Summary: Works

blogsiread.py

@@ -1,14 +1,18 @@
 #!/usr/bin/python3
 
-# 	$Id: blogsiread.py,v 1.3 2022/09/02 05:06:33 springm Exp springm $
-#       $Revision: 1.3 $
-#       $Date: 2022/09/02 05:06:33 $
+# 	$Id: blogsiread.py,v 1.4 2022/09/29 04:42:00 springm Exp springm $
+#       $Revision: 1.4 $
+#       $Date: 2022/09/29 04:42:00 $
 #       $Log: blogsiread.py,v $
+#       Revision 1.4  2022/09/29 04:42:00  springm
+#       Summary: works, but LFI gets on top too often
+#
 #       Revision 1.3  2022/09/02 05:06:33  springm
 #       Summary: photoplacegallery hash jetzt vom Titel der ersten Ausstellung
 #
 
 
+
 """
 * if yes
   * read the spring2life linklist on blogger,
@@ -175,13 +179,14 @@ def lfionlinede(b, domain, i):
     # logger.debug(f"{b[1]}")
     with urllib.request.urlopen(b[1]) as response:
         html = response.read()
-        m.update(html)
+        p = re.search('titlebox30 cu-pointer[\'"] onclick=[\'"]window.location\s*=\s*[\'"](https://.*?)[\'"][\'"]>\s*<h1.*?>(.*?)</h1', html.decode('utf-8'), re.MULTILINE | re.DOTALL)
+        string2hash = f"""p[2]"""
+        m.update(string2hash.encode('utf-8'))
         hash = (m.hexdigest())
         if not domain in meta_values: # first run
             meta_values[domain] = { 'hash': '1' } # fake value
         if not meta_values[domain]['hash'] == hash:      # Unterschiedliche Hashes
             meta_values[domain]['hash'] = hash
-            p = re.search('titlebox30 cu-pointer[\'"] onclick=[\'"]window.location\s*=\s*[\'"](https://.*?)[\'"][\'"]>\s*<h1.*?>(.*?)</h1', html.decode('utf-8'), re.MULTILINE | re.DOTALL)
             if p:
                 logger.debug(f"search result {p[1]} {p[2]}")
                 string2hash = f"""p[2]"""