linkey 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 24c584ed39c86e327994d6ec7d8d7ce7bfdf89f9
+  data.tar.gz: 733a082d58fd5de3c8bd6588f9ed0a52562ca8a3
+SHA512:
+  metadata.gz: b0dad21a6b2a51435d59a190fd95204df043e755a061c83efb6a353d789f4a239d60b762f06a4eae5bac845dc134f718a6c232224c4897edb352f8c425e5a525
+  data.tar.gz: e4b8a8512585bd56f3add88b9887e3fe77f803651fd3743a31228d35be96dffa7038bc1108164908a7b8b200277567f7b1b4cfed68b067811d12b41930730b24

data/.gitignore

@@ -0,0 +1,6 @@
+.bundle/*
+pages/
+.DS_Store
+Gemfile.lock
+*.md
+!README.md

data/.ruby-version

@@ -0,0 +1 @@
+2.0.0-p353

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in ..gemspec
+gemspec

data/LICENSE

@@ -0,0 +1,177 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS

data/README.md

@@ -0,0 +1,50 @@
+Linkey
+=====
+
+Link checker for BBC News/WS Sites
+
+The idea is to quickly check a page for broken links by doing a status check on all the relative URL's on the page. 
+
+There are 4 parts to this tool, the URL, the base URL, the regex and the filename.  
+The URL is the page that you want to check for broken links, e.g www.bbc.co.uk/news/uk-29928282
+The Base URL is used with the relative URL from the regex to create a full URL, e.g www.bbc.co.uk
+THe regex is the point of the URL that you want to keep from the regex, e.g bbc.co.uk/news/uk, specifying /news would create /news/uk.
+The filename is .md file where all the page links are stored, this can be useful for manual checks, e.g file.md
+
+Install 
+
+`gem install linkey`
+
+To use run 
+
+```
+linkey check URL BASEURL /regex Filename
+```
+Example
+
+```
+linkey check http://www.live.bbc.co.uk/arabic http://www.live.bbc.co.uk /arabic arabic.md
+```
+Another
+
+```ruby
+linkey check http://www.theguardian.com/technology/2014/feb/15/year-of-code-needs-reboot-teachers http://theguardian.com /technology news.md
+```
+
+Script it
+```ruby
+
+require 'linkey/html'
+require 'linkey/ping'
+
+url = 'http://www.live.bbc.co.uk/arabic'
+base = 'http://www.live.bbc.co.uk'
+reg = '/arabic'
+filename = 'arabic.md'
+
+page = Linkey::SaveLinks.new(url, filename)
+status = Linkey::CheckResponse.new(url, base, reg, filename)
+
+page.capture_links
+status.check_links
+```

data/bin/linkey

@@ -0,0 +1,13 @@
+#!/usr/bin/env ruby
+require 'rubygems'
+require 'bundler/setup'
+
+begin
+  require 'linkey/cli'
+  Linkey::CLI.start
+rescue Interrupt => e
+  puts "\nQuitting..."
+  exit 1
+rescue SystemExit => e
+  exit e.status
+end

data/lib/linkey.rb

@@ -0,0 +1,5 @@
+require "linkey/version"
+
+module Linkey
+  autoload :CLI, 'linkey/cli'
+end

data/lib/linkey/cli.rb

@@ -0,0 +1,25 @@
+require 'thor'
+require 'linkey/html'
+require 'linkey/ping'
+
+class Linkey::CLI < Thor
+  include Thor::Actions
+
+  desc "scan", "Save some URL's"
+  def scan(url, filename)
+    html = Linkey::SaveLinks.new(url, filename)
+    html.capture_links
+  end
+
+  desc "status", "checks links for errors"
+  def status(url, base, reg, filename)
+    status = Linkey::CheckResponse.new(url, base, reg, filename)
+    status.check_links
+  end
+
+  desc "check URL Base_URL File", "A full linkey job"
+  def check(url, base, reg, filename)
+    scan(url, filename)
+    status(url, base, reg, filename)
+  end
+end

data/lib/linkey/html.rb

@@ -0,0 +1,18 @@
+require 'linkey'
+
+class Linkey::SaveLinks
+  attr_accessor :url, :file_name
+
+  def initialize(url, file_name)
+    @url = url
+    @file_name = file_name
+  end
+
+  def js_file
+    File.expand_path('javascript/snap.js', File.dirname(__FILE__))
+  end
+
+  def capture_links
+    puts `phantomjs "#{js_file}" "#{url}" > "#{file_name}"`
+  end
+end

data/lib/linkey/javascript/snap.js

@@ -0,0 +1,88 @@
+var system = require('system');
+var page = require('webpage').create();
+var fs = require('fs');
+
+var url = system.args[1];
+var lastRequestTimeout;
+var finalTimeout;
+var currentRequests = 0;
+
+// You can place custom headers here, example below.
+// page.customHeaders = {
+
+     // 'X-Candy-OVERRIDE': 'https://api.test.bbc.co.uk/'
+     // 'X-Country': 'cn'
+
+ // };
+
+// If you want to set a cookie, just add your details below in the following way.
+
+phantom.addCookie({
+    'name': 'ckns_policy',
+    'value': '111',
+    'domain': '.bbc.co.uk'
+});
+phantom.addCookie({
+    'name': 'locserv',
+    'value': '1#l1#i=6691484:n=Oxford+Circus:h=e@w1#i=8:p=London@d1#1=l:2=e:3=e:4=2@n1#r=40',
+    'domain': '.bbc.co.uk'
+});
+
+var checkLinks = function checkLinks () {
+    page.evaluate(function() {
+        var anchorsArray = Array.prototype.slice.call(document.querySelectorAll("a"));
+
+        anchorsArray.forEach(function(anchor) {
+            console.log(anchor.pathname);
+        });
+
+        window.callPhantom();
+    });
+};
+
+var debouncedCheckFinish = function debouncedCheckFinish () {
+    clearTimeout(lastRequestTimeout);
+    clearTimeout(finalTimeout);
+
+    if (currentRequests < 1) {
+        clearTimeout(finalTimeout);
+        lastRequestTimeout = setTimeout(function() {
+            // Page has finished loading all resources
+            // Do stuff here
+            checkLinks();
+        }, 1000);
+    }
+
+    finalTimeout = setTimeout(function() {
+        // Page is tired of waiting for resources to load
+        // Exit but do stuff anyway
+
+        checkLinks();
+    }, 9000);
+};
+
+page.onResourceRequested = function(req) {
+    currentRequests += 1;
+};
+
+page.onResourceReceived = function(res) {
+    if (res.stage === 'end') {
+        currentRequests -= 1;
+        debouncedCheckFinish();
+    }
+};
+
+page.onConsoleMessage = function(msg) {
+    console.log(msg);
+};
+
+page.onCallback = function() {
+    phantom.exit();
+};
+
+page.open(url, function(status) {
+    if (status === 'fail') {
+        console.error('Couldn\'t load url');
+        phantom.exit(1);
+    }
+});

data/lib/linkey/ping.rb

@@ -0,0 +1,45 @@
+require 'linkey'
+require 'open-uri'
+
+class Linkey::CheckResponse
+  attr_accessor :url, :base, :reg, :file_name
+
+  def initialize(url, base, reg, file_name)
+    @url = url
+    @base = base
+    @reg = reg
+    @file_name = file_name
+  end
+
+  def check_links
+    array = []
+    links = File.read(file_name)
+    array << links
+    links(array)
+  end
+
+  def links(links)
+    links.each do |url_links|
+      scan(url_links)
+    end
+  end
+
+  def scan(page_links)
+    urls = page_links.scan(/^#{Regexp.quote(reg)}(?:|.+)?$/)
+    status(urls)
+  end
+
+  def status(urls)
+    puts "Checking..."
+    urls.each do |page_path|
+      begin
+        gets = open(base + page_path)
+        status = gets.status.first
+        puts "Status is #{status} for #{base}#{page_path}"
+      rescue OpenURI::HTTPError => ex
+        puts "Status is NOT GOOD for #{base}#{page_path}" 
+      end  
+    end
+    puts "All Done!"
+  end
+end

data/lib/linkey/version.rb

@@ -0,0 +1,3 @@
+module Linkey
+  VERSION = '0.1.0'
+end

data/linkey.gemspec

@@ -0,0 +1,21 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'linkey/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "linkey"
+  spec.version       = Linkey::VERSION
+  spec.authors       = ["Dave Blooman"]
+  spec.email         = ["david.blooman@gmail.com"]
+  spec.summary       = 'Linkey'
+  spec.description   = 'Linkey'
+  spec.homepage      = "http://responsivenews.co.uk"
+  spec.license       = "Apache 2"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_runtime_dependency "thor"
+end

metadata

@@ -0,0 +1,73 @@
+--- !ruby/object:Gem::Specification
+name: linkey
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Dave Blooman
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-02-17 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: thor
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Linkey
+email:
+- david.blooman@gmail.com
+executables:
+- linkey
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .ruby-version
+- Gemfile
+- LICENSE
+- README.md
+- bin/linkey
+- lib/linkey.rb
+- lib/linkey/cli.rb
+- lib/linkey/html.rb
+- lib/linkey/javascript/snap.js
+- lib/linkey/ping.rb
+- lib/linkey/version.rb
+- linkey.gemspec
+homepage: http://responsivenews.co.uk
+licenses:
+- Apache 2
+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: 2.0.14
+signing_key: 
+specification_version: 4
+summary: Linkey
+test_files: []
+has_rdoc: