test

foodie_automator_rss.py

@@ -65,14 +65,20 @@ def setup_logging():
             lines = f.readlines()
         cutoff = datetime.now(timezone.utc) - timedelta(days=LOG_PRUNE_DAYS)
         pruned_lines = []
+        malformed_count = 0
         for line in lines:
+            if len(line) < 19 or not line[:19].replace('-', '').replace(':', '').replace(' ', '').isdigit():
+                malformed_count += 1
+                continue
             try:
                 timestamp = datetime.strptime(line[:19], '%Y-%m-%d %H:%M:%S').replace(tzinfo=timezone.utc)
                 if timestamp > cutoff:
                     pruned_lines.append(line)
             except ValueError:
-                logging.warning(f"Skipping malformed log line: {line.strip()[:50]}...")
+                malformed_count += 1
                 continue
+        if malformed_count > 0:
+            logging.info(f"Skipped {malformed_count} malformed log lines during pruning")
         with open(LOG_FILE, 'w') as f:
             f.writelines(pruned_lines)
     
@@ -240,6 +246,16 @@ def curate_from_rss():
             attempts += 1
             continue
 
+        # Remove the original title from the summary
+        title_pattern = re.compile(
+            r'\*\*' + re.escape(title) + r'\*\*|' + re.escape(title),
+            re.IGNORECASE
+        )
+        final_summary = title_pattern.sub('', final_summary).strip()
+        # Clean up any extra spaces or newlines left after removal
+        final_summary = re.sub(r'\s+', ' ', final_summary)
+        final_summary = '\n'.join(para.strip() for para in final_summary.split('\n') if para.strip())
+
         final_summary = insert_link_naturally(final_summary, source_name, link)
         post_data, author, category, image_url, image_source, uploader, pixabay_url = prepare_post_data(final_summary, title)
         if not post_data: