try image mismatch

foodie_utils.py

@@ -29,63 +29,62 @@ from foodie_config import (
 load_dotenv()
 client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
 
-def load_json_file(filename, expiration_days=None):
-    data = []
-    if os.path.exists(filename):
-        try:
-            with open(filename, 'r') as f:
-                lines = f.readlines()
-                for i, line in enumerate(lines, 1):
-                    if line.strip():
-                        try:
-                            entry = json.loads(line.strip())
-                            if not isinstance(entry, dict) or "title" not in entry or "timestamp" not in entry:
-                                logging.warning(f"Skipping malformed entry in {filename} at line {i}: {entry}")
-                                continue
-                            data.append(entry)
-                        except json.JSONDecodeError as e:
-                            logging.warning(f"Skipping invalid JSON line in {filename} at line {i}: {e}")
-            if expiration_days:
-                cutoff = (datetime.now(timezone.utc) - timedelta(days=expiration_days)).isoformat()
-                data = [entry for entry in data if entry["timestamp"] > cutoff]
-            logging.info(f"Loaded {len(data)} entries from {filename}, {len(data)} valid after expiration check")
-        except Exception as e:
-            logging.error(f"Failed to load {filename}: {e}")
-            data = []  # Reset to empty on failure
-    return data
-
-def save_json_file(filename, key, value):
-    entry = {"title": key, "timestamp": value}
-    PRUNE_INTERVAL_DAYS = 180
+def load_json_file(file_path, expiration_hours):
+    entries = []
+    cutoff = datetime.now(timezone.utc) - timedelta(hours=expiration_hours)
+    
+    if not os.path.exists(file_path):
+        logging.info(f"File {file_path} does not exist, returning empty list")
+        return entries
+    
     try:
-        data = load_json_file(filename, expiration_days=PRUNE_INTERVAL_DAYS)
-        # Remove duplicates by title
-        data = [item for item in data if item["title"] != key]
-        data.append(entry)
-        # Special handling for used_images.json to save as a flat list with one URL per line
-        if filename.endswith('used_images.json'):
-            used_images.add(key)
-            with open(filename, 'w') as f:
-                f.write('[\n')
-                urls = list(used_images)
-                for i, url in enumerate(urls):
-                    f.write(f'"{url}"')
-                    if i < len(urls) - 1:
-                        f.write(',\n')
-                    else:
-                        f.write('\n')
-                f.write(']')
-        else:
-            with open(filename, 'w') as f:
-                for item in data:
-                    json.dump(item, f)
-                    f.write('\n')
-        logging.info(f"Saved '{key}' to {filename}")
-        print(f"DEBUG: Saved '{key}' to {filename}")
-        loaded_data = load_json_file(filename, expiration_days=PRUNE_INTERVAL_DAYS)
-        logging.info(f"Pruned {filename} to {len(loaded_data)} entries (older than {PRUNE_INTERVAL_DAYS} days removed)")
+        with open(file_path, 'r') as f:
+            lines = f.readlines()
+        
+        for i, line in enumerate(lines, 1):
+            try:
+                entry = json.loads(line.strip())
+                if not isinstance(entry, dict) or "title" not in entry or "timestamp" not in entry:
+                    logging.warning(f"Skipping malformed entry in {file_path} at line {i}: {line.strip()}")
+                    continue
+                
+                timestamp = datetime.fromisoformat(entry["timestamp"])
+                if timestamp > cutoff:
+                    entries.append(entry)
+                else:
+                    logging.debug(f"Entry expired in {file_path}: {entry['title']}")
+            except json.JSONDecodeError as e:
+                logging.warning(f"Skipping invalid JSON line in {file_path} at line {i}: {e}")
+                continue
+            except Exception as e:
+                logging.warning(f"Skipping malformed entry in {file_path} at line {i}: {line.strip()}")
+                continue
+        
+        logging.info(f"Loaded {len(entries)} entries from {file_path}, {len(entries)} valid after expiration check")
+        return entries
     except Exception as e:
-        logging.error(f"Failed to save or prune {filename}: {e}")
+        logging.error(f"Failed to load {file_path}: {e}")
+        return entries
+
+def save_json_file(file_path, title, timestamp):
+    try:
+        entries = load_json_file(file_path, 24 if "posted_" in file_path else 7 * 24)  # 24 hours for titles, 7 days for images
+        entry = {"title": title, "timestamp": timestamp}
+        entries.append(entry)
+        
+        # Prune entries older than expiration period
+        expiration_hours = 24 if "posted_" in file_path else 7 * 24
+        cutoff = datetime.now(timezone.utc) - timedelta(hours=expiration_hours)
+        pruned_entries = [e for e in entries if datetime.fromisoformat(e["timestamp"]) > cutoff]
+        
+        with open(file_path, 'w') as f:
+            for entry in pruned_entries:
+                f.write(json.dumps(entry) + '\n')
+        
+        logging.info(f"Saved '{title}' to {file_path}")
+        logging.info(f"Pruned {file_path} to {len(pruned_entries)} entries (older than {expiration_hours//24} days removed)")
+    except Exception as e:
+        logging.error(f"Failed to save to {file_path}: {e}")
 
 def load_post_counts():
     counts = []
@@ -886,7 +885,8 @@ def post_to_wp(post_data, category, link, author, image_url, original_source, im
         if content is None:
             logging.error(f"Post content is None for title '{post_data['title']}' - using fallback")
             content = "Content unavailable. Check the original source for details."
-        formatted_content = "\n".join(f"<p>{para}</p>" for para in content.split('\n') if para.strip())        
+        formatted_content = "\n".join(f"<p>{para}</p>" for para in content.split('\n') if para.strip())
+        
         author_id_map = {
             "owenjohnson": 10,
             "javiermorales": 2,
@@ -897,6 +897,20 @@ def post_to_wp(post_data, category, link, author, image_url, original_source, im
         }
         author_id = author_id_map.get(author["username"], 5)
         
+        # Handle image upload
+        image_id = None
+        if image_url:
+            logging.info(f"Attempting image upload for '{post_data['title']}', URL: {image_url}, source: {image_source}")
+            image_id = upload_image_to_wp(image_url, post_data["title"], wp_base_url, wp_username, wp_password, image_source, uploader, pixabay_url)
+            if not image_id:
+                logging.info(f"Flickr upload failed for '{post_data['title']}', falling back to Pixabay")
+                pixabay_query = post_data["title"][:50]
+                image_url, image_source, uploader, pixabay_url = get_image(pixabay_query)
+                if image_url:
+                    image_id = upload_image_to_wp(image_url, post_data["title"], wp_base_url, wp_username, wp_password, image_source, uploader, pixabay_url)
+            if not image_id:
+                logging.warning(f"All image uploads failed for '{post_data['title']}' - posting without image")
+        
         payload = {
             "title": post_data["title"],
             "content": formatted_content,
@@ -911,19 +925,9 @@ def post_to_wp(post_data, category, link, author, image_url, original_source, im
             }
         }
         
-        if image_url and not post_id:
-            logging.info(f"Attempting image upload for '{post_data['title']}', URL: {image_url}, source: {image_source}")
-            image_id = upload_image_to_wp(image_url, post_data["title"], wp_base_url, wp_username, wp_password, image_source, uploader, pixabay_url)
-            if not image_id:
-                logging.info(f"Flickr upload failed for '{post_data['title']}', falling back to Pixabay")
-                pixabay_query = post_data["title"][:50]
-                image_url, image_source, uploader, pixabay_url = get_image(pixabay_query)
-                if image_url:
-                    image_id = upload_image_to_wp(image_url, post_data["title"], wp_base_url, wp_username, wp_password, image_source, uploader, pixabay_url)
-            if image_id:
-                payload["featured_media"] = image_id
-            else:
-                logging.warning(f"All image uploads failed for '{post_data['title']}' - posting without image")
+        if image_id:
+            payload["featured_media"] = image_id
+            logging.info(f"Set featured image for post '{post_data['title']}': Media ID={image_id}")
         
         endpoint = f"{wp_base_url}/posts/{post_id}" if post_id else f"{wp_base_url}/posts"
         method = requests.post
@@ -951,7 +955,7 @@ def post_to_wp(post_data, category, link, author, image_url, original_source, im
             try:
                 post = {"title": post_data["title"], "url": post_url}
                 tweet = generate_article_tweet(author, post, author["persona"])
-                if post_tweet(author, tweet):  # Use the actual post_tweet function
+                if post_tweet(author, tweet):
                     logging.info(f"Successfully posted article tweet for {author['username']} on X")
                 else:
                     logging.warning(f"Failed to post article tweet for {author['username']} on X")