site_analyzer 0.3.16 → 0.3.17

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c0e7966cf9a63a7dae34d25472924438852f4275
-  data.tar.gz: f96f6d1781e13fe7e98da60349d2db4ad1df423e
+  metadata.gz: cc00445497ff1b19d012ade1eef41f9ec4ddad99
+  data.tar.gz: 21a5e0ecfe14c07069ff8fb35a2d56d60d3062ea
 SHA512:
-  metadata.gz: 31cc2b27a8773526df07f5f50fa39b5af970db45282df38e5af34f32035970a9c5a99541dc70a19085bdae8972ee640f68e096da08a710293eab5243ea15dfe2
-  data.tar.gz: 3fe3b59534526a07207459747013762bc137a1771cbf1e271dbfa61ac4cf536bf631c790e2ab13e8b362e06eee6225269b939395702c9157c34b0e78a3420412
+  metadata.gz: 13edaa969a406d7eb64c5965b037caefad6361bf3704e4e288e7b595f21bf1cd3743f95c407fe6d993b0054714cbcbe8164322b440f7f9752f438353dce1e27a
+  data.tar.gz: 9ce13e82b5bb231cd4d84dd14e14a3aee42dd2b3675b64eba53a4f933e230951e980341d8fa766849fc88c3d1e9d51a320a47e29b2390f69463829b3708d6557

data/.gitignore

@@ -1,4 +1,7 @@
-/.idea/
+.idea/*
 SiteAnalyzer.iml
 /log
-*.gem
+*.gem
+.gems
+log
+tmp

data/.rbenv-gemsets

@@ -0,0 +1 @@
+.gems

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    site_analyzer (0.3.12)
+    site_analyzer (0.3.16)
       addressable (~> 2.3)
       nokogiri (~> 1.6)
       robotstxt (~> 0.5)
@@ -26,7 +26,7 @@ GEM
       shellany (~> 0.0)
       thor (>= 0.18.1)
     guard-compat (1.2.1)
-    guard-rspec (4.6.3)
+    guard-rspec (4.6.4)
       guard (~> 2.1)
       guard-compat (~> 1.1)
       rspec (>= 2.99.0, < 4.0)
@@ -81,4 +81,4 @@ DEPENDENCIES
   site_analyzer!
 
 BUNDLED WITH
-   1.10.5
+   1.10.6

data/Guardfile

@@ -47,9 +47,9 @@ guard :rspec, cmd: 'bundle exec rspec' do
 
   watch(rails.controllers) do |m|
     [
-      rspec.spec.("routing/#{m[1]}_routing"),
-      rspec.spec.("controllers/#{m[1]}_controller"),
-      rspec.spec.("acceptance/#{m[1]}")
+      rspec.spec.call("routing/#{m[1]}_routing"),
+      rspec.spec.call("controllers/#{m[1]}_controller"),
+      rspec.spec.call("acceptance/#{m[1]}")
     ]
   end
 
@@ -59,8 +59,8 @@ guard :rspec, cmd: 'bundle exec rspec' do
   watch(rails.app_controller)  { "#{rspec.spec_dir}/controllers" }
 
   # Capybara features specs
-  watch(rails.view_dirs)     { |m| rspec.spec.("features/#{m[1]}") }
-  watch(rails.layouts)       { |m| rspec.spec.("features/#{m[1]}") }
+  watch(rails.view_dirs)     { |m| rspec.spec.call("features/#{m[1]}") }
+  watch(rails.layouts)       { |m| rspec.spec.call("features/#{m[1]}") }
 
   # Turnip features and steps
   watch(%r{^spec/acceptance/(.+)\.feature$})

data/Rakefile

@@ -3,4 +3,4 @@ require 'rspec/core/rake_task'
 
 RSpec::Core::RakeTask.new(:spec)
 
-task :default => :spec
+task default: :spec

data/lib/site_analyzer/open-uri-patching.rb

@@ -1,6 +1,5 @@
 module OpenURI
-
-  def OpenURI.redirectable?(uri1, uri2) # :nodoc:
+  def self.redirectable?(uri1, uri2) # :nodoc:
     # This test is intended to forbid a redirection from http://... to
     # file:///etc/passwd, file:///dev/zero, etc.  CVE-2011-1521
     # https to http redirect is also forbidden intentionally.
@@ -8,6 +7,6 @@ module OpenURI
     # (RFC 2109 4.3.1, RFC 2965 3.3, RFC 2616 15.1.3)
     # However this is ad hoc.  It should be extensible/configurable.
     uri1.scheme.downcase == uri2.scheme.downcase ||
-        (/\A(?:http|ftp|https)\z/i =~ uri1.scheme && /\A(?:http|ftp|https)\z/i =~ uri2.scheme)
+      (/\A(?:http|ftp|https)\z/i =~ uri1.scheme && /\A(?:http|ftp|https)\z/i =~ uri2.scheme)
   end
-end
+end

data/lib/site_analyzer/page.rb

@@ -1,5 +1,5 @@
+# Get site page and provide data for future analyse
 module SiteAnalyzer
-  # Get site page and provide data for future analyse
   require 'nokogiri'
   require 'addressable/uri'
   require 'timeout'
@@ -25,29 +25,25 @@ module SiteAnalyzer
     end
     # get all home (that on this site) url on page
     def home_a
-      if @page_a_tags
-        home_a = []
-        @page_a_tags.uniq.each do |link|
-          uri = URI(link[0].to_ascii) rescue nil #TODO: write additional logic for link to image
-          if uri && @site_domain
-            home_a << link[0] if uri.host == @site_domain
-          end
-        end
-        home_a
+      return unless @page_a_tags
+      home_a = []
+      @page_a_tags.uniq.each do |link|
+        uri = URI(link[0].to_ascii) rescue nil # TODO: write additional logic for link to image
+        home_a << link[0] if uri.host == @site_domain if uri && @site_domain
       end
+      home_a
     end
     # get all remote link on page
     def remote_a
-      if @page_a_tags
-        remote_a = []
-        @page_a_tags.uniq.each do |link|
-          uri = URI(link[0].to_ascii)
-          if uri && @site_domain
-            remote_a << link[0] unless uri.host == @site_domain
-          end
+      return unless @page_a_tags
+      remote_a = []
+      @page_a_tags.uniq.each do |link|
+        uri = URI(link[0].to_ascii)
+        if uri && @site_domain
+          remote_a << link[0] unless uri.host == @site_domain
         end
-        remote_a
       end
+      remote_a
     end
 
     private
@@ -72,16 +68,14 @@ module SiteAnalyzer
     end
     # get page with open-uri, then parse it with Nokogiri. Get site domain and path from URI
     def get_page(url)
-      begin
-        timeout(30) do
-          page = open(url)
-          @site_domain = page.base_uri.host
-          @page_path = page.base_uri.request_uri
-          @page = Nokogiri::HTML(page)
-        end
-      rescue Timeout::Error, EOFError, OpenURI::HTTPError, Errno::ENOENT, TypeError
-        return nil
+      timeout(30) do
+        page = open(url)
+        @site_domain = page.base_uri.host
+        @page_path = page.base_uri.request_uri
+        @page = Nokogiri::HTML(page)
       end
+    rescue Timeout::Error, EOFError, OpenURI::HTTPError, Errno::ENOENT, TypeError
+      return nil
     end
     # check that title is one and less then 70 symbols
     def title_good?
@@ -89,48 +83,44 @@ module SiteAnalyzer
     end
     # true if title and h1 have no duplicates
     def title_and_h1_good?
-      if @page
-        arr = []
-        @page.css('h1').each { |node| arr << node.text }
-        @page.css('title').size == 1 && arr.uniq.size == arr.size
-      end
+      return unless @page
+      arr = []
+      @page.css('h1').each { |node| arr << node.text }
+      @page.css('title').size == 1 && arr.uniq.size == arr.size
     end
     # true if metadescription less then 200 symbols
     def metadescription_good?
-      if @page
-        tags = @page.css("meta[name='description']")
-        return false if tags.size == 0
-        tags.each do |t|
-          unless t['value'].nil?
-            return false if t['content'].size == 0 || t['content'].size > 200
-          end
+      return unless @page
+      tags = @page.css("meta[name='description']")
+      return false if tags.size == 0
+      tags.each do |t|
+        unless t['value'].nil?
+          return false if t['content'].size == 0 || t['content'].size > 200
         end
-        true
       end
+      true
     end
     # true if keywords less then 600 symbols
     def keywords_good?
-      if @page
-        tags = @page.css("meta[name='keywords']")
-        return false if tags.size == 0
-        tags.each do |t|
-          unless t['value'].nil?
-            return false if t['content'].size == 0 || t['content'].size > 600
-          end
+      return unless @page
+      tags = @page.css("meta[name='keywords']")
+      return false if tags.size == 0
+      tags.each do |t|
+        unless t['value'].nil?
+          return false if t['content'].size == 0 || t['content'].size > 600
         end
-        true
       end
+      true
     end
     # true if code of page less then text on it
     def code_less?
-      if @page
-        sum = 0
-        page_text = @page.text.size
-        @page.css('script').each do |tag|
-          sum += tag.text.size
-        end
-        sum < page_text / 2
+      return unless @page
+      sum = 0
+      page_text = @page.text.size
+      @page.css('script').each do |tag|
+        sum += tag.text.size
       end
+      sum < page_text / 2
     end
     # collect meta tags for future report
     def collect_metadates
@@ -140,22 +130,20 @@ module SiteAnalyzer
     end
     # check meta and title tags duplicates
     def metadates_good?
-      if @page
-        return false if @all_titles.size > 1 || @meta_data.empty?
-        node_names = []
-        @meta_data.each { |node| node_names << node['name'] }
-        node_names.compact!
-        node_names.uniq.size == node_names.size unless node_names.nil? || node_names.size < 1
-      end
+      return unless @page
+      return false if @all_titles.size > 1 || @meta_data.empty?
+      node_names = []
+      @meta_data.each { |node| node_names << node['name'] }
+      node_names.compact!
+      node_names.uniq.size == node_names.size unless node_names.nil? || node_names.size < 1
     end
     # return hash with all titles, h1 and h2
     def all_titles_h1_h2
-      if @page
-        out = []
-        out << @page.css('title').text << { @page_url => @page.css('h1').text }
-        out << { @page_url => @page.css('h2').text }
-        out
-      end
+      return unless @page
+      out = []
+      out << @page.css('title').text << { @page_url => @page.css('h1').text }
+      out << { @page_url => @page.css('h2').text }
+      out
     end
     # check if page have h2 tags
     def h2?
@@ -167,43 +155,39 @@ module SiteAnalyzer
     end
     # get all a tags
     def all_a_tags
-      if @page
-        tags = []
-        @page.css('a').each do |node|
-          tags << [node['href'], node['target'], node['rel']]
-        end
-        tags.compact
+      return unless @page
+      tags = []
+      @page.css('a').each do |node|
+        tags << [node['href'], node['target'], node['rel']]
       end
+      tags.compact
     end
     # return all page titles
     def titles
-      if @page
-        titles = []
-        @page.css('title').each { |tag| titles << tag.text }
-        titles
-      end
+      return unless @page
+      titles = []
+      @page.css('title').each { |tag| titles << tag.text }
+      titles
     end
     # return all meta description content
     def all_meta_description_content
-      if @page
-        tags = []
-        @page.css("meta[name='description']").each do |t|
-          tags << t['content']
-        end
-        tags
+      return unless @page
+      tags = []
+      @page.css("meta[name='description']").each do |t|
+        tags << t['content']
       end
+      tags
     end
     # return all h2 tags text
     def h2
-      if @page
-        h2s = []
-        @page.css('h2').each { |tag| h2s << tag.text }
-        h2s
-      end
+      return unless @page
+      h2s = []
+      @page.css('h2').each { |tag| h2s << tag.text }
+      h2s
     end
     # check url of page that is must be HLU
     def bad_url
-      @page_url if @page_path.size > 1 unless @page_path =~ /^[\w.\-\/]+$/i
+      @page_url if @page_path.size > 1 unless @page_path =~ %r(/^[\w.\-\/]+$/i)
     end
     # clear page from don't needed information
     def clear!

data/lib/site_analyzer/report.rb

@@ -97,7 +97,7 @@ module SiteAnalyzer
     def pages_size
       result = []
       @site.pages.each do |page|
-        result << [page.page_url , page.page_text_size]
+        result << [page.page_url, page.page_text_size]
       end
       result
     end
@@ -144,10 +144,9 @@ module SiteAnalyzer
       counter = {}
       result = []
       in_array.compact.each do |url_desc_cont|
-        if url_desc_cont[1][0]
-          url_desc_cont[1][0].scan(/\w+/).each do |word|
-            all_words << word
-          end
+        next unless url_desc_cont[1][0]
+        url_desc_cont[1][0].scan(/\w+/).each do |word|
+          all_words << word
         end
       end
       all_words.each do |word|

data/lib/site_analyzer/site.rb

@@ -29,13 +29,12 @@ module SiteAnalyzer
       add_pages_for_scan!
       while @pages_for_scan.size > 0
         page = convert_to_valid @pages_for_scan.pop
-        if page
-          @max_pages -= 1
-          add_page convert_to_valid(page)
-          return if @max_pages <= 0
-          add_pages_for_scan!
-          optimize_scan!
-        end
+        next unless page
+        @max_pages -= 1
+        add_page convert_to_valid(page)
+        return if @max_pages <= 0
+        add_pages_for_scan!
+        optimize_scan!
       end
     end
     # add pages for scan array, also add bad pages to bad_pages array
@@ -44,10 +43,9 @@ module SiteAnalyzer
       @bad_pages = []
       @pages.each do |page|
         @bad_pages << page.page_url unless page.page_a_tags
-        if page.page_a_tags
-          page.home_a.each do |link|
-            @pages_for_scan << link
-          end
+        next unless page.page_a_tags
+        page.home_a.each do |link|
+          @pages_for_scan << link
         end
       end
     end
@@ -65,9 +63,7 @@ module SiteAnalyzer
     def all_titles
       result = []
       @pages.each do |page|
-        if page.page_a_tags
-          result << [page.page_url, page.all_titles]
-        end
+        result << [page.page_url, page.all_titles] if page.page_a_tags
       end
       result
     end
@@ -75,9 +71,7 @@ module SiteAnalyzer
     def all_descriptions
       result = []
       @pages.each do |page|
-        if page.page_a_tags
-          result << [page.page_url, page.meta_desc_content]
-        end
+        result << [page.page_url, page.meta_desc_content] if page.page_a_tags
       end
       result
     end
@@ -85,9 +79,7 @@ module SiteAnalyzer
     def all_h2
       result = []
       @pages.each do |page|
-        unless page.page_a_tags
-          result << [page.page_url, page.h2_text]
-        end
+        result << [page.page_url, page.h2_text] unless page.page_a_tags
       end
       result
     end
@@ -95,13 +87,12 @@ module SiteAnalyzer
     def all_a
       result = []
       @pages.each do |page|
-        if page.page_a_tags
-          page.page_a_tags.compact.each do |tag|
-            tag[0] = '-' unless tag[0]
-            tag[1] = '-' unless tag[1]
-            tag[2] = '-' unless tag[2]
-            result << [page.page_url, tag[0], tag[1], tag[2]]
-          end
+        next unless page.page_a_tags
+        page.page_a_tags.compact.each do |tag|
+          tag[0] = '-' unless tag[0]
+          tag[1] = '-' unless tag[1]
+          tag[2] = '-' unless tag[2]
+          result << [page.page_url, tag[0], tag[1], tag[2]]
         end
       end
       result.compact
@@ -118,7 +109,7 @@ module SiteAnalyzer
     def optimize_scan!
       @pages_for_scan = @pages_for_scan.compact.uniq
       @scanned_pages = @scanned_pages.compact.uniq
-      @pages_for_scan = @pages_for_scan - @scanned_pages
+      @pages_for_scan -= @scanned_pages
     end
     # check url and try to convert it to valid, remove .jpg links, add scheme to url
     def convert_to_valid(url)

data/lib/site_analyzer/version.rb

@@ -1,3 +1,3 @@
 module SiteAnalyzer
-  VERSION = '0.3.16'
+  VERSION = '0.3.17'
 end

data/site_analyzer.gemspec

@@ -9,8 +9,8 @@ Gem::Specification.new do |spec|
   spec.authors       = ['Denis Savchuk']
   spec.email         = ['mordorreal@gmail.com']
   spec.date          = '2015-07-01'
-  spec.summary       = %q{Make report for SEO. Analyse site like SEOs like. }
-  spec.description   = %q{Create site report for SEO many options.}
+  spec.summary       = 'Make report for SEO. Analyse site like SEOs like. '
+  spec.description   = 'Create site report for SEO many options.'
   spec.homepage      = 'https://github.com/Mordorreal/SiteAnalyzer'
   spec.license       = 'MIT'
   spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
@@ -21,7 +21,7 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency 'bundler', '~> 1.10'
   spec.add_development_dependency 'rake', '~> 10.4'
   spec.add_development_dependency 'rspec', '~> 3.3'
-  spec.add_development_dependency 'guard-rspec', '~> 3.3'
+  spec.add_development_dependency 'guard-rspec', '~> 4.6'
   spec.add_runtime_dependency 'nokogiri', '~> 1.6'
   spec.add_runtime_dependency 'addressable', '~> 2.3'
   spec.add_runtime_dependency 'robotstxt', '~> 0.5'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: site_analyzer
 version: !ruby/object:Gem::Version
-  version: 0.3.16
+  version: 0.3.17
 platform: ruby
 authors:
 - Denis Savchuk
@@ -58,14 +58,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.3'
+        version: '4.6'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.3'
+        version: '4.6'
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
@@ -144,6 +144,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".gitignore"
+- ".rbenv-gemsets"
 - ".rspec"
 - ".travis.yml"
 - CODE_OF_CONDUCT.md