From 4549ebdb702777ab689d764758c6c006ff2aff8c Mon Sep 17 00:00:00 2001
From: christophercarlon <cmcarleone@gmail.com>
Date: Wed, 10 Jul 2024 21:01:08 +0100
Subject: [PATCH] Updates 2024-07-10 - Updated data catalogue list and addeddd
 new get creds module

---
 .../lambda_jobs/get_creds.py                  | 34 ++++++++
 herding_cats_pipelines/lambda_jobs/main.py    | 86 ++++++++-----------
 2 files changed, 69 insertions(+), 51 deletions(-)
 create mode 100644 herding_cats_pipelines/lambda_jobs/get_creds.py

diff --git a/herding_cats_pipelines/lambda_jobs/get_creds.py b/herding_cats_pipelines/lambda_jobs/get_creds.py
new file mode 100644
index 0000000..8c7cb93
--- /dev/null
+++ b/herding_cats_pipelines/lambda_jobs/get_creds.py
@@ -0,0 +1,34 @@
+import boto3
+import json
+from loguru import logger
+
+def get_param(parameter_name: str, region_name: str = "eu-west-2") -> str:
+    """
+    Retrieve a parameter from AWS Systems Manager Parameter Store.
+    """
+    ssm = boto3.client('ssm', region_name=region_name)
+    try:
+        response = ssm.get_parameter(Name=parameter_name, WithDecryption=True)
+        return response['Parameter']['Value']
+    except Exception as e:
+        logger.error(f"Unable to retrieve parameter: {str(e)}")
+        raise e
+
+def get_secret(secret_name: str, region_name: str = "eu-west-2") -> json:
+    """
+    Create an AWS Secrets Manager client. 
+    
+    Returns a JSON with env vars. 
+    """
+    session = boto3.session.Session()
+    client = session.client(service_name='secretsmanager',
+                            region_name=region_name)
+
+    try:
+        get_secret_value_response = client.get_secret_value(SecretId=secret_name)
+    except Exception as e:
+        logger.error(f"Unable to retrieve secret: {str(e)}")
+        raise e
+    else:
+        secret = get_secret_value_response['SecretString']
+        return json.loads(secret)
\ No newline at end of file
diff --git a/herding_cats_pipelines/lambda_jobs/main.py b/herding_cats_pipelines/lambda_jobs/main.py
index 57f680e..9f6a3cc 100644
--- a/herding_cats_pipelines/lambda_jobs/main.py
+++ b/herding_cats_pipelines/lambda_jobs/main.py
@@ -6,66 +6,50 @@
 
 from loguru import logger
 
-
-def get_param(parameter_name: str, region_name: str = "eu-west-2") -> str:
-    """
-    Retrieve a parameter from AWS Systems Manager Parameter Store.
-    """
-    ssm = boto3.client('ssm', region_name=region_name)
-    try:
-        response = ssm.get_parameter(Name=parameter_name, WithDecryption=True)
-        return response['Parameter']['Value']
-    except Exception as e:
-        logger.error(f"Unable to retrieve parameter {parameter_name}: {str(e)}")
-        raise e
-
-def get_secret(secret_name: str, region_name: str = "eu-west-2") -> json:
-    """
-    Create an AWS Secrets Manager client. 
-    
-    Returns a JSON with env vars. 
-    """
-    session = boto3.session.Session()
-    client = session.client(service_name='secretsmanager',
-                            region_name=region_name)
-
-    try:
-        get_secret_value_response = client.get_secret_value(SecretId=secret_name)
-    except Exception as e:
-        logger.error(f"Unable to retrieve secret {secret_name}: {str(e)}")
-        raise e
-    else:
-        secret = get_secret_value_response['SecretString']
-        return json.loads(secret)
+from get_creds import get_param, get_secret
+from urllib.parse import urlparse
 
 def lambda_handler(event, context) -> json:
     """
-    AWS Lambda function to fetch data catalogue from London Datastore and dump it to S3
+    AWS Lambda function to fetch UK open data catalogues. 
+    
+    Loop through links and dump catalogue data to s3 bucket.  
     """
+    
+    catalogues_list = [
+        "https://data.london.gov.uk/api/action/package_search",
+        "https://opendata.bristol.gov.uk/api/feed/dcat-ap/2.1.1.json"
+    ]
+    
     try:
+        # Fetch aws params and secrets
         secret_name = get_param("herding_cats_param")
         secret = get_secret(secret_name)
         bucket_name = secret["herding_cats_raw_data_bucket"]
         
-        url = "https://data.london.gov.uk/api/action/package_search"
-        response = requests.get(url)
-        response.raise_for_status()
-        data = response.json()
-        print("Data Successfully Fetched")
-
-        # Dump data to S3
-        s3 = boto3.client('s3')
-        bucket_name = bucket_name
-        file_name = 'london_datastore.json'
+        # Loop through the links
+        for link in catalogues_list:
+            response = requests.get(link, timeout=15)
+            response.raise_for_status()
+            data = response.json()
+            logger.success(f"Data Successfully Fetched for {link}")
+            
+            # Extract domain name from the link
+            domain = urlparse(link).netloc
+            
+            # Use domain as file name
+            file_name = f"{domain}.json"
+            
+            # Dump data to S3
+            s3 = boto3.client('s3')
+            s3.put_object(
+                Bucket=bucket_name,
+                Key=file_name,
+                Body=json.dumps(data),
+                ContentType='application/json'
+            )
+            logger.success(f"Data Was Successfully Dumped to {file_name}")
         
-        s3.put_object(
-            Bucket=bucket_name,
-            Key=file_name,
-            Body=json.dumps(data),
-            ContentType='application/json'
-        )
-        logger.success("Data Was Successfully Dumped...")
-
         return {
             'statusCode': 200,
             'body': json.dumps({'message': 'Data successfully fetched and dumped to S3'})
@@ -81,4 +65,4 @@ def lambda_handler(event, context) -> json:
         return {
             'statusCode': 500,
             'body': json.dumps({'error': f'S3 dump error: {str(e)}'})
-        }
\ No newline at end of file
+        }