jobparser 0.12.0 → 0.13.0

data/lib/jobparser/facets/title.rb

@@ -7,7 +7,7 @@ module JobParser
 
         title_scorer = Scorer.new
         page_title = @doc.at_css("title").content
-        title_scorer.store_and_score(page_title, 20)
+        title_scorer.store_and_score(page_title, 10)
 
         # first see if we find something with a matching id
         loop_over_elements do |name, elem|
@@ -35,7 +35,7 @@ module JobParser
           }
         end
 
-        title_scorer.top_match.strip.gsub(NBSP, "")
+        clean_title(title_scorer.top_match.strip.gsub(NBSP, ""))
       end
 
       private
@@ -43,6 +43,10 @@ module JobParser
       def elem_is_heading?(name)
         %w{h1 h2 h3 h4 h5}.include?(name)
       end
+
+      def clean_title(title)
+        Cleaner.strip_all_white_space(title.split(":").last)
+      end
     end
   end
 end

data/lib/jobparser/regex.rb

@@ -15,5 +15,5 @@ module JobParser
 
   # words commonly used in job listings - not sure if this is a good way to go but I think it's worth a go
   # could scope this regex just to headers
-  JOB_TITLE_WORDS = /representative|sales|nurse|manager/i
+  JOB_TITLE_WORDS = /representative|sales|nurse|manager|assistant/i
 end

data/lib/jobparser/version.rb

@@ -1,3 +1,3 @@
 module JobParser
-  VERSION = "0.12.0"
+  VERSION = "0.13.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: jobparser
 version: !ruby/object:Gem::Version
-  version: 0.12.0
+  version: 0.13.0
   prerelease: 
 platform: ruby
 authors: