site_health 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 251746b898058b968e3e9f5a50406a9e6d4ab4d3
+  data.tar.gz: 6889e72c9f4d2b925381d9f41ef28a5acf0e84d6
+SHA512:
+  metadata.gz: c06a8679ef7fc7ebb6f9b926b8730119201ff4ad07439fae7b5e38fb15499ec51c11cca6664be80cb1d4dbde3a63d65c6d2861fcd0e567f9041908b39fa46b02
+  data.tar.gz: af62e5459f0882e659da7a2e9e7b47b12aaf8d87d1835acf621dbdc3234999002f5e25ade7ed64da93ec9c95d2231aa0671adddb22ad7896447b2bc2a91be8c9

data/.gitignore

@@ -0,0 +1,15 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+Gemfile.lock
+
+# rspec failure tracking
+.rspec_status
+
+.byebug_history

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.4.1
+before_install: gem install bundler -v 1.16.0.pre.2

data/Gemfile

@@ -0,0 +1,6 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in site_health.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2017 Jacob Burenstam
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -0,0 +1,64 @@
+# SiteHealth
+
+:warning: Project is still experimental, API will change (a lot) without notice.
+
+Crawl a site and check various health indicators, such as:
+
+- HTTP error status
+- Invalid HTML/CSS/XML
+- Missing HTML page title
+- Broken links
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'site_health'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install site_health
+
+## Usage
+
+```ruby
+journal = SiteHealth.check('https://example.com')
+
+# HTML
+journal.missing_html_title # List of URLs that are missing the HTML title
+journal.html_error_urls # List of URLs with HTML errors in them
+
+# CSS
+journal.css_error_urls # List of URLs with CSS errors in them
+
+# XML
+journal.xml_error_urls # List of URLs with XML errors in them
+
+# Broken URLs
+broken = journal.broken_urls.first
+broken.url # The URL that failed
+broken.exists_on # Array of URLs where the broken URL was present
+
+# HTTP
+journal.http_error_urls # All URLs with HTTP status code >= 400
+```
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/buren/site_health.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "site_health"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/site_health.rb

@@ -0,0 +1,136 @@
+require "spidr"
+require 'w3c_validators'
+require "site_health/version"
+
+require "site_health/key_struct"
+
+require 'site_health/journals/css_journal'
+require 'site_health/journals/html_journal'
+require 'site_health/journals/xml_journal'
+require 'site_health/journals/w3c_journal'
+
+require "site_health/checkers/css_page"
+require "site_health/checkers/html_page"
+require "site_health/checkers/xml_page"
+
+module SiteHealth
+  def self.check(site)
+    Check.call(site: site)
+  end
+
+  class Check
+    def self.call(**args)
+      new(**args).call
+    end
+
+    BrokenLinkJournal = KeyStruct.new(:url, :exists_on)
+
+    HTTPCodeJournal = KeyStruct.new(:url, :code)
+    class HTTPCodeJournal
+      def error?
+        code >= 400
+      end
+    end
+
+    ChecksJournal = KeyStruct.new(
+      :missing_html_title,
+      :broken_urls,
+      :http_error_urls,
+      :html_error_urls,
+      :html_warning_urls,
+      :xml_error_urls,
+      :css_error_urls,
+      :css_warning_urls
+    )
+
+    attr_reader :site
+
+    def initialize(site:)
+      @site = site
+    end
+
+    def call
+      url_map = Hash.new { |hash, key| hash[key] = [] }
+
+      missing_html_title = []
+      http_error_urls = []
+      html_error_urls = []
+      html_warning_urls = []
+      xml_error_urls = []
+      css_error_urls = []
+      css_warning_urls = []
+
+      spider = Spidr.site(site) do |spider|
+        spider.every_link do |origin, destination|
+          url_map[destination] << origin
+        end
+
+        spider.every_page do |page|
+          code_journal = HTTPCodeJournal.new(url: page.url, code: page.code)
+          http_error_urls << code_journal if code_journal.error?
+
+          if page.css?
+            result = Checkers::CSSPage.check(page)
+            xml_error_urls << result if result.errors?
+          end
+
+          if page.xml?
+            result = Checkers::XMLPage.check(page)
+            xml_error_urls << result if result.errors?
+          end
+
+          if page.html?
+            result = Checkers::HTMLPage.check(page)
+            missing_html_title << result if result.missing_title?
+            html_error_urls << result if result.errors?
+          end
+        end
+      end
+
+      http_error_urls = map_http_error_urls(http_error_urls, url_map)
+      broken_urls = broken_links(spider, url_map) + http_error_urls
+
+      ChecksJournal.new(
+        missing_html_title: missing_html_title,
+        broken_urls: broken_urls,
+        http_error_urls: http_error_urls,
+        html_error_urls: html_error_urls,
+        html_warning_urls: html_warning_urls,
+        xml_error_urls: xml_error_urls,
+        css_error_urls: css_error_urls,
+        css_warning_urls: css_warning_urls
+      )
+    end
+
+    def validate_css_page(page, errors)
+      css_checker = Checkers::CSSPage.new(page)
+      result = css_checker.check
+      return unless result.errors?
+
+      result
+    end
+
+    def map_http_error_urls(urls, url_map)
+      urls.map do |failed_url|
+        BrokenLinkJournal.new(url: failed_url, exists_on: url_map[failed_url])
+      end
+    end
+
+    # Finds all pages which have broken links:
+    def broken_links(spider, url_map)
+      # FIXME: spider#failures only returns timeout errors etc and not HTTP error status codes..
+      #        so we need to have 2 types of "failed" URLs
+      spider.failures.map do |failed_url|
+        BrokenLinkJournal.new(url: failed_url, exists_on: url_map[failed_url])
+      end
+    end
+
+    # @return [W3CValidators::Results]
+    # @raise [W3CValidators::ValidatorUnavailable] the service is offline or returns 400 Bad Request
+    # @see https://github.com/w3c-validators/w3c_validators/issues/39 we really want to use #validate_text instead of #validate_uri but due to the linked issue thats not possible
+    def validate_html(html_url)
+      validator = W3CValidators::NuValidator.new
+      validator.validate_uri(html_url)
+    end
+  end
+end

data/lib/site_health/checkers/css_page.rb

@@ -0,0 +1,36 @@
+module SiteHealth
+  module Checkers
+    class CSSPage
+      def self.check(page)
+        new(page).check
+      end
+
+      attr_reader :page, :url
+
+      # @param [Spidr::Page] the crawled page
+      def initialize(page)
+        @page = page
+        @url = page.url
+      end
+
+      def check
+        result = check_content
+
+        CSSJournal.new(
+          url: url,
+          page: page,
+          errors: result.errors.map { |e| W3CJournalBuilder.build(e) },
+          warnings: result.warnings.map { |e| W3CJournalBuilder.build(e) }
+        )
+      end
+
+      # @return [W3CValidators::Results]
+      # @raise [W3CValidators::ValidatorUnavailable] the service is offline or returns 400 Bad Request
+      # @see https://github.com/w3c-validators/w3c_validators/issues/39 we really want to use #validate_text instead of #validate_uri but due to the linked issue thats not possible
+      def check_content
+        validator = W3CValidators::CSSValidator.new
+        validator.validate_uri(url)
+      end
+    end
+  end
+end

data/lib/site_health/checkers/html_page.rb

@@ -0,0 +1,41 @@
+module SiteHealth
+  module Checkers
+    class HTMLPage
+      def self.check(page)
+        new(page).check
+      end
+
+      attr_reader :page, :url
+
+      # @param [Spidr::Page] the crawled page
+      def initialize(page)
+        @page = page
+        @url = page.url
+      end
+
+      def check
+        result = check_content
+
+        HTMLJournal.new(
+          url: url,
+          page: page,
+          missing_title: missing_title?,
+          errors: result.errors.map { |e| W3CJournalBuilder.build(e) },
+          warnings: result.warnings.map { |e| W3CJournalBuilder.build(e) }
+        )
+      end
+
+      def missing_title?
+        page.title.to_s.strip.empty?
+      end
+
+      # @return [W3CValidators::Results]
+      # @raise [W3CValidators::ValidatorUnavailable] the service is offline or returns 400 Bad Request
+      # @see https://github.com/w3c-validators/w3c_validators/issues/39 we really want to use #validate_text instead of #validate_uri but due to the linked issue thats not possible
+      def check_content
+        validator = W3CValidators::NuValidator.new
+        validator.validate_uri(url)
+      end
+    end
+  end
+end

data/lib/site_health/checkers/xml_page.rb

@@ -0,0 +1,21 @@
+module SiteHealth
+  module Checkers
+    class XMLPage
+      def self.check(page)
+        new(page).check
+      end
+
+      attr_reader :page, :url
+
+      # @param [Spidr::Page] the crawled page
+      def initialize(page)
+        @page = page
+        @url = page.url
+      end
+
+      def check
+        XMLJournal.new(url: url, page: page, errors: page.doc.errors)
+      end
+    end
+  end
+end

data/lib/site_health/journals/css_journal.rb

@@ -0,0 +1,12 @@
+module SiteHealth
+  CSSJournal = KeyStruct.new(:page, :url, :errors, :warnings)
+  class CSSJournal
+    def errors?
+      errors.any?
+    end
+
+    def warnings?
+      warnings.any?
+    end
+  end
+end

data/lib/site_health/journals/html_journal.rb

@@ -0,0 +1,16 @@
+module SiteHealth
+  HTMLJournal = KeyStruct.new(:page, :url, :errors, :warnings, :missing_title)
+  class HTMLJournal
+    def missing_title?
+      missing_title
+    end
+
+    def errors?
+      errors.any?
+    end
+
+    def warnings?
+      warnings.any?
+    end
+  end
+end

data/lib/site_health/journals/w3c_journal.rb

@@ -0,0 +1,43 @@
+module SiteHealth
+  W3CJournal = KeyStruct.new(
+    :message,
+    :value,
+    :source,
+    :type,
+    :explanation,
+    :parent,
+    :line,
+    :context,
+    :element,
+    :error?,
+    :warning?,
+    :col,
+    :message_id,
+    :message_count,
+    :skipped_string
+  )
+
+  module W3CJournalBuilder
+    # @param [W3CValidators::Result]
+    # @return [W3CJournal]
+    def self.build(result)
+      W3CJournal.new(
+        message: (result.message || '').strip,
+        value: result.value,
+        source: result.source,
+        type: result.type,
+        explanation: result.explanation,
+        parent: result.parent,
+        line: result.line,
+        context: result.context,
+        element: result.element,
+        error?: result.is_error?,
+        warning?: result.is_warning?,
+        col: result.col,
+        message_id: result.message_id,
+        message_count: result.message_count,
+        skipped_string: result.skippedstring
+      )
+    end
+  end
+end

data/lib/site_health/journals/xml_journal.rb

@@ -0,0 +1,8 @@
+module SiteHealth
+  XMLJournal = KeyStruct.new(:page, :url, :errors)
+  class XMLJournal
+    def errors?
+      errors.any?
+    end
+  end
+end

data/lib/site_health/key_struct.rb

@@ -0,0 +1,13 @@
+module SiteHealth
+  class KeyStruct < Struct
+    def initialize(**keyword_args)
+      keyword_args.each do |key, value|
+        if members.include?(key)
+          self[key] = value
+        else
+          raise ArgumentError, "Unknown key struct member: #{key}"
+        end
+      end
+    end
+  end
+end

data/lib/site_health/version.rb

@@ -0,0 +1,3 @@
+module SiteHealth
+  VERSION = "0.1.0"
+end

data/site_health.gemspec

@@ -0,0 +1,31 @@
+
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "site_health/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "site_health"
+  spec.version       = SiteHealth::VERSION
+  spec.authors       = ["Jacob Burenstam"]
+  spec.email         = ["burenstam@gmail.com"]
+
+  spec.summary       = %q{Crawl a site and check various helth indicators.}
+  spec.description   = %q{Crawl a site and check various health indicators, such as: HTTP 4XX, 5XX status and valid HTML.}
+  spec.homepage      = "https://github.com/buren/site_health"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+    f.match(%r{^(test|spec|features)/})
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency "spidr", "~> 0.6"
+  spec.add_dependency "w3c_validators", "~> 1.3"
+
+  spec.add_development_dependency "bundler", "~> 1.16.a"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+  spec.add_development_dependency "byebug"
+end

metadata

@@ -0,0 +1,149 @@
+--- !ruby/object:Gem::Specification
+name: site_health
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Jacob Burenstam
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2017-10-24 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: spidr
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.6'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.6'
+- !ruby/object:Gem::Dependency
+  name: w3c_validators
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.16.a
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.16.a
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: byebug
+  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: 'Crawl a site and check various health indicators, such as: HTTP 4XX,
+  5XX status and valid HTML.'
+email:
+- burenstam@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/site_health.rb
+- lib/site_health/checkers/css_page.rb
+- lib/site_health/checkers/html_page.rb
+- lib/site_health/checkers/xml_page.rb
+- lib/site_health/journals/css_journal.rb
+- lib/site_health/journals/html_journal.rb
+- lib/site_health/journals/w3c_journal.rb
+- lib/site_health/journals/xml_journal.rb
+- lib/site_health/key_struct.rb
+- lib/site_health/version.rb
+- site_health.gemspec
+homepage: https://github.com/buren/site_health
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.13
+signing_key: 
+specification_version: 4
+summary: Crawl a site and check various helth indicators.
+test_files: []