jobs-former_students 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: c9cbfaa0cba18e517da45135e3dc0fe923b84be4
+  data.tar.gz: 1c6025da1723cad63f686ed02e224ad051881268
+SHA512:
+  metadata.gz: 016a0fc67bbfbcdcd4b4d18581875df377b8dc26f6c31ade2a207b9b123226cd37a003ad40e2d4c0aa78e54681597fe9b5f7025312c55ec12c6b0e319e8be0fc
+  data.tar.gz: 14e0abbe226512dee4bb8d7548db933cb0d7f40536e1fe844cced0f30aec036c2f35e9496d5789a477a39efd77bc4fe8f2fc8ea8259eb10b5fb83eddd362d96f

data/.gitignore

@@ -0,0 +1,14 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+*.bundle
+*.so
+*.o
+*.a
+mkmf.log

data/Gemfile

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

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2014 Jim Sutton
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,78 @@
+# Jobs::FormerStudents
+
+#####This is a small gem intended for use with the [Turing School]('https://turing.io') jobs-basket gem. It returns a list of all companies that have employed or currently employ former gSchool students as indicated by the gSchool website. 
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'jobs-former_students'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install jobs-former_students
+
+## Basic Usage
+This gem provides instance methods to return single company names or an array of all company names. Start by creating a new instance of the Scraper class:  
+ ```ruby
+ scraper = Scraper.new
+ ```  
+
+To return a full, current list of company names, pass in a range limit to the `get_company_names` method:  
+```ruby
+  scraper.get_company_names(80)
+```  
+  
+The above method will search students 1 through 80 and return an array of all companies found. As of the publishing date of Version 0.0.1 of this gem, student 65 is the last student with a valid company name. Pages after this represent either pages that do not exist or students who have incomplete profiles (i.e. no company listed).
+
+It is possible (though less useful) to search for a single company. This requires you to know which id is associated with the student, and probably means you can find this information by simply browsing the site yourself. But the world is your oyster, so ` scraper.get_company_name(12) ` will return the single company name of the student matching the number you pass in.
+
+
+##Sorting Methods
+The gem provides three methods to sort the output provided by the `get_company_names`  methods. 
+
+#####1. To return an array of unique company names, use the following method:
+
+```ruby
+scraper.get_unique_company_names(80)
+```
+
+#####2. To return a hash showing the total number of students employed at each company, use the `total_students_employed_per_company` method:  
+
+```ruby
+scraper.total_students_employed_per_company(80)
+```
+
+**Example output:**
+```ruby
+{"Welltok"=>1, "Zayo"=>4, "Active Junky"=>1, "Acumen Digital"=>4, "Kapost"=>1, "Verbalize.it"=>1, "Galvanize / gSchool"=>3, "TeamSnap"=>1, "Sports Shares"=>1, "Pivotal Labs"=>1, "Keen.io"=>1, "Blogmutt"=>1, "QuickLeft"=>2, "IBM BlueMix Garage"=>2, "HobbyDB"=>1, "Oildecks"=>1, "Lee Reedy"=>1, "Dfuzr"=>1, "Colorado Access"=>2, "CloudElements"=>1, "P2Binvestor"=>1, "gSchool"=>3, "Haught Codeworks"=>1, "Amex"=>2, "LegitScript"=>1, "RxRevu"=>1, "Apto"=>1, "Mondo Robot"=>1, "JayBird"=>1}
+```  
+
+You can query the results of this method by passing in a company name as a hash key:
+```ruby
+results = scraper.total_students_employed_per_company(80)
+results["Zayo"] # => 4 
+```
+
+#####3. To return a sorted list of these results, use the `sort_by_frequency` method:
+
+`scraper.sort_by_frequency(80)`  
+
+**Example output:**
+```ruby
+[["Zayo", 4], ["Acumen Digital", 4], ["Galvanize / gSchool", 3], ["gSchool", 3], ["IBM BlueMix Garage", 2], ["Amex", 2], ["Colorado Access", 2], ["QuickLeft", 2], ["HobbyDB", 1], ["CloudElements", 1], ["Haught Codeworks", 1], ["Dfuzr", 1], ["Lee Reedy", 1], ["Oildecks", 1], ["P2Binvestor", 1], ["LegitScript", 1], ["RxRevu", 1], ["Blogmutt", 1], ["Keen.io", 1], ["Pivotal Labs", 1], ["Sports Shares", 1], ["TeamSnap", 1], ["Apto", 1], ["Verbalize.it", 1], ["Kapost", 1], ["Mondo Robot", 1], ["Active Junky", 1], ["JayBird", 1], ["Welltok", 1]]
+```  
+
+## Contributing
+
+1. Fork it ( https://github.com/[my-github-username]/jobs-former_students/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 +1,2 @@
+require "bundler/gem_tasks"
+

data/jobs-former_students.gemspec

@@ -0,0 +1,28 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'jobs/former_students/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "jobs-former_students"
+  spec.version       = Jobs::FormerStudents::VERSION
+  spec.authors       = ["Jim Sutton"]
+  spec.email         = ["jimsuttonjimsutton@gmail.com"]
+  spec.summary       = "Small gem to scrape company names from former students." 
+  spec.description   = "Small gem to scrape company names from former students." 
+  spec.homepage      = "http://github.com/turingschool/jobs-former_students"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.7"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "minitest"
+  spec.add_development_dependency "pry"
+
+  spec.add_dependency "mechanize", "~> 2.7"
+  
+end

data/lib/jobs/former_students.rb

@@ -0,0 +1,8 @@
+require "jobs/former_students/version"
+require "jobs/former_students/scraper"
+
+module Jobs
+  module FormerStudents
+
+  end
+end

data/lib/jobs/former_students/scraper.rb

@@ -0,0 +1,58 @@
+require 'mechanize'
+
+module Jobs
+  module FormerStudents
+    class Scraper
+      attr_reader :companies, :agent
+
+      def initialize
+        @companies = [] 
+        @agent = Mechanize.new
+      end
+
+      def url_to_scrape(uri)
+        base_url = 'https://students.gschool.it/students/'
+        agent.get( base_url + "#{uri}" )
+      end
+
+      def get_company_name(student_number)
+        page = url_to_scrape(student_number)
+        company_name = page.at('.hero-subtitle > h3').text.strip
+        companies.push(company_name) unless company_name.empty?
+        puts "Company at /students/" + "#{student_number} is: " + "#{company_name}" 
+        companies
+        rescue Mechanize::ResponseCodeError
+          puts "404 error at /students" + "#{student_number}"
+          return companies
+      end
+
+      def get_company_names(total_students)
+        i = 1
+        until i == total_students
+          get_company_name(i)
+          i += 1
+        end
+        companies.find_all { |co| !co.empty? }
+      end
+
+      def get_unique_company_names(total_students)
+        get_company_names(total_students).uniq
+      end
+
+      def total_students_employed_per_company(total_students)
+        companies = get_company_names(total_students)
+        companies.inject(Hash.new(0)) do |h,v| 
+          h[v] += 1 
+          h 
+        end 
+      end
+
+      def sort_by_frequency(total_students)
+        frequency = total_students_employed_per_company(total_students)
+        frequency.sort_by { |k,v| v }.reverse
+      end
+
+    end
+  end
+end
+

data/lib/jobs/former_students/version.rb

@@ -0,0 +1,5 @@
+module Jobs
+  module FormerStudents
+    VERSION = "0.0.1"
+  end
+end

data/test/jobs/former_students/scraper_test.rb

@@ -0,0 +1,56 @@
+require 'minitest/autorun'
+require 'minitest/pride'
+require './lib/jobs/former_students/scraper'
+require 'mechanize'
+
+class ScraperTest < Minitest::Test
+
+  def test_it_exists
+    assert Jobs::FormerStudents::Scraper
+  end
+
+  def test_it_returns_company_name
+    scraper = Jobs::FormerStudents::Scraper.new
+    results = scraper.get_company_name(12)
+    assert_equal ["Acumen Digital"], results 
+  end
+
+  def test_it_returns_empty_array_if_matching_selector_is_not_on_page
+    scraper = Jobs::FormerStudents::Scraper.new
+    result = scraper.get_company_name(80) # this page exists but with no information 
+    assert_equal [], result 
+  end
+
+  def test_it_returns_empty_string_if_matching_selector_is_not_on_page
+    scraper = Jobs::FormerStudents::Scraper.new
+    result = scraper.get_company_name(2) # this page does not exist / is a 404 page
+    assert_equal [], result 
+  end
+
+  def test_it_creates_array_of_company_names
+    scraper = Jobs::FormerStudents::Scraper.new
+    results = scraper.get_unique_company_names(90) # Searches '/students/1' through '/students/90' 
+    refute results.nil?
+    assert results.kind_of?(Array)
+    refute results.any? { |result| result.empty?}
+  end
+
+  def test_it_returns_only_unique_names
+    scraper = Jobs::FormerStudents::Scraper.new
+    results = scraper.get_unique_company_names(30) # There are 4 students at Zayo in this search group 
+    zayo = results.find_all {|co| co == "Zayo" }
+    refute zayo.count > 1 
+  end
+
+  def test_it_totals_students_per_company
+    scraper = Jobs::FormerStudents::Scraper.new
+    results = scraper.total_students_employed_per_company(80) # There are 4 students at Zayo in this search group 
+    assert_equal 4, results["Zayo"]
+  end
+
+  def test_it_sorts_by_frequency
+    scraper = Jobs::FormerStudents::Scraper.new
+    results = scraper.sort_by_frequency(80)  
+    assert_equal ["Zayo", 4], results.first
+  end
+end

metadata

@@ -0,0 +1,125 @@
+--- !ruby/object:Gem::Specification
+name: jobs-former_students
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Jim Sutton
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-12-25 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.7'
+- !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: minitest
+  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'
+- !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'
+- !ruby/object:Gem::Dependency
+  name: mechanize
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.7'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.7'
+description: Small gem to scrape company names from former students.
+email:
+- jimsuttonjimsutton@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- jobs-former_students.gemspec
+- lib/jobs/former_students.rb
+- lib/jobs/former_students/scraper.rb
+- lib/jobs/former_students/version.rb
+- test/jobs/former_students/scraper_test.rb
+homepage: http://github.com/turingschool/jobs-former_students
+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: 2.4.2
+signing_key: 
+specification_version: 4
+summary: Small gem to scrape company names from former students.
+test_files:
+- test/jobs/former_students/scraper_test.rb