ref: improve export code

api/src/backend/api/specs/v1.yaml

@@ -4112,12 +4112,13 @@ paths:
       summary: Download ZIP report
       parameters:
       - in: query
-        name: fields[scans]
+        name: fields[scan-reports]
         schema:
           type: array
           items:
             type: string
-            enum: []
+            enum:
+            - id
         description: endpoint return only specific fields in the response on a per-type
           basis by including a fields[TYPE] query parameter.
         explode: false

api/src/backend/api/tests/test_views.py

@@ -854,9 +854,9 @@ class TestProviderViewSet:
 
         included_data = response.json()["included"]
         for expected_type in expected_resources:
-            assert any(
-                d.get("type") == expected_type for d in included_data
-            ), f"Expected type '{expected_type}' not found in included data"
+            assert any(d.get("type") == expected_type for d in included_data), (
+                f"Expected type '{expected_type}' not found in included data"
+            )
 
     def test_providers_retrieve(self, authenticated_client, providers_fixture):
         provider1, *_ = providers_fixture
@@ -2243,9 +2243,9 @@ class TestResourceViewSet:
 
         included_data = response.json()["included"]
         for expected_type in expected_resources:
-            assert any(
-                d.get("type") == expected_type for d in included_data
-            ), f"Expected type '{expected_type}' not found in included data"
+            assert any(d.get("type") == expected_type for d in included_data), (
+                f"Expected type '{expected_type}' not found in included data"
+            )
 
     @pytest.mark.parametrize(
         "filter_name, filter_value, expected_count",
@@ -2451,9 +2451,9 @@ class TestFindingViewSet:
 
         included_data = response.json()["included"]
         for expected_type in expected_resources:
-            assert any(
-                d.get("type") == expected_type for d in included_data
-            ), f"Expected type '{expected_type}' not found in included data"
+            assert any(d.get("type") == expected_type for d in included_data), (
+                f"Expected type '{expected_type}' not found in included data"
+            )
 
     @pytest.mark.parametrize(
         "filter_name, filter_value, expected_count",
@@ -2735,9 +2735,9 @@ class TestJWTFields:
             reverse("token-obtain"), data, format="json"
         )
 
-        assert (
-            response.status_code == status.HTTP_200_OK
-        ), f"Unexpected status code: {response.status_code}"
+        assert response.status_code == status.HTTP_200_OK, (
+            f"Unexpected status code: {response.status_code}"
+        )
 
         access_token = response.data["attributes"]["access"]
         payload = jwt.decode(access_token, options={"verify_signature": False})
@@ -2751,23 +2751,23 @@ class TestJWTFields:
         # Verify expected fields
         for field in expected_fields:
             assert field in payload, f"The field '{field}' is not in the JWT"
-            assert (
-                payload[field] == expected_fields[field]
-            ), f"The value of '{field}' does not match"
+            assert payload[field] == expected_fields[field], (
+                f"The value of '{field}' does not match"
+            )
 
         # Verify time fields are integers
         for time_field in ["exp", "iat", "nbf"]:
             assert time_field in payload, f"The field '{time_field}' is not in the JWT"
-            assert isinstance(
-                payload[time_field], int
-            ), f"The field '{time_field}' is not an integer"
+            assert isinstance(payload[time_field], int), (
+                f"The field '{time_field}' is not an integer"
+            )
 
         # Verify identification fields are non-empty strings
         for id_field in ["jti", "sub", "tenant_id"]:
             assert id_field in payload, f"The field '{id_field}' is not in the JWT"
-            assert (
-                isinstance(payload[id_field], str) and payload[id_field]
-            ), f"The field '{id_field}' is not a valid string"
+            assert isinstance(payload[id_field], str) and payload[id_field], (
+                f"The field '{id_field}' is not a valid string"
+            )
 
 
 @pytest.mark.django_db

api/src/backend/api/v1/serializers.py

@@ -819,12 +819,12 @@ class ScanTaskSerializer(RLSSerializer):
         ]
 
 
-class ScanReportSerializer(RLSSerializer):
+class ScanReportSerializer(serializers.Serializer):
+    id = serializers.CharField(source="scan")
+
     class Meta:
-        model = Scan
-        fields = [
-            "id",
-        ]
+        resource_name = "scan-reports"
+        fields = ["id"]
 
 
 class ResourceTagSerializer(RLSSerializer):

api/src/backend/api/v1/views.py

@@ -1115,22 +1115,22 @@ class ScanViewSet(BaseRLSViewSet):
     def report(self, request, pk=None):
         scan_instance = Scan.objects.get(pk=pk)
         output_path = scan_instance.output_path
-        if 1 == 2 and scan_instance.upload_to_s3:
+        if scan_instance.upload_to_s3:
             s3_client = None
             try:
-                s3_client = boto3.client("s3")
+                s3_client = boto3.client(
+                    "s3",
+                    aws_access_key_id=env.str("DJANGO_ARTIFACTS_AWS_ACCESS_KEY_ID"),
+                    aws_secret_access_key=env.str(
+                        "DJANGO_ARTIFACTS_AWS_SECRET_ACCESS_KEY"
+                    ),
+                    aws_session_token=env.str("DJANGO_ARTIFACTS_AWS_SESSION_TOKEN"),
+                    region_name=env.str("DJANGO_ARTIFACTS_AWS_DEFAULT_REGION"),
+                )
                 s3_client.list_buckets()
             except (ClientError, NoCredentialsError, ParamValidationError):
                 try:
-                    s3_client = boto3.client(
-                        "s3",
-                        aws_access_key_id=env.str("DJANGO_ARTIFACTS_AWS_ACCESS_KEY_ID"),
-                        aws_secret_access_key=env.str(
-                            "DJANGO_ARTIFACTS_AWS_SECRET_ACCESS_KEY"
-                        ),
-                        aws_session_token=env.str("DJANGO_ARTIFACTS_AWS_SESSION_TOKEN"),
-                        region_name=env.str("DJANGO_ARTIFACTS_AWS_DEFAULT_REGION"),
-                    )
+                    s3_client = boto3.client("s3")
                     s3_client.list_buckets()
                 except (ClientError, NoCredentialsError, ParamValidationError):
                     return Response(

api/src/backend/tasks/jobs/export.py

@@ -16,9 +16,9 @@ from prowler.lib.outputs.html.html import HTML
 from prowler.lib.outputs.ocsf.ocsf import OCSF
 
 logger = get_task_logger(__name__)
-
 tmp_output_directory = "/tmp/prowler_api_output"
 
+
 # Predefined mapping for output formats and their configurations
 OUTPUT_FORMATS_MAPPING = {
     "csv": {
@@ -30,14 +30,6 @@ OUTPUT_FORMATS_MAPPING = {
     "html": {"class": HTML, "suffix": html_file_suffix, "kwargs": {"stats": {}}},
 }
 
-# Mapping provider types to their identity components for output paths
-PROVIDER_IDENTITY_MAP = {
-    "aws": lambda p: p.identity.account,
-    "azure": lambda p: p.identity.tenant_domain,
-    "gcp": lambda p: p.identity.profile,
-    "kubernetes": lambda p: p.identity.context.replace(":", "_").replace("/", "_"),
-}
-
 
 def _compress_output_files(output_directory: str) -> str:
     """