myuniversaljobsmatch 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 9aa5f6b90e8b5767466dffc713be7ec0292c3412
-  data.tar.gz: 26e96baa046bb40cb29e56e1fea21e2097876034
+  metadata.gz: 51b06cb74f5610ee5f670f9cc07b6a2092957dc5
+  data.tar.gz: a692634d9a195f1a00f0ec3c9d80b4392f861750
 SHA512:
-  metadata.gz: 97b6bd231e57d6bccd8985db59a15cc8ecab0133cc846acaf99dff2f0303a78156ad872d2bd013632340b3dc1a868646fe81f260f02eb0976654d03b657fd140
-  data.tar.gz: ae4b8503ac5ef3549f3b42d5c693638aedaa2d013d9a886edcf2061ffcdb253e172297c42466eea26be54c56668f0b3b8df04fb8293fa4f2df5c3024318de9aa
+  metadata.gz: 79ca20c095f73204be96f10dd6b1d06d4c22ba62ebe016166adb10f77f0d29626f409a2f18d110584bb69d3f9ff1462847ef5fe56f1b321a3821dc5e85d8efbb
+  data.tar.gz: f119fd90a9442fc23b5dff218e1af3cd3cf5d86915e254538de711b7bbb6bb548721299afc08a90d3702063ad99bc9d2a3265e18e316c9555fd8a9a68ad983d2

data/lib/myuniversaljobsmatch.rb

@@ -10,15 +10,21 @@ class MyUniversalJobsMatch
   def initialize(filepath: '')
 
     @filepath = filepath
+    @url_base = 'https://jobsearch.direct.gov.uk/'
+    
+    @dx = Dynarex.new 'ujm[title,tags]/item(job_id, title, ' + \
+        'description, posting_date, company, location, industries, job_type)'
 
   end
+  
+  def dynarex()
+    @dx
+  end
 
   def search(title: '', where: '')
 
-
-    url = "https://jobsearch.direct.gov.uk/jobsearch/" + \
-       "powersearch.aspx?qt=2&rad=20&tm=-1&where=#{where}" + \
-                                                 "&tjt=#{title}"
+    url = @url_base + "jobsearch/powersearch.aspx?qt=2&rad=20&tm=-1&" + \
+                                                "where=#{where}&tjt=#{title}"
     doc = Nokorexi.new(url).to_doc
 
     table = doc.root.at_css('.JSresults')
@@ -27,30 +33,46 @@ class MyUniversalJobsMatch
       # get the date
       date = row.element('td/span/text()')
       link = row.element('td[3]/a')
+      jobid = link.attributes[:href][/JobID=(\d+)/,1]
       title = link.text
       url = link.attributes[:href]
       company = row.element('td[4]/span/text()')
       location = row.element('td[5]/span/text()')
 
-      [date, title, url, company, location]
+      [jobid, date, title, url, company, location]
       
     end
 
-    dx = Dynarex.new('vacancies[title, desc, date, time, tags, xslt]/vacancy' \
-                      + '(date, title, url, company, location, created_at)')
-                      
-    dx.default_key = 'uid'
+    dx = Dynarex.new('vacancies[title, desc, date, time, tags, xslt]/' + \
+             'vacancy(jobid, date, title, url, company, location, created_at)')
 
     dx.title = "Universal Jobmatch jobs - Search results for '#{title}'"
-    dx.desc = "generated from web scrape of jobsearch.direct.gov.uk; source: " + url
+    dx.desc = "generated from web scrape of jobsearch." + \
+                                                "direct.gov.uk; source: " + url
     dx.tags = 'jobs vacancies jobmatch ' + title.split.first
     dx.date = Time.now.strftime("%Y-%b-%s")
     dx.time = Time.now.strftime("%H:%M")
 
     a.each do |row|
-      dx.create Hash[%i(date title url company location created_at).zip(row)]
+      dx.create Hash[%i(jobid date title url company location created_at).\
+                                                                      zip(row)]
     end
 
     return dx
   end
-end
+  
+  def query(id)
+    
+    url = @url_base + 'GetJob.aspx?JobID=' + id
+    doc = Nokorexi.new(url).to_doc
+    content = doc.root.at_css '.jobViewContent'
+    description = content.element('div')
+
+    raw_summary = doc.root.at_css('.jobViewSummary').xpath('dl/dd/text()')
+    job_id, posting_date, company, location, industries, job_type = raw_summary
+    
+    fields = %i(job_id posting_date company location industries job_type description)
+    Hash[fields.zip(raw_summary + [description])]
+    
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: myuniversaljobsmatch
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
 platform: ruby
 authors:
 - James Robertson