r.value.strip }.reject(&:empty?).uniq
       end
     end
   end

data/lib/meta_inspector/parsers/images.rb

@@ -1,8 +1,8 @@
 module MetaInspector
   module Parsers
     class ImagesParser < Base
-      def_delegators :@main_parser, :parsed, :meta, :base_url
-      def_delegators :images_collection, :each, :length, :size, :last, :[]
+      delegate [:parsed, :meta, :base_url]         => :@main_parser
+      delegate [:each, :length, :size, :[], :last] => :images_collection
 
       include Enumerable
 
@@ -11,7 +11,7 @@ module MetaInspector
       end
 
       # Returns the parsed image from Facebook's open graph property tags
-      # Most all major websites now define this property and is usually very relevant
+      # Most major websites now define this property and is usually relevant
       # See doc at http://developers.facebook.com/docs/opengraph/
       # If none found, tries with Twitter image
       def best
@@ -30,11 +30,15 @@ module MetaInspector
       private
 
       def images_collection
-        @images_collection ||= parsed_images.map{ |i| URL.absolutify(i, base_url) }
+        @images_collection ||= absolutified_images
+      end
+
+      def absolutified_images
+        parsed_images.map { |i| URL.absolutify(i, base_url) }
       end
 
       def parsed_images
-        @parsed_images ||= cleanup(parsed.search('//img/@src'))
+        cleanup(parsed.search('//img/@src'))
       end
     end
   end

data/lib/meta_inspector/parsers/links.rb

@@ -1,7 +1,7 @@
 module MetaInspector
   module Parsers
     class LinksParser < Base
-      def_delegators :@main_parser, :parsed, :url, :scheme, :host
+      delegate [:parsed, :url, :scheme, :host] => :@main_parser
 
       def links
         self
@@ -9,37 +9,39 @@ module MetaInspector
 
       # Returns all links found, unprocessed
       def raw
-        @raw ||= cleanup(parsed.search("//a/@href")).compact.uniq
+        @raw ||= cleanup(parsed.search('//a/@href')).compact.uniq
       end
 
       # Returns all links found, unrelavitized and absolutified
       def all
-        @all ||= raw.map { |l| URL.absolutify(URL.unrelativize(l, scheme), base_url) }
+        @all ||= raw.map { |link| URL.absolutify(URL.unrelativize(link, scheme), base_url) }
                     .compact.uniq
       end
 
       # Returns all HTTP links found
       def http
-        @http ||= all.select {|l| l =~ /^http(s)?:\/\//i}
+        @http ||= all.select { |link| link =~ /^http(s)?:\/\//i}
       end
 
       # Returns all non-HTTP links found
       def non_http
-        @non_http ||= all.select {|l| l !~ /^http(s)?:\/\//i}
+        @non_http ||= all.select { |link| link !~ /^http(s)?:\/\//i}
       end
 
       # Returns all internal HTTP links found
       def internal
-        @internal ||= http.select {|link| URL.new(link).host == host }
+        @internal ||= http.select { |link| URL.new(link).host == host }
       end
 
       # Returns all external HTTP links found
       def external
-        @external ||= http.select {|link| URL.new(link).host != host }
+        @external ||= http.select { |link| URL.new(link).host != host }
       end
 
       def to_hash
-        { 'internal' => internal, 'external' => external, 'non_http' => non_http }
+        { 'internal' => internal,
+          'external' => external,
+          'non_http' => non_http }
       end
 
       # Returns the parsed document meta rss link
@@ -47,7 +49,8 @@ module MetaInspector
         @feed ||= (parsed_feed('rss') || parsed_feed('atom'))
       end
 
-      # Returns the base url to absolutify relative links. This can be the one set on a <base> tag,
+      # Returns the base url to absolutify relative links.
+      # This can be the one set on a <base> tag,
       # or the url of the document if no <base> tag was found.
       def base_url
         base_href || url
@@ -60,7 +63,7 @@ module MetaInspector
         feed ? URL.absolutify(feed.attributes['href'].value, base_url) : nil
       end
 
-      # Returns the value of the href attribute on the <base /> tag, if it exists
+      # Returns the value of the href attribute on the <base /> tag, if exists
       def base_href
         parsed.search('base').first.attributes['href'].value rescue nil
       end

data/lib/meta_inspector/parsers/meta_tags.rb

@@ -1,7 +1,7 @@
 module MetaInspector
   module Parsers
     class MetaTagsParser < Base
-      def_delegators :@main_parser, :parsed
+      delegate :parsed => :@main_parser
 
       def meta_tags
         {
@@ -20,10 +20,10 @@ module MetaInspector
         meta_tag['name']
           .merge(meta_tag['http-equiv'])
           .merge(meta_tag['property'])
-          .merge({'charset' => meta_tag['charset']})
+          .merge('charset' => meta_tag['charset'])
       end
 
-      # Returns the charset from the meta tags, looking for it in the following order:
+      # Returns the charset from the meta tags, searching in this order:
       # <meta charset='utf-8' />
       # <meta http-equiv="Content-Type" content="text/html; charset=windows-1252" />
       def charset
@@ -33,12 +33,12 @@ module MetaInspector
       private
 
       def charset_from_meta_charset
-        parsed.css("meta[charset]")[0].attributes['charset'].value rescue nil
+        parsed.css('meta[charset]')[0].attributes['charset'].value rescue nil
       end
 
       def charset_from_meta_content_type
         parsed.css("meta[http-equiv='Content-Type']")[0]
-          .attributes['content'].value.split(";")[1].split("=")[1] rescue nil
+          .attributes['content'].value.split(';')[1].split('=')[1] rescue nil
       end
 
       def meta_tags_by(attribute)
@@ -58,12 +58,12 @@ module MetaInspector
       def convert_each_array_to_first_element_on(hash)
         hash.each_pair do |k, v|
           hash[k] = if v.is_a?(Hash)
-            convert_each_array_to_first_element_on(v)
-          elsif v.is_a?(Array)
-            v.first
-          else
-            v
-          end
+                      convert_each_array_to_first_element_on(v)
+                    elsif v.is_a?(Array)
+                      v.first
+                    else
+                      v
+                    end
         end
       end
 

data/lib/meta_inspector/parsers/texts.rb

@@ -1,7 +1,7 @@
 module MetaInspector
   module Parsers
     class TextsParser < Base
-      def_delegators :@main_parser, :parsed, :meta
+      delegate [:parsed, :meta] => :@main_parser
 
       # Returns the parsed document title, from the content of the <title> tag
       # within the <head> section.
@@ -9,8 +9,9 @@ module MetaInspector
         @title ||= parsed.css('head title').inner_text rescue nil
       end
 
-      # A description getter that first checks for a meta description and if not present will
-      # guess by looking at the first paragraph with more than 120 characters
+      # A description getter that first checks for a meta description
+      # and if not present will guess by looking at the first paragraph
+      # with more than 120 characters
       def description
         meta['description'] || secondary_description
       end

data/lib/meta_inspector/request.rb

@@ -18,25 +18,24 @@ module MetaInspector
       @exception_log      = options[:exception_log]
       @headers            = options[:headers]
 
-      response            # as soon as it is set up, we make the request so we can fail early
+      response            # request early so we can fail early
     end
 
     extend Forwardable
-    def_delegators :@url, :url
+    delegate :url => :@url
 
     def read
       response.body if response
     end
 
     def content_type
-      response.headers["content-type"].split(";")[0] if response
+      response.headers['content-type'].split(';')[0] if response
     end
 
     def response
-      request_count ||= 0
-      request_count += 1
       @response ||= fetch
-    rescue Faraday::TimeoutError, Faraday::Error::ConnectionFailed, RuntimeError => e
+    rescue Faraday::TimeoutError, Faraday::Error::ConnectionFailed,
+           RuntimeError => e
       @exception_log << e
       nil
     end

data/lib/meta_inspector/url.rb

@@ -28,20 +28,23 @@ module MetaInspector
       @url = normalized(with_default_scheme(new_url))
     end
 
-    # Converts a protocol-relative url to its full form, depending on the scheme of the page that contains it
+    # Converts a protocol-relative url to its full form,
+    # depending on the scheme of the page that contains it
     def self.unrelativize(url, scheme)
       url =~ /^\/\// ? "#{scheme}://#{url[2..-1]}" : url
     end
 
-    # Convert a relative url like "/users" to an absolute one like "http://example.com/users"
-    # Respecting already absolute URLs like the ones starting with http:, ftp:, telnet:, mailto:, javascript: ...
+    # Converts a relative URL to an absolute URL, like:
+    #   "/faq" => "http://example.com/faq"
+    # Respecting already absolute URLs like the ones starting with
+    #   http:, ftp:, telnet:, mailto:, javascript: ...
     def self.absolutify(url, base_url)
       if url =~ /^\w*\:/i
         MetaInspector::URL.new(url).url
       else
         Addressable::URI.join(base_url, url).normalize.to_s
       end
-    rescue Addressable::URI::InvalidURIError => e
+    rescue Addressable::URI::InvalidURIError
       nil
     end
 
@@ -52,7 +55,8 @@ module MetaInspector
       parsed(url) && parsed(url).scheme.nil? ? 'http://' + url : url
     end
 
-    # Normalize url to deal with characters that should be encodes, add trailing slash, convert to downcase...
+    # Normalize url to deal with characters that should be encoded,
+    # add trailing slash, convert to downcase...
     def normalized(url)
       Addressable::URI.parse(url).normalize.to_s
     end

data/lib/meta_inspector/version.rb

@@ -1,3 +1,3 @@
 module MetaInspector
-  VERSION = "4.0.0.rc3"
+  VERSION = "4.0.0"
 end

data/meta_inspector.gemspec

@@ -28,4 +28,5 @@ Gem::Specification.new do |gem|
   gem.add_development_dependency 'pry'
   gem.add_development_dependency 'guard'
   gem.add_development_dependency 'guard-rspec'
+  gem.add_development_dependency 'rubocop'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: metainspector
 version: !ruby/object:Gem::Version
-  version: 4.0.0.rc3
+  version: 4.0.0
 platform: ruby
 authors:
 - Jaime Iniesta
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-11-20 00:00:00.000000000 Z
+date: 2014-11-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -192,6 +192,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: MetaInspector lets you scrape a web page and get its title, charset,
   link and meta tags
 email:
@@ -202,6 +216,7 @@ extra_rdoc_files: []
 files:
 - ".gitignore"
 - ".rspec.example"
+- ".rubocop.yml.example"
 - ".travis.yml"
 - Gemfile
 - Guardfile
@@ -286,9 +301,9 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">"
+  - - ">="
     - !ruby/object:Gem::Version
-      version: 1.3.1
+      version: '0'
 requirements: []
 rubyforge_project: 
 rubygems_version: 2.2.2