adjust logging levels, fix to get_seen_shortcodes

Author: ericahan22

.github/workflows/update-events-data.yml

@@ -4,7 +4,6 @@ on:
   schedule:
     - cron: '0 13 * * *'  # 8am EST (UTC-5)
   workflow_dispatch:
-    inputs:
 
 jobs:
   instagram_feed:

backend/scraping/instagram_feed.py

@@ -37,7 +37,7 @@
 load_dotenv()
 
 CUTOFF_DAYS = 1
-MAX_CONCURRENT_TASKS = int(os.getenv("MAX_CONCURRENT_TASKS", "10"))
+MAX_CONCURRENT_TASKS = int(os.getenv("MAX_CONCURRENT_TASKS", "5"))
 APIFY_API_TOKEN = os.getenv("APIFY_API_TOKEN")
 
 
@@ -483,7 +483,7 @@ async def process_scraped_posts(posts_data, cutoff_date):
     logger.info(f"Starting post processing for {len(posts_data)} scraped posts.")
     logger.info(f"Concurrency limit set to {MAX_CONCURRENT_TASKS} tasks.")
 
-    seen_shortcodes = get_seen_shortcodes()
+    seen_shortcodes = await sync_to_async(get_seen_shortcodes)()
 
     semaphore = asyncio.Semaphore(MAX_CONCURRENT_TASKS)
     tasks = []

backend/scraping/logging_config.py

@@ -20,6 +20,7 @@ def setup_logging():
     logging.getLogger("httpcore").setLevel(logging.WARNING)
     logging.getLogger("openai").setLevel(logging.WARNING)
     logging.getLogger("PIL").setLevel(logging.INFO)
+    logging.getLogger("apify_client").setLevel(logging.WARNING)
 
     fmt = "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
     handlers = [
@@ -28,6 +29,7 @@ def setup_logging():
     ]
     logging.basicConfig(level=logging.DEBUG, format=fmt, handlers=handlers)
     root_logger._wat2do_configured = True
+    root_logger.propagate = False
 
 
 setup_logging()

backend/services/storage_service.py

@@ -58,10 +58,9 @@ def _download_image_from_url(self, image_url: str) -> bytes | None:
         try:
             response = requests.get(image_url, timeout=60)
             response.raise_for_status()
-
             return response.content
-        except Exception:
-            logger.exception(f"Failed to download image from {image_url}")
+        except Exception as e:
+            logger.error(f"Failed to download image from {image_url}: {e}")
             return None
 
     def upload_image_from_url(