--- a/documents/scrape.py
+++ b/documents/scrape.py
@@ -12,6 +12,9 @@
 import urllib
 import urlparse
 
+def mkhash(input):
+    return hashlib.md5(input).hexdigest().encode("utf-8")
+
 def canonurl(url):
     r"""Return the canonical, ASCII-encoded form of a UTF-8 encoded URL, or ''
     if the URL looks invalid.
@@ -63,6 +66,11 @@
     url = urlparse.urlunsplit((scheme, netloc, path, query, fragment))
     return url[:4096]
 
+def fullurl(url,href):
+    href = href.replace(" ","%20")
+    href = re.sub('#.*$','',href)
+    return urljoin(url,href)
+
 #http://diveintopython.org/http_web_services/etags.html
 class NotModifiedHandler(urllib2.BaseHandler):  
     def http_error_304(self, req, fp, code, message, headers):
@@ -72,7 +80,7 @@
 
 def fetchURL(docsdb, url, fieldName, agencyID, scrape_again=True):
     url = canonurl(url)
-    hash = hashlib.md5(url).hexdigest().encode("utf-8")
+    hash = mkhash(url)
     req = urllib2.Request(url)
     print "Fetching %s" % url
     if url.startswith("mailto") or url.startswith("javascript") or url.startswith("#") or url == None or url == "":
@@ -174,9 +182,7 @@
 				None
 			else:
 				# remove anchors and spaces in urls
-				link['href'] = link['href'].replace(" ","%20")
-				link['href'] = re.sub('#.*$','',link['href'])
-                		linkurls.add(urljoin(url,link['href']))
+                		linkurls.add(fullurl(url,link['href']))
             for linkurl in linkurls:
 		#print linkurl
 		scrapeAndStore(docsdb, linkurl, depth-1, fieldName, agencyID)