metainspector 5.14.0 → 5.16.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 71467ae16d368978ce8ee13d605c95a12be2fc207a7d7c28e5243658f70a0837
-  data.tar.gz: f7774783e9c4e7282ce5c10683fdcd521ee483f0becb9c8bdce45d276920af30
+  metadata.gz: 8311486a8156f619d20a7cc93283e57ae055dd9fdcb222e14d3900adfae6d6a2
+  data.tar.gz: 9f1288adf02bc224d5d5e6915a0c24aaab342cabe3d6a85e07989f553966324a
 SHA512:
-  metadata.gz: b623421b6f265833566eba954bb1d3bae0a00032720950a0a97316fd2e493ec98b5de46b4a48c9c0a7b28158101e8aecd4991e0043ca2601e75d387df97a769e
-  data.tar.gz: 84cb6be32451c083adfa5ccb01e1746485a67e55fa9a1d56b1b2d496fec6154bfbf60f947c72a8c9ec8ea48e616641dcc30dc3b3579d1ef953475cc85354e8da
+  metadata.gz: 0ef843e07a8af813a4ed27f18b53eab03f5bfeaa60af5014fb3474346f3d02081891b94828ea034ffd7c5734f40c4fcb0e4028a2ccfe682152408d8f69820aec
+  data.tar.gz: c8da85989e7c11ad7bccff3d9f53c94daf75962492c4fa0d54550db2a02bee7928747b36354c89d47f0875c459310ea404bea9154f7e3cbd414b489fb45110e3

data/.circleci/config.yml

@@ -2,36 +2,27 @@ version: 2.1
 orbs:
   ruby: circleci/ruby@1.0.4
 jobs:
-  test_2_6:
-    docker:
-      - image: cimg/ruby:2.6.10
-    steps:
-      - checkout
-      - ruby/install-deps
-      - run:
-          name: Run tests
-          command: bundle exec rake
-  test_2_7:
+  test_3_1:
     docker:
-      - image: cimg/ruby:2.7.6
+      - image: cimg/ruby:3.1.7
     steps:
       - checkout
       - ruby/install-deps
       - run:
           name: Run tests
           command: bundle exec rake
-  test_3_0:
+  test_3_2:
     docker:
-      - image: cimg/ruby:3.0.4
+      - image: cimg/ruby:3.2.6
     steps:
       - checkout
       - ruby/install-deps
       - run:
           name: Run tests
           command: bundle exec rake
-  test_3_1:
+  test_3_3:
     docker:
-      - image: cimg/ruby:3.1.2
+      - image: cimg/ruby:3.3.8
     steps:
       - checkout
       - ruby/install-deps
@@ -42,7 +33,6 @@ workflows:
   version: 2
   deploy:
     jobs:
-      - test_2_6
-      - test_2_7
-      - test_3_0
-      - test_3_1
+      - test_3_1
+      - test_3_2
+      - test_3_3

data/CHANGELOG.md

@@ -1,15 +1,28 @@
-# MetaInpector Changelog
+# MetaInspector Changelog
 
-## [Changes in 5.13.0](https://github.com/metainspector/metainspector/compare/v5.12.1...v5.13.0)
+## [Changes in 5.16.0](https://github.com/jaimeiniesta/metainspector/compare/v5.15.0...v5.16.0)
+
+* Upgraded dependencies and supported Ruby versions.
+
+## [Changes in 5.15.0](https://github.com/jaimeiniesta/metainspector/compare/v5.14.0...v5.15.0)
+
+* Added mechanism to use all available options in the `FollowRedirects` Faraday middleware,
+https://github.com/jaimeiniesta/metainspector/pull/355 thanks to @bruno-b-martins and @miguelrod
+
+## [Changes in 5.14.0](https://github.com/jaimeiniesta/metainspector/compare/v5.13.0...v5.14.0)
+
+* Several dependency updates, including Addressable 2.8.1 which fixes invalid_byte_sequence exception.
+
+## [Changes in 5.13.0](https://github.com/jaimeiniesta/metainspector/compare/v5.12.1...v5.13.0)
 
 * Remove support for #feed that was deprecated in 5.9
 * Add support for Ruby 3.1
 
-## [Changes in 5.12.1](https://github.com/metainspector/metainspector/compare/v5.12.0...v5.12.1)
+## [Changes in 5.12.1](https://github.com/jaimeiniesta/metainspector/compare/v5.12.0...v5.12.1)
 
 * Update dependencies: rubocop, nokogiri
 
-## [Changes in 5.12.0](https://github.com/metainspector/metainspector/compare/v5.11.2...v5.12.0)
+## [Changes in 5.12.0](https://github.com/jaimeiniesta/metainspector/compare/v5.11.2...v5.12.0)
 
 * Support Ruby 3.0
 

data/Gemfile.lock

@@ -1,23 +1,23 @@
 PATH
   remote: .
   specs:
-    metainspector (5.14.0)
-      addressable (~> 2.8)
+    metainspector (5.16.0)
+      addressable (~> 2.8.4)
       faraday (~> 2.5)
       faraday-cookie_jar (~> 0.0)
       faraday-encoding (~> 0.0)
       faraday-follow_redirects (~> 0.3)
-      faraday-gzip (>= 0.1, < 2.0)
-      faraday-http-cache (~> 2.4)
+      faraday-gzip (>= 0.1, < 3.0)
+      faraday-http-cache (~> 2.5)
       faraday-retry (~> 2.0)
       fastimage (~> 2.2)
       nesty (~> 1.0)
-      nokogiri (~> 1.13)
+      nokogiri (~> 1.18.8)
 
 GEM
   remote: http://rubygems.org/
   specs:
-    addressable (2.8.1)
+    addressable (2.8.5)
       public_suffix (>= 2.0.2, < 6.0)
     ast (2.4.2)
     awesome_print (1.9.2)
@@ -25,49 +25,64 @@ GEM
     crack (0.4.5)
       rexml
     diff-lcs (1.5.0)
-    domain_name (0.5.20190701)
-      unf (>= 0.0.5, < 1.0.0)
-    faraday (2.7.4)
-      faraday-net_http (>= 2.0, < 3.1)
-      ruby2_keywords (>= 0.0.4)
+    domain_name (0.6.20240107)
+    faraday (2.13.1)
+      faraday-net_http (>= 2.0, < 3.5)
+      json
+      logger
     faraday-cookie_jar (0.0.7)
       faraday (>= 0.8.0)
       http-cookie (~> 1.0.0)
-    faraday-encoding (0.0.5)
+    faraday-encoding (0.0.6)
       faraday
     faraday-follow_redirects (0.3.0)
       faraday (>= 1, < 3)
-    faraday-gzip (1.0.0)
+    faraday-gzip (2.0.1)
       faraday (>= 1.0)
-      zlib (~> 2.1)
-    faraday-http-cache (2.4.1)
+      zlib (~> 3.0)
+    faraday-http-cache (2.5.1)
       faraday (>= 0.8)
-    faraday-net_http (3.0.2)
-    faraday-retry (2.0.0)
+    faraday-net_http (3.4.0)
+      net-http (>= 0.5.0)
+    faraday-retry (2.3.1)
       faraday (~> 2.0)
-    fastimage (2.2.6)
+    fastimage (2.4.0)
     hashdiff (1.0.1)
-    http-cookie (1.0.5)
+    http-cookie (1.0.8)
       domain_name (~> 0.5)
-    json (2.6.3)
+    json (2.7.1)
+    language_server-protocol (3.17.0.3)
+    logger (1.7.0)
     method_source (1.0.0)
-    mini_portile2 (2.8.1)
+    mustermann (3.0.0)
+      ruby2_keywords (~> 0.0.1)
     nesty (1.0.2)
-    nokogiri (1.14.2)
-      mini_portile2 (~> 2.8.0)
+    net-http (0.6.0)
+      uri
+    nio4r (2.5.9)
+    nokogiri (1.18.8-arm64-darwin)
       racc (~> 1.4)
-    parallel (1.22.1)
-    parser (3.2.1.0)
+    nokogiri (1.18.8-x86_64-linux-gnu)
+      racc (~> 1.4)
+    parallel (1.24.0)
+    parser (3.3.0.5)
       ast (~> 2.4.1)
+      racc
     pry (0.14.2)
       coderay (~> 1.1)
       method_source (~> 1.0)
-    public_suffix (5.0.1)
-    racc (1.6.2)
+    public_suffix (5.0.3)
+    puma (6.4.0)
+      nio4r (~> 2.0)
+    racc (1.8.1)
+    rack (2.2.14)
+    rack-protection (3.0.6)
+      rack
     rainbow (3.1.1)
-    rake (13.0.6)
-    regexp_parser (2.7.0)
-    rexml (3.2.5)
+    rake (13.1.0)
+    regexp_parser (2.9.0)
+    resolv (0.2.2)
+    rexml (3.2.6)
     rspec (3.12.0)
       rspec-core (~> 3.12.0)
       rspec-expectations (~> 3.12.0)
@@ -81,40 +96,50 @@ GEM
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.12.0)
     rspec-support (3.12.0)
-    rubocop (1.46.0)
+    rubocop (1.62.0)
       json (~> 2.3)
+      language_server-protocol (>= 3.17.0)
       parallel (~> 1.10)
-      parser (>= 3.2.0.0)
+      parser (>= 3.3.0.2)
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 1.8, < 3.0)
       rexml (>= 3.2.5, < 4.0)
-      rubocop-ast (>= 1.26.0, < 2.0)
+      rubocop-ast (>= 1.31.1, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 2.4.0, < 3.0)
-    rubocop-ast (1.26.0)
-      parser (>= 3.2.1.0)
-    ruby-progressbar (1.11.0)
+    rubocop-ast (1.31.1)
+      parser (>= 3.3.0.4)
+    ruby-progressbar (1.13.0)
     ruby2_keywords (0.0.5)
-    unf (0.1.4)
-      unf_ext
-    unf_ext (0.0.8.2)
-    unicode-display_width (2.4.2)
+    sinatra (3.0.6)
+      mustermann (~> 3.0)
+      rack (~> 2.2, >= 2.2.4)
+      rack-protection (= 3.0.6)
+      tilt (~> 2.0)
+    tilt (2.1.0)
+    unicode-display_width (2.5.0)
+    uri (1.0.3)
     webmock (3.18.1)
       addressable (>= 2.8.0)
       crack (>= 0.3.2)
       hashdiff (>= 0.4.0, < 2.0.0)
-    zlib (2.1.1)
+    zlib (3.2.1)
 
 PLATFORMS
-  ruby
+  arm64-darwin-22
+  arm64-darwin-24
+  x86_64-linux
 
 DEPENDENCIES
   awesome_print (~> 1.9)
   metainspector!
   pry (~> 0.14)
+  puma (~> 6.4.0)
   rake (~> 13.0)
+  resolv (~> 0.2.2)
   rspec (~> 3.11)
   rubocop (~> 1.34)
+  sinatra (~> 3.0.6)
   webmock (~> 3.17)
 
 BUNDLED WITH

data/README.md

@@ -1,14 +1,10 @@
 # MetaInspector
-[![Gem Version](https://badge.fury.io/rb/metainspector.svg)](http://badge.fury.io/rb/metainspector) [![CircleCI](https://circleci.com/gh/metainspector/metainspector.svg?style=svg)](https://circleci.com/gh/metainspector/metainspector) [![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)
+[![Gem Version](https://badge.fury.io/rb/metainspector.svg)](http://badge.fury.io/rb/metainspector) [![CircleCI](https://circleci.com/gh/jaimeiniesta/metainspector.svg?style=svg)](https://circleci.com/gh/jaimeiniesta/metainspector) [![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.
 
 You give it an URL, and it lets you easily get its title, links, images, charset, description, keywords, meta tags...
 
-## See it in action!
-
-You can try MetaInspector using this little demo: [https://github.com/metainspector/metainspectordemo](https://github.com/metainspector/metainspectordemo)
-
 ## Installation
 
 Install the gem from RubyGems:
@@ -23,7 +19,7 @@ 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).
+Supported Ruby versions are defined in [`.circleci/config.yml`](.circleci/config.yml).
 
 ## Usage
 
@@ -309,6 +305,27 @@ If you want to disallow redirects, you can do it like this:
 page = MetaInspector.new('facebook.com', :allow_redirections => false)
 ```
 
+You can also customize how many redirects you wish to allow:
+
+```ruby
+page = MetaInspector.new('facebook.com', :faraday_options => { redirect: { limit: 5 } })
+```
+
+And even customize what to do in between each redirect:
+
+```ruby
+callback = proc do |previous_response, next_request|
+  ip_address = Resolv.getaddress(next_request.url.host)
+  raise 'Invalid address' if IPAddr.new(ip_address).private?
+end
+
+page = MetaInspector.new(url, faraday_options: { redirect: { callback: callback } })
+```
+
+
+The `faraday_options[:redirect]` hash is passed to the `FollowRedirects` middleware used by `Faraday`, so that we can use all available options.
+Check them [here](https://github.com/lostisland/faraday_middleware/blob/main/lib/faraday_middleware/response/follow_redirects.rb#L44).
+
 ### Headers
 
 By default, the following headers are set:

data/examples/faraday_redirect_options.rb

@@ -0,0 +1,42 @@
+# A MetaInspector example that runs a callback in between redirects.
+# The callback raises an exception if the redirection points to a URL that resolves into a private IP address.
+# This is one way of triggering a known security exploit called server-side request forgery (SSRF).
+#
+# To properly run this example you need a server which redirects to a service like nip.io.
+# The easiest way to achieve that is running the examples/redirect_web_server.rb server in one terminal window,
+# and calling its address with this example in another terminal window.
+#
+# Usage example:
+#   In terminal #1:
+#   ruby redirect_web_server.rb
+#
+#   In terminal #2:
+#   ruby faraday_redirect_options.rb http://127.0.0.1:4567
+
+require 'resolv'
+require '../lib/metainspector'
+puts "Using MetaInspector #{MetaInspector::VERSION}"
+
+# Get the starting URL
+url = ARGV[0] || (puts "Enter an url"; gets.strip)
+
+# redirect options to be passed along to Faraday::FollowRedirects::Middleware
+redirects_opts = {
+  limit: 5,
+  callback: proc do |_old_response, new_response|
+    ip_address = Resolv.getaddress(new_response.url.host)
+    raise 'Invalid address' if IPAddr.new(ip_address).private?
+  end
+}
+
+begin
+  page = MetaInspector.new(url, faraday_options: { redirect: redirects_opts })
+rescue StandardError => e
+  puts e.message
+else
+  puts "\nScraping #{page.url} returned these results:"
+  puts "\nTITLE: #{page.title}"
+
+  puts "\nto_hash..."
+  puts page.to_hash
+end

data/examples/redirect_web_server.rb

@@ -0,0 +1,5 @@
+require 'sinatra'
+
+get '/' do
+  redirect 'http://10.0.0.0.nip.io/'
+end

data/lib/meta_inspector/request.rb

@@ -58,6 +58,7 @@ module MetaInspector
     def fetch
       Timeout::timeout(fatal_timeout) do
         @faraday_options.merge!(:url => url)
+        follow_redirects_options = @faraday_options.delete(:redirect) || {}
 
         session = Faraday.new(@faraday_options) do |faraday|
           faraday.request :retry, max: @retries
@@ -65,7 +66,8 @@ module MetaInspector
           faraday.request :gzip
 
           if @allow_redirections
-            faraday.use Faraday::FollowRedirects::Middleware, limit: 10
+            follow_redirects_options[:limit] ||= 10
+            faraday.use Faraday::FollowRedirects::Middleware, **follow_redirects_options
             faraday.use :cookie_jar
           end
 
@@ -84,7 +86,9 @@ module MetaInspector
           req.options.open_timeout = @read_timeout
         end
 
-        @url.url = response.env.url.to_s
+        if @allow_redirections
+          @url.url = response.env.url.to_s
+        end
 
         response
       end

data/lib/meta_inspector/version.rb

@@ -1,3 +1,3 @@
 module MetaInspector
-  VERSION = '5.14.0'
+  VERSION = '5.16.0'
 end

data/meta_inspector.gemspec

@@ -5,7 +5,7 @@ Gem::Specification.new do |gem|
   gem.email         = "jaimeiniesta@gmail.com"
   gem.description   = %q{MetaInspector lets you scrape a web page and get its links, images, texts, meta tags...}
   gem.summary       = %q{MetaInspector is a ruby gem for web scraping purposes, that returns metadata from a given URL}
-  gem.homepage      = "https://github.com/metainspector/metainspector"
+  gem.homepage      = "https://github.com/jaimeiniesta/metainspector"
   gem.license       = "MIT"
 
   gem.files         = `git ls-files`.split("\n")
@@ -14,15 +14,15 @@ Gem::Specification.new do |gem|
   gem.require_paths = ["lib"]
   gem.version       = MetaInspector::VERSION
 
-  gem.add_dependency 'nokogiri', '~> 1.13'
+  gem.add_dependency 'nokogiri', '~> 1.18.8'
   gem.add_dependency 'faraday', '~> 2.5'
   gem.add_dependency 'faraday-cookie_jar', '~> 0.0'
   gem.add_dependency 'faraday-encoding', '~> 0.0'
   gem.add_dependency 'faraday-follow_redirects', '~> 0.3'
-  gem.add_dependency 'faraday-gzip', '>= 0.1', '< 2.0'
-  gem.add_dependency 'faraday-http-cache', '~> 2.4'
+  gem.add_dependency 'faraday-gzip', '>= 0.1', '< 3.0'
+  gem.add_dependency 'faraday-http-cache', '~> 2.5'
   gem.add_dependency 'faraday-retry', '~> 2.0'
-  gem.add_dependency 'addressable', '~> 2.8'
+  gem.add_dependency 'addressable', '~> 2.8.4'
   gem.add_dependency 'fastimage', '~> 2.2'
   gem.add_dependency 'nesty', '~> 1.0'
 
@@ -31,5 +31,8 @@ Gem::Specification.new do |gem|
   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 'puma', '~> 6.4.0'
   gem.add_development_dependency 'rubocop', '~> 1.34'
+  gem.add_development_dependency 'resolv', '~> 0.2.2'
+  gem.add_development_dependency 'sinatra', '~> 3.0.6'
 end

data/spec/document_spec.rb

@@ -130,11 +130,11 @@ describe MetaInspector::Document do
 
   describe 'url normalization' do
     it 'should normalize by default' do
-      expect(MetaInspector.new('http://example.com/%EF%BD%9E').url).to eq('http://example.com/~')
+      expect(MetaInspector.new('http://example.com?name=joe martins', allow_redirections: false).url).to eq('http://example.com/?name=joe%20martins')
     end
 
     it 'should not normalize if the normalize_url option is false' do
-      expect(MetaInspector.new('http://example.com/%EF%BD%9E', normalize_url: false).url).to eq('http://example.com/%EF%BD%9E')
+      expect(MetaInspector.new('http://example.com?name=joe martins', normalize_url: false, allow_redirections: false).url).to eq('http://example.com?name=joe martins')
     end
   end
 

data/spec/meta_inspector/links_spec.rb

@@ -52,29 +52,35 @@ describe MetaInspector do
       it "should get correct absolute links, encoding the URLs as needed" do
         m = MetaInspector.new('http://international.com')
 
-        expect(m.links.internal).to eq([ "http://international.com/espa%C3%B1a.asp",
-                                       "http://international.com/roman%C3%A9e",
-                                       "http://international.com/faqs#cami%C3%B3n",
-                                       "http://international.com/search?q=cami%C3%B3n",
-                                       "http://international.com/search?q=espa%C3%B1a#top",
-                                       "http://international.com/index.php?q=espa%C3%B1a&url=aHR0zZQ==&cntnt01pageid=21"])
-
-        expect(m.links.external).to eq([ "http://example.com/espa%C3%B1a.asp",
-                                       "http://example.com/roman%C3%A9e",
-                                       "http://example.com/faqs#cami%C3%B3n",
-                                       "http://example.com/search?q=cami%C3%B3n",
-                                       "http://example.com/search?q=espa%C3%B1a#top"])
+        expect(m.links.internal).to eq([
+          "http://international.com/espa%C3%83%C2%B1a.asp",
+          "http://international.com/roman%C3%83%C2%A9e",
+          "http://international.com/faqs#cami%C3%83%C2%B3n",
+          "http://international.com/search?q=cami%C3%83%C2%B3n",
+          "http://international.com/search?q=espa%C3%83%C2%B1a#top",
+          "http://international.com/index.php?q=espa%C3%83%C2%B1a&url=aHR0zZQ==&cntnt01pageid=21"
+        ])
+
+        expect(m.links.external).to eq([
+          "http://example.com/espa%C3%83%C2%B1a.asp",
+          "http://example.com/roman%C3%83%C2%A9e",
+          "http://example.com/faqs#cami%C3%83%C2%B3n",
+          "http://example.com/search?q=cami%C3%83%C2%B3n",
+          "http://example.com/search?q=espa%C3%83%C2%B1a#top"])
       end
 
       describe "internal links" do
         it "should get correct internal links, encoding the URLs as needed but respecting # and ?" do
           m = MetaInspector.new('http://international.com')
-          expect(m.links.internal).to eq([ "http://international.com/espa%C3%B1a.asp",
-                                       "http://international.com/roman%C3%A9e",
-                                       "http://international.com/faqs#cami%C3%B3n",
-                                       "http://international.com/search?q=cami%C3%B3n",
-                                       "http://international.com/search?q=espa%C3%B1a#top",
-                                       "http://international.com/index.php?q=espa%C3%B1a&url=aHR0zZQ==&cntnt01pageid=21"])
+
+          expect(m.links.internal).to eq([
+            "http://international.com/espa%C3%83%C2%B1a.asp",
+            "http://international.com/roman%C3%83%C2%A9e",
+            "http://international.com/faqs#cami%C3%83%C2%B3n",
+            "http://international.com/search?q=cami%C3%83%C2%B3n",
+            "http://international.com/search?q=espa%C3%83%C2%B1a#top",
+            "http://international.com/index.php?q=espa%C3%83%C2%B1a&url=aHR0zZQ==&cntnt01pageid=21"
+          ])
         end
 
         it "should not crash when processing malformed hrefs" do
@@ -86,11 +92,14 @@ describe MetaInspector do
       describe "external links" do
         it "should get correct external links, encoding the URLs as needed but respecting # and ?" do
           m = MetaInspector.new('http://international.com')
-          expect(m.links.external).to eq([ "http://example.com/espa%C3%B1a.asp",
-                                       "http://example.com/roman%C3%A9e",
-                                       "http://example.com/faqs#cami%C3%B3n",
-                                       "http://example.com/search?q=cami%C3%B3n",
-                                       "http://example.com/search?q=espa%C3%B1a#top"])
+
+          expect(m.links.external).to eq([
+            "http://example.com/espa%C3%83%C2%B1a.asp",
+            "http://example.com/roman%C3%83%C2%A9e",
+            "http://example.com/faqs#cami%C3%83%C2%B3n",
+            "http://example.com/search?q=cami%C3%83%C2%B3n",
+            "http://example.com/search?q=espa%C3%83%C2%B1a#top"
+          ])
         end
 
         it "should not crash when processing malformed hrefs" do
@@ -108,7 +117,7 @@ describe MetaInspector do
 
     it "should handle links that have an invalid byte sequence" do
       m = MetaInspector.new('http://example.com/invalid_byte_seq')
-      expect(m.links.all).to eq(["http://pagerankalert.posterous.com/", "http://element%B3wgarderoby.com/", "http://twitter.com/pagerankalert"])
+      expect(m.links.all).to eq(["http://pagerankalert.posterous.com/", "http://twitter.com/pagerankalert"])
     end
 
   end

data/spec/meta_inspector/redirections_spec.rb

@@ -1,4 +1,7 @@
 require 'spec_helper'
+require 'resolv'
+
+class PrivateIPAddressError < StandardError; end
 
 describe MetaInspector do
   describe "redirections" do
@@ -47,6 +50,25 @@ describe MetaInspector do
         expect(page.url).to eq("http://blogs.clarionledger.com/dechols/2014/03/24/digital-medicine/?nclick_check=1")
       end
     end
+
+    context "when there is a callback to be ran between redirects that blocks redirections to private IP addresses" do
+      it "raises an exception" do
+        stub_request(:get, "https://www.facebook.com/")
+          .to_return(:status => 302,
+                     :headers => { "Location" => "http://10.0.0.0/" })
+
+        redirect_options = {
+          callback: proc do |_previous_response, next_request|
+            ip_address = Resolv.getaddress(next_request.url.host)
+            raise PrivateIPAddressError if IPAddr.new(ip_address).private?
+          end
+        }
+
+        expect {
+          MetaInspector.new("https://www.facebook.com/", faraday_options: { redirect: redirect_options })
+        }.to raise_error PrivateIPAddressError
+      end
+    end
   end
 
   private

data/spec/spec_helper.rb

@@ -50,7 +50,8 @@ RSpec.configure do |config|
     stub_request(:get, "http://example.com/author_in_body").to_return(fixture_file("author_in_body.response"))
     stub_request(:get, "http://example.com/author_in_link").to_return(fixture_file("author_in_link.response"))
     stub_request(:get, "http://example.com/author_in_twitter").to_return(fixture_file("author_in_twitter.response"))
-    stub_request(:get, "http://example.com/~").to_return(fixture_file("example.response"))
+    stub_request(:get, "http://example.com/?name=joe martins").to_return(fixture_file("example.response"))
+    stub_request(:get, "http://example.com/?name=joe+martins").to_return(fixture_file("example.response"))
     stub_request(:get, "http://facebook.com/").to_return(fixture_file("facebook.com.response"))
     stub_request(:get, "http://international.com").to_return(fixture_file("international.response"))
     stub_request(:get, "http://pagerankalert-shortcut-and-icon.com").to_return(fixture_file("pagerankalert-shortcut-and-icon.com.response"))

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: metainspector
 version: !ruby/object:Gem::Version
-  version: 5.14.0
+  version: 5.16.0
 platform: ruby
 authors:
 - Jaime Iniesta
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-02-27 00:00:00.000000000 Z
+date: 2025-05-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.13'
+        version: 1.18.8
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.13'
+        version: 1.18.8
 - !ruby/object:Gem::Dependency
   name: faraday
   requirement: !ruby/object:Gem::Requirement
@@ -89,7 +89,7 @@ dependencies:
         version: '0.1'
     - - "<"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -99,21 +99,21 @@ dependencies:
         version: '0.1'
     - - "<"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.0'
 - !ruby/object:Gem::Dependency
   name: faraday-http-cache
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.4'
+        version: '2.5'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.4'
+        version: '2.5'
 - !ruby/object:Gem::Dependency
   name: faraday-retry
   requirement: !ruby/object:Gem::Requirement
@@ -134,14 +134,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.8'
+        version: 2.8.4
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.8'
+        version: 2.8.4
 - !ruby/object:Gem::Dependency
   name: fastimage
   requirement: !ruby/object:Gem::Requirement
@@ -240,6 +240,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.14'
+- !ruby/object:Gem::Dependency
+  name: puma
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 6.4.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 6.4.0
 - !ruby/object:Gem::Dependency
   name: rubocop
   requirement: !ruby/object:Gem::Requirement
@@ -254,6 +268,34 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.34'
+- !ruby/object:Gem::Dependency
+  name: resolv
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.2.2
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.2.2
+- !ruby/object:Gem::Dependency
+  name: sinatra
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.0.6
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.0.6
 description: MetaInspector lets you scrape a web page and get its links, images, texts,
   meta tags...
 email: jaimeiniesta@gmail.com
@@ -275,7 +317,9 @@ files:
 - Rakefile
 - bin/console
 - examples/basic_scraping.rb
+- examples/faraday_redirect_options.rb
 - examples/link_checker.rb
+- examples/redirect_web_server.rb
 - examples/spider.rb
 - lib/meta_inspector.rb
 - lib/meta_inspector/document.rb
@@ -369,7 +413,7 @@ files:
 - spec/request_spec.rb
 - spec/spec_helper.rb
 - spec/url_spec.rb
-homepage: https://github.com/metainspector/metainspector
+homepage: https://github.com/jaimeiniesta/metainspector
 licenses:
 - MIT
 metadata: {}
@@ -388,7 +432,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.7
+rubygems_version: 3.5.22
 signing_key:
 specification_version: 4
 summary: MetaInspector is a ruby gem for web scraping purposes, that returns metadata