url_scrubber 0.8.16 → 0.8.21

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 455a7dccc82ca65d302205f525100c2c59700cbf41950533cae59269e47355c0
-  data.tar.gz: 558a14779d4edcb5766896cab6ed21b1b7ad2f5cc924d30a007aa670d4fe7bd7
+  metadata.gz: dfe7609c65d93e0b93cdc01f8b9ff08b6abbd417a4be183a19993f2df17a5451
+  data.tar.gz: 7f85340db035fa6330cc894ae0290261633d3c626ba76210ddea2be1c0a57352
 SHA512:
-  metadata.gz: fba24e3059a04408972ef8fc52013b726aff9b2995adc1bf153bb9723673b65f9add9334a1c4fd2f93c7a92fa9db960b1e9469b81590f20a60a4c830e92632ea
-  data.tar.gz: 2d30bdcaf8d61e516cacc933dc2cfd2dd8010cea0edaab786a6d8b2c4a0f94c657d97c6b63ace038cc0f12a14e0ee0d2979e8bda43d9d814b74a56d0f7e3ae02
+  metadata.gz: 2751402307e2edb719e12279c11301d3a7084920e19dc7dc7ec18b37bf19a684b69b5ad8f7dcca7867667a463012d6f08c339fa4842458edc5c8003d303d69e1
+  data.tar.gz: d9156d4cb46a3a232b4e80df2759bba624d2366ec691cece5f0c025a24ccc4faf5706a7e48f6ef35d4bde8b50b354fb3965ff54f056cca59f29beac926f71a73

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]
@@ -179,7 +179,11 @@ module UrlScrubber
 
   def self.downcase_domain(url)
     domain_match = url.match(%r{http://[^/]+}i)
-    domain_match[0].downcase + domain_match.post_match
+    if domain_match
+      domain_match[0].downcase + domain_match.post_match
+    else
+      url
+    end
   end
 
 
@@ -285,13 +289,15 @@ 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/"
@@ -300,10 +306,7 @@ 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]
@@ -313,11 +316,6 @@ 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]
@@ -326,11 +324,16 @@ 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 = "0.8.16"
+  VERSION = "0.8.21"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: url_scrubber
 version: !ruby/object:Gem::Version
-  version: 0.8.16
+  version: 0.8.21
 platform: ruby
 authors:
 - Colin Langton
@@ -12,7 +12,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-02-12 00:00:00.000000000 Z
+date: 2021-01-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -125,8 +125,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.8
+rubygems_version: 3.0.6
 signing_key: 
 specification_version: 4
 summary: Clean up URLs.