traffic_channelizer 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 6e209cd5064bf38df0b29712c13814fc060305e2
+  data.tar.gz: 359b711366ecc0be0d1c8da126adb3b7f852e6cf
+SHA512:
+  metadata.gz: f4ec19f2539aeb901e3cd462a4108cec72a995c6dbb284ad537c55d77fbc0c04a5235dd8341491ebf7e065ddb6ee07b72f50bad35ed8677a85e4dc5d8691ef62
+  data.tar.gz: 97edaba49ac1e050bf31c1903f4870c353be5129520be7ffb3f76dbc97c7d2240ea375cc4ed9877504e67ae2d1faf6e039d595f4f0c9e2a93b525a82f1e9694d

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,3 @@
+language: ruby
+rvm:
+  - 2.2.1

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in traffic_channelizer.gemspec
+gemspec

data/README.md

@@ -0,0 +1,55 @@
+# TrafficChannelizer
+
+Given a referrer_url and destination landing_page_url, this gem will determine the 
+marketing attribution for the visit (source, medium, campaign) and channel group 
+(eg Social, Direct, Organic Search, Paid Search). 
+
+The categorizations are based on Google Analytics' [default channel definitions](https://support.google.com/analytics/answer/3297892)
+
+## Limitations
+
+1. Display and Paid Search groupings do not take into account the Ad Distribution Network
+2. The list of Social Networks and Search Engines may differ from Google's lists.
+
+## Usage
+
+```Ruby
+TrafficChannelizer.analyze(referrer_url: 'https://www.google.com?s=some-query', landing_page_url: 'https://your-site.com')
+=> {:referrer_domain=>"google.com", :landing_page_domain=>"your-site.com", :medium=>"search", :source=>"Google", :term=>nil, :campaign=>nil, :content=>nil, :channel_group=>"Organic Search"}
+
+TrafficChannelizer.analyze(referrer_url: 'https://www.some-site.com', landing_page_url: 'https://your-site.com?utm_medium=cpc')
+=> {:referrer_domain=>"some-site.com", :landing_page_domain=>"your-site.com", :medium=>"cpc", :source=>"some-site.com", :term=>nil, :campaign=>nil, :content=>nil, :channel_group=>"Paid Search"}
+
+TrafficChannelizer.analyze(referrer_url: nil, landing_page_url: 'https://your-site.com')
+=> {:referrer_domain=>nil, :landing_page_domain=>"your-site.com", :medium=>"(none)", :source=>"(direct)", :term=>nil, :campaign=>nil, :content=>nil, :channel_group=>"Direct"}
+```
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'traffic_channelizer'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install traffic_channelizer
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release` to create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+1. Fork it ( https://github.com/[my-github-username]/traffic_channelizer/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create a new Pull Request

data/Rakefile

@@ -0,0 +1 @@
+require 'bundler/gem_tasks'

data/bin/console

@@ -0,0 +1,7 @@
+#!/usr/bin/env ruby
+
+require 'bundler/setup'
+require 'traffic_channelizer'
+require 'pry'
+
+Pry.start

data/bin/setup

@@ -0,0 +1,7 @@
+#!/bin/bash
+set -euo pipefail
+IFS=$'\n\t'
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/traffic_channelizer.rb

@@ -0,0 +1,14 @@
+require 'traffic_channelizer/version'
+require 'traffic_channelizer/referrer'
+require 'traffic_channelizer/landing_page'
+require 'traffic_channelizer/channel_group'
+require 'traffic_channelizer/visit'
+
+module TrafficChannelizer
+  def self.analyze(referrer_url:, landing_page_url:)
+    Visit.new(
+      referrer_url: referrer_url,
+      landing_page_url: landing_page_url
+    ).attribution_data
+  end
+end

data/lib/traffic_channelizer/channel_group.rb

@@ -0,0 +1,18 @@
+module TrafficChannelizer
+  class ChannelGroup
+    def self.identify(source:, medium:)
+      return 'Email' if medium =~ /^email$/i
+      return 'Affiliates' if medium =~ /^affiliate$/i
+      return 'Referral' if medium =~ /^referral$/i
+      return 'Organic Search' if medium =~ /^(organic|search)$/i
+      return 'Paid Search' if medium =~ /^(cpc|ppc|paidsearch)$/i
+      return 'Other Advertising' if medium =~ /^(cpv|cpa|cpp)$/i
+      return 'Display' if medium =~ /^(display|cpm|banner)$/i
+      return 'Social' if medium =~ /^(social|social-network|social-media|sm|social network|social media)$/i
+      return 'Other' unless medium == '(none)'
+      return 'Direct' if source == '(direct)'
+      return 'Internal' if source == '(internal)'
+      'Referral'
+    end
+  end
+end

data/lib/traffic_channelizer/landing_page.rb

@@ -0,0 +1,38 @@
+require 'addressable/uri'
+
+module TrafficChannelizer
+  class LandingPage
+    attr_reader :url
+
+    def initialize(url)
+      @url = url
+    end
+
+    %w(utm_source utm_medium utm_campaign utm_term utm_content).each do |utm_param|
+      define_method utm_param do
+        query_params[utm_param] unless query_params[utm_param] == ''
+      end
+    end
+
+    def domain
+      domain_without_www
+    end
+
+    private
+
+    def domain_without_www
+      return unless uri.host
+      uri.host.gsub(/^www\./, '')
+    end
+
+    def uri
+      @uri ||= Addressable::URI.parse(url.to_s)
+    rescue
+      nil
+    end
+
+    def query_params
+      @query_params ||= (uri && uri.query_values) || {}
+    end
+  end
+end

data/lib/traffic_channelizer/referrer.rb

@@ -0,0 +1,55 @@
+require 'referer-parser'
+require 'addressable/uri'
+
+module TrafficChannelizer
+  class Referrer
+    attr_reader :url
+
+    def self.parser
+      @parser ||= RefererParser::Parser.new
+    end
+
+    class << self
+      attr_writer :parser
+    end
+
+    def initialize(url)
+      @url = url
+    end
+
+    def medium
+      referrer_data[:medium]
+    end
+
+    def source
+      referrer_data[:source] || domain_without_www
+    end
+
+    def domain
+      domain_without_www
+    end
+
+    def term
+      referrer_data[:term]
+    end
+
+    private
+
+    def domain_without_www
+      return unless normalized_uri.host
+      normalized_uri.host.gsub(/^www\./, '')
+    end
+
+    def normalized_uri
+      @normalized_uri ||= Addressable::URI.parse(url.to_s).normalize
+    rescue
+      nil
+    end
+
+    def referrer_data
+      @referrer_data ||= self.class.parser.parse(normalized_uri.to_s)
+    rescue RefererParser::InvalidUriError
+      {}
+    end
+  end
+end

data/lib/traffic_channelizer/version.rb

@@ -0,0 +1,3 @@
+module TrafficChannelizer
+  VERSION = '1.0.0'
+end

data/lib/traffic_channelizer/visit.rb

@@ -0,0 +1,57 @@
+module TrafficChannelizer
+  class Visit
+    def initialize(referrer_url:, landing_page_url:)
+      @referrer_url = referrer_url
+      @landing_page_url = landing_page_url
+    end
+
+    def attribution_data
+      {
+        referrer_domain: referrer.domain,
+        landing_page_domain: landing_page.domain,
+        medium: medium,
+        source: source,
+        term: term,
+        campaign: landing_page.utm_campaign,
+        content: landing_page.utm_content,
+        channel_group: channel_group
+      }
+    end
+
+    def medium
+      landing_page.utm_medium || referrer.medium || '(none)'
+    end
+
+    def source
+      s = landing_page.utm_source
+      s ||= '(internal)' if internal?
+      s ||= referrer.source
+      s ||= '(direct)'
+      s
+    end
+
+    def term
+      landing_page.utm_term || referrer.term
+    end
+
+    def channel_group
+      ChannelGroup.identify(medium: medium, source: source)
+    end
+
+    private
+
+    def internal?
+      landing_page.domain == referrer.domain
+    end
+
+    def landing_page
+      @landing_page ||= LandingPage.new(landing_page_url)
+    end
+
+    def referrer
+      @referrer ||= Referrer.new(referrer_url)
+    end
+
+    attr_reader :referrer_url, :landing_page_url
+  end
+end

data/traffic_channelizer.gemspec

@@ -0,0 +1,30 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'traffic_channelizer/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'traffic_channelizer'
+  spec.version       = TrafficChannelizer::VERSION
+  spec.authors       = ['Ian Yamey']
+  spec.email         = ['ian@policygenius.com']
+
+  spec.summary       = 'Analyzes website visits to determine the source, medium, campaign and channel grouping, similar to the classifications used by Google Analytics'
+  spec.description   = "Given a referrer_url and destination landing_page_url, this gem will determine the traffic's " \
+                       'source, medium, campaign, term, content and channel (eg Social, Direct, Organic Search, Paid Search). The categorization is ' \
+                       "based on Google Analytics' default channel definitions (see https://support.google.com/analytics/answer/3297892)"
+  spec.homepage      = 'https://github.com/ianyamey/traffic_channelizer'
+  spec.license       = 'MIT'
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = 'exe'
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ['lib']
+
+  spec.add_dependency 'rack'
+  spec.add_dependency 'referer-parser'
+  spec.add_dependency 'addressable'
+  spec.add_development_dependency 'rspec', '~> 3.2'
+  spec.add_development_dependency 'bundler', '~> 1.9'
+  spec.add_development_dependency 'rake', '~> 10.0'
+  spec.add_development_dependency 'pry'
+end

metadata

@@ -0,0 +1,161 @@
+--- !ruby/object:Gem::Specification
+name: traffic_channelizer
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Ian Yamey
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2016-05-04 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rack
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: referer-parser
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: addressable
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Given a referrer_url and destination landing_page_url, this gem will
+  determine the traffic's source, medium, campaign, term, content and channel (eg
+  Social, Direct, Organic Search, Paid Search). The categorization is based on Google
+  Analytics' default channel definitions (see https://support.google.com/analytics/answer/3297892)
+email:
+- ian@policygenius.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/traffic_channelizer.rb
+- lib/traffic_channelizer/channel_group.rb
+- lib/traffic_channelizer/landing_page.rb
+- lib/traffic_channelizer/referrer.rb
+- lib/traffic_channelizer/version.rb
+- lib/traffic_channelizer/visit.rb
+- traffic_channelizer.gemspec
+homepage: https://github.com/ianyamey/traffic_channelizer
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.6
+signing_key: 
+specification_version: 4
+summary: Analyzes website visits to determine the source, medium, campaign and channel
+  grouping, similar to the classifications used by Google Analytics
+test_files: []