Updated parsing to remove the 'Reviewed by' segment of the reviewers.

lib/parse_source.rb

@@ -2,7 +2,7 @@
 require 'hpricot'
 require 'yaml'
 require 'logger'
-log     = Logger.new(LOG_FILE, 5, 10*1024)
+log     = Logger.new(File.join(File.dirname(__FILE__), '../tmp/parse_source.log'), 5, 10*1024)
 
 exceptions = []
 log.info "\n"
@@ -29,19 +29,22 @@
         original_html = content.to_original_html.sub("<div id=\"review\">", '')[0..-7]
         dictionary['review_id']    = review_id.strip.to_i
         [
-          ['catalog_id', 'h1'],
-          ['authors', 'h4'],
-          ['review_title', 'h2'],
-          ['bibliography', 'p.biblio'],
-          ['reviewer', 'p strong'],
-        ].each do |key, selector|
+          ['catalog_id', 'h1', nil],
+          ['authors', 'h4', nil],
+          ['review_title', 'h2', nil],
+          ['bibliography', 'p.biblio', nil],
+          ['reviewer', 'p strong', /\A *Reviewed by(.*)\Z/],
+        ].each do |key, selector, regex|
           node = (content/"#{selector}:first-of-type")
           dictionary[key] = node[0].inner_html.strip
           if key == 'reviewer'
             node[0].search("/..p").each { |n| original_html.sub!(n.to_original_html,'') }
           else
             original_html.sub!(node[0].to_original_html,'')
           end
+          if regex
+            dictionary[key] = dictionary[key].sub(regex, '\1').strip
+          end
         end
         (content/"div#hr:first-of-type").each {|n| original_html.sub!(n.to_original_html, '')}
 
@@ -57,7 +60,7 @@
         # dictionary['bibliography'] = (content/"p.biblio").first.inner_html.strip
         # dictionary['reviewer']     = (content/"p strong").first.inner_html.strip
         # review_content = (content/"div#hr").first.following_siblings.collect{|sib| sib.to_original_html}.join("\n")
-        dictionary['content']      = original_html
+        dictionary['content']      = original_html.strip
       end
       File.open(File.join(File.dirname(__FILE__), "../src/yml/review-#{review_id}.yml"), 'w+') do |file|
         file.puts YAML.dump(dictionary)

lib/render.rb

@@ -4,7 +4,6 @@
 require 'yaml'
 
 Dir.glob(File.join(File.dirname(__FILE__), "../src/yml/*.yml")).each do |filename|
-  puts "Processing #{filename}"
   object = YAML.load_file(filename)
   buffer = ERB.new(File.read(File.join(File.dirname(__FILE__), '../src/template.erb.html'))).result(binding)
   target_filename = File.join(File.dirname(__FILE__), "../src/output/review-#{object['review_id']}.html")

src/template.erb.html

@@ -54,7 +54,7 @@ <h4><%= object['authors'] %></h4>
   <h2><%= object['review_title'] %></h2>
 
   <p class="biblio"><%= object['bibliography'] %></p>
-  <p><strong><%= object['reviewer'] %></strong></p>
+  <p><strong>Reviewed by <%= object['reviewer'] %></strong></p>
     <div id="hr"><hr /></div>
 
 <%= object['content'] %>