webinspector 1.1.0 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: df0bf76a03246a803f338a903611f128ee8b6d09329f33a9745a27eeb4e9793b
-  data.tar.gz: adda6867a10d3dc5f7a9fd0ec414d7046e140fe016d945eb20098a84a5176642
+  metadata.gz: 7ef69ac6245db062331d4f0b269d1f389cb9e730e4ad39e51d75236f30e0b6c9
+  data.tar.gz: b37d5b30a01ea6b0e74553edb9944acdeac4d5ce2808e319798b8d0d3a9f5390
 SHA512:
-  metadata.gz: 01ce7c5aab007a3c9ef300c61a990a6f00d00604c14f0a3fdec28fdfb620a1e50ad576055b892cfe4d59de66975236674ce1f81f66e2d60c0ad0e0a0c3f4a951
-  data.tar.gz: ca58cdda149cf3b0cc6dcb29017b8e080b70b4ed881c924acddfba98760246417bb0304bc4eb42242a328d4ade99408181cc3ac10016998cd2b23de8fe34a8bf
+  metadata.gz: '098f7c7f19f8bfe8b8f3b4977cac590e9c107cb8864128e4abbb3b47327e34743844fcde2d5bf6e3038e39e7271d565dbd19157b703ea041f31e4c3fbc84aa47'
+  data.tar.gz: 5fdeaa74861245796f15bf70ba5fcc00e7e7eb2f0c1192a60395a119b24ea1c72b579a24296cb66c1fd77cc7c4cfff8b2505d321a2ef74dd7b5618b84e69ae5c

data/README.md

@@ -4,7 +4,6 @@ Ruby gem to inspect web pages. It scrapes a given URL and returns its title, des
 
 <a href="https://codeclimate.com/github/davidesantangelo/webinspector"><img src="https://codeclimate.com/github/davidesantangelo/webinspector/badges/gpa.svg" /></a>
 
-
 ## Installation
 
 Add this line to your application's Gemfile:
@@ -34,7 +33,7 @@ page = WebInspector.new('http://example.com')
 ```ruby
 page = WebInspector.new('http://example.com', {
   timeout: 30,                         # Request timeout in seconds (default: 30)
-  retries: 3,                          # Number of retries (default: 3) 
+  retries: 3,                          # Number of retries (default: 3)
   headers: {'User-Agent': 'Custom UA'} # Custom HTTP headers
 })
 ```
@@ -138,16 +137,73 @@ page.technologies  # hash of detected technologies: { jquery: true, react: true,
 page.tag_count  # hash with counts of each HTML tag: { "div" => 45, "p" => 12, ... }
 ```
 
+#### RSS/Atom Feeds
+
+```ruby
+page.feeds  # array of RSS/Atom feed URLs found on the page
+```
+
+#### Social Media Links
+
+```ruby
+page.social_links  # hash of social media profiles: { facebook: "url", twitter: "url", ... }
+```
+
+#### Robots.txt and Sitemap
+
+```ruby
+page.robots_txt_url  # URL to robots.txt
+page.sitemap_url     # array of sitemap URLs
+```
+
+#### CMS Detection
+
+```ruby
+page.cms_info  # hash with CMS details: { name: "WordPress", version: "6.0", themes: [...], plugins: [...] }
+```
+
+#### Accessibility Score
+
+```ruby
+page.accessibility_score  # hash with score (0-100) and details: { score: 85, details: [...] }
+```
+
+#### Mobile-Friendly Check
+
+```ruby
+page.mobile_friendly?  # true if the page has viewport meta tag and responsive CSS
+```
+
 ### Export all data to JSON
 
 ```ruby
 page.to_hash # returns a hash with all page data
 ```
 
+## Changelog
+
+### Version 1.2.0
+
+**New Features:**
+
+- RSS/Atom feed detection with `feeds` method
+- Social media profile extraction with `social_links` method
+- CMS detection and information with `cms_info` method (WordPress, Drupal, Joomla, Shopify, Wix, Squarespace)
+- Accessibility scoring with `accessibility_score` method
+- Mobile-friendly detection with `mobile_friendly?` method
+- Robots.txt and sitemap URL detection with `robots_txt_url` and `sitemap_url` methods
+
+**Improvements:**
+
+- Enhanced `Request` module with `valid?` and `ssl?` methods for better URL validation
+- Improved `Meta` module with author and publisher extraction
+- Better error handling across all modules
+- Performance improvements with internal caching
+
 ## Contributors
 
-  * Steven Shelby ([@stevenshelby](https://github.com/stevenshelby))
-  * Sam Nissen ([@samnissen](https://github.com/samnissen))
+- Steven Shelby ([@stevenshelby](https://github.com/stevenshelby))
+- Sam Nissen ([@samnissen](https://github.com/samnissen))
 
 ## License
 

data/lib/web_inspector/inspector.rb

@@ -228,6 +228,203 @@ module WebInspector
       tags
     end
 
+    # Extract RSS/Atom feeds from the page
+    # @return [Array<String>] Array of feed URLs
+    def feeds
+      @feeds ||= begin
+        feeds = []
+
+        # Look for feed link tags
+        @page.css('link[type="application/rss+xml"], link[type="application/atom+xml"]').each do |link|
+          href = link[:href]
+          feeds << make_absolute_url(href) if href
+        end
+
+        # Look for common feed patterns in links
+        links.each do |link|
+          feeds << link if link =~ %r{/(feed|rss|atom)(/|\.xml|$)}i
+        end
+
+        feeds.uniq.compact
+      end
+    end
+
+    # Extract social media profile links
+    # @return [Hash] Hash of social platform => URL
+    def social_links
+      @social_links ||= begin
+        socials = {}
+        platforms = {
+          facebook: /facebook\.com/,
+          twitter: /(twitter\.com|x\.com)/,
+          linkedin: /linkedin\.com/,
+          instagram: /instagram\.com/,
+          youtube: /youtube\.com/,
+          github: /github\.com/,
+          tiktok: /tiktok\.com/
+        }
+
+        # Check links
+        links.each do |link|
+          platforms.each do |platform, pattern|
+            socials[platform] ||= link if link.match?(pattern)
+          end
+        end
+
+        socials
+      end
+    end
+
+    # Get robots.txt URL
+    # @return [String] robots.txt URL
+    def robots_txt_url
+      "#{@url.split('/')[0..2].join('/')}/robots.txt" if @url
+    end
+
+    # Get sitemap URL
+    # @return [Array<String>] Array of sitemap URLs
+    def sitemap_url
+      @sitemap_url ||= begin
+        sitemaps = []
+
+        # Check for sitemap link tag
+        @page.css('link[rel="sitemap"]').each do |link|
+          href = link[:href]
+          sitemaps << make_absolute_url(href) if href
+        end
+
+        # Add default sitemap.xml
+        sitemaps << "#{@url.split('/')[0..2].join('/')}/sitemap.xml" if @url
+
+        sitemaps.uniq.compact
+      end
+    end
+
+    # Detect CMS and get detailed information
+    # @return [Hash] CMS information
+    def cms_info
+      @cms_info ||= begin
+        info = { name: nil, version: nil, themes: [], plugins: [] }
+
+        # WordPress detection
+        if @page.to_html.include?('wp-content') || @meta['generator']&.include?('WordPress')
+          info[:name] = 'WordPress'
+          # Try to extract version from generator meta tag
+          info[:version] = Regexp.last_match(1) if @meta['generator'] =~ /WordPress\s+([\d.]+)/
+
+          # Detect themes
+          @page.css('link[href*="wp-content/themes"]').each do |link|
+            info[:themes] << Regexp.last_match(1) if link[:href] =~ %r{themes/([^/]+)}
+          end
+
+          # Detect plugins
+          @page.css('link[href*="wp-content/plugins"], script[src*="wp-content/plugins"]').each do |elem|
+            src = elem[:href] || elem[:src]
+            info[:plugins] << Regexp.last_match(1) if src =~ %r{plugins/([^/]+)}
+          end
+        # Drupal detection
+        elsif @page.to_html.include?('Drupal') || @meta['generator']&.include?('Drupal')
+          info[:name] = 'Drupal'
+          info[:version] = Regexp.last_match(1) if @meta['generator'] =~ /Drupal\s+([\d.]+)/
+        # Joomla detection
+        elsif @meta['generator']&.include?('Joomla')
+          info[:name] = 'Joomla'
+          info[:version] = Regexp.last_match(1) if @meta['generator'] =~ /Joomla!\s+([\d.]+)/
+        # Shopify detection
+        elsif @page.to_html.include?('cdn.shopify.com') || @page.to_html.include?('Shopify')
+          info[:name] = 'Shopify'
+        # Wix detection
+        elsif @page.to_html.include?('wix.com') || @page.to_html.include?('_wix')
+          info[:name] = 'Wix'
+        # Squarespace detection
+        elsif @page.to_html.include?('squarespace')
+          info[:name] = 'Squarespace'
+        end
+
+        info[:themes].uniq!
+        info[:plugins].uniq!
+        info
+      end
+    end
+
+    # Calculate a basic accessibility score
+    # @return [Hash] Accessibility score and details
+    def accessibility_score
+      @accessibility_score ||= begin
+        score = 100
+        details = []
+
+        # Check images for alt text
+        images_without_alt = @page.css('img:not([alt])').count
+        total_images = @page.css('img').count
+
+        if total_images.positive?
+          alt_percentage = ((total_images - images_without_alt).to_f / total_images * 100).round
+          if alt_percentage < 100
+            penalty = (100 - alt_percentage) / 4 # Max 25 points penalty
+            score -= penalty
+            details << "#{images_without_alt} images missing alt text"
+          end
+        end
+
+        # Check heading hierarchy
+        h1_count = @page.css('h1').count
+        if h1_count.zero?
+          score -= 15
+          details << 'No H1 heading found'
+        elsif h1_count > 1
+          score -= 10
+          details << 'Multiple H1 headings found'
+        end
+
+        # Check for ARIA labels on interactive elements
+        buttons_without_aria = @page.css('button:not([aria-label]):not([aria-labelledby])').select do |btn|
+          btn.text.strip.empty?
+        end.count
+
+        if buttons_without_aria.positive?
+          score -= [buttons_without_aria * 5, 20].min
+          details << "#{buttons_without_aria} buttons without accessible labels"
+        end
+
+        # Check for language attribute
+        html_tag = @page.at('html')
+        if html_tag.nil? || html_tag['lang'].nil? || html_tag['lang'].empty?
+          score -= 10
+          details << 'No language attribute on HTML element'
+        end
+
+        # Check for form labels
+        inputs = @page.css('input[type="text"], input[type="email"], input[type="password"], textarea')
+        inputs_without_labels = inputs.select do |input|
+          id = input['id']
+          !id || @page.css("label[for=\"#{id}\"]").empty?
+        end.count
+
+        if inputs_without_labels.positive?
+          score -= [inputs_without_labels * 5, 15].min
+          details << "#{inputs_without_labels} form inputs without labels"
+        end
+
+        { score: [score, 0].max, details: details }
+      end
+    end
+
+    # Check if the page is mobile-friendly
+    # @return [Boolean] true if mobile-friendly
+    def mobile_friendly?
+      @mobile_friendly ||= begin
+        # Check for viewport meta tag
+        viewport = @meta['viewport']
+        has_viewport = !viewport.nil? && viewport.include?('width=device-width')
+
+        # Check for responsive CSS (media queries)
+        has_media_queries = stylesheets.any? || @page.to_html.include?('@media')
+
+        has_viewport && has_media_queries
+      end
+    end
+
     private
 
     # Count occurrences of words in text

data/lib/web_inspector/meta.rb

@@ -26,6 +26,19 @@ module WebInspector
         .merge(meta_tag['property'])
         .merge(meta_tag['itemprop'] || {})
         .merge('charset' => meta_tag['charset'])
+        .merge('author' => author, 'publisher' => publisher)
+    end
+
+    def author
+      meta_tag['name']['author'] || meta_tag['property']['article:author']
+    rescue StandardError
+      nil
+    end
+
+    def publisher
+      meta_tag['property']['article:publisher'] || meta_tag['property']['og:site_name']
+    rescue StandardError
+      nil
     end
 
     def charset

data/lib/web_inspector/page.rb

@@ -70,7 +70,7 @@ module WebInspector
 
     # Delegate methods to inspector
     %i[title description body links images meta javascripts stylesheets language structured_data microdata
-       tag_count].each do |method|
+       tag_count feeds social_links robots_txt_url sitemap_url cms_info accessibility_score mobile_friendly?].each do |method|
       define_method(method) do
         return nil unless success?
 
@@ -249,6 +249,13 @@ module WebInspector
         'load_time' => load_time,
         'technologies' => technologies,
         'tag_count' => tag_count,
+        'feeds' => feeds,
+        'social_links' => social_links,
+        'robots_txt_url' => robots_txt_url,
+        'sitemap_url' => sitemap_url,
+        'cms_info' => cms_info,
+        'accessibility_score' => accessibility_score,
+        'mobile_friendly' => mobile_friendly?,
         'response' => {
           'status' => status_code,
           'headers' => response&.headers || {},

data/lib/web_inspector/request.rb

@@ -28,6 +28,22 @@ module WebInspector
       URI(normalized_uri).port
     end
 
+    def valid?
+      !uri.nil? && !uri.host.nil?
+    rescue StandardError
+      false
+    end
+
+    def ssl?
+      scheme == 'https'
+    end
+
+    def error_message
+      return nil if valid?
+
+      'Invalid URL: Unable to parse the provided URL'
+    end
+
     private
 
     def suffix_domain
@@ -47,7 +63,11 @@ module WebInspector
     end
 
     def normalized_uri
+      return '' if uri.nil?
+
       uri.normalize.to_s
+    rescue StandardError
+      @url
     end
   end
 end

data/lib/web_inspector/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module WebInspector
-  VERSION = '1.1.0'
+  VERSION = '1.2.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: webinspector
 version: !ruby/object:Gem::Version
-  version: 1.1.0
+  version: 1.2.0
 platform: ruby
 authors:
 - Davide Santangelo
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-07-29 00:00:00.000000000 Z
+date: 2025-11-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake