broken_link_finder 0.4.1 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 134dfae975f01be474a18d86cfa173a8509a6548f3d48343b7c4dc26de40dc53
-  data.tar.gz: bbf9d2d32bc016637c9dfb97ab7a74f8fe6d50ea21f4998d167ed226926ad12d
+  metadata.gz: 364ec155bda54b8757fbce6425c8978d8d17cd91618d5650dc14f8a63e712a2f
+  data.tar.gz: b5c0e405f159aaed54725042105c519e1e9d0e085bf40aad99b114200ec8713a
 SHA512:
-  metadata.gz: 9698dda0c3a1b513c425060a29207df1e6b56c32aff9fbfd3ada97d4e57fcb77ee893073c4cd4a1af40d425bba9c6a47fbe23730b87f2cd85f3088f1afab1581
-  data.tar.gz: 581f2acd266a151b567708f6fe7e522972367fbcf4db0f6e746105483766a8ba2d3bfc699434961c4a6291d71a722dc11f47ea299a80074aed89fe46388cca4d
+  metadata.gz: eaf1aa2ea2b4f9177561291a8b729e91610f9b2fbd8541ceb2fa96f039a667ffd546dd758b9e4edb4fba9cad25c55368cb4af95ffbe9d0fdc20c546e3d4e5f0b
+  data.tar.gz: 8c6d407f74d900553782d7aedcdc4027c14e436bdb73b2888830827da9e305456e653ad9398c8752e01c8aae381871eb239aee5d7394ea995c5b68b0cbd38404

data/Gemfile.lock

@@ -1,10 +1,10 @@
 PATH
   remote: .
   specs:
-    broken_link_finder (0.4.1)
+    broken_link_finder (0.5.0)
       thor (= 0.20.3)
       thread (= 0.2)
-      wgit (= 0.0.10)
+      wgit (= 0.0.12)
 
 GEM
   remote: https://rubygems.org/
@@ -36,9 +36,9 @@ GEM
       addressable (>= 2.3.6)
       crack (>= 0.3.2)
       hashdiff
-    wgit (0.0.10)
+    wgit (0.0.12)
       mongo (~> 2.8.0)
-      nokogiri (~> 1.10)
+      nokogiri (~> 1.10.3)
 
 PLATFORMS
   ruby

data/README.md

@@ -4,6 +4,14 @@ Does what it says on the tin. Finds a website's broken links.
 
 Simply point it at a website and it will crawl all of its webpages searching for and identifing any broken links. You will then be presented with a nice concise summary of the broken links found.
 
+## How It Works
+
+Any page element with a `href` or `src` attribute is considered a link. For each link on a given page, any of the following conditions (in order) constitutes that the link is broken:
+
+1) A response status code of `404 Not Found` is returned.
+2) An empty HTML response body is returned.
+3) The HTML response body doesn't contain an element ID matching that of the link's anchor e.g. `http://server.com#about` must contain an element with an ID of `about` or the link is considered broken.
+
 ## Made Possible By
 
 This repository utilises the awesome `wgit` Ruby gem. See its [repository](https://github.com/michaeltelford/wgit) for more details.
@@ -74,7 +82,6 @@ http://imgur.com
 
 ## TODO
 
-- Improve the intelligence of the finder. Currently a custom 'Not Found' webpage will not be discovered as a broken link; it should.
 - Add logger functionality (especially useful in the console during development).
 
 ## Development

data/Rakefile

@@ -7,4 +7,19 @@ Rake::TestTask.new(:test) do |t|
   t.test_files = FileList['test/**/*_test.rb']
 end
 
-task :default => :test
+desc "Print help information"
+task default: :help
+
+desc "Print help information"
+task :help do
+  system "bundle exec rake -D"
+end
+
+desc "Compile all project Ruby files with warnings."
+task :compile do
+  paths = Dir["**/*.rb", "**/*.gemspec", 'exe/broken_link_finder']
+  paths.each do |f|
+    puts "\nCompiling #{f}..."
+    puts `ruby -cw #{f}`
+  end
+end

data/broken_link_finder.gemspec

@@ -13,7 +13,7 @@ Gem::Specification.new do |spec|
   spec.description   = "Finds a website's broken links using the 'wgit' gem and reports back to you with a summary."
   spec.homepage      = "https://github.com/michaeltelford/broken-link-finder"
   spec.license       = "MIT"
-  spec.metadata      = { 
+  spec.metadata      = {
     "source_code_uri" => "https://github.com/michaeltelford/broken-link-finder",
   }
 
@@ -43,7 +43,7 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "byebug", "~> 11.0"
   spec.add_development_dependency "webmock", "~> 3.5"
 
-  spec.add_runtime_dependency "wgit", "0.0.10"
+  spec.add_runtime_dependency "wgit", "0.0.12"
   spec.add_runtime_dependency "thread", "0.2"
   spec.add_runtime_dependency "thor", "0.20.3"
 end

data/lib/broken_link_finder/finder.rb

@@ -67,7 +67,7 @@ module BrokenLinkFinder
 
     # Pretty prints the contents of broken_links into a stream e.g. Kernel
     # (STDOUT) or a file - anything that respond_to? :puts.
-    # Returns true if there were broken links and vice versa. 
+    # Returns true if there were broken links and vice versa.
     def pretty_print_broken_links(stream = Kernel)
       raise "stream must respond_to? :puts" unless stream.respond_to? :puts
 
@@ -96,13 +96,24 @@ broken links...")
     def find_broken_links(doc)
       links = doc.internal_full_links + doc.external_links
       links.each do |link|
-        ok = @crawler.crawl_url(link)
-        if not ok # a.k.a. if the link is broken...
+        link_doc = @crawler.crawl_url(link)
+        if @crawler.last_response.is_a?(Net::HTTPNotFound) or
+            link_doc.nil? or
+            has_broken_anchor(link_doc)
           append_broken_link(doc.url, link)
         end
       end
     end
 
+    # Returns true if the link is/contains a broken anchor.
+    def has_broken_anchor(doc)
+      raise "link document is nil" unless doc
+      return false unless doc.url.anchor
+
+      anchor = doc.url.anchor[1..-1] # Remove the # prefix.
+      doc.xpath("//*[@id='#{anchor}']").empty?
+    end
+
     # Append url => [link] to @broken_links.
     def append_broken_link(url, link)
       @lock.synchronize do

data/lib/broken_link_finder/version.rb

@@ -1,3 +1,3 @@
 module BrokenLinkFinder
-  VERSION = "0.4.1"
+  VERSION = "0.5.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: broken_link_finder
 version: !ruby/object:Gem::Version
-  version: 0.4.1
+  version: 0.5.0
 platform: ruby
 authors:
 - Michael Telford
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-07-12 00:00:00.000000000 Z
+date: 2019-07-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -100,14 +100,14 @@ dependencies:
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 0.0.10
+        version: 0.0.12
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 0.0.10
+        version: 0.0.12
 - !ruby/object:Gem::Dependency
   name: thread
   requirement: !ruby/object:Gem::Requirement