url_scrubber 0.8.15 → 0.8.20

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 608b40e9de605ac987e39f8fa5b1640d6543c8dc8a83553f2689f2fbe716b50a
-  data.tar.gz: d6d1c7905a4875ef9fb6f2ce7ab03f18ff31e524b180c3e13bd10467513c79b8
+  metadata.gz: 5392c3c6b9af7ba8d175315c846027174b8801d0a8371525a6c7eb1eb0e115be
+  data.tar.gz: dc671761ac0e450afd851a1c8890db403b68a47af341485408ba10f01e24f056
 SHA512:
-  metadata.gz: f6f43dd74cec24acd3f7e2a376b89476f00eb09e627a96c55ba5ec0e97c7ccc994385858183c13230a98066d2b687a462225a3347f6aa27d36f8a668eaef087c
-  data.tar.gz: 395a1561434cc85197f10211393cfdaabea3e35fb50a2559f0c0c3dd669aea3cd13b8e68192a4eda105a2abce1c7476bde167ad00c8704d0e62052ce92ca94ba
+  metadata.gz: 6d0b8e970868607dea54065027ef662a59780b88db21cfb36e933cff0086ecaedac63e1f23e588e6a7f9d0bcb649950385b5351e354116e825ff65649adad1a1
+  data.tar.gz: 70fcdd156dc4aa2aae15a0b16e0a8e70fdd14808003840719ed9cbda415113fcf94ca26facff5d34a4fa26ef7ce568037a945d09f22c7ececf64dec075e6529b

data/lib/url_scrubber.rb

@@ -12,7 +12,7 @@ module UrlScrubber
 
     url = url.clone # don't modify the original argument
 
-    m = url.match(/(htt?ps?:\/\/\S*)/i)
+    m = url.match(/(htt?ps?:\/\/\S+)/i)
     return nil unless m
 
     url = m[1]
@@ -48,6 +48,8 @@ module UrlScrubber
       when 'tumblr'             then return :tumblr
       when 'twitter'            then return :twitter
       when 'vimeo'              then return :vimeo
+      when 'vk'                 then return :vkontakte
+      when 'weibo'              then return :weibo
       when 'yelp'               then return :yelp
       when 'youtube'            then return :youtube
       end
@@ -69,6 +71,10 @@ module UrlScrubber
     return false unless url
 
     case service_of(url)
+    when :vkontakte
+      !!url.match(%r{^http://vk\.com/[\w_]+$})
+    when :weibo
+      !!url.match(%r{^http://weibo\.com/[\w_-]+$})
     when :youtube
       !!url.match(%r{^http://youtube\.com/[\w_-]+$})
     when :twitter
@@ -279,13 +285,15 @@ module UrlScrubber
 
   # TODO This needs to be rewritten to be independent of the Facebook domain and public suffix used: e.g. facebook.com vs fb.com vs. fb.me
   def self.sc_facebook(url)
-    #puts "sc_facebook: #{url}"
-    regex1  = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/((pages?|pg)\/)*(?<uname>.*)[\/-](?<uid>[0-9]+))($|\/|\/(about|timeline|info|app_)?)/i
+
+    url = url.gsub(/(_rdr=.+&)|(&_rdr=.+$)/,"")
+
+    regex1  = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/(((?<group>groups?)|pages?|pg)\/)*(?<uname>.*)[\/-](?<uid>[0-9]+))($|\/|\/(about|timeline|info|app_)?)/i
     regex2  = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/profile.php\?id=(?<uid>[0-9]+))($|\/|\/.*|&.*)/i
-    regex2a = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/profile.php\?_rdr=p&id=(?<uid>[0-9]+))($|\/|\/.*|&.*)/i
-    regex3  = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/((pages?|pg)\/)*(?<uname>[^\?\/]*))($|\/$|\/(about|timeline|info|app_.*)?)/i
+    regex3  = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/(((?<group>groups?)|pages?|pg)\/)*(?<uname>[^\?\/]*))($|\/$|\/(about|timeline|info|app_.*)?)/i
     regex4  = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/)(?<php>home.php\?([#!]+\/)*)(?<uname>.*)/i
     regex5  = /^(?<url>(https?:\/\/)((business|www)\.)?facebook\.com\/(?<uid>[0-9]+))($|\/|\/.*|&.*)/i
+    regex6  = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/home\/accounts\?business_id=(?<uid>[0-9]+))($|\/|\/.*|&.*)/i
 
     # If the user gives us a path to a Post, "http://facebook.com/LoansByJanet/posts/1691075027771418"
     # then drop the post part, "/posts/1691075027771418" to get the base url, "http://facebook.com/LoansByJanet/"
@@ -294,10 +302,7 @@ module UrlScrubber
     end
 
     if url.match("/media/albums") || url.match("/media/set")
-      # puts "media"
       url = url.match('\&') ? url.split('&',2)[0] : url
-    elsif url.include?('facebook.com/groups/')
-      url = drop_url_query!(url)
     elsif mdata = url.match(regex1)
       # "http://facebook.com/pages/Command-Canada/1434248516885065/timeline"
       url = mdata[:url]
@@ -307,11 +312,6 @@ module UrlScrubber
       # "https://www.facebook.com/profile.php?id=100009574328879"
       url, http_response = check_for_facebook_redirection(mdata[:url])
       uid = mdata[:uid]
-    elsif mdata = url.match(regex2a)
-      # "https://www.facebook.com/profile.php?_rdr=p&id=100009574328879"
-      url = "http://facebook.com/profile.php?id=" + mdata[:uid]
-      url, http_response = check_for_facebook_redirection(url)
-      uid = mdata[:uid]
     elsif mdata = url.match(regex4)
       # "http://facebook.com/home.php?#!/person.name"
         url = mdata[:url] + mdata[:uname]
@@ -320,11 +320,16 @@ module UrlScrubber
         # "https://www.facebook.com/100009574328879"
         url = "http://facebook.com/" + mdata[:uid]
         uid = mdata[:uid]
+      elsif mdata = url.match(regex6)
+        # "http://business.facebook.com/home/accounts?business_id=1145724702268347"
+        url = mdata[:url]
+        uid = mdata[:uid]
     elsif mdata = url.match(regex3)
       # "http://facebook.com/TonyMollHomeLoans/timeline"
       # "http://facebook.com/pg/TonyMollHomeLoans/timeline"
-      if ["page", "pages", "pg"].exclude?(mdata[:uname])
-        url = "http://facebook.com/" + mdata[:uname]
+      # "https://www.facebook.com/groups/practicewithclaritygroup"
+      if ["group", "groups", "page", "pages", "pg"].exclude?(mdata[:uname])
+        url = (mdata[:group] ? "http://facebook.com/groups/" : "http://facebook.com/") + mdata[:uname]
         uname = mdata[:uname]
       end
       url = drop_url_query!(url)

data/lib/url_scrubber/version.rb

@@ -1,3 +1,3 @@
 module UrlScrubber
-  VERSION = "0.8.15"
+  VERSION = "0.8.20"
 end

data/url_scrubber.gemspec

@@ -7,6 +7,7 @@ Gem::Specification.new do |gem|
   gem.description   = %q{Remove extraneous bits from URLs, follow redirects, identify social media urls, etc.}
   gem.summary       = %q{Clean up URLs.}
   gem.homepage      = "http://brandle.net"
+  gem.license       = "MIT"
 
   gem.files         = `git ls-files`.split($\)
   gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: url_scrubber
 version: !ruby/object:Gem::Version
-  version: 0.8.15
+  version: 0.8.20
 platform: ruby
 authors:
 - Colin Langton
@@ -12,7 +12,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-11-22 00:00:00.000000000 Z
+date: 2020-08-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -97,7 +97,6 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".gitignore"
-- ".rvmrc"
 - Gemfile
 - Guardfile
 - README.md
@@ -108,7 +107,8 @@ files:
 - spec/url_scrubber_spec.rb
 - url_scrubber.gemspec
 homepage: http://brandle.net
-licenses: []
+licenses:
+- MIT
 metadata: {}
 post_install_message: 
 rdoc_options: []
@@ -125,8 +125,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.7
+rubygems_version: 3.0.6
 signing_key: 
 specification_version: 4
 summary: Clean up URLs.

data/.rvmrc

@@ -1 +0,0 @@
-rvm use 1.9.3@url_scrubber --create