Merge branch 'crawler' into 'master'

Create crawler

See merge request !2

Gemfile

@@ -6,6 +6,9 @@ ruby '3.0.1'
 # Bundle edge Rails instead: gem 'rails', github: 'rails/rails', branch: 'main'
 gem 'rails', '~> 6.1.3', '>= 6.1.3.2'
 gem 'bootstrap', '~> 5.0.1'
+gem 'nokogiri', '~> 1.11', '>= 1.11.7'
+
+
 # Use sqlite3 as the database for Active Record
 gem 'mysql2', '~> 0.5.3'
 # Use Puma as the app server
@@ -28,6 +31,7 @@ gem 'jbuilder', '~> 2.7'
 
 # Reduces boot times through caching; required in config/boot.rb
 gem 'bootsnap', '>= 1.4.4', require: false
+gem 'whenever', require: false
 
 group :development, :test do
   # Call 'byebug' anywhere in the code to stop execution and get a debugger console

Gemfile.lock

@@ -82,6 +82,7 @@ GEM
       regexp_parser (>= 1.5, < 3.0)
       xpath (~> 3.2)
     childprocess (3.0.0)
+    chronic (0.10.2)
     concurrent-ruby (1.1.9)
     crass (1.0.6)
     erubi (1.10.0)
@@ -200,6 +201,8 @@ GEM
     websocket-driver (0.7.5)
       websocket-extensions (>= 0.1.0)
     websocket-extensions (0.1.5)
+    whenever (1.0.0)
+      chronic (>= 0.6.3)
     xpath (3.2.0)
       nokogiri (~> 1.8)
     zeitwerk (2.4.2)
@@ -215,6 +218,7 @@ DEPENDENCIES
   jbuilder (~> 2.7)
   listen (~> 3.3)
   mysql2 (~> 0.5.3)
+  nokogiri (~> 1.11, >= 1.11.7)
   puma (~> 5.0)
   rack-mini-profiler (~> 2.0)
   rails (~> 6.1.3, >= 6.1.3.2)
@@ -226,6 +230,7 @@ DEPENDENCIES
   web-console (>= 4.1.0)
   webdrivers
   webpacker (~> 5.0)
+  whenever
 
 RUBY VERSION
    ruby 3.0.1p64

config/application.rb

-require_relative "boot"
+require_relative 'boot'
 
-require "rails/all"
+require 'rails/all'
 
 # Require the gems listed in Gemfile, including any gems
 # you've limited to :test, :development, or :production.

config/boot.rb

 ENV['BUNDLE_GEMFILE'] ||= File.expand_path('../Gemfile', __dir__)
 
-require "bundler/setup" # Set up gems listed in the Gemfile.
-require "bootsnap/setup" # Speed up boot time by caching expensive operations.
+require 'bundler/setup' # Set up gems listed in the Gemfile.
+require 'bootsnap/setup' # Speed up boot time by caching expensive operations.

config/environment.rb

 # Load the Rails application.
-require_relative "application"
+require_relative 'application'
 
 # Initialize the Rails application.
 Rails.application.initialize!

config/environments/development.rb

-require "active_support/core_ext/integer/time"
+require 'active_support/core_ext/integer/time'
 
 Rails.application.configure do
   # Settings specified here will take precedence over those in config/application.rb.

config/environments/production.rb

-require "active_support/core_ext/integer/time"
+require 'active_support/core_ext/integer/time'
 
 Rails.application.configure do
   # Settings specified here will take precedence over those in config/application.rb.
@@ -53,7 +53,7 @@ Rails.application.configure do
   config.log_level = :info
 
   # Prepend all log lines with the following tags.
-  config.log_tags = [ :request_id ]
+  config.log_tags = [:request_id]
 
   # Use a different cache store in production.
   # config.cache_store = :mem_cache_store
@@ -88,7 +88,7 @@ Rails.application.configure do
   # require "syslog/logger"
   # config.logger = ActiveSupport::TaggedLogging.new(Syslog::Logger.new 'app-name')
 
-  if ENV["RAILS_LOG_TO_STDOUT"].present?
+  if ENV['RAILS_LOG_TO_STDOUT'].present?
     logger           = ActiveSupport::Logger.new(STDOUT)
     logger.formatter = config.log_formatter
     config.logger    = ActiveSupport::TaggedLogging.new(logger)

config/environments/test.rb

-require "active_support/core_ext/integer/time"
+require 'active_support/core_ext/integer/time'
 
 # The test environment is used exclusively to run your application's
 # test suite. You never need to work with it otherwise. Remember that

config/initializers/backtrace_silencers.rb

@@ -5,4 +5,4 @@
 
 # You can also remove all the silencers if you're trying to debug a problem that might stem from framework code
 # by setting BACKTRACE=1 before calling your invocation, like "BACKTRACE=1 ./bin/rails runner 'MyClass.perform'".
-Rails.backtrace_cleaner.remove_silencers! if ENV["BACKTRACE"]
+Rails.backtrace_cleaner.remove_silencers! if ENV['BACKTRACE']

config/initializers/filter_parameter_logging.rb

 # Be sure to restart your server when you modify this file.
 
 # Configure sensitive parameters which will be filtered from the log file.
-Rails.application.config.filter_parameters += [
-  :passw, :secret, :token, :_key, :crypt, :salt, :certificate, :otp, :ssn
+Rails.application.config.filter_parameters += %i[
+  passw secret token _key crypt salt certificate otp ssn
 ]

config/puma.rb

@@ -4,25 +4,25 @@
 # the maximum value specified for Puma. Default is set to 5 threads for minimum
 # and maximum; this matches the default thread size of Active Record.
 #
-max_threads_count = ENV.fetch("RAILS_MAX_THREADS") { 5 }
-min_threads_count = ENV.fetch("RAILS_MIN_THREADS") { max_threads_count }
+max_threads_count = ENV.fetch('RAILS_MAX_THREADS') { 5 }
+min_threads_count = ENV.fetch('RAILS_MIN_THREADS') { max_threads_count }
 threads min_threads_count, max_threads_count
 
 # Specifies the `worker_timeout` threshold that Puma will use to wait before
 # terminating a worker in development environments.
 #
-worker_timeout 3600 if ENV.fetch("RAILS_ENV", "development") == "development"
+worker_timeout 3600 if ENV.fetch('RAILS_ENV', 'development') == 'development'
 
 # Specifies the `port` that Puma will listen on to receive requests; default is 3000.
 #
-port ENV.fetch("PORT") { 3000 }
+port ENV.fetch('PORT') { 3000 }
 
 # Specifies the `environment` that Puma will run in.
 #
-environment ENV.fetch("RAILS_ENV") { "development" }
+environment ENV.fetch('RAILS_ENV') { 'development' }
 
 # Specifies the `pidfile` that Puma will use.
-pidfile ENV.fetch("PIDFILE") { "tmp/pids/server.pid" }
+pidfile ENV.fetch('PIDFILE') { 'tmp/pids/server.pid' }
 
 # Specifies the number of `workers` to boot in clustered mode.
 # Workers are forked web server processes. If using threads and workers together

config/schedule.rb

+every 1.day, at: '08:00 am' do
+  rake 'crawler:all'
+end

config/spring.rb

 Spring.watch(
-  ".ruby-version",
-  ".rbenv-vars",
-  "tmp/restart.txt",
-  "tmp/caching-dev.txt"
+  '.ruby-version',
+  '.rbenv-vars',
+  'tmp/restart.txt',
+  'tmp/caching-dev.txt'
 )

db/migrate/20210720102108_remove_address_from_cities.rb

+class RemoveAddressFromCities < ActiveRecord::Migration[6.1]
+  def change
+    remove_column :cities, :address, :string
+  end
+end

db/migrate/20210720102427_remove_message_from_companies.rb

+class RemoveMessageFromCompanies < ActiveRecord::Migration[6.1]
+  def change
+    remove_column :companies, :message, :text
+    remove_column :companies, :benefits, :string
+    remove_column :companies, :type, :string
+    remove_column :companies, :total_employee, :integer
+  end
+end

db/migrate/20210720103200_add_address_overview_to_companies.rb

+class AddAddressOverviewToCompanies < ActiveRecord::Migration[6.1]
+  def change
+    add_column :companies, :address, :string
+    add_column :companies, :overview, :text
+  end
+end

db/migrate/20210720103330_remove_degree_from_jobs.rb

+class RemoveDegreeFromJobs < ActiveRecord::Migration[6.1]
+  def change
+    remove_column :jobs, :degree, :string
+  end
+end

db/migrate/20210720145646_change_jobs.rb

+class ChangeJobs < ActiveRecord::Migration[6.1]
+  def up
+    change_column :jobs, :experience, :string
+    change_column :jobs, :salary, :string
+    rename_column :jobs, :type, :job_type
+  end
+
+  def down
+    change_column :jobs, :experience, :integer
+    change_column :jobs, :salary, :integer
+  end
+end

db/migrate/20210723035105_change_companies.rb

+class ChangeCompanies < ActiveRecord::Migration[6.1]
+  def change
+    change_column :companies, :address, :text
+  end
+end

db/schema.rb

@@ -10,7 +10,7 @@
 #
 # It's strongly recommended that you check this file into your version control system.
 
-ActiveRecord::Schema.define(version: 2021_07_09_043354) do
+ActiveRecord::Schema.define(version: 2021_07_23_035105) do
 
   create_table "apply_jobs", charset: "utf8mb4", collation: "utf8mb4_0900_ai_ci", force: :cascade do |t|
     t.bigint "user_id", null: false
@@ -25,7 +25,6 @@ ActiveRecord::Schema.define(version: 2021_07_09_043354) do
   create_table "cities", charset: "utf8mb4", collation: "utf8mb4_0900_ai_ci", force: :cascade do |t|
     t.bigint "region_id", null: false
     t.string "name"
-    t.string "address"
     t.datetime "created_at", precision: 6, null: false
     t.datetime "updated_at", precision: 6, null: false
     t.index ["region_id"], name: "index_cities_on_region_id"
@@ -43,12 +42,10 @@ ActiveRecord::Schema.define(version: 2021_07_09_043354) do
   create_table "companies", charset: "utf8mb4", collation: "utf8mb4_0900_ai_ci", force: :cascade do |t|
     t.string "name"
     t.text "description"
-    t.integer "total_employee"
-    t.string "type"
-    t.string "benefits"
-    t.text "message"
     t.datetime "created_at", precision: 6, null: false
     t.datetime "updated_at", precision: 6, null: false
+    t.text "address"
+    t.text "overview"
   end
 
   create_table "companies_cities", charset: "utf8mb4", collation: "utf8mb4_0900_ai_ci", force: :cascade do |t|
@@ -99,11 +96,10 @@ ActiveRecord::Schema.define(version: 2021_07_09_043354) do
     t.text "overview"
     t.text "requirement"
     t.text "other_requirement"
-    t.integer "salary"
-    t.string "type"
+    t.string "salary"
+    t.string "job_type"
     t.string "level"
-    t.integer "experience"
-    t.string "degree"
+    t.string "experience"
     t.string "benefits"
     t.datetime "expired_at"
     t.datetime "created_at", precision: 6, null: false

lib/tasks/crawler.rake

+require 'open-uri'
+
+namespace :crawler do
+  desc 'Crawl Jobs and Companies'
+  task jobs: :environment do
+    logger = Logger.new("#{Rails.root}/log/crawler_jobs.log")
+    logger.info "Start crawler job at: #{Time.current}"
+    base_url = Nokogiri::HTML(URI.open('https://careerbuilder.vn/'))
+    job_page = base_url.css('div.menu div.dropdown-menu ul li a')[0].attributes['href'].value
+    parse_job_page = Nokogiri::HTML(URI.open(job_page))
+    job_listing = parse_job_page.css('div.job-item')
+    per_page = job_listing.present? ? job_listing.length : 0
+    page = 1
+    total = parse_job_page.css('div.job-found p').text.gsub(/[^0-9]/, '')
+    last_page = (total.to_f / per_page).round
+
+    while page <= last_page
+      pagination_page_job = "https://careerbuilder.vn/viec-lam/tat-ca-viec-lam-trang-#{page}-vi.html"
+      parse_pagination_page_job = Nokogiri::HTML(URI.open(pagination_page_job))
+      pagination_job_listing = parse_pagination_page_job.css('div.job-item')
+      pagination_job_listing.each do |detail_jobs|
+        company_url = detail_jobs.css('a.company-name').attribute('href').text
+        next if company_url == 'javascript:void(0);'
+
+        slug_company = CGI.escape(company_url.gsub('https://careerbuilder.vn/vi/nha-tuyen-dung/', '').strip)
+        company_page = "https://careerbuilder.vn/vi/nha-tuyen-dung/#{slug_company}"
+        parse_company_page = Nokogiri::HTML(URI.open(company_page).read)
+        company = parse_company_page.css('div.container')
+        company_name = company.css('div.company-info div.content p.name')
+        next if company_name.nil?
+
+        logger.info("Link company: #{company_page}")
+
+        company_info = company.css('div.company-info div.content')
+        address = company_info.css('p')[1].try(:text)
+        description = company_info.css('ul li').text
+        overview = company.css('div.row div.content p').text.squish.strip
+
+        Company.find_or_create_by(
+          name: company_name.text,
+          address: address,
+          description: description,
+          overview: overview
+        )
+
+        slug_job = CGI.escape(detail_jobs.css('a.job_link').attribute('href').text
+        .gsub('https://careerbuilder.vn/vi/tim-viec-lam/', '').strip)
+        job_detail_page = "https://careerbuilder.vn/vi/tim-viec-lam/#{slug_job}"
+        parse_job_detail_page = Nokogiri::HTML(URI.open(job_detail_page))
+        detail_job = parse_job_detail_page.css('div.container')
+        title = detail_job.css('div.job-desc h1.title')
+        next if title.nil?
+
+        logger.info("Link job: #{job_detail_page}")
+
+        salary, experience, type, level, expired_at = ''
+        detail_content = detail_job.css('div.row div.detail-box.has-background ul li')
+        detail_content.each do |content|
+          case content.css('strong').text.strip
+          when 'Lương'
+            salary = content.css('p').text
+          when 'Kinh nghiệm'
+            experience = content.css('p').text.gsub('\r\n', '').strip
+          when 'Hình thức'
+            type = content.css('p').text
+          when 'Cấp bậc'
+            level = content.css('p').text
+          when 'Hết hạn nộp'
+            expired_at = content.css('p').text
+          end
+        end
+        benefits, overview, requirement, other_requirement = ''
+        detail_require = detail_job.css('div.detail-row')
+        detail_require.each do |detail|
+          case detail.css('h3').text
+          when 'Phúc lợi '
+            benefits = detail.css('ul li').text
+          when 'Mô tả Công việc'
+            overview = detail.css('p').text
+          when 'Yêu Cầu Công Việc'
+            requirement = detail.css('p').text
+          when 'Thông tin khác'
+            other_requirement = detail.css('div.content_fck ul li').text.squish
+          end
+        end
+
+        job = Job.find_or_create_by(
+          title: title.text,
+          salary: salary,
+          experience: experience,
+          job_type: type,
+          level: level,
+          expired_at: expired_at,
+          benefits: benefits,
+          overview: overview,
+          requirement: requirement,
+          other_requirement: other_requirement,
+          company_id: Company.find_by(name: company_name.text).id
+        )
+
+        job_industries = []
+        industries = detail_job.css('div.detail-box.has-background ul li p a')
+        industries.each do |industry|
+          name = industry.text.squish
+          job_industry = Industry.find_by(name: name)
+          next if job_industry.nil?
+
+          job_industries << job_industry
+        end
+        job.industries << job_industries
+
+        job_cities = []
+        location = detail_job.css('div.map p a')
+        location.each do |city|
+          name = city.text
+          job_city = City.find_by(name: name)
+          next if job_city.nil?
+
+          job_cities << job_city
+        end
+
+        job.cities << job_cities
+      rescue StandardError => error
+        logger.error "The company url has error: #{company_page}"
+        logger.error "The job url has error: #{job_detail_page}"
+        logger.error error
+        next
+      end
+      page += 1
+    end
+    logger.info "End crawler job at: #{Time.current}"
+  end
+
+  desc 'Crawl Industries'
+  task industries: :environment do
+    industries_listing = parse_base_url.css('div.col-md-6.col-lg-4.cus-col ul.list-jobs li a')
+    industries_listing.each do |industry|
+      industry_name = industry.text
+      Industry.find_or_create_by(
+        name: industry_name
+      )
+    end
+  end
+
+  desc 'Crawl Cities'
+  task cities: :environment do
+    cities = parse_base_url.css('div.container div.jobs-in-country li a')
+    cities.each do |city|
+      city_name = city.text.gsub('Việc làm tại', '').strip
+      City.find_or_create_by(
+        name: city_name,
+        region_id: Region.find_by(name: 'Trong Nước').id
+      )
+    end
+    cities_foreign = parse_base_url.css('div.container div.overseas-jobs li a')
+    cities_foreign.each do |city|
+      city_name = city.text.strip
+      City.find_or_create_by(
+        name: city_name,
+        region_id: Region.find_by(name: 'Nước Ngoài').id
+      )
+    end
+  end
+
+  desc 'Crawl Regions'
+  task regions: :environment do
+    regions = parse_base_url.css('div.container div.col-xl-3 div.main-jobs-by-location h3')
+    regions.each do |region|
+      region_name = region.text.gsub('Việc Làm', '').strip
+      Region.find_or_create_by(
+        name: region_name
+      )
+    end
+  end
+
+  desc 'Craw regions, cities, industries, jobs and companies'
+  task all: %i[regions cities industries jobs]
+
+  def parse_base_url
+    base_url = Nokogiri::HTML(URI.open('https://careerbuilder.vn/'))
+    industries_url = base_url.css('div.menu div.dropdown-menu ul li a')[1].attributes['href'].text
+    Nokogiri::HTML(URI.open(industries_url))
+  end
+end