fix image upload issue

foodie_automator_rss.py

@@ -37,23 +37,12 @@ load_dotenv()
 
 is_posting = False
 LOCK_FILE = "/home/shane/foodie_automator/locks/foodie_automator_rss.lock"
-
-def signal_handler(sig, frame):
-    logging.info("Received termination signal, checking if safe to exit...")
-    if is_posting:
-        logging.info("Currently posting, will exit after completion.")
-    else:
-        logging.info("Safe to exit immediately.")
-        sys.exit(0)
-
-signal.signal(signal.SIGTERM, signal_handler)
-signal.signal(signal.SIGINT, signal_handler)
-
 LOG_FILE = "/home/shane/foodie_automator/logs/foodie_automator_rss.log"
 LOG_PRUNE_DAYS = 30
 FEED_TIMEOUT = 15
 MAX_RETRIES = 3
 RETRY_BACKOFF = 2
+IMAGE_UPLOAD_TIMEOUT = 30  # Added to match foodie_utils.py
 
 POSTED_TITLES_FILE = '/home/shane/foodie_automator/posted_rss_titles.json'
 USED_IMAGES_FILE = '/home/shane/foodie_automator/used_images.json'
@@ -65,39 +54,48 @@ posted_titles = set(entry["title"] for entry in posted_titles_data)
 used_images = set(entry["title"] for entry in load_json_file(USED_IMAGES_FILE, IMAGE_EXPIRATION_DAYS) if "title" in entry)
 
 def setup_logging():
-    if os.path.exists(LOG_FILE):
+    """Initialize logging with pruning of old logs."""
-        with open(LOG_FILE, 'r') as f:
+    try:
-            lines = f.readlines()
+        os.makedirs(os.path.dirname(LOG_FILE), exist_ok=True)
-        cutoff = datetime.now(timezone.utc) - timedelta(days=LOG_PRUNE_DAYS)
+        if not os.access(os.path.dirname(LOG_FILE), os.W_OK):
-        pruned_lines = []
+            raise PermissionError(f"No write permission for {os.path.dirname(LOG_FILE)}")
-        malformed_count = 0
+        if os.path.exists(LOG_FILE):
-        for line in lines:
+            with open(LOG_FILE, 'r') as f:
-            if len(line) < 19 or not line[:19].replace('-', '').replace(':', '').replace(' ', '').isdigit():
+                lines = f.readlines()
-                malformed_count += 1
+            cutoff = datetime.now(timezone.utc) - timedelta(days=LOG_PRUNE_DAYS)
-                continue
+            pruned_lines = []
-            try:
+            malformed_count = 0
-                timestamp = datetime.strptime(line[:19], '%Y-%m-%d %H:%M:%S').replace(tzinfo=timezone.utc)
+            for line in lines:
-                if timestamp > cutoff:
+                if len(line) < 19 or not line[:19].replace('-', '').replace(':', '').replace(' ', '').isdigit():
-                    pruned_lines.append(line)
+                    malformed_count += 1
-            except ValueError:
+                    continue
-                malformed_count += 1
+                try:
-                continue
+                    timestamp = datetime.strptime(line[:19], '%Y-%m-%d %H:%M:%S').replace(tzinfo=timezone.utc)
-        if malformed_count > 0:
+                    if timestamp > cutoff:
-            logging.info(f"Skipped {malformed_count} malformed log lines during pruning")
+                        pruned_lines.append(line)
-        with open(LOG_FILE, 'w') as f:
+                except ValueError:
-            f.writelines(pruned_lines)
+                    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)
         
-    logging.basicConfig(
+        logging.basicConfig(
-        filename=LOG_FILE,
+            filename=LOG_FILE,
-        level=logging.INFO,
+            level=logging.INFO,
-        format="%(asctime)s - %(levelname)s - %(message)s",
+            format="%(asctime)s - %(levelname)s - %(message)s",
-        datefmt="%Y-%m-%d %H:%M:%S"
+            datefmt="%Y-%m-%d %H:%M:%S"
-    )
+        )
-    console_handler = logging.StreamHandler()
+        console_handler = logging.StreamHandler()
-    console_handler.setFormatter(logging.Formatter('%(asctime)s - %(levelname)s - %(message)s'))
+        console_handler.setFormatter(logging.Formatter('%(asctime)s - %(levelname)s - %(message)s'))
-    logging.getLogger().addHandler(console_handler)
+        logging.getLogger().addHandler(console_handler)
-    logging.getLogger("requests").setLevel(logging.WARNING)
+        logging.getLogger("requests").setLevel(logging.WARNING)
-    logging.info("Logging initialized for foodie_automator_rss.py")
+        logging.getLogger("openai").setLevel(logging.WARNING)
+        logging.info("Logging initialized for foodie_automator_rss.py")
+    except Exception as e:
+        print(f"Failed to setup logging: {e}")
+        sys.exit(1)
 
 def acquire_lock():
     os.makedirs(os.path.dirname(LOCK_FILE), exist_ok=True)
@@ -111,6 +109,17 @@ def acquire_lock():
         logging.info("Another instance of foodie_automator_rss.py is running")
         sys.exit(0)
 
+def signal_handler(sig, frame):
+    logging.info("Received termination signal, checking if safe to exit...")
+    if is_posting:
+        logging.info("Currently posting, will exit after completion.")
+    else:
+        logging.info("Safe to exit immediately.")
+        sys.exit(0)
+
+signal.signal(signal.SIGTERM, signal_handler)
+signal.signal(signal.SIGINT, signal_handler)
+
 def create_http_session() -> requests.Session:
     session = requests.Session()
     retry_strategy = Retry(
@@ -209,7 +218,7 @@ def fetch_duckduckgo_news_context(title, hours=24):
                         if '+00:00' in date_str:
                             dt = datetime.strptime(date_str, "%Y-%m-%dT%H:%M:%S+00:00").replace(tzinfo=timezone.utc)
                         else:
-                            dt = datetime.strptime(date_str, "%Y-%m-%dT%H:%M:%S%Z").replace(tzinfo=timezone.utc)
+                            dt = datetime.strptime(date_str, "%Y-%m-%dT%H:%M:%SZ").replace(tzinfo=timezone.utc)
                         if dt > (datetime.now(timezone.utc) - timedelta(hours=24)):
                             titles.append(r["title"].lower())
                     except ValueError as e:
@@ -324,6 +333,10 @@ def curate_from_rss():
                     interest_score=interest_score,
                     should_post_tweet=True
                 )
+                if not post_id:
+                    logging.warning(f"Failed to post to WordPress for '{title}', skipping")
+                    attempts += 1
+                    continue
             except Exception as e:
                 logging.error(f"Failed to post to WordPress for '{title}': {e}", exc_info=True)
                 attempts += 1
@@ -383,6 +396,7 @@ def run_rss_automator():
     lock_fd = None
     try:
         lock_fd = acquire_lock()
+        setup_logging()
         logging.info("***** RSS Automator Launched *****")
         post_data, category, should_continue = curate_from_rss()
         if not post_data:
@@ -392,6 +406,7 @@ def run_rss_automator():
         return post_data, category, should_continue
     except Exception as e:
         logging.error(f"Fatal error in run_rss_automator: {e}", exc_info=True)
+        print(f"Fatal error: {e}")
         return None, None, False
     finally:
         if lock_fd:
@@ -400,7 +415,4 @@ def run_rss_automator():
             os.remove(LOCK_FILE) if os.path.exists(LOCK_FILE) else None
 
 if __name__ == "__main__":
-    setup_logging()
+    run_rss_automator()
-    post_data, category, should_continue = run_rss_automator()
-    # Remove sleep timer, let manage_scripts.sh control execution
-    logging.info(f"Run completed, should_continue: {should_continue}")

foodie_utils.py

@@ -448,25 +448,24 @@ def upload_image_to_wp(image_url, post_title, wp_base_url, wp_username, wp_passw
         }
         logging.info(f"Fetching image from {image_url} for '{post_title}'")
         
-        for attempt in range(3):
+        for attempt in range(MAX_RETRIES):
             try:
-                image_response = requests.get(image_url, headers=image_headers, timeout=10)
+                image_response = requests.get(image_url, headers=image_headers, timeout=IMAGE_UPLOAD_TIMEOUT)
                 if image_response.status_code == 429:
-                    wait_time = 10 * (2 ** attempt)
+                    wait_time = RETRY_BACKOFF * (2 ** attempt)
-                    logging.warning(f"Rate limit hit for {image_url}. Retrying after {wait_time}s (attempt {attempt+1}/3).")
+                    logging.warning(f"Rate limit hit for {image_url}. Retrying after {wait_time}s (attempt {attempt+1}/{MAX_RETRIES}).")
                     time.sleep(wait_time)
                     continue
                 image_response.raise_for_status()
                 break
-            except requests.exceptions.HTTPError as e:
+            except requests.exceptions.RequestException as e:
-                if e.response.status_code == 429:
+                logging.warning(f"Image fetch failed for {image_url} (attempt {attempt+1}/{MAX_RETRIES}): {e}")
-                    wait_time = 10 * (2 ** attempt)
+                if attempt == MAX_RETRIES - 1:
-                    logging.warning(f"Rate limit hit for {image_url}. Retrying after {wait_time}s (attempt {attempt+1}/3).")
+                    logging.error(f"Failed to fetch image {image_url} after {MAX_RETRIES} attempts")
-                    time.sleep(wait_time)
+                    return None
-                    continue
+                time.sleep(RETRY_BACKOFF * (2 ** attempt))
-                raise
         else:
-            logging.warning(f"Rate limit hit for {image_url} after retries. Failing image upload.")
+            logging.error(f"Failed to fetch image {image_url} after retries")
             return None
 
         response = requests.post(
@@ -492,7 +491,8 @@ def upload_image_to_wp(image_url, post_title, wp_base_url, wp_username, wp_passw
         logging.info(f"Uploaded image '{safe_title}.jpg' to WP (ID: {image_id}) with caption '{caption}'")
         return image_id
     except Exception as e:
-        logging.error(f"Image upload to WP failed for '{post_title}': {e}")
+        logging.error(f"Image upload to WP failed for '{post_title}': {e}", exc_info=True)
+        print(f"Image upload to WP failed for '{post_title}': {e}")
         return None
 
 def determine_paragraph_count(interest_score):