user-agent-randomizer 0.1.2 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 667fae99b6eecdd25b4d32d5873e705f5361399d
-  data.tar.gz: fc57c51ea2a99186c0dc54064bfc8a6dde22407a
+  metadata.gz: b1da61f53ea46a7db46dcb9c06e1e818a3e7b20f
+  data.tar.gz: 4ea424da7f7426c52ef4521471d29c61900a03ff
 SHA512:
-  metadata.gz: 3a783b6123aa88426df83a9c7e6e4be773e865cde45f01e9e7dc50e6dd9aca80558b24acc0e29cf76e8f59cb3a378a57567e402e7d647ba31427d5bfc480e26b
-  data.tar.gz: 2c9f4e69fb6445576f86e33e3e991859bd9932475d37bc4e216135faa118cfce5be0784ce1ecaaace2667d79f0b9d8306b515dd74531fcf4fcf2fc6bc689be1a
+  metadata.gz: d06f2088b10ffa1497a4d372951e7af1664d83f5d62563e6999e17ea84a8223c9fdd45b1501d8c95046bda731d2d95fad99cd9eaf166e3375d80b5b44873f934
+  data.tar.gz: 1a15e25a49920f5a63ce3e8273799f2fe7bc0b784da6e2d5d80b1652fe26eb9db7a60c41c3263d5a369b5d42ccc9f4c338ee1390a9dd1b1c97e4ebea443844e6

data/README.md

@@ -36,23 +36,34 @@ And then execute:
 
 Or install it manually:
 
-    $ gem install user_agent_randomizer
+    $ gem install user-agent-randomizer
 
 ## Usage
 
 The usage is pretty simple. You can fetch a random HTTP User-Agent string from the entire pool as well as one from a specified category (see the list above):
 
-```ruby
-require 'user-agent-randomizer'
+Open an IRB and require the gem first of all:
 
-# Fetch a random HTTP User-Agent string from the entire pool
-UserAgentRandomizer::UserAgent.new
-# => "AppEngine-Google; (+http://code.google.com/appengine; appid: longbows-hideout)"
+    irb> require 'user_agent_randomizer'
+    # => true
 
-# Fetch a random HTTP User-Agent for a desktop browser
-UserAgentRandomizer::UserAgent.new("desktop_browser")
-# => "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Iron/0.2.152.0 Safari/12733120.525"
-```
+Fetch a random HTTP User-Agent string from the entire pool:
+
+    irb> ua_all = UserAgentRandomizer::UserAgent.fetch
+    # => #<UserAgentRandomizer::UserAgent:0x007fe1f30a6658 @type="crawler", @string="CatchBot/1.0;  http://www.catchbot.com">
+
+Fetch a random HTTP User-Agent for a desktop browser:
+
+    irb> ua_desktop = UserAgentRandomizer::UserAgent.fetch(type: "desktop_browser")
+    # => #<UserAgentRandomizer::UserAgent:0x007fe1f2282b58 @type="desktop_browser", @string="Mozilla/4.6 [en] (WinNT; I)">
+
+Retrieve the type and the string from the objects above:
+
+    irb> puts "UA general -> type: '#{ua_all.type}', string: '#{ua_all.string}'"
+    # => "UA general -> type: 'crawler', string: 'CatchBot/1.0;  http://www.catchbot.com'"
+
+    irb> puts "UA desktop browser -> type: '#{ua_desktop.type}', string: '#{ua_desktop.string}'"
+    # => "UA desktop browser -> type: 'desktop_browser', string: 'Mozilla/4.6 [en] (WinNT; I)'"
 
 ## Contributing
 

data/benchmark/generate.rb

@@ -0,0 +1,26 @@
+#!/usr/bin/env ruby
+# coding: utf-8
+
+$LOAD_PATH.unshift File.expand_path(File.dirname(__FILE__) + '/..')
+$LOAD_PATH.unshift File.expand_path(File.dirname(__FILE__) + '/../lib')
+
+# require 'rubygems'
+# require 'bundler'
+require 'benchmark'
+require 'user_agent_randomizer'
+include Benchmark
+
+times = ARGV[0] ? ARGV[0].to_i : 100_000
+puts "Starting benchmark generating #{times} HTTP User-Agent strings ..."
+Benchmark.benchmark(CAPTION, 40, FORMAT, nil) do |x|
+	x.report("UserAgent.fetch") do
+    times.times do
+      UserAgentRandomizer::UserAgent.fetch
+    end
+  end
+  x.report("UserAgent.fetch(type: 'desktop_browser'") do
+    times.times do
+      UserAgentRandomizer::UserAgent.fetch(type: 'desktop_browser')
+    end
+  end
+end

data/lib/user_agent_randomizer.rb

@@ -23,12 +23,28 @@ end
 
 UserAgentRandomizer.config do
   parameter :user_agent_types
-  parameter :user_agents
+  parameter :user_agents_hash
+  parameter :user_agents_array
+end
+
+if Gem.loaded_specs['user-agent-randomizer'].nil?
+  gem_path = File.expand_path("../..", __FILE__)
+else
+  gem_path = Gem.loaded_specs['user-agent-randomizer'].full_gem_path
+end
+
+user_agents_hash = YAML.load_file(File.join(gem_path, 'data', 'user_agents.yml'))
+user_agents_array = []
+user_agents_hash.each_pair do |type, ua_strings|
+  ua_strings.each do |ua_string|
+    user_agents_array << {type: type, string: ua_string}
+  end
 end
 
 UserAgentRandomizer.config do
   user_agent_types ["crawler", "desktop_browser", "mobile_browser", "console",
       "offline_browser", "email_client", "link_checker", "email_collector",
-      "validator", "feed_reader", "library", "cloud_platform", "other"]
-  user_agents YAML.load_file(File.expand_path("data/user_agents.yml", Gem.datadir("user_agent_randomizer")))
+      "validator", "feed_reader", "library", "cloud_platform", "other"]      
+  user_agents_hash user_agents_hash
+  user_agents_array user_agents_array
 end

data/lib/user_agent_randomizer/user_agent.rb

@@ -12,13 +12,12 @@ module UserAgentRandomizer
     def self.fetch(options = {})
       type = options[:type]
       ua_types = UserAgentRandomizer.user_agent_types
-      user_agents = UserAgentRandomizer.user_agents
+      user_agents_hash = UserAgentRandomizer.user_agents_hash
       if ua_types.include?(type)
-        UserAgentRandomizer::UserAgent.new(type: type, string: user_agents[type].sample)
+        UserAgentRandomizer::UserAgent.new(type: type, string: user_agents_hash[type].sample)
       else
-        ua_string = user_agents.values.flatten.sample
-        ua_type = user_agents.select{|_,vals| vals.include?(ua_string)}.keys.first
-        UserAgentRandomizer::UserAgent.new(type: ua_type, string: ua_string)
+        ua = UserAgentRandomizer.user_agents_array.sample
+        UserAgentRandomizer::UserAgent.new(type: ua[:type], string: ua[:string])
       end
     end
   end

data/lib/user_agent_randomizer/version.rb

@@ -1,4 +1,4 @@
 module UserAgentRandomizer
-  VERSION = "0.1.2"
+  VERSION = "0.2.0"
 end
 

data/user_agent_randomizer.gemspec

@@ -6,7 +6,7 @@ require 'user_agent_randomizer/version'
 Gem::Specification.new do |spec|
   spec.name          = "user-agent-randomizer"
   spec.version       = UserAgentRandomizer::VERSION
-  spec.date          = "2014-06-27"
+  spec.date          = "2014-10-22"
   spec.authors       = ["Christoph Pilka"]
   spec.email         = ["c.pilka@asconix.com"]
   spec.summary       = %q{Random HTTP User-Agent string generator}

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: user-agent-randomizer
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.2.0
 platform: ruby
 authors:
 - Christoph Pilka
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-06-27 00:00:00.000000000 Z
+date: 2014-10-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -107,6 +107,7 @@ files:
 - LICENSE
 - README.md
 - Rakefile
+- benchmark/generate.rb
 - data/user_agents.yml
 - lib/user_agent_randomizer.rb
 - lib/user_agent_randomizer/user_agent.rb