diff --git a/mongo/mongocrawler.py b/mongo/mongocrawler.py
index 36ff4e0..0fbecbe 100644
--- a/mongo/mongocrawler.py
+++ b/mongo/mongocrawler.py
@@ -175,7 +175,7 @@ def fetch_page(link:str)->(str,str):
         good = True
         if response.status != 200:
             good = False
-            LOGGER.error('not a 200 response: %s for URL %s', response.status, url)
+            LOGGER.error('not a 200 response: %s for URL %s', response.status, link)
         elif response.data is None or len(response.data) < MIN_FILE_SIZE:
             LOGGER.error('too small/incorrect for URL %s', link)
             good = False
@@ -278,7 +278,7 @@ def index_page(db,original_link:str,final_link:str,html:bytes,doc,filter_content
         htdoc = get_link_doc(link,state)
         htdoc["html"] = html
         htdoc["html_size"] = len(html)
-        htdoc["html_md5"]= hashlib.md5(html).hexdigest()
+        htdoc["html_md5"]= hashlib.md5(html.encode("utf8")).hexdigest()
         # can be revisited - upsert
         del htdoc["url"]
         htmlcol.update_one({"url":link},{"$set":htdoc},upsert=True)
@@ -682,6 +682,16 @@ def classify(start_link):
     cl.train(trainset)
     cl.test(testset)
 
+def index_pages(hostname,extracted_pages):
+    final_states = []
+    docs = []
+    for original_link,final_link,html,doc in extracted_pages:
+        status = index_page(db,original_link,final_link,html,doc,filter_content)
+        final_states.append(status)
+        docs.append(doc)
+    save_batch_info(db,hostname,final_states,docs)
+ 
+
 def visit(hostname,filter_content=True):
     myclient = pymongo.MongoClient(CONNECTION)
     db=myclient[DBNAME]
@@ -712,6 +722,7 @@ def visit(hostname,filter_content=True):
         extracted_pages.append((original_link,final_link,html,doc))
 
     extracted_links = extract_links(links,responses,hostname,rules,"frontlink")
+
     index_links(db,extracted_links)
     final_states = []
     docs = []