url-privacy 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 13006f4f0e38cbc252c8d2f0dd4e6b2e48c278001c46e4292ecb1af961362c03
+  data.tar.gz: 448e7c4b11e2fb4c1c3cbfa58b59613715ffc27facc69106a4fc860560419278
+SHA512:
+  metadata.gz: 9c27045c00b8b6142c8d2514b944eb07a3c2c818955467ddd4a6d75d8ad5ff72ba2bd85e767c1f5c5cd4ebdda0f5313b348d48222e065c7ddc8fae1000f7de1a
+  data.tar.gz: c466b66f6b0aa0b51d59f214646f45acd6b6a28a651980792df69889a1ee08382ec702e68aa934c13b02bf4ee0c02e7b9ca1e1f4583e26869e0046b47b22647f

data/README.md

@@ -0,0 +1,47 @@
+# url-privacy
+
+Removes tracking parameters from URLs.
+
+## Installation
+
+Add this line to your Gemfile:
+
+```ruby
+gem 'url-privacy'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it as:
+
+    $ gem install url-privacy
+
+## Usage
+
+```yaml
+UrlPrivacy.clean url
+```
+
+## Contributing
+
+Bug reports and pull requests are welcome on 0xacab.org at
+<https://0xacab.org/sutty/url-privacy>. This project is intended to be
+a safe, welcoming space for collaboration, and contributors are expected
+to adhere to the [Sutty code of
+conduct](https://sutty.nl/en/code-of-conduct/).
+
+If you like our plugins, [please consider
+donating](https://donaciones.sutty.nl/en/)!
+
+## License
+
+The gem is available as free software under the terms of the LGPL3
+License.
+
+## Code of Conduct
+
+Everyone interacting in the url-privacy project’s codebases, issue
+trackers, chat rooms and mailing lists is expected to follow the [code
+of conduct](https://sutty.nl/en/code-of-conduct/).

data/lib/url_privacy.rb

@@ -0,0 +1,149 @@
+# frozen_string_literal: true
+
+# Usage:
+#
+# UrlPrivacy.clean(url)
+class UrlPrivacy
+  class << self
+
+    # Remove these params from URLs.  Taken from Neat URL and
+    # CleanURLs plus some others manually found.
+    #
+    # @see {https://github.com/Smile4ever/Neat-URL}
+    # @see {https://gitlab.com/anti-tracking/ClearURLs/rules/-/blob/master/data.json}
+    # @see {https://github.com/Smile4ever/Neat-URL/issues/235}
+    TRACKING_PARAMS = %w[pf_rd_*@imdb.com ref_@imdb.com gclid ref
+    terminal_id igshid tracking_id action_object_map action_type_map
+    action_ref_map spm@*.aliexpress.com scm@*.aliexpress.com
+    aff_platform aff_trace_key algo_expid@*.aliexpress.*
+    algo_pvid@*.aliexpress.* btsid ws_ab_test pd_rd_*@amazon.*
+    _encoding@amazon.* psc@amazon.* tag@amazon.* ref_@amazon.*
+    pf_rd_*@amazon.* pf@amazon.* qid@amazon.* sr@amazon.*
+    srs@amazon.* __mk_*@amazon.* spIA@amazon.* ms3_c@amazon.*
+    ie*@amazon.* refRID@amazon.* colid@amazon.* coliid@amazon.*
+    *adId@amazon.* qualifier@amazon.* _encoding@amazon.*
+    smid@amazon.* field-lbr_brands_browse-bin@amazon.* ved@google.*
+    bi*@google.* gfe_*@google.* ei@google.* source@google.*
+    gs_*@google.* site@google.* oq@google.* esrc@google.*
+    uact@google.* cd@google.* cad@google.* gws_*@google.*
+    atyp@google.* vet@google.* zx@google.* _u@google.* je@google.*
+    dcr@google.* ie@google.* sei@google.* sa@google.* dpr@google.*
+    hl@google.* btn*@google.* sa@google.* usg@google.* cd@google.*
+    cad@google.* uact@google.* src@shutterstock.com
+    snr@steampowered.com wbdcd@tchibo.de smid@nytimes.com
+    spm@youku.com tpa@youku.com xid@prvnizpravy.cz pl@net-parade.it
+    u1@walmart.com* ath*@walmart.com* utm_* ga_source ga_medium
+    ga_term ga_content ga_campaign ga_place yclid _openstat
+    fb_action_ids fb_action_types fb_source fb_ref fbclid
+    action_object_map action_type_map action_ref_map gs_l mkt_tok
+    hmb_campaign hmb_medium hmb_source ref ref_ ref_*@twitter.com
+    src@twitter.com trackId@netflix.* tctx@netflix.* jb*@netflix.*
+    ncid@techcrunch.com sr@techcrunch.com sr_share@techcrunch.com
+    guccounter@techcrunch.com guce_referrer_*@techcrunch.com
+    cvid@bing.com form@bing.com sk@bing.com sp@bing.com sc@bing.com
+    qs@bing.com qp@bing.com nb@tweakers.net u@tweakers.net
+    tt_medium@twitch.* tt_content@twitch.* pk_campaign@vivaldi.com
+    pk_kwd@vivaldi.com from@indeed.com alid@indeed.com
+    *tk@indeed.com vss@hh.ru t@hh.ru swnt@hh.ru grpos@hh.ru
+    ptl@hh.ru stl@hh.ru exp@hh.ru plim@hh.ru _trkparms@ebay.*
+    _trksid@ebay.* _from@ebay.* ftag@cnet.com callback@bilibili.com
+    cvid@bing.com form@bing.com sk@bing.com sp@bing.com sc@bing.com
+    qs@bing.com pq@bing.com mkt_tok trk trkCampaign ga_* gclid
+    gclsrc hmb_campaign hmb_medium hmb_source spReportId spJobID
+    spUserID spMailingID itm_* s_cid elqTrackId elqTrack assetType
+    assetId recipientId campaignId siteId mc_cid mc_eid pk_*
+    sc_campaign sc_channel sc_content sc_medium sc_outcome sc_geo
+    sc_country utm_* nr_email_referer vero_conv vero_id yclid
+    _openstat mbid cmpid cid c_id campaign_id Campaign hash@ebay.*
+    fb_action_ids fb_action_types fb_ref fb_source fbclid
+    refsrc@facebook.com hrc@facebook.com gs_l gs_lcp@google.*
+    ved@google.* ei@google.* sei@google.* gws_rd@google.*
+    gs_gbg@google.* gs_mss@google.* gs_rn@google.* _hsenc _hsmi
+    __hssc __hstc hsCtaTracking source@sourceforge.net
+    position@sourceforge.net tt_medium tt_content lr@yandex.*
+    redircnt@yandex.* feature@youtube.com kw@youtube.com wt_zmc
+    source@google.* iflsig@google.* sclient@google.*
+    sfnsn@facebook.com extid@facebook.com d@facebook.com
+    vh@facebook.com hc_*@facebook.com *ref*@facebook.com
+    __tn__@facebook.com eid@facebook.com __xts__@facebook.com
+    so_medium@stackoverflow.com so_source@stackoverflow.com
+    preview_pb@tiktok.com _d@tiktok.com share_item_id@tiktok.com
+    timestamp@tiktok.com user_id@tiktok.com tt_from@tiktok.com
+    source@tiktok.com].uniq.freeze
+
+    # Clean the given URL.  If the URL can't be parsed, returns the
+    # URL unmodified.
+    #
+    # Caches in case there're duplicates.
+    #
+    # @param [String]
+    # @return [String]
+    def clean(url)
+      @cleaned_urls ||= {}
+      @cleaned_urls[url] ||= begin
+        uri = URI(url)
+
+        if uri.query
+          hostname = uri.hostname.sub(/\Awww\./, '')
+          params = URI.decode_www_form(uri.query).to_h
+
+          # Remove params by name first
+          params.reject! do |param, _|
+            TRACKING_PARAMS.include? param
+          end
+
+          # Remove params with globs
+          params.reject! do |param, _|
+            simple_tracking_params.any? do |pattern_param|
+              File.fnmatch(pattern_param, param)
+            end
+          end
+
+          # Remove params matching by hostname and then param
+          params.reject! do |param, _|
+            complex_tracking_params.any? do |pattern_hostname, pattern_params|
+              next false unless File.fnmatch(pattern_hostname, hostname)
+
+              pattern_params.any? do |pattern_param|
+                File.fnmatch(pattern_param, param)
+              end
+            end
+          end
+
+          uri.query = URI.encode_www_form(params)
+        end
+
+        uri.to_s
+      end
+    rescue URI::Error
+      @cleaned_urls[url] ||= url
+    end
+
+    private
+
+    # This is all so we can just copy and paste from Neat URL source
+    # code, it produces a hash of hostname => [ params ] that can be
+    # glob-matched.
+    #
+    # @return [Hash]
+    def complex_tracking_params
+      @complex_tracking_params ||= TRACKING_PARAMS.map do |param|
+        next unless param.include? '@'
+
+        Hash[*param.split('@', 2).reverse]
+      end.compact.reduce({}) do |hash, pairs|
+        pairs.each do |key, value|
+          (hash[key] ||= []) << value
+        end
+
+        hash
+      end
+    end
+
+    def simple_tracking_params
+      @simple_tracking_params ||= TRACKING_PARAMS.select do |param|
+        !param.include?('@')
+      end
+    end
+  end
+end

metadata

@@ -0,0 +1,58 @@
+--- !ruby/object:Gem::Specification
+name: url-privacy
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- f
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2021-01-31 00:00:00.000000000 Z
+dependencies: []
+description:
+email:
+- f@sutty.nl
+executables: []
+extensions: []
+extra_rdoc_files:
+- README.md
+files:
+- README.md
+- lib/url_privacy.rb
+homepage: https://0xacab.org/sutty/url-privacy
+licenses:
+- LGPL-3.0
+metadata:
+  bug_tracker_uri: https://0xacab.org/sutty/url-privacy/issues
+  homepage_uri: https://0xacab.org/sutty/url-privacy
+  source_code_uri: https://0xacab.org/sutty/url-privacy
+  changelog_uri: https://0xacab.org/sutty/url-privacy/-/blob/master/CHANGELOG.md
+  documentation_uri: https://rubydoc.info/gems/url-privacy
+post_install_message:
+rdoc_options:
+- "--title"
+- url-privacy - Removes tracking parameters from URLs
+- "--main"
+- README.md
+- "--line-numbers"
+- "--inline-source"
+- "--quiet"
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.6.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.1.2
+signing_key:
+specification_version: 4
+summary: Removes tracking parameters from URLs
+test_files: []