remote_job_scraper 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: debb2440ac5898b2fc0642017b9bf01aa6adb89f
+  data.tar.gz: e370546575983d780c9ed6aa28d7611270b08b86
+SHA512:
+  metadata.gz: '0844c2a152641653717d587829e8a73aca58292afb175e014a4edc08386ff009de153703fc37d8d271cfd5919441a73a25b5f6ee79c2dda2cd375d1bccbe2e70'
+  data.tar.gz: cfd1916966d735458d11f4953f0ec26932833e7c03fb028890bfb3f6226ff30c0ce1c58f5a733597f070d3b185dca3597abcacf8f3aaa6befc690cb699366cd5

data/.gitignore

@@ -0,0 +1,13 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+data/
+
+# rspec failure tracking
+.rspec_status
+.DS_Store

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.ruby-version

@@ -0,0 +1 @@
+2.4.1

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.0.0
+before_install: gem install bundler -v 1.16.0

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at rt.trojanowski@gmail.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

data/Gemfile

@@ -0,0 +1,6 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in remote_job_scraper.gemspec
+gemspec

data/Gemfile.lock

@@ -0,0 +1,61 @@
+PATH
+  remote: .
+  specs:
+    remote_job_scraper (0.1.0)
+      nokogiri
+      spreadsheet
+      thor
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    addressable (2.6.0)
+      public_suffix (>= 2.0.2, < 4.0)
+    byebug (10.0.2)
+    crack (0.4.3)
+      safe_yaml (~> 1.0.0)
+    diff-lcs (1.3)
+    hashdiff (0.3.8)
+    mini_portile2 (2.4.0)
+    nokogiri (1.10.1)
+      mini_portile2 (~> 2.4.0)
+    public_suffix (3.0.3)
+    rake (10.5.0)
+    rspec (3.8.0)
+      rspec-core (~> 3.8.0)
+      rspec-expectations (~> 3.8.0)
+      rspec-mocks (~> 3.8.0)
+    rspec-core (3.8.0)
+      rspec-support (~> 3.8.0)
+    rspec-expectations (3.8.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.8.0)
+    rspec-mocks (3.8.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.8.0)
+    rspec-support (3.8.0)
+    ruby-ole (1.2.12.1)
+    safe_yaml (1.0.4)
+    spreadsheet (1.1.8)
+      ruby-ole (>= 1.0)
+    thor (0.20.3)
+    vcr (4.0.0)
+    webmock (3.5.1)
+      addressable (>= 2.3.6)
+      crack (>= 0.3.2)
+      hashdiff
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.16)
+  byebug
+  rake (~> 10.0)
+  remote_job_scraper!
+  rspec (~> 3.0)
+  vcr
+  webmock
+
+BUNDLED WITH
+   1.16.5

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2019 Rafał Trojanowski
+
+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 +1,49 @@
+# RemoteJobScraper 💻🌏
+
+Ruby gem that collects job offers for remote positions with ease.
+
+Going through many job listings and finding the right one may be a time-consuming process. That's why this tool has been built. It allows to automate the process, retrieve necessary data and store it in CSV/Excel file in just a few minutes. The main focus is to inform a user about the location (time-zone) required for a position.
+
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'remote_job_scraper'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install remote_job_scraper
+
+## Usage
+
+    $ bundle exec exe/remote_job_scraper
+
+
+* Tested with Ruby versions:
+
+  * [x] 2.4.1
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also 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`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/remote_job_scraper. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+
+## Code of Conduct
+
+Everyone interacting in the RemoteJobScraper project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/remote_job_scraper/blob/master/CODE_OF_CONDUCT.md).

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "remote_job_scraper"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/exe/remote_job_scraper

@@ -0,0 +1,5 @@
+#!/usr/bin/env ruby
+
+require "remote_job_scraper"
+
+RemoteJobScraper::CLI.start(ARGV)

data/lib/remote_job_scraper/version.rb

@@ -0,0 +1,3 @@
+module RemoteJobScraper
+  VERSION = "0.1.0"
+end

data/lib/remote_job_scraper.rb

@@ -0,0 +1,64 @@
+require 'remote_job_scraper/version'
+
+require 'sites/we_work_remotely'
+require 'sites/remote_ok'
+require 'sites/jobs_rails42'
+
+require 'support/offer_parser'
+require 'support/user_agent'
+require 'support/spreadsheet_creator'
+
+require 'nokogiri'
+require 'open-uri'
+require 'csv'
+require "thor"
+
+module RemoteJobScraper
+
+  AVAILABLE_SERVICES = %w(we_work_remotely remote_ok 42jobs_rails)
+
+  class CLI < Thor
+
+    desc 'collect_jobs', 'Retrieves data from all sites'
+    def collect_jobs
+      [Sites::WeWorkRemotely, Sites::RemoteOk].each do |klass|
+        klass.new.collect_jobs
+      end
+    end
+
+    desc 'collect_jobs_from', 'Retrieves data from specified service'
+    def collect_jobs_from(service_name)
+      case service_name
+      when 'we_work_remotely'
+        then Sites::WeWorkRemotely.new.collect_jobs
+      when 'remote_ok'
+        then Sites::RemoteOk.new.collect_jobs
+      when '42jobs_rails'
+        then Sites::JobsRails42.new.collect_jobs
+      else
+        raise "#{service_name} is not correct. Use: #{AVAILABLE_SERVICES.join(', ')}."
+      end
+    end
+
+    desc 'generate_summary', 'Collect all data and export to XLS file'
+    def generate_summary
+      Support::SpreadsheetCreator.generate
+    end
+
+    desc 'clean_up', 'Removes all stored data'
+    def clean_up
+      puts "This command will remote all stored data."
+      puts "Press Ctrl-C to abort."
+
+      sleep 2
+
+      FileUtils.rm_rf('data')
+      puts "Removed data."
+    end
+
+  end
+
+  def self.root
+    File.dirname __dir__
+  end
+end

data/lib/sites/base.rb

@@ -0,0 +1,62 @@
+module Sites
+  class Base
+
+    attr_reader :job_type, :doc, :url
+
+    def initialize(job_type: :programming)
+      @job_type = job_type
+      @url = build_url
+      @doc = Nokogiri::HTML(open_page(@url))
+      @current_time = Time.new
+      @timestamp = @current_time.strftime("%Y%m%d%H%M%S")
+      @count = get_count
+    end
+
+    def open_page(url)
+      sleep(rand(0..2.0)) unless ENV['RAILS_ENV'] == 'test' # less mechanical behaviour
+
+      if ENV['RAILS_ENV'] == 'test'
+        open(url)
+      else
+        open(url, 'User-Agent' => user_agent)
+      end
+    end
+
+    private
+
+    def user_agent
+      Support::UserAgent::LIST.sample
+    end
+
+    def build_url
+      case job_type
+        when :programming
+          then "#{self.class::HOST}#{self.class::PROGRAMMING}"
+        when :devops
+          then "#{self.class::HOST}#{self.class::DEVOPS}"
+        else
+          raise "Error"
+        end
+    end
+
+    def filepath
+      return test_filepath if ENV["RAILS_ENV"] == 'test'
+      "#{self.class::STORE_DIR}/#{@timestamp}.csv"
+    end
+
+    def test_filepath
+      "spec/fixtures/data/#{underscore(self.class.name.split('::').last)}/#{@timestamp}.csv"
+    end
+
+    # https://stackoverflow.com/a/5622585
+    def underscore(camel_cased_word)
+      word = camel_cased_word.dup
+      word.gsub!(/::/, '/')
+      word.gsub!(/([A-Z]+)([A-Z][a-z])/,'\1_\2')
+      word.gsub!(/([a-z\d])([A-Z])/,'\1_\2')
+      word.tr!("-", "_")
+      word.downcase!
+      word
+    end
+  end
+end

data/lib/sites/elixir_radar.rb

@@ -0,0 +1,10 @@
+require_relative 'base'
+
+module Sites
+  class ElixirRadar < Base
+
+    HOST = 'http://plataformatec.com.br/'.freeze
+    PROGRAMMING = '/elixir-radar/jobs'.freeze
+
+  end
+end

data/lib/sites/jobs_rails42.rb

@@ -0,0 +1,64 @@
+module Sites
+  class JobsRails42 < Base
+
+    # @TODO/NOTE: There is pagination on this site, it would be cool to find a way
+    # to grab more offers than just first page (25 items)
+
+    # I had to rename this class because we are not allowed to have numbers
+    # on the beginning of the class name (42JobsRails won't work).
+
+    HOST = 'https://www.42jobs.io'.freeze
+    PROGRAMMING = '/rails/jobs-remote'.freeze
+    JOB_ITEM_SELECTOR = 'li.job-offers__item a'.freeze
+    STORE_DIR = 'data/jobs_rails42'.freeze
+
+    NUMBER_OF_PAGES = 10
+
+    def initialize(job_type: :programming)
+      @job_type = job_type
+      @url = build_url
+      @doc = nil
+      @current_time = Time.new
+      @timestamp = @current_time.strftime("%Y%m%d%H%M%S")
+      @count = get_count
+    end
+
+    def collect_jobs
+      (1..NUMBER_OF_PAGES).to_a.each do |page|
+        current_page = "#{@url}?page=#{page}"
+        doc = Nokogiri::HTML(open_page(current_page))
+        process_page(doc, current_page, page)
+      end
+    end
+
+    private
+
+    def process_page(doc, page_url, page)
+      puts "[Info] Getting the data from #{page_url} at #{@current_time}..."
+      FileUtils.mkdir_p STORE_DIR
+
+      CSV.open(filepath, 'ab') do |csv|
+        doc.css(JOB_ITEM_SELECTOR).each do |link|
+          job_url = "#{HOST}#{link["href"]}"
+          puts "[Info] Processing #{job_url}..."
+          job_page = Nokogiri::HTML(open_page(job_url))
+          offer_text = job_page.css('.job-offer__description').to_s
+
+          location = Support::OfferParser.get_location(offer_text)
+          region   = nil
+          keywords = Support::OfferParser.get_keywords(offer_text)
+
+          csv << [job_url, location, region, keywords]
+        end
+      end
+
+      puts "[Done] Collected #{@count} job offers from #{url}. Data stores in: #{filepath}." if page == NUMBER_OF_PAGES
+    end
+
+    private
+
+    def get_count
+      25 * NUMBER_OF_PAGES
+    end
+  end
+end

data/lib/sites/rails_jobs.rb

@@ -0,0 +1,9 @@
+require_relative 'base'
+
+module Sites
+  class RailsJobs < Base
+
+    HOST = 'https://www.railsjobs.com'.freeze
+
+  end
+end

data/lib/sites/remote_ok.rb

@@ -0,0 +1,45 @@
+require_relative 'base'
+
+module Sites
+  class RemoteOk < Base
+
+    HOST = 'https://remoteok.io'.freeze
+    PROGRAMMING = '/remote-dev-jobs'.freeze
+    JOB_ITEM_SELECTOR = 'tr.job'.freeze
+    STORE_DIR = 'data/remote_ok'.freeze
+
+    def initialize(args = {})
+      super(args = {})
+    end
+
+    def collect_jobs
+      puts "[Info] Getting the data from #{url} at #{@current_time}..."
+      FileUtils.mkdir_p STORE_DIR
+
+      CSV.open(filepath, 'w') do |csv|
+        doc.css(JOB_ITEM_SELECTOR).each do |link|
+          job_url = "#{HOST}#{link["data-url"]}"
+          puts "[Info] Processing #{job_url}..."
+          job_page = Nokogiri::HTML(open_page(job_url))
+          offer_text = job_page.css('td.heading').to_s
+
+          location = Support::OfferParser.get_location(offer_text)
+          region   = nil
+          keywords = Support::OfferParser.get_keywords(offer_text)
+
+          csv << [job_url, location, region, keywords]
+        end
+      end
+
+      puts "[Done] Collected #{@count} job offers from #{url}. Data stores in: #{filepath}."
+    end
+
+    private
+
+    def get_count
+      count = doc.css(JOB_ITEM_SELECTOR).map { |link| link['data-url'] }.size
+      puts "[Info] There is #{count} remote jobs available."
+      count
+    end
+  end
+end

data/lib/sites/we_work_remotely.rb

@@ -0,0 +1,52 @@
+require_relative 'base'
+
+module Sites
+  class WeWorkRemotely < Base
+
+    HOST = 'https://weworkremotely.com'.freeze
+    PROGRAMMING = '/categories/remote-programming-jobs'.freeze
+    DEVOPS     = '/categories/remote-devops-sysadmin-jobs'.freeze
+    JOB_ITEM_SELECTOR = '.jobs-container li a'.freeze
+    STORE_DIR = 'data/we_work_remotely'
+
+    def initialize(args = {})
+      super(args = {})
+    end
+
+    def collect_jobs
+      puts "[Info] Getting the data from #{url} at #{@current_time}..."
+      FileUtils.mkdir_p STORE_DIR
+
+      CSV.open(filepath, 'w') do |csv|
+        doc.css(JOB_ITEM_SELECTOR).each do |link|
+          if link["href"].start_with?("/remote-jobs")
+            job_url = "#{HOST}#{link["href"]}"
+            puts "[Info] Processing #{job_url}..."
+            job_page = Nokogiri::HTML(open_page(job_url))
+            offer_text = job_page.css('.listing-container').to_s
+
+            region = job_page.css('span.region').first
+            location = job_page.css('span.location').first
+
+            keywords = Support::OfferParser.get_keywords(offer_text)
+
+            csv << [job_url, location, region, keywords]
+          end
+        end
+      end
+
+      puts "[Done] Collected #{@count} job offers from #{url}. Data stores in: #{filepath}."
+    end
+
+    private
+
+    def get_count
+      count = doc.css(JOB_ITEM_SELECTOR)
+        .map { |link| link['href'] }
+        .select { |href| href.start_with?('/remote-jobs') }
+        .size
+      puts "[Info] There is #{count} remote jobs available."
+      count
+    end
+  end
+end

data/lib/support/offer_parser.rb

@@ -0,0 +1,52 @@
+module Support
+  module OfferParser
+
+    LOCATION_DICT = ['location', 'based']
+    KEYWORDS      = [
+      'ruby',
+      'elixir',
+      'react',
+      'remote',
+      'graphql'
+    ]
+
+    def self.get_location(content, dict = LOCATION_DICT)
+      indexes = Array.new
+      tokens = get_tokens(content)
+      indexes = dict.map { |q| [tokens.find_index(q), q] }
+      locations = Array.new
+
+      indexes.each do |index|
+        next if index[0].nil?
+
+        locations << tokens[index[0] + 1].gsub(',', '') if index[1] == 'location'
+        locations << tokens[index[0] - 1].gsub(',', '') if index[1] == 'based'
+      end
+
+      locations.join(', ').capitalize
+    end
+
+    def self.get_keywords(content, keywords = KEYWORDS)
+      indexes = Array.new
+      tokens = get_tokens(content)
+      indexes = keywords.map { |q| [tokens.find_index(q), q] }
+      keywords = Array.new
+
+      indexes.each do |index|
+        next if index[0].nil?
+        keywords << tokens[index[0]].gsub(',', '')
+      end
+
+      keywords.map(&:capitalize).join(', ')
+    end
+
+    def self.get_tokens(content)
+      content
+        .gsub('.', '')
+        .gsub(',', '')
+        .gsub(':', '')
+        .downcase
+        .split(/[\s-]/)
+    end
+  end
+end