url_scrubber 0.8.13 → 0.8.15

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5b0e2a469b840847dde026eaaeb18f48938e49080a737ba2f70b53333f889aeb
-  data.tar.gz: df9c7c316151a830d000f1adffcf043a95fe46e71822824a9526a9a309522b11
+  metadata.gz: 608b40e9de605ac987e39f8fa5b1640d6543c8dc8a83553f2689f2fbe716b50a
+  data.tar.gz: d6d1c7905a4875ef9fb6f2ce7ab03f18ff31e524b180c3e13bd10467513c79b8
 SHA512:
-  metadata.gz: 0c45b738609ad89ffbf7e69cb46378710fe7fdb69f88abcb61df71e112a02194493eb1175650a446d81a51601ee36f9acabf8d5f68853f561ead495025eb9e3f
-  data.tar.gz: 8a293e4f32b7cf355bd3a2e8570ac1b5e5569b116ab92e0b98c6eeff92d028ac25952c8df4d8a49a1d0f829919b9fdc716fbade35063922f3157c1f26710b45b
+  metadata.gz: f6f43dd74cec24acd3f7e2a376b89476f00eb09e627a96c55ba5ec0e97c7ccc994385858183c13230a98066d2b687a462225a3347f6aa27d36f8a668eaef087c
+  data.tar.gz: 395a1561434cc85197f10211393cfdaabea3e35fb50a2559f0c0c3dd669aea3cd13b8e68192a4eda105a2abce1c7476bde167ad00c8704d0e62052ce92ca94ba

data/lib/url_scrubber/version.rb

@@ -1,3 +1,3 @@
 module UrlScrubber
-  VERSION = "0.8.13"
+  VERSION = "0.8.15"
 end

data/lib/url_scrubber.rb

@@ -34,39 +34,30 @@ module UrlScrubber
 
 
   def self.service_of(url)
-
-    domain_match = url.match(%r{https?://([^/]+)})
-
-    if domain_match
-      domain = domain_match[1]
-      first_dot = domain.index(".")
-
-  	  #first_dot_position = domain.index(".")
-  	  #first_dot_position += 1 if first_dot_position
-
-  	  #Rails.logger.debug "domain = #{domain}, first dot = #{first_dot ? first_dot : 'none'}, first dot 1= #{first_dot ? domain[first_dot+1..domain.size] : 'NIL'}"
-  	  if first_dot
-        # tumblr is a unique format
-        return :tumblr if domain[first_dot+1..domain.size].index("tumblr.com") == 0
+    url_parts = Domainatrix.parse(url)
+    if url_parts.host.present?
+
+      case url_parts.domain
+      when 'facebook'           then return :facebook
+      when 'fb'                 then return :facebook
+      when 'flickr'             then return :flickr
+      when 'instagram'          then return :instagram
+      when 'linkedin'           then return :linkedin
+      when 'pinterest'          then return :pinterest
+      when 'slideshare'         then return :slideshare
+      when 'tumblr'             then return :tumblr
+      when 'twitter'            then return :twitter
+      when 'vimeo'              then return :vimeo
+      when 'yelp'               then return :yelp
+      when 'youtube'            then return :youtube
       end
 
-      case domain
-      when /\byoutube\.com$/            then return :youtube
-      when /\btwitter\.com$/            then return :twitter
-      when /\bfacebook\.com$/           then return :facebook
-      when /\bbusiness.facebook\.com$/  then return :facebook
-      when /\blinkedin\.com$/           then return :linkedin
-      when /\bplus\.google\.com$/       then return :google
-      when /\bbusiness\.google\.com$/   then return :google
-      when /\bslideshare\.net$/         then return :slideshare
-      when /\bflickr\.com$/             then return :flickr
-      when /\bpinterest\.com$/          then return :pinterest
-      when /\bvimeo\.com$/              then return :vimeo
-      when /\binstagram\.com$/          then return :instagram
-      when /\byelp\.com$/               then return :yelp
+      case url_parts.host
+      when /\bplus\.google\.com$/ then return :google
       end
+
     else
-  	  Rails.logger.debug "No Domain Match"
+      Rails.logger.debug "No Domain Match"
     end
 
     :other
@@ -286,6 +277,7 @@ module UrlScrubber
   end
 
 
+  # 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]+))($|\/|\/(about|timeline|info|app_)?)/i
@@ -293,6 +285,7 @@ module UrlScrubber
     regex2a = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/profile.php\?_rdr=p&id=(?<uid>[0-9]+))($|\/|\/.*|&.*)/i
     regex3  = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/((pages?|pg)\/)*(?<uname>[^\?\/]*))($|\/$|\/(about|timeline|info|app_.*)?)/i
     regex4  = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/)(?<php>home.php\?([#!]+\/)*)(?<uname>.*)/i
+    regex5  = /^(?<url>(https?:\/\/)((business|www)\.)?facebook\.com\/(?<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/"
@@ -306,32 +299,31 @@ module UrlScrubber
     elsif url.include?('facebook.com/groups/')
       url = drop_url_query!(url)
     elsif mdata = url.match(regex1)
-      # puts "regex1"
       # "http://facebook.com/pages/Command-Canada/1434248516885065/timeline"
       url = mdata[:url]
       uname = mdata[:uname]
       uid = mdata[:uid]
     elsif mdata = url.match(regex2)
-      # puts "regex2"
       # "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)
-      # puts "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)
-      # puts "#{url} - #{mdata[:uname]}"
       # "http://facebook.com/home.php?#!/person.name"
         url = mdata[:url] + mdata[:uname]
         url = drop_url_query!(url)
+      elsif mdata = url.match(regex5)
+        # "https://www.facebook.com/100009574328879"
+        url = "http://facebook.com/" + mdata[:uid]
+        uid = mdata[:uid]
     elsif mdata = url.match(regex3)
-      # puts "regex3"
       # "http://facebook.com/TonyMollHomeLoans/timeline"
       # "http://facebook.com/pg/TonyMollHomeLoans/timeline"
-      if ["pages", "pg"].exclude?(mdata[:uname])
+      if ["page", "pages", "pg"].exclude?(mdata[:uname])
         url = "http://facebook.com/" + mdata[:uname]
         uname = mdata[:uname]
       end
@@ -353,6 +345,7 @@ module UrlScrubber
   end
 
 
+  # TODO This needs to be rewritten to be independent of the LinkedIn domain and public suffix used: e.g. linkedin.com vs lnkd.in vs linkedin.ca
   def self.sc_linkedin(url)
     url.sub!('linkedin.com/companies/', 'linkedin.com/company/')
     if !!url.match(%r{com/company/})

data/url_scrubber.gemspec

@@ -2,8 +2,8 @@
 require File.expand_path('../lib/url_scrubber/version', __FILE__)
 
 Gem::Specification.new do |gem|
-  gem.authors       = ["Colin Langton", "Christopher Maujean", "David Hillard", "Edgar Abadines"]
-  gem.email         = ["colin@hoteldelta.net", "cmaujean@brandle.net", "dhillard@brandle.net", "ed@brandle.net"]
+  gem.authors       = ["Colin Langton", "Christopher Maujean", "David Hillard", "Edgar Abadines", "Chip Roberson"]
+  gem.email         = ["colin@hoteldelta.net", "cmaujean@brandle.net", "dhillard@brandle.net", "ed@brandle.net", "chip@brandle.net"]
   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"

metadata

@@ -1,17 +1,18 @@
 --- !ruby/object:Gem::Specification
 name: url_scrubber
 version: !ruby/object:Gem::Version
-  version: 0.8.13
+  version: 0.8.15
 platform: ruby
 authors:
 - Colin Langton
 - Christopher Maujean
 - David Hillard
 - Edgar Abadines
+- Chip Roberson
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-11-20 00:00:00.000000000 Z
+date: 2018-11-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -90,6 +91,7 @@ email:
 - cmaujean@brandle.net
 - dhillard@brandle.net
 - ed@brandle.net
+- chip@brandle.net
 executables: []
 extensions: []
 extra_rdoc_files: []