--- a/documents/genericScrapers.py
+++ b/documents/genericScrapers.py
@@ -30,13 +30,14 @@
 		""" do the scraping """
 		return
 
+	@abc.abstractmethod
+        def getDescription(self, content, entry, doc):
+                """ get description"""
+		return
+
 
 
 class GenericRSSDisclogScraper(GenericDisclogScraper):
-        def getDescription(self, entry, doc):
-                """ get description from rss entry"""
-                doc['description'] = entry.summary
-		return
 
        	def doScrape(self):
                	foidocsdb = scrape.couch['disclosr-foidocuments']
@@ -54,16 +55,29 @@
 				edate = datetime.fromtimestamp(mktime( entry.published_parsed)).strftime("%Y-%m-%d")
                                 doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': entry.link, 'docID': entry.id,
                                 "date": edate,"title": entry.title}
-				self.getDescription(entry, doc)
+				self.getDescription(entry,entry, doc)
                                 foidocsdb.save(doc)
                         else:
                         	print "already saved"			
+        def getDescription(self, content, entry, doc):
+                """ get description from rss entry"""
+                doc.update({'description': content.summary})
+		return
 
 class GenericOAICDisclogScraper(GenericDisclogScraper):
         __metaclass__ = abc.ABCMeta
 	@abc.abstractmethod
 	def getColumns(self,columns):
 		""" rearranges columns if required """
+		return
+        def getColumnCount(self):
+                return 5
+        def getDescription(self, content, entry, doc):
+                """ get description from rss entry"""
+		descriptiontxt = ""
+		for string in content.stripped_strings:
+                	descriptiontxt = descriptiontxt + " \n" + string
+                doc.update({'description': descriptiontxt})
 		return
 
 	def doScrape(self):
@@ -76,7 +90,7 @@
 				soup = BeautifulSoup(content)
 				for row in soup.table.find_all('tr'):
 					columns = row.find_all('td')
-					if len(columns) == 5:
+					if len(columns) == self.getColumnCount():
 						(id, date, description, title, notes) = self.getColumns(columns)
 						print id.string
 						hash = scrape.mkhash(url+id.string)
@@ -85,9 +99,6 @@
 							if atag.has_key('href'):
 								links.append(scrape.fullurl(url,atag['href']))
 						doc = foidocsdb.get(hash)
-						descriptiontxt = ""
-						for string in description.stripped_strings:
-							descriptiontxt = descriptiontxt + " \n" + string
 							
 						if doc == None:
 							print "saving"
@@ -97,14 +108,20 @@
 								print dtdate
                                                         	edate = ""+str(dtdate[0])+'-'+str(dtdate[1])+'-'+str(dtdate[2])
 							else:
-								edate = ""
-							doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), "links": links, 'docID': id.string,
-			 				 "date": edate, "description": descriptiontxt,"title": title.string,"notes": notes.string}
+								edate = datetime.strptime(date.string, "%d %B %Y").strftime("%Y-%m-%d")
+							doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), 'docID': id.string,
+			 				 "date": edate,"title": title.string}
+							self.getDescription(description,row, doc)
+
+                                			if links != []:
+                                        			doc.update({'links': links})
+                                			if notes != None:
+                                        			doc.update({ 'notes': notes.string})
 							foidocsdb.save(doc)
 						else:
-							print "already saved"
+							print "already saved "+hash
 					
-					elif len(row.find_all('th')) == 5:
+					elif len(row.find_all('th')) == self.getColumnCount():
 						print "header row"
 					
 					else: