jobparser 0.3.0 → 0.4.0

data/lib/jobparser/facets/salary.rb

@@ -11,8 +11,6 @@ module JobParser
         }
         final_salary = nil
         if salary && !salary.empty?
-          p "got slaary"
-          p salary
           SALARY_GROUP_REGEX.match(salary.gsub(CLEAN_SALARY_REGEX, "")) { |match|
             final_salary = [match[1].to_i, match[2].to_i]
           }

data/lib/jobparser/parsehtml.rb

@@ -1,45 +1,9 @@
 # encoding: utf-8
-require "nokogiri"
 module JobParser
-  class ParseHtml
-    ACCEPTED_ELEMENTS = %w{p a h1 h2 h3 h4 h5 span dl dd dt td}
-
-    attr_reader :doc, :plain_text
-
-    def initialize(html, from_url)
-      @url = from_url
-      @doc = strip_bad_elements(Nokogiri::HTML(html))
-      @doc.css("br").each { |br| br.replace "\n" }
-      @plain_text = get_plain_text
-    end
-
-    def job
-      { :url => @url,
-        :salary => job_salary,
-        :title => job_title,
-        :apply => apply_link,
-        :salary_string => job_salary_string,
-        :location => job_location
-      }
-    end
+  class ParseHtml < Parser
 
     private
 
-    def strip_bad_elements(doc)
-      blacklist = ['script', 'style', 'button']
-      blacklist.each do |tag|
-        doc.xpath("//#{tag}").remove
-      end
-      doc
-    end
-
-    def get_plain_text
-      doc = @doc.dup
-      blacklist = ['title', 'script', 'style', 'button']
-      nodelist = doc.search('//text()')
-      nodelist.text
-    end
-
     def job_location
       Facets::Location.new(@doc, @url, @plain_text).parse
     end

data/lib/jobparser/parser.rb

@@ -0,0 +1,41 @@
+require "nokogiri"
+module JobParser
+  class Parser
+    ACCEPTED_ELEMENTS = %w{p a h1 h2 h3 h4 h5 span dl dd dt td}
+    attr_reader :doc, :plain_text
+
+    def initialize(html, from_url)
+      @url = from_url
+      @doc = strip_bad_elements(Nokogiri::HTML(html))
+      @plain_text = get_plain_text
+    end
+
+    def job
+      { :url => @url,
+        :salary => job_salary,
+        :title => job_title,
+        :apply => apply_link,
+        :salary_string => job_salary_string,
+        :location => job_location
+      }
+    end
+
+    private
+
+    def strip_bad_elements(doc)
+      blacklist = ['script', 'style', 'button']
+      blacklist.each do |tag|
+        doc.xpath("//#{tag}").remove
+      end
+      doc.css("br").each { |br| br.replace "\n" }
+      doc
+    end
+
+    def get_plain_text
+      doc = @doc.dup
+      blacklist = ['title', 'script', 'style', 'button']
+      nodelist = doc.search('//text()')
+      nodelist.text
+    end
+  end
+end

data/lib/jobparser/parseschema.rb

@@ -0,0 +1,60 @@
+# encoding: utf-8
+module JobParser
+  class ParseSchema < Parser
+    private
+
+    def job_salary
+      salary = job_salary_string
+      SALARY_GROUP_REGEX.match(salary.gsub(CLEAN_SALARY_REGEX, "")) { |match|
+        [match[1].to_i, match[2].to_i]
+      }
+    end
+
+    def job_title
+      get_content_at_prop("title")
+    end
+
+    def apply_link
+      Facets::Apply.new(@doc, @url, @plain_text).parse
+    end
+
+    def job_salary_string
+      get_content_at_prop("baseSalary")
+    end
+
+    def job_location
+      # some sites don't use the address stuff properly
+      if is_content_at_prop?("addressLocality")
+        get_content_at_prop("addressLocality")
+      else
+        get_content_at_prop("jobLocation")
+      end
+    end
+
+    def does_use_schema?
+      @doc.css("*").any? { |elem|
+        elem['itemtype'] == "http://schema.org/JobPosting"
+      }
+    end
+
+    def get_content_at_prop(prop)
+      elem = find_with_itemprop(prop)
+      if elem
+        Cleaner.strip_all_white_space(find_with_itemprop(prop).content)
+      else
+        ""
+      end
+    end
+
+    def is_content_at_prop?(prop)
+      elem = find_with_itemprop("prop")
+      elem && !elem.empty?
+    end
+
+    def find_with_itemprop(prop)
+      @doc.css("*").select { |elem|
+        elem['itemprop'] == prop
+      }.first
+    end
+  end
+end

data/lib/jobparser/version.rb

@@ -1,3 +1,3 @@
 module JobParser
-  VERSION = "0.3.0"
+  VERSION = "0.4.0"
 end

data/lib/jobparser.rb

@@ -1,5 +1,7 @@
 require "jobparser/version"
+require "jobparser/parser"
 require "jobparser/parsehtml"
+require "jobparser/parseschema"
 require "jobparser/parseurl"
 require "jobparser/cleaner"
 require "jobparser/scorer"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: jobparser
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.4.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-07-25 00:00:00.000000000 Z
+date: 2013-07-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -106,6 +106,8 @@ files:
 - lib/jobparser/facets/salarystring.rb
 - lib/jobparser/facets/title.rb
 - lib/jobparser/parsehtml.rb
+- lib/jobparser/parser.rb
+- lib/jobparser/parseschema.rb
 - lib/jobparser/parseurl.rb
 - lib/jobparser/regex.rb
 - lib/jobparser/scorer.rb