Add logging configuration and info statements for content updates and reference extraction

controllers/utils.py

@@ -37,6 +37,11 @@ with open('xpath.json', 'r', encoding='UTF-8') as f:
 with open('patterns.json', 'r', encoding='UTF-8') as f:
     patterns = json.load(f)
 
+logging.basicConfig(
+    format='%(asctime)s - %(levelname)s - %(funcName)s - %(message)s',
+    datefmt="%Y-%m-%d %H:%M:%S",
+    level=logging.INFO
+)
 
 def datemodifier(date_string, date_format):
     """Date Modifier Function
@@ -218,6 +223,7 @@ def update_content(report):
     Returns:
         None
     """
+    logging.info("Updating content for %s", report['id'])
     dynamodb = get_client_connection()
     response = dynamodb.update_item(
         TableName="article_china",
@@ -429,6 +435,7 @@ def extract_reference(row):
         None
     """
     try:
+        logging.info("Extracting reference for %s", row['id'])
         pattern = next(
             (elem for elem in patterns if elem['site'] == row['site']), None)
         extracted_text = extract_from_pdf_by_pattern(row['attachment'],