better defaults for websites

blogs-i-read_v2.py

@@ -6,6 +6,7 @@ from dateutil.parser import parse
 import feedparser
 import hashlib
 import json
+import os
 import requests
 import re
 import sys
@@ -142,7 +143,16 @@ def examine_generic_website(soup, url, md5):
 
 def examine_url(url):
     logger.debug(url)
+    # initialize variables, suitable for new urls
     (md5, post_title, post_url, last_update) = ['', '', '', 0]
+    if url in md5_sums:
+        # get stored values if they exist
+        try:
+            last_update = md5_sums[url]['timestamp']
+            post_title = md5_sums[url]['post_title']
+            post_url = md5_sums[url]['post_url']
+        except:
+            pass
     try:
         response = requests.get(url)
         md5 = hashlib.md5(response.content).hexdigest()  # Calculate the MD5 hash
@@ -202,6 +212,9 @@ def get_url_info( blog ):
         change_status = 'Changed'
         md5_sums[url] = { 'md5' : md5, 'timestamp' : last_update }
 
+    md5_sums[url]['post_url'] = post_url
+    md5_sums[url]['current_title'] = post_title
+    
     results[url] = { 'blog_url': blog['url'],
                      'blog_title': blog['title'],
                      'current_title': post_title,