metainspector 5.9.0 → 5.11.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b88f82dd95de4917883dcadd783df5b6053613f8c014488828c20a41c41ea965
-  data.tar.gz: 5a46882cc6f225c80953fdb9e3209bab0ca84860daa5781593fafd20a5c130f1
+  metadata.gz: 8508f38adaf43e789f0ec8f966384749fc9e372dc98f0a4ee4f20f5b1abbbd71
+  data.tar.gz: a97d211784760153c28826b7f4a5c7f3f57d55746aa53680553a50bbeb388c07
 SHA512:
-  metadata.gz: d9c175ca8140e4fca246a5ab4c5acad327acfae672adc6c1eec499fd57d2ea552649f364c8e5e3b9a8c12be314fe96a3683296db0e0ace71438b8eb9c25323b5
-  data.tar.gz: f307118a739f0a48bd49f1ea062156406c245b2274522116fc178e1eaad222305bb5ff0ff06b66355d851dd273ce1fbc62fa7ed555dc8c38da0a7af6728b7590
+  metadata.gz: ed7c4c4103648c7debedc89cdf8c34dcbfaff369308133ea04895971cf948aa55086767c224bf1b0f8ded7aa7139ad363898c166585089be0f180e7ae132a78c
+  data.tar.gz: e5ec04d99b161701187b1296a78e7d940d8b4c725cbf3e58c59a9c2e5d10d993a3ed95d24b09b180b10043314cce7ae07541102899660027a104a3672b80dab7

data/.github/FUNDING.yml

@@ -0,0 +1 @@
+github: jaimeiniesta

data/.gitignore

@@ -9,3 +9,4 @@ pkg/*
 .idea/
 .rubocop_todo.yml
 .rubocop.yml
+.tool-versions

data/.travis.yml

@@ -1,6 +1,5 @@
 script: "bundle exec rspec -b"
 rvm:
-- 2.3.6
-- 2.4.3
-- 2.5.0
-- 2.6.4
+- 2.5.8
+- 2.6.6
+- 2.7.1

data/CHANGELOG.md

@@ -1,5 +1,26 @@
 # MetaInpector Changelog
 
+## [Changes in 5.11.2](https://github.com/jaimeiniesta/metainspector/compare/v5.11.1...v5.11.2)
+
+* Relax dependencies to allow minor releases.
+
+## [Changes in 5.11.0](https://github.com/jaimeiniesta/metainspector/compare/v5.11.0...v5.11.1)
+
+* Upgrade to Nokogiri 1.11.0.
+
+## [Changes in 5.11.0](https://github.com/jaimeiniesta/metainspector/compare/v5.10.1...v5.11.0)
+
+* Upgrade to Faraday 1.1.
+
+## [Changes in 5.10.1](https://github.com/jaimeiniesta/metainspector/compare/v5.10.0...v5.10.1)
+
+* Fix for empty base_href. Makes relative links work when base_href is nil but empty ("").
+* Drop support for Ruby 2.4, add support for Ruby 2.7.
+
+## [Changes in 5.10](https://github.com/jaimeiniesta/metainspector/compare/v5.9.0...v5.10.0)
+
+* Upgrade to Faraday 1.0.
+
 ## [Changes in 5.9](https://github.com/jaimeiniesta/metainspector/compare/v5.8.0...v5.9.0)
 
 * Added #feeds method to retrieve all feeds of a page.

data/README.md

@@ -1,4 +1,5 @@
-# MetaInspector [![Build Status](https://secure.travis-ci.org/jaimeiniesta/metainspector.png)](http://travis-ci.org/jaimeiniesta/metainspector) [![Code Climate](https://codeclimate.com/github/jaimeiniesta/metainspector/badges/gpa.svg)](https://codeclimate.com/github/jaimeiniesta/metainspector)
+# MetaInspector
+[![Gem Version](https://badge.fury.io/rb/metainspector.svg)](http://badge.fury.io/rb/metainspector) [![Build Status](https://secure.travis-ci.org/jaimeiniesta/metainspector.png)](http://travis-ci.org/jaimeiniesta/metainspector) [![SemVer](https://api.dependabot.com/badges/compatibility_score?dependency-name=metainspector&package-manager=bundler&version-scheme=semver)](https://dependabot.com/compatibility-score.html?dependency-name=metainspector&package-manager=bundler&version-scheme=semver) [![Code Climate](https://codeclimate.com/github/jaimeiniesta/metainspector/badges/gpa.svg)](https://codeclimate.com/github/jaimeiniesta/metainspector) [![Mentioned in Awesome Ruby](https://awesome.re/mentioned-badge.svg)](https://github.com/markets/awesome-ruby)
 
 MetaInspector is a gem for web scraping purposes.
 
@@ -22,6 +23,8 @@ If you're using it on a Rails application, just add it to your Gemfile and run `
 gem 'metainspector'
 ```
 
+Supported Ruby versions are defined in [`.travis.yml`](.travis.yml).
+
 ## Usage
 
 Initialize a MetaInspector instance for an URL, like this:

data/lib/meta_inspector/parsers/links.rb

@@ -47,7 +47,8 @@ module MetaInspector
       # This can be the one set on a <base> tag,
       # or the url of the document if no <base> tag was found.
       def base_url
-        base_href || url
+        current_base_href = base_href.to_s.strip.empty? ? nil : URL.absolutify(base_href, URL.new(url).root_url)
+        current_base_href || url
       end
 
       # Returns the value of the href attribute on the <base /> tag, if exists

data/lib/meta_inspector/request.rb

@@ -48,7 +48,7 @@ module MetaInspector
       @response ||= fetch
     rescue Faraday::TimeoutError => e
       raise MetaInspector::TimeoutError.new(e)
-    rescue Faraday::Error::ConnectionFailed, Faraday::SSLError, URI::InvalidURIError, FaradayMiddleware::RedirectLimitReached => e
+    rescue Faraday::ConnectionFailed, Faraday::SSLError, URI::InvalidURIError, FaradayMiddleware::RedirectLimitReached => e
       raise MetaInspector::RequestError.new(e)
     end
 

data/lib/meta_inspector/version.rb

@@ -1,3 +1,3 @@
 module MetaInspector
-  VERSION = '5.9.0'
+  VERSION = '5.11.2'
 end

data/meta_inspector.gemspec

@@ -14,20 +14,20 @@ Gem::Specification.new do |gem|
   gem.require_paths = ["lib"]
   gem.version       = MetaInspector::VERSION
 
-  gem.add_dependency 'nokogiri', '~> 1.10.7'
-  gem.add_dependency 'faraday', '~> 0.17.0'
-  gem.add_dependency 'faraday_middleware', '~> 0.13.1'
-  gem.add_dependency 'faraday-cookie_jar', '~> 0.0.6'
-  gem.add_dependency 'faraday-http-cache', '~> 2.0.0'
-  gem.add_dependency 'faraday-encoding', '~> 0.0.5'
-  gem.add_dependency 'addressable', '~> 2.7.0'
-  gem.add_dependency 'fastimage', '~> 2.1.7'
-  gem.add_dependency 'nesty', '~> 1.0.2'
+  gem.add_dependency 'nokogiri', '~> 1.11'
+  gem.add_dependency 'faraday', '~> 1.4'
+  gem.add_dependency 'faraday_middleware', '~> 1.0'
+  gem.add_dependency 'faraday-cookie_jar', '~> 0.0'
+  gem.add_dependency 'faraday-http-cache', '~> 2.2'
+  gem.add_dependency 'faraday-encoding', '~> 0.0'
+  gem.add_dependency 'addressable', '~> 2.7'
+  gem.add_dependency 'fastimage', '~> 2.2'
+  gem.add_dependency 'nesty', '~> 1.0'
 
-  gem.add_development_dependency 'rspec', '~> 3.9.0'
-  gem.add_development_dependency 'webmock', '~> 3.7.6'
-  gem.add_development_dependency 'awesome_print', '~> 1.8.0'
-  gem.add_development_dependency 'rake', '~> 13.0.1'
-  gem.add_development_dependency 'pry', '~> 0.12.2'
-  gem.add_development_dependency 'rubocop', '~> 0.79.0'
+  gem.add_development_dependency 'rspec', '~> 3.10'
+  gem.add_development_dependency 'webmock', '~> 3.13'
+  gem.add_development_dependency 'awesome_print', '~> 1.9'
+  gem.add_development_dependency 'rake', '~> 13.0'
+  gem.add_development_dependency 'pry', '~> 0.14'
+  gem.add_development_dependency 'rubocop', '~> 1.16'
 end

data/spec/fixtures/relative_links_with_empty_base.response

@@ -0,0 +1,22 @@
+HTTP/1.1 200 OK
+Server: nginx/1.0.5
+Date: Thu, 29 Dec 2011 23:10:13 GMT
+Content-Type: text/html
+Content-Length: 15013
+Last-Modified: Fri, 02 Dec 2011 21:00:49 GMT
+Connection: keep-alive
+Accept-Ranges: bytes
+
+<!DOCTYPE html>
+<html>
+<head>
+  <base href=""/>
+  <meta charset="utf-8" />
+  <title>Relative links</title>
+</head>
+<body>
+  <p>Relative links</p>
+  <a href="about">About</a>
+  <a href="../sitemap">Sitemap</a>
+</body>
+</html>

data/spec/fixtures/relative_links_with_relative_dir_base.response

@@ -0,0 +1,22 @@
+HTTP/1.1 200 OK
+Server: nginx/1.0.5
+Date: Thu, 29 Dec 2011 23:10:13 GMT
+Content-Type: text/html
+Content-Length: 15013
+Last-Modified: Fri, 02 Dec 2011 21:00:49 GMT
+Connection: keep-alive
+Accept-Ranges: bytes
+
+<!DOCTYPE html>
+<html>
+<head>
+  <base href="/other/" />
+  <meta charset="utf-8" />
+  <title>Relative links</title>
+</head>
+<body>
+  <p>Relative links</p>
+  <a href="about">About</a>
+  <a href="../sitemap">Sitemap</a>
+</body>
+</html>

data/spec/fixtures/relative_links_with_relative_doc_base.response

@@ -0,0 +1,22 @@
+HTTP/1.1 200 OK
+Server: nginx/1.0.5
+Date: Thu, 29 Dec 2011 23:10:13 GMT
+Content-Type: text/html
+Content-Length: 15013
+Last-Modified: Fri, 02 Dec 2011 21:00:49 GMT
+Connection: keep-alive
+Accept-Ranges: bytes
+
+<!DOCTYPE html>
+<html>
+<head>
+  <base href="/other" />
+  <meta charset="utf-8" />
+  <title>Relative links</title>
+</head>
+<body>
+  <p>Relative links</p>
+  <a href="about">About</a>
+  <a href="../sitemap">Sitemap</a>
+</body>
+</html>

data/spec/fixtures/relative_links_with_relative_root_base.response

@@ -0,0 +1,22 @@
+HTTP/1.1 200 OK
+Server: nginx/1.0.5
+Date: Thu, 29 Dec 2011 23:10:13 GMT
+Content-Type: text/html
+Content-Length: 15013
+Last-Modified: Fri, 02 Dec 2011 21:00:49 GMT
+Connection: keep-alive
+Accept-Ranges: bytes
+
+<!DOCTYPE html>
+<html>
+<head>
+  <base href="/" />
+  <meta charset="utf-8" />
+  <title>Relative links</title>
+</head>
+<body>
+  <p>Relative links</p>
+  <a href="about">About</a>
+  <a href="../sitemap">Sitemap</a>
+</body>
+</html>

data/spec/meta_inspector/links_spec.rb

@@ -145,6 +145,13 @@ describe MetaInspector do
     end
   end
 
+  describe 'Relative links with empty or blank base' do
+    it 'should get the relative links from a document' do
+      m = MetaInspector.new('http://relativewithemptybase.com/company')
+      expect(m.links.internal).to eq(['http://relativewithemptybase.com/about', 'http://relativewithemptybase.com/sitemap'])
+    end
+  end
+
   describe 'Relative links with base' do
     it 'should get the relative links from a document' do
       m = MetaInspector.new('http://relativewithbase.com/company/page2')
@@ -157,6 +164,26 @@ describe MetaInspector do
     end
   end
 
+  describe 'Relative links with relative base' do
+    it 'should get the relative links with relative directory base' do
+      m = MetaInspector.new('http://relativewithrelativebase.com/relativedir')
+      expect(m.links.all).to eq(['http://relativewithrelativebase.com/other/about',
+                                 'http://relativewithrelativebase.com/sitemap'])
+    end
+
+    it 'should get the relative links with relative document base' do
+      m = MetaInspector.new('http://relativewithrelativebase.com/relativedoc')
+      expect(m.links.all).to eq(['http://relativewithrelativebase.com/about',
+                                 'http://relativewithrelativebase.com/sitemap'])
+    end
+
+    it 'should get the relative links with relative root base' do
+      m = MetaInspector.new('http://relativewithrelativebase.com/')
+      expect(m.links.all).to eq(['http://relativewithrelativebase.com/about',
+                                 'http://relativewithrelativebase.com/sitemap'])
+    end
+  end
+
   describe 'Non-HTTP links' do
     before(:each) do
       @m = MetaInspector.new('http://example.com/nonhttp')

data/spec/spec_helper.rb

@@ -65,6 +65,10 @@ RSpec.configure do |config|
     stub_request(:get, "http://relativewithbase.com/").to_return(fixture_file("relative_links_with_base.response"))
     stub_request(:get, "http://relativewithbase.com/company/page2").to_return(fixture_file("relative_links_with_base.response"))
     stub_request(:get, "http://relativewithbase.com/company/page2/").to_return(fixture_file("relative_links_with_base.response"))
+    stub_request(:get, "http://relativewithemptybase.com/company").to_return(fixture_file("relative_links_with_empty_base.response"))
+    stub_request(:get, "http://relativewithrelativebase.com/relativedoc").to_return(fixture_file("relative_links_with_relative_doc_base.response"))
+    stub_request(:get, "http://relativewithrelativebase.com/relativedir").to_return(fixture_file("relative_links_with_relative_dir_base.response"))
+    stub_request(:get, "http://relativewithrelativebase.com/").to_return(fixture_file("relative_links_with_relative_root_base.response"))
     stub_request(:get, "http://theonion-no-description.com").to_return(fixture_file("theonion-no-description.com.response"))
     stub_request(:get, "http://www.24-horas.mx/mexico-firma-acuerdo-bilateral-automotriz-con-argentina/").to_return(fixture_file("relative_og_image.response"))
     stub_request(:get, "http://www.alazan.com").to_return(fixture_file("alazan.com.response"))

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: metainspector
 version: !ruby/object:Gem::Version
-  version: 5.9.0
+  version: 5.11.2
 platform: ruby
 authors:
 - Jaime Iniesta
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-01-21 00:00:00.000000000 Z
+date: 2021-07-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -16,210 +16,210 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.10.7
+        version: '1.11'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.10.7
+        version: '1.11'
 - !ruby/object:Gem::Dependency
   name: faraday
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.17.0
+        version: '1.4'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.17.0
+        version: '1.4'
 - !ruby/object:Gem::Dependency
   name: faraday_middleware
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.13.1
+        version: '1.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.13.1
+        version: '1.0'
 - !ruby/object:Gem::Dependency
   name: faraday-cookie_jar
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.0.6
+        version: '0.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.0.6
+        version: '0.0'
 - !ruby/object:Gem::Dependency
   name: faraday-http-cache
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.0.0
+        version: '2.2'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.0.0
+        version: '2.2'
 - !ruby/object:Gem::Dependency
   name: faraday-encoding
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.0.5
+        version: '0.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.0.5
+        version: '0.0'
 - !ruby/object:Gem::Dependency
   name: addressable
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.7.0
+        version: '2.7'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.7.0
+        version: '2.7'
 - !ruby/object:Gem::Dependency
   name: fastimage
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.1.7
+        version: '2.2'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.1.7
+        version: '2.2'
 - !ruby/object:Gem::Dependency
   name: nesty
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.0.2
+        version: '1.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.0.2
+        version: '1.0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 3.9.0
+        version: '3.10'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 3.9.0
+        version: '3.10'
 - !ruby/object:Gem::Dependency
   name: webmock
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 3.7.6
+        version: '3.13'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 3.7.6
+        version: '3.13'
 - !ruby/object:Gem::Dependency
   name: awesome_print
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.8.0
+        version: '1.9'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.8.0
+        version: '1.9'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 13.0.1
+        version: '13.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 13.0.1
+        version: '13.0'
 - !ruby/object:Gem::Dependency
   name: pry
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.12.2
+        version: '0.14'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.12.2
+        version: '0.14'
 - !ruby/object:Gem::Dependency
   name: rubocop
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.79.0
+        version: '1.16'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.79.0
+        version: '1.16'
 description: MetaInspector lets you scrape a web page and get its links, images, texts,
   meta tags...
 email: jaimeiniesta@gmail.com
@@ -227,6 +227,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/FUNDING.yml"
 - ".gitignore"
 - ".rspec.example"
 - ".rubocop.yml.example"
@@ -302,6 +303,10 @@ files:
 - spec/fixtures/protocol_relative.response
 - spec/fixtures/relative_links.response
 - spec/fixtures/relative_links_with_base.response
+- spec/fixtures/relative_links_with_empty_base.response
+- spec/fixtures/relative_links_with_relative_dir_base.response
+- spec/fixtures/relative_links_with_relative_doc_base.response
+- spec/fixtures/relative_links_with_relative_root_base.response
 - spec/fixtures/relative_og_image.response
 - spec/fixtures/theonion-no-description.com.response
 - spec/fixtures/theonion.com.response
@@ -332,7 +337,7 @@ homepage: https://github.com/metainspector/metainspector
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -347,8 +352,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.4
-signing_key: 
+rubygems_version: 3.2.15
+signing_key:
 specification_version: 4
 summary: MetaInspector is a ruby gem for web scraping purposes, that returns metadata
   from a given URL