Parse and cache all years of clinical law rankings

Author: s2t2

lib/us_news_rankings/category.rb

@@ -15,10 +15,10 @@ def html_dir
     end
 
     def pages
-      source_urls.each_with_index.map{|url, number| UsNewsRankings::Page.new({
+      source_urls.each_with_index.map{|url, i| UsNewsRankings::Page.new({
         category: self,
         url: url,
-        number: number + 1
+        number: i + 1
       })}
     end
 
@@ -31,7 +31,10 @@ def extract_rankings
       extracted_rankings = []
       pages.each do |page|
         page.table_rows.each do |row|
-          ranking = UsNewsRankings::Education::GraduateSchools::LawClinical::Ranking.new(row)
+          ranking = UsNewsRankings::Education::GraduateSchools::LawClinical::Ranking.new({
+            year: year,
+            row: row
+          })
           extracted_rankings << ranking.to_h if ranking.ranked?
         end
       end

lib/us_news_rankings/education/graduate_schools/law_clinical/ranking.rb

@@ -3,6 +3,23 @@ module Education
     module GraduateSchools
       module LawClinical
         class Ranking < UsNewsRankings::Ranking
+          def rank_selector
+            case year
+            when 2014, 2013, 2012
+              return ".rankings-score"
+            else
+              return ".rankscore-bronze"
+            end
+          end
+
+          def rank
+            @rank || row.at_css(rank_selector).text.strip.gsub("#","").gsub("Tie","")
+          end
+
+          def tie?
+            row.at_css(rank_selector).text.include?("Tie")
+          end
+
           def tuition
             row.at_css(".search_tuition").text.strip #.gsub(" per year (full-time)","")
           end
@@ -14,7 +31,7 @@ def enrollment
           def to_h
             {
               rank: rank.to_i, # assumes school is ranked
-              tie: tie,
+              tie: tie?,
               school_name: school_name,
               school_city: school_city,
               tuition: tuition,

lib/us_news_rankings/ranking.rb

@@ -2,15 +2,17 @@
 
 module UsNewsRankings
   class Ranking
-    attr_reader :row
+    attr_reader :year, :row
 
+    # @param year [Integer] the rankings year
     # @param row [Nokogiri::XML::Element] a rankings table row ("tr") element
-    def initialize(row)
+    def initialize(year:, row:)
+      @year = year
       @row = row
     end
 
     def rank
-      @rank || row.at_css(".rankscore-bronze").text.strip.gsub("#","").gsub("Tie","")
+      raise "Oh, please implement #rank on the child class."
     end
 
     def ranked?
@@ -29,7 +31,7 @@ def school_city
     end
 
     def tie
-      row.at_css(".rankscore-bronze").text.include?("Tie")
+      raise "Oh, please implement #tie on the child class."
     end
 
     def to_h

spec/category_spec.rb

@@ -1,9 +1,17 @@
 RSpec.describe UsNewsRankings::Category do
-  describe "#rankings" do
+  describe "#source_urls" do
     let(:category){ described_class.new(2017) }
 
     it "should be implemented in a child class" do
-      expect{category.rankings}.to raise_error("please implement #rankings on the child class")
+      expect{category.source_urls}.to raise_error("Oh, please implement #source_urls on the child class.")
+    end
+  end
+
+  describe "#html_dir" do
+    let(:category){ described_class.new(2017) }
+
+    it "should be implemented in a child class" do
+      expect{category.html_dir}.to raise_error("Oh, please implement #html_dir on the child class.")
     end
   end
 end

spec/education/graduate_schools/law_clinical/category_spec.rb

@@ -8,21 +8,118 @@
   end
 
   describe "#rankings" do
-    let(:category){ described_class.new(2017) }
+    describe "for 2017" do
+      let(:category){ described_class.new(2017) }
+
+      it "should return a list of ranked schools" do
+        expect(category.rankings.count).to eql(11)
+      end
+
+      it "should contain the expected rankings" do
+        expect(category.rankings.first).to eql({
+          :rank=>1,
+          :tie=>false,
+          :school_name=>"Georgetown University",
+          :school_city=>"Washington, DC",
+          :tuition=>"$57,576 per year (full-time)",
+          :enrollment=>"1,721"
+        })
+      end
+    end
+
+    describe "for 2016" do
+      let(:category){ described_class.new(2016) }
+
+      it "should return a list of ranked schools" do
+        expect(category.rankings.count).to eql(11)
+      end
+
+      it "should contain the expected rankings" do
+        expect(category.rankings.first).to eql({
+          :rank=>1,
+          :tie=>false,
+          :school_name=>"Georgetown University",
+          :school_city=>"Washington, DC",
+          :tuition=>"$55,255 per year (full-time)",
+          :enrollment=>"1,725"
+        })
+      end
+    end
+
+    describe "for 2015" do
+      let(:category){ described_class.new(2015) }
+
+      it "should return a list of ranked schools" do
+        expect(category.rankings.count).to eql(12)
+      end
 
-    it "should return a list of ranked schools" do
-      expect(category.rankings.count).to eql(11)
+      it "should contain the expected rankings" do
+        expect(category.rankings.first).to eql({
+          :rank=>1,
+          :tie=>false,
+          :school_name=>"Georgetown University",
+          :school_city=>"Washington, DC",
+          :tuition=>"$53,130 per year (full-time)",
+          :enrollment=>"1,719"
+        })
+      end
     end
 
-    it "should contain the expected rankings" do
-      expect(category.rankings.first).to eql({
-        :rank=>1,
-        :tie=>false,
-        :school_name=>"Georgetown University",
-        :school_city=>"Washington, DC",
-        :tuition=>"$57,576 per year (full-time)",
-        :enrollment=>"1,721"
-      })
+    describe "for 2014" do
+      let(:category){ described_class.new(2014) }
+
+      it "should return a list of ranked schools" do
+        expect(category.rankings.count).to eql(11)
+      end
+
+      it "should contain the expected rankings" do
+        expect(category.rankings.first).to eql({
+          :rank=>1,
+          :tie=>false,
+          :school_name=>"Georgetown University",
+          :school_city=>"Washington, DC",
+          :tuition=>"$50,890 per year (full-time)",
+          :enrollment=>"1,694"
+        })
+      end
+    end
+
+    describe "for 2013" do
+      let(:category){ described_class.new(2013) }
+
+      it "should return a list of ranked schools" do
+        expect(category.rankings.count).to eql(11)
+      end
+
+      it "should contain the expected rankings" do
+        expect(category.rankings.first).to eql({
+          :rank=>1,
+          :tie=>false,
+          :school_name=>"Georgetown University",
+          :school_city=>"Washington, DC",
+          :tuition=>"$48,835 per year (full-time)",
+          :enrollment=>"1,683"
+        })
+      end
+    end
+
+    describe "for 2012" do
+      let(:category){ described_class.new(2012) }
+
+      it "should return a list of ranked schools" do
+        expect(category.rankings.count).to eql(11)
+      end
+
+      it "should contain the expected rankings" do
+        expect(category.rankings.first).to eql({
+          :rank=>1,
+          :tie=>false,
+          :school_name=>"Georgetown University",
+          :school_city=>"Washington, DC",
+          :tuition=>"Full-time: $46,865 per year",
+          :enrollment=>"1,671"
+        })
+      end
     end
   end
 end