broken_link_finder 0.2.0 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 87ed607a6fa9669142546f0af4d62c11fb8767ae25c54f4c27373cc823706368
-  data.tar.gz: f90f38d18482eed566995288b669cfc71c0d66fe177e44850e8732bd7a6532b5
+  metadata.gz: 4b9617c6016a37c3afeec665d3f5d70e8574e8cf28100f4c661ee95fd7f7ccee
+  data.tar.gz: cf517abd6b554f3cdf01b535dfd4417dd226fdde8edae4556190b0da69cd3bda
 SHA512:
-  metadata.gz: 7450e7671c5559de801e3c8f8eae7c01ae0c37bfb7c1a476f95639ea987139d7638fc14655eb4b3948f87b3021c1716e3842a902bc09c46413e1a16529cdf870
-  data.tar.gz: 3b89341b5c35de1ed61b1ab39d324d5f7c33d5d69597f87286710921f4aff7b20ce3368b5889d446895ea8cc7b1ad2ecc9630ced62310fef56ef743457a2dcb1
+  metadata.gz: 691714c983790ff8d8a004e3c92f1edae1a50e44e4771f123d177904364c65679c034580a3b182209a18b2baa83277b88c571e0cddcf131c638fcc106cc031a5
+  data.tar.gz: '0093753cea2740b13b5b8fda6dde5046e76ce4e8e7cf93e3be7ae99cf7bd6e6aa164218105fe81b4a35ddf4622717f01d69455be9dc65b738e7ae32c33341c32'

data/Gemfile.lock

@@ -1,8 +1,8 @@
 PATH
   remote: .
   specs:
-    broken_link_finder (0.2.0)
-      wgit
+    broken_link_finder (0.2.1)
+      wgit (> 0)
 
 GEM
   remote: https://rubygems.org/
@@ -32,7 +32,7 @@ GEM
       addressable (>= 2.3.6)
       crack (>= 0.3.2)
       hashdiff
-    wgit (0.0.8)
+    wgit (0.0.9)
       mongo (~> 2.6)
       nokogiri (~> 1.10)
 

data/README.md

@@ -8,8 +8,6 @@ Simply point it at a website and it will crawl all of its webpages searching for
 
 This repository utilises the awesome `wgit` Ruby gem. See its [repository](https://github.com/michaeltelford/wgit) for more details.
 
-The only gotcha is that `wgit` doesn't currently follow redirects meaning they will appear as broken links in the results.
-
 ## Installation
 
 Add this line to your application's Gemfile:
@@ -28,7 +26,7 @@ Or install it yourself as:
 
 ## Usage
 
-Below is a sample script which crawls a website and outputs its broken links to a file.
+Below is a simple script which crawls a website and outputs its broken links to STDOUT.
 
 > main.rb
 
@@ -36,8 +34,8 @@ Below is a sample script which crawls a website and outputs its broken links to
 require 'broken_link_finder'
 
 finder = BrokenLinkFinder::Finder.new
-finder.crawl_site "http://txti.es" # Also, see Finder#crawl_url for a single webpage.
-finder.pretty_print_broken_links
+finder.crawl_site "http://txti.es" # Also, see Finder#crawl_page for a single webpage.
+finder.pretty_print_broken_links # Also, see Finder#broken_links for a Hash.
 ```
 
 Then execute the script with:
@@ -62,19 +60,19 @@ http://imgur.com
 
 ## TODO
 
+- Speed boost.
 - Create a `broken_link_finder` executable.
 - Add logger functionality (especially useful in the console during development).
-- Update the `wgit` gem as soon as redirects are implemented.
 
 ## Development
 
-After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `bundle exec rake test` 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).
+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[origin]`, 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 [here](https://github.com/michaeltelford/broken-link-finder).
+Bug reports and pull requests are welcome on [GitHub](https://github.com/michaeltelford/broken-link-finder).
 
 ## License
 

data/broken_link_finder.gemspec

@@ -42,5 +42,5 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "byebug", "~> 11.0"
   spec.add_development_dependency "webmock", "~> 3.5"
 
-  spec.add_runtime_dependency "wgit"
+  spec.add_runtime_dependency "wgit", "> 0"
 end

data/lib/broken_link_finder/finder.rb

@@ -20,8 +20,8 @@ module BrokenLinkFinder
     def crawl_site(url)
       clear_broken_links
       url = Wgit::Url.new(url)
-      crawled_pages = []
 
+      crawled_pages = []
       @crawler.crawl_site(url) do |doc|
         # Ensure the given website url is valid.
         raise "Invalid URL: #{url}" if doc.url == url and doc.empty?
@@ -32,8 +32,7 @@ module BrokenLinkFinder
 
         # Get all page links and determine which are broken.
         next unless doc
-        links = doc.internal_full_links + doc.external_links
-        find_broken_links(doc.url, links)
+        find_broken_links(doc)
       end
 
       !@broken_links.empty?
@@ -50,8 +49,7 @@ module BrokenLinkFinder
       raise "Invalid URL: #{url}" unless doc
 
       # Get all page links and determine which are broken.
-      links = doc.internal_full_links + doc.external_links
-      find_broken_links(url, links)
+      find_broken_links(doc)
 
       !@broken_links.empty?
     end
@@ -84,11 +82,12 @@ broken links...")
     private
 
     # Finds which links are broken and append the details to @broken_links.
-    def find_broken_links(url, 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...
-          append_broken_link(url, link)
+          append_broken_link(doc.url, link)
         end
       end
     end

data/lib/broken_link_finder/version.rb

@@ -1,3 +1,3 @@
 module BrokenLinkFinder
-  VERSION = "0.2.0"
+  VERSION = "0.2.1"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: broken_link_finder
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
 platform: ruby
 authors:
 - Michael Telford
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-05-31 00:00:00.000000000 Z
+date: 2019-06-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -98,14 +98,14 @@ dependencies:
   name: wgit
   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: Finds a website's broken links using the 'wgit' gem and reports back
@@ -152,7 +152,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.7.8
+rubygems_version: 2.7.6
 signing_key: 
 specification_version: 4
 summary: Finds a website's broken links and reports back to you with a summary.