jobs_crawler 0.1.3 → 0.1.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a817c1a6c6757e2183dff2ede4daf2ad39ae140d7c5a4f2d6863cc59de562fc8
-  data.tar.gz: b807d2ffcd566f6953bf97ef72457ac2657e447694adc394b234b742ba01eda5
+  metadata.gz: 07b12ecf9c7a3bbaa3b6a64a7df48ed4a0ea5d73b6500e75a6324ed35a17cafc
+  data.tar.gz: ce32b52ec4c6cb59ec21383b85c9d9dbdd7a7b4f81f9834b2db309fd71a0c7ae
 SHA512:
-  metadata.gz: 7e19c50037052f0689cba5cf030fe343fe5880b5c074e0d4fdc004cfaa58ec2098a84822f262991a7be68a1c19dc3566d3f8d9a6d835488cc906a472d2561236
-  data.tar.gz: f55f16430096811e666380e5b7a881f8a10a8dad7556347a9ee50e972f7aaf701589f2a6bbc9215d6b8f13c27cd9140f87829745960a0a58e9928761fb14e471
+  metadata.gz: f1981134e58e19aef91430542eb611bf4267e01b4b9ce3f6cf9b1dedde907df0692b45a1d7aa1951dfe0cd3fc097368b550d9864d3d480db34deafa51b8453fa
+  data.tar.gz: cba1310909ee0b858c530894e6a7dfa4b643a952ca9ef878f9dd11f4e71a1d69681ac696cccdaf77e13e4546ca69a5332661a3609e8cea60710062c352012ac0

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    jobs_crawler (0.1.2)
+    jobs_crawler (0.1.3)
       wombat
 
 GEM

data/lib/jobs_crawler/indexers/atoo_job.rb

@@ -0,0 +1,13 @@
+module JobsCrawler
+  class Indexers::AtooJob
+    include Wombat::Crawler
+
+    base_url 'https://www.atoojob.com'
+    path     '/jobs'
+    ¬
+    links 'css=.cs-post-title h5 a', :iterator do
+      url({ xpath: ".//@href" })
+      titre({ xpath: ".//text()" })
+    end
+  end
+end

data/lib/jobs_crawler/robots/atoo_job.rb

@@ -0,0 +1,39 @@
+module JobsCrawler
+  class Robots::AtooJob
+    attr_reader :url
+
+    def initialize(url)
+      @url    = url
+      @engine = Mechanize.new
+    end
+
+    def crawl
+      set_html
+      to_json
+    end
+
+    private
+
+    def set_html
+      @html = Nokogiri::HTML(body)
+    end
+
+    def to_json
+      {
+        date_de_publication: date_publication,
+        description:         description,
+      }
+    end
+    def description
+      @html.css('#main > article > div.main-section.jobs-detail-3 > div:nth-child(2) > div > div > div.section-content.col-lg-8.col-md-8.col-sm-12.col-xs-12 > div.row > div.col-lg-8.col-md-8.col-sm-12.col-xs-12.col-xs-12 > div').text
+    end
+
+    def date_publication
+      @html.css('#main > article > div.main-section.jobs-detail-3 > div:nth-child(1) > div > div > div > div > div > div > div.cs-text > ul > li:nth-child(1) > span').text
+    end
+
+    def body
+      @engine.get(url).body
+    end
+  end
+end

data/lib/jobs_crawler/robots/emploi_senegal.rb

@@ -0,0 +1,13 @@
+module JobsCrawler
+  class Robots::EmploiSenegal
+    include Wombat::Crawler
+
+    base_url 'https://www.emploisenegal.com'
+    path     '/recherche-jobs-senegal'
+    ¬
+    links 'css=.search-results .job-description-wrapper', :iterator do
+      url({ xpath: ".//@data-href" })
+      titre({ xpath: ".//text()" })
+    end
+  end
+end

data/lib/jobs_crawler/robots/pages_jaunes_senegal.rb

@@ -0,0 +1,13 @@
+module JobsCrawler
+  class Robots::PagesJaunesSenegal
+    include Wombat::Crawler
+
+    base_url 'https://www.emploisenegal.com'
+    path     '/recherche-jobs-senegal'
+    ¬
+    links 'css=.search-results .job-description-wrapper', :iterator do
+      url({ xpath: ".//@data-href" })
+      titre({ xpath: ".//text()" })
+    end
+  end
+end

data/lib/jobs_crawler/robots/senjob.rb

@@ -0,0 +1,9 @@
+module JobsCrawler::Robots
+  class Senjob
+    include Wombat::Crawler
+
+    description "css=#articlebi .preview"
+    reference   "xpath=//html/body/div[3]/table/tbody/tr[5]/td[2]"
+    deadline    "css=body > div:nth-child(16) > table > tbody > tr:nth-child(5) > td:nth-child(2)"
+  end
+end

data/lib/jobs_crawler/robots.rb

@@ -0,0 +1,12 @@
+module JobsCrawler::Robots
+  require 'jobs_crawler/robots/senjob'
+  require 'jobs_crawler/robots/atoo_job'
+  require 'jobs_crawler/robots/emploi_senegal'
+  require 'jobs_crawler/robots/pages_jaunes_senegal'
+
+  class << self
+     def crawl_atoo_job(url)
+       JobsCrawler::Robots::AtooJob.new(url).crawl
+     end
+  end
+end

data/lib/jobs_crawler/version.rb

@@ -1,3 +1,3 @@
 module JobsCrawler
-  VERSION = "0.1.3"
+  VERSION = "0.1.4"
 end

data/lib/jobs_crawler.rb

@@ -1,6 +1,7 @@
 require "wombat"
 require "jobs_crawler/version"
 require "jobs_crawler/indexers"
+require "jobs_crawler/robots"
 require "jobs_crawler/indexers/senjob"
 require "jobs_crawler/indexers/atoo_job"
 require "jobs_crawler/indexers/emploi_senegal"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: jobs_crawler
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.1.4
 platform: ruby
 authors:
 - Pathe
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-04-02 00:00:00.000000000 Z
+date: 2019-04-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -88,9 +88,15 @@ files:
 - jobs_crawler.gemspec
 - lib/jobs_crawler.rb
 - lib/jobs_crawler/indexers.rb
+- lib/jobs_crawler/indexers/atoo_job.rb
 - lib/jobs_crawler/indexers/emploi_senegal.rb
 - lib/jobs_crawler/indexers/pages_jaunes_senegal.rb
 - lib/jobs_crawler/indexers/senjob.rb
+- lib/jobs_crawler/robots.rb
+- lib/jobs_crawler/robots/atoo_job.rb
+- lib/jobs_crawler/robots/emploi_senegal.rb
+- lib/jobs_crawler/robots/pages_jaunes_senegal.rb
+- lib/jobs_crawler/robots/senjob.rb
 - lib/jobs_crawler/version.rb
 homepage: http://taag-at.com
 licenses: