lib/govfeed.rb in govfeed-0.0.1 vs lib/govfeed.rb in govfeed-0.0.2

@@ -62,58 +62,104 @@
       :ca_pe => "http://www.gov.pe.ca/index.php3?number=rss",
       :ca_sk => "http://www.gov.sk.ca/Common/PageTemplates/rss.aspx"
     }
   end
 
+  def self.getItemTitle(item)
+    
+    title = String.new
+    
+    if (item/"title") != nil
+      title = "<a href=\"" + (item/"link").inner_text + "\"><h2 class=\"govfeedHeading\">" + (item/"title").inner_text + "</h2></a>\n"
+    end
+    
+    title
+    
+  end
+  
+  def self.getItemPubDate(item)
+    
+    pubDate = String.new
+    
+    if (item/"pubDate") != nil
+      pubDate = "<div class=\"govfeedPubDate\">" + (item/"pubDate").inner_text + "</div>\n" 
+    end
+    
+    pubDate
+    
+  end
+  
+  def self.getItemDescription(item)
+    
+    description = String.new
+    
+    if (item/"description") != nil
+      description = "<div class=\"govfeedDescription\">" + self.truncate_words((item/"description").inner_text, 40) + "</div>\n"
+    end
+    
+    description
+    
+  end
 
   def self.getFeed(feed, numberOfStories = 0)
+    begin
+      counter = 0
+    
+      # This hash contains the Feed URLs
+      # The format goes Federal feeds, State\Province feeds, Think Tank\Institution feeds
+      # Some states\provinces\territories do not yet have RSS feeds or feeds that work (Idaho).
+      # They will be added to this hash when they are created or fixed.
+      feed_url = self.getFeedList
 
-    # This hash contains the Feed URLs
-    # The format goes Federal feeds, State\Province feeds, Think Tank\Institution feeds
-    # Some states\provinces\territories do not yet have RSS feeds or feeds that work (Idaho).
-    # They will be added to this hash when they are created or fixed.
-    feed_url = self.getFeedList
-
-    # Curb-Fu will be fetching the feed.
-    feed = CurbFu.get(feed_url[feed])
+      # Curb-Fu will be fetching the feed.
+      feed = CurbFu.get(feed_url[feed])
     
-    # the hpricot gem will be used to parse it as we build the HTML
-    doc = Hpricot(feed.body.to_s)
+      # the hpricot gem will be used to parse it as we build the HTML
+      doc = Hpricot.XML(feed.body.to_s)
 
-    # RSS feed heading
-    rss = "<h1 id=\"govfeedTitle\">" + (doc/"title")[0].inner_text  + "</h1>\n"
+      # RSS feed title
+      rss = "<h1 class=\"govfeedTitle\">" + (doc/"title")[0].inner_text  + "</h1>\n"
 
-    # Make sure that the feed description exists before attempting to parse it
-    if (((doc/"description")[0] != nil) || ((doc/"description")[0] != ""))
-      rss += "<div class=\"govfeedDiv\">" + (doc/"description")[0].inner_text + "</div>\n"
-    end    
+      # Make sure that the feed description exists before attempting to parse it
+      if (((doc/"description")[0] != nil) || ((doc/"description")[0] != ""))
+        rss += "<div class=\"govfeedDescription\">" + (doc/"description")[0].inner_text + "</div>\n"
+      end    
 
-    # Make sure that the feed image exists before attempting to parse it
-    if (doc/"image")[0] != nil
-      rss += "<div class=\"govfeedImage\"><img src=\"" + (doc/"image"/"url")[0].inner_text + "\" alt=\"\" /></div>\n"
-    end    
+      # Make sure that the feed image exists before attempting to parse it
+      if (doc/"image")[0] != nil
+        rss += "<div class=\"govfeedImage\"><img src=\"" + (doc/"image"/"url")[0].inner_text + "\" alt=\"" + (doc/"image"/"title")[0].inner_text  + "\" /></div>\n"
+      end    
 
-    # individual RSS feed items
-    # If the number of stories parameter was not passed in, fetch all
-    if numberOfStories == 0
+      # individual RSS feed items
+      # If the number of stories parameter was not passed in, fetch all      
       (doc/"item").each do |item|
-        rss += "<a href=\"" + (item/"link").inner_text + "\"><h2 class=\"govfeedHeading\">" + (item/"title").inner_text + "</h2></a>\n"
-        rss += "<div class=\"govfeedDiv\">" + (item/"pubDate").inner_text + "<br />" + self.truncate_words((item/"description").inner_text, 40) + "</div>\n"
-      end
-    else
-      counter = 0
-      (doc/"item").each do |item|
-        rss += item.inner_text
-        rss += "<a href=\"" + (item/"link").inner_text + "\"><h2 class=\"govfeedHeading\">" + (item/"title").inner_text + "</h2></a>\n"        
-        rss += "<div class=\"govfeedDiv\">" + (item/"pubDate").inner_text + "<br />" + self.truncate_words((item/"description").inner_text, 40) + "</div>\n"
-        counter = counter + 1
-        if counter == numberOfStories
-          break
+        
+        rss += self.getItemTitle(item)  
+        
+        rss += self.getItemPubDate(item)
+        
+        rss += self.getItemDescription(item)  
+    
+        # If the number of stories is not equal to 0, that means it was limited
+        if numberOfStories != 0
+            
+          counter = counter + 1
+            
+          if counter == numberOfStories
+            break
+          end
+            
         end
+        
       end
-    end
 
-    rss
+      rss
+
+    rescue
+ 
+      "Could not parse RSS feed."
+
+    end
 
   end
 
 end