jobparser 0.13.9 → 0.13.10

data/lib/jobparser/facets/title.rb

@@ -1,45 +1,78 @@
 module JobParser
   module Facets
     class Title < Facet
+      def initialize(*args)
+        super(*args)
+        @scorer = Scorer.new
+      end
+
       def parse
         special_case_result = use_special_case(:title)
         return special_case_result unless special_case_result.nil?
 
-        title_scorer = Scorer.new
-        page_title = @doc.at_css("title").content
-        title_scorer.store_and_score(page_title, 10)
+        score_page_title
 
         # first see if we find something with a matching id
         loop_over_elements do |name, elem|
-          next if elem.content == "" || elem.content.split(" ").length > 10 || elem.content.strip.empty?
+          next if elem_not_suitable_as_title?(elem)
 
           content = Cleaner.strip_all_white_space(elem.content)
 
           # does the element have an id that means it might store the title?
-          title_scorer.store(content, 60).if_regex_match(JOB_TITLE_ID_REGEX, elem.attribute("id").to_s)
+          elem_has_job_title_id_score(elem, content)
 
           # or if a heading element matches the page title
-          if elem_is_heading?(name)
-            title_scorer.store(content, 40).if_block_true { page_title.include?(content) }
-          end
+          elem_heading_matches_page_title(elem, content)
 
-          title_scorer.store(content, 20).if_regex_match(JOB_TITLE_WORDS, content)
+          # if it has some common words that feature in job titles
+          elem_matches_job_title_words(content)
 
-          VACANCY_TITLE_REGEX.match(content) {
-            if elem.next_element && !Cleaner.strip_all_white_space(elem.next_element.content).empty?
-              next_content = Cleaner.strip_all_white_space(elem.next_element.content)
-              title_scorer.store(next_content, 30).if_block_true {
-                ACCEPTED_ELEMENTS.include?(elem.next_element.name)
-              }
-            end
-          }
+          # if it's the title, get the content of the next element
+          elem_is_vacancy_title(elem, content)
         end
 
-        clean_title(title_scorer.top_match.strip.gsub(NBSP, ""))
+        clean_title(@scorer.top_match.strip.gsub(NBSP, ""))
       end
 
       private
 
+      def elem_is_vacancy_title(elem, content)
+        VACANCY_TITLE_REGEX.match(content) {
+          if elem.next_element && !Cleaner.strip_all_white_space(elem.next_element.content).empty?
+            next_content = Cleaner.strip_all_white_space(elem.next_element.content)
+            @scorer.store(next_content, 30).if_block_true {
+              ACCEPTED_ELEMENTS.include?(elem.next_element.name)
+            }
+          end
+        }
+      end
+
+      def elem_matches_job_title_words(content)
+        @scorer.store(content, 20).if_regex_match(JOB_TITLE_WORDS, content)
+      end
+
+      def elem_heading_matches_page_title(elem, content)
+        if elem_is_heading?(elem.name)
+          @scorer.store(content, 40).if_block_true { page_title.include?(content) }
+        end
+      end
+
+      def elem_has_job_title_id_score(elem, content)
+        @scorer.store(content, 60).if_regex_match(JOB_TITLE_ID_REGEX, elem.attribute("id").to_s)
+      end
+
+      def page_title
+        @doc.at_css("title").content
+      end
+
+      def score_page_title
+        @scorer.store_and_score(page_title, 10)
+      end
+
+      def elem_not_suitable_as_title?(elem)
+        elem.content == "" || elem.content.split(" ").length > 10 || elem.content.strip.empty?
+      end
+
       def elem_is_heading?(name)
         %w{h1 h2 h3 h4 h5}.include?(name)
       end

data/lib/jobparser/parser.rb

@@ -12,18 +12,18 @@ module JobParser
 
     def job
       if JobParser.cache.valid_for_url?(@url)
-        return JobParser.cache.fetch_result_for_url(@url)
+        JobParser.cache.fetch_result_for_url(@url)
+      else
+        { :url => @url,
+          :salary => job_salary,
+          :title => job_title,
+          :apply => apply_link,
+          :salary_string => job_salary_string,
+          :location => job_location,
+          :deadline => deadline,
+          :postcode => job_postcode
+        }
       end
-
-      { :url => @url,
-        :salary => job_salary,
-        :title => job_title,
-        :apply => apply_link,
-        :salary_string => job_salary_string,
-        :location => job_location,
-        :deadline => deadline,
-        :postcode => job_postcode
-      }
     end
 
     private

data/lib/jobparser/parseschema.rb

@@ -96,11 +96,7 @@ module JobParser
 
     def get_content_at_prop(prop)
       elem = find_with_itemprop(prop)
-      if elem
-        Cleaner.strip_all_white_space(elem.content)
-      else
-        ""
-      end
+      elem ? Cleaner.strip_all_white_space(elem.content) : ""
     end
 
     def is_content_at_prop?(prop)

data/lib/jobparser/version.rb

@@ -1,3 +1,3 @@
 module JobParser
-  VERSION = "0.13.9"
+  VERSION = "0.13.10"
 end

data/lib/jobparser.rb

@@ -40,7 +40,7 @@ module JobParser
           ParseHtml.new(html, url)
         end
       rescue URI::InvalidURIError
-        raise JobParser::Error::InvalidUrl, "The URI given was not valid"
+        raise JobParser::Error::InvalidUrl, "The URI given (\"#{url}\") was not valid"
       end
     end
   end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: jobparser
 version: !ruby/object:Gem::Version
-  version: 0.13.9
+  version: 0.13.10
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-08-23 00:00:00.000000000 Z
+date: 2013-08-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler