castor-extractor 0.24.15__tar.gz → 0.24.21__tar.gz

{castor_extractor-0.24.15 → castor_extractor-0.24.21}/CHANGELOG.md

@@ -1,5 +1,29 @@
 # Changelog
 
+## 0.24.21 - 2025-05-26
+
+* Looker Studio: add option to skip the extraction of view activity logs
+
+## 0.24.20 - 2025-05-19
+
+* Powerbi: allow custom api base and login url
+
+## 0.24.19 - 2025-05-14
+
+* Confluence: extract databases
+
+## 0.24.18 - 2025-05-13
+
+* Improve folder organisation for transformation tools
+
+## 0.24.17 - 2025-05-13
+
+* Strategy: fix dashboard URL format
+
+## 0.24.16 - 2025-05-12
+
+* Confluence: extract folders to complete the page hierarchy
+
 ## 0.24.15 - 2025-05-12
 
 * Tableau: Add argument to skip columns extraction

{castor_extractor-0.24.15 → castor_extractor-0.24.21}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: castor-extractor
-Version: 0.24.15
+Version: 0.24.21
 Summary: Extract your metadata assets.
 Home-page: https://www.castordoc.com/
 License: EULA
@@ -215,6 +215,30 @@ For any questions or bug report, contact us at [support@coalesce.io](mailto:supp
 
 # Changelog
 
+## 0.24.21 - 2025-05-26
+
+* Looker Studio: add option to skip the extraction of view activity logs
+
+## 0.24.20 - 2025-05-19
+
+* Powerbi: allow custom api base and login url
+
+## 0.24.19 - 2025-05-14
+
+* Confluence: extract databases
+
+## 0.24.18 - 2025-05-13
+
+* Improve folder organisation for transformation tools
+
+## 0.24.17 - 2025-05-13
+
+* Strategy: fix dashboard URL format
+
+## 0.24.16 - 2025-05-12
+
+* Confluence: extract folders to complete the page hierarchy
+
 ## 0.24.15 - 2025-05-12
 
 * Tableau: Add argument to skip columns extraction

{castor_extractor-0.24.15 → castor_extractor-0.24.21}/castor_extractor/commands/extract_looker_studio.py

@@ -24,6 +24,12 @@ def main():
             "This can be the same file path as for Looker Studio."
         ),
     )
+    parser.add_argument(
+        "--skip-view-activity-logs",
+        action="store_true",
+        default=False,
+        help="Skips the extraction of activity logs",
+    )
 
     parser.add_argument("-o", "--output", help="Directory to write to")
 

{castor_extractor-0.24.15 → castor_extractor-0.24.21}/castor_extractor/commands/extract_powerbi.py

@@ -20,5 +20,7 @@ def main():
         nargs="*",
     )
     parser.add_argument("-o", "--output", help="Directory to write to")
+    parser.add_argument("-l", "--login_url", help="Login url (Optional)")
+    parser.add_argument("-a", "--api_base", help="REST API base (Optional)")
 
     powerbi.extract_all(**parse_filled_arguments(parser))

{castor_extractor-0.24.15 → castor_extractor-0.24.21}/castor_extractor/knowledge/confluence/assets.py

@@ -4,5 +4,7 @@ from ...types import ExternalAsset
 class ConfluenceAsset(ExternalAsset):
     """Confluence assets"""
 
+    DATABASES = "databases"
+    FOLDERS = "folders"
     PAGES = "pages"
     USERS = "users"

{castor_extractor-0.24.15 → castor_extractor-0.24.21}/castor_extractor/knowledge/confluence/client/client.py

@@ -1,6 +1,7 @@
+import logging
 from collections.abc import Iterator
 from functools import partial
-from typing import Optional
+from typing import Iterable, Optional
 
 from ....utils import (
     APIClient,
@@ -14,6 +15,8 @@ from .credentials import ConfluenceCredentials
 from .endpoints import ConfluenceEndpointFactory
 from .pagination import ConfluencePagination
 
+logger = logging.getLogger(__name__)
+
 _HEADERS = {
     "Accept": "application/json",
     "Content-Type": "application/json",
@@ -46,6 +49,43 @@ class ConfluenceClient(APIClient):
         self.space_ids_allowed = space_ids_allowed or set()
         self.space_ids_blocked = space_ids_blocked or set()
 
+    def databases(self, database_ids: Iterable[str]) -> Iterator[dict]:
+        """
+        Extracts all given databases
+        """
+        for _id in database_ids:
+            database = self._get(
+                endpoint=ConfluenceEndpointFactory.database(_id),
+            )
+            yield database
+
+    def folders(self, folder_ids: Iterable[str]) -> Iterator[dict]:
+        """
+        Extracts all given folders and their parent folders.
+        """
+        candidate_ids = set(folder_ids)
+        seen = set()
+
+        while candidate_ids:
+            folder_id = candidate_ids.pop()
+            if folder_id in seen:
+                continue
+
+            seen.add(folder_id)
+            folder = self._get(
+                endpoint=ConfluenceEndpointFactory.folder(folder_id),
+            )
+            yield folder
+
+            parent_type = folder.get("parentType")
+            if parent_type == "folder":
+                folder_id = folder["parentId"]
+                if folder_id not in seen:
+                    candidate_ids.add(folder["parentId"])
+
+            if not parent_type:
+                logger.info(f"folder with unknown parent: {folder_id}")
+
     def pages(self):
         """Extracts all pages from all relevant Spaces."""
         for space in self.spaces():
@@ -106,9 +146,23 @@ class ConfluenceClient(APIClient):
         )
         yield from fetch_all_pages(request, ConfluencePagination)
 
-    def fetch(self, asset: ConfluenceAsset) -> Iterator[dict]:
+    def fetch(
+        self,
+        asset: ConfluenceAsset,
+        *,
+        folder_ids: Optional[Iterator[str]] = None,
+        database_ids: Optional[Iterator[str]] = None,
+    ) -> Iterator[dict]:
         """Returns the needed metadata for the queried asset"""
-        if asset == ConfluenceAsset.PAGES:
+        if asset == ConfluenceAsset.FOLDERS:
+            assert folder_ids is not None
+            yield from self.folders(folder_ids)
+
+        elif asset == ConfluenceAsset.DATABASES:
+            assert database_ids is not None
+            yield from self.databases(database_ids)
+
+        elif asset == ConfluenceAsset.PAGES:
             yield from self.pages()
 
         elif asset == ConfluenceAsset.USERS:

{castor_extractor-0.24.15 → castor_extractor-0.24.21}/castor_extractor/knowledge/confluence/client/client_test.py

@@ -3,6 +3,36 @@ from unittest.mock import MagicMock, patch
 from .client import ConfluenceClient
 
 
+def test_ConfluenceClient_folders():
+    """
+    Folder 1 -> Page A -> Folder 2 -> Folder 3 -> Folder 4 -> Page B
+             -> Page C -> Folder 5 -> Page D
+
+    After extracting the pages, we should have all IDs of folders that are
+    immediate parents of pages. We still need to look out for nested folders.
+    """
+    folder_ids = {"1", "3", "4", "5"}
+    mock_responses = {
+        "1": {"id": "1", "parentType": None, "parentId": None},
+        "2": {"id": "2", "parentType": "page", "parentId": "A"},
+        "3": {"id": "3", "parentType": "folder", "parentId": "2"},
+        "4": {"id": "4", "parentType": "folder", "parentId": "3"},
+        "5": {"id": "5", "parentType": "page", "parentId": "C"},
+    }
+
+    def mock_get(endpoint):
+        folder_id = endpoint.split("/")[-1]
+        return mock_responses[folder_id]
+
+    client = ConfluenceClient(credentials=MagicMock())
+
+    with patch.object(client, "_get", side_effect=mock_get):
+        result = list(client.folders(folder_ids))
+
+    assert len(result) == 5
+    assert {folder["id"] for folder in result} == set(mock_responses.keys())
+
+
 def test_ConfluenceClient_filtered_spaces_with_allowlist():
     both_blocked_and_allowed_space_id = "789"
     archived_space_id = "934"

{castor_extractor-0.24.15 → castor_extractor-0.24.21}/castor_extractor/knowledge/confluence/client/endpoints.py

@@ -5,10 +5,28 @@ class ConfluenceEndpointFactory:
     """
 
     API = "wiki/api/v2/"
+    DATABASE = "databases"
+    FOLDERS = "folders"
     PAGES = "pages"
     SPACES = "spaces"
     USERS = "users-bulk"
 
+    @classmethod
+    def database(cls, database_id: str) -> str:
+        """
+        Endpoint to fetch a database by id.
+        More: https://developer.atlassian.com/cloud/confluence/rest/v2/api-group-database/#api-databases-id-get
+        """
+        return f"{cls.API}{cls.DATABASE}/{database_id}"
+
+    @classmethod
+    def folder(cls, folder_id: str) -> str:
+        """
+        Endpoint to fetch a folder by id.
+        More: https://developer.atlassian.com/cloud/confluence/rest/v2/api-group-folder/#api-folders-id-get
+        """
+        return f"{cls.API}{cls.FOLDERS}/{folder_id}"
+
     @classmethod
     def pages(cls, space_id: str) -> str:
         """

{castor_extractor-0.24.15 → castor_extractor-0.24.21}/castor_extractor/knowledge/confluence/extract.py

@@ -13,6 +13,7 @@ from ...utils import (
 )
 from .assets import ConfluenceAsset
 from .client import ConfluenceClient, ConfluenceCredentials
+from .utils import pages_to_database_ids, pages_to_folder_ids
 
 logger = logging.getLogger(__name__)
 
@@ -32,6 +33,16 @@ def iterate_all_data(
     yield ConfluenceAsset.PAGES, pages
     logger.info(f"Extracted {len(pages)} pages from API")
 
+    folder_ids = pages_to_folder_ids(pages)
+    logger.info("Extracting FOLDERS from API")
+    folders = list(deep_serialize(client.folders(folder_ids)))
+    yield ConfluenceAsset.FOLDERS, folders
+
+    database_ids = pages_to_database_ids(pages)
+    logger.info("Extracting DATABASES from API")
+    databases = list(deep_serialize(client.databases(database_ids)))
+    yield ConfluenceAsset.DATABASES, databases
+
 
 def extract_all(**kwargs) -> None:
     """

castor_extractor-0.24.21/castor_extractor/knowledge/confluence/utils.py

@@ -0,0 +1,12 @@
+def pages_to_folder_ids(pages: list[dict]) -> set:
+    """Returns all unique folder parents."""
+    return {
+        page["parentId"] for page in pages if page["parentType"] == "folder"
+    }
+
+
+def pages_to_database_ids(pages: list[dict]) -> set:
+    """Returns all unique database parents."""
+    return {
+        page["parentId"] for page in pages if page["parentType"] == "database"
+    }

castor_extractor-0.24.21/castor_extractor/knowledge/confluence/utils_test.py

@@ -0,0 +1,30 @@
+from .utils import pages_to_database_ids, pages_to_folder_ids
+
+
+def test_pages_to_folder_ids():
+    """Test the pages_to_folder_ids function."""
+    pages = [
+        {"id": "9", "parentId": None, "parentType": None},
+        {"id": "8", "parentId": "2", "parentType": "folder"},
+        {"id": "7", "parentId": "9", "parentType": "page"},
+        {"id": "6", "parentId": "4", "parentType": "folder"},
+        {"id": "5", "parentId": "4", "parentType": "folder"},
+    ]
+    expected = {"2", "4"}
+    result = pages_to_folder_ids(pages)
+    assert result == expected
+
+
+def test_pages_to_database_id():
+    """Test the pages_to_database_id function."""
+    pages = [
+        {"id": "1", "parentId": "db1", "parentType": "database"},
+        {"id": "2", "parentId": "db2", "parentType": "database"},
+        {"id": "3", "parentId": "4", "parentType": "folder"},
+        {"id": "4", "parentId": None, "parentType": None},
+        {"id": "5", "parentId": "db1", "parentType": "database"},
+        {"id": "6", "parentId": "9", "parentType": "page"},
+    ]
+    expected = {"db1", "db2"}
+    result = pages_to_database_ids(pages)
+    assert result == expected

{castor_extractor-0.24.15/castor_extractor/utils → castor_extractor-0.24.21/castor_extractor/transformation}/dbt/client_test.py

@@ -9,9 +9,7 @@ from dateutil.tz import tzutc
 from .client import ContentType, DbtClient, DbtRun, _account_url  # type: ignore
 from .credentials import DbtCredentials
 
-_DBT_CLIENT_PATH = (
-    "source.packages.extractor.castor_extractor.utils.dbt.client.DbtClient"
-)
+_DBT_CLIENT_PATH = "source.packages.extractor.castor_extractor.transformation.dbt.client.DbtClient"
 _OLD_DATE = datetime(2023, 7, 10, 12, 6, 23, 109171, tzinfo=tzutc())
 _OLD_DATE_STR = "2023-07-10 12:06:23.109171+00:00"
 _RECENT_DATE = datetime(2023, 10, 6, 5, 9, 31, 731991, tzinfo=tzutc())

{castor_extractor-0.24.15 → castor_extractor-0.24.21}/castor_extractor/utils/__init__.py

@@ -52,7 +52,7 @@ from .time import (
     yesterday,
 )
 from .type import Callback, Getter, JsonType, SerializedAsset
-from .validation import validate_baseurl
+from .validation import clean_path, validate_baseurl
 from .write import (
     get_output_filename,
     get_summary_filename,

{castor_extractor-0.24.15 → castor_extractor-0.24.21}/castor_extractor/utils/validation.py

@@ -14,7 +14,7 @@ def _preprocess_url(base_url: str) -> str:
     return base_url.strip()
 
 
-def _clean_path(path: str) -> str:
+def clean_path(path: str) -> str:
     return path.rstrip("/")
 
 
@@ -44,7 +44,7 @@ def _urlsplit(base_url: str) -> tuple[str, str, str, str, str, str]:
     url = urlsplit(base_url)
 
     hostname, port = _get_hostname_port(url.netloc)
-    path = _clean_path(url.path)
+    path = clean_path(url.path)
 
     return url.scheme, hostname, path, port, url.query, url.fragment
 

castor_extractor-0.24.21/castor_extractor/visualization/looker_studio/assets.py

@@ -0,0 +1,11 @@
+from ...types import ExternalAsset, classproperty
+
+
+class LookerStudioAsset(ExternalAsset):
+    ASSETS = "assets"
+    SOURCE_QUERIES = "source_queries"
+    VIEW_ACTIVITY = "view_activity"
+
+    @classproperty
+    def optional(cls) -> set["LookerStudioAsset"]:
+        return {LookerStudioAsset.VIEW_ACTIVITY}

{castor_extractor-0.24.15 → castor_extractor-0.24.21}/castor_extractor/visualization/looker_studio/client/admin_sdk_client.py

@@ -12,7 +12,6 @@ from ....utils import (
 )
 from .credentials import LookerStudioCredentials
 from .pagination import LookerStudioPagination
-from .scopes import SCOPES
 
 USER_EMAIL_FIELD = "primaryEmail"
 
@@ -26,7 +25,7 @@ class AdminSDKClient:
     def __init__(self, credentials: LookerStudioCredentials):
         self._credentials = Credentials.from_service_account_info(
             credentials.model_dump(),
-            scopes=SCOPES,
+            scopes=credentials.scopes,
             subject=credentials.admin_email,  # impersonates an admin
         )
         self.directory_api = discovery.build(

castor_extractor-0.24.21/castor_extractor/visualization/looker_studio/client/credentials.py

@@ -0,0 +1,46 @@
+from typing import Optional
+
+from pydantic import BaseModel, SecretStr, field_serializer
+
+SCOPES_NO_ACTIVITY: tuple[str, ...] = (
+    "https://www.googleapis.com/auth/datastudio",
+    "https://www.googleapis.com/auth/userinfo.profile",
+    "https://www.googleapis.com/auth/admin.directory.user.readonly",
+)
+
+DEFAULT_SCOPES: tuple[str, ...] = (
+    *SCOPES_NO_ACTIVITY,
+    "https://www.googleapis.com/auth/admin.reports.audit.readonly",
+)
+
+
+class LookerStudioCredentials(BaseModel):
+    """
+    Looker Studio Credentials match the Service Account credentials JSON
+    but with an additional admin_email field.
+    """
+
+    admin_email: str
+    auth_provider_x509_cert_url: str
+    auth_uri: str
+    client_email: str
+    client_id: str
+    client_x509_cert_url: str
+    private_key: SecretStr
+    private_key_id: str
+    project_id: str
+    token_uri: str
+    type: str
+
+    has_view_activity_logs: Optional[bool] = True
+    scopes: Optional[tuple] = DEFAULT_SCOPES
+
+    def model_post_init(self, __context):
+        """Set scopes based on has_view_activity_logs after initialization"""
+        if self.has_view_activity_logs is False:
+            self.scopes = SCOPES_NO_ACTIVITY
+
+    @field_serializer("private_key")
+    def dump_secret(self, pk):
+        """When using model_dump, show private_key value"""
+        return pk.get_secret_value()

{castor_extractor-0.24.15 → castor_extractor-0.24.21}/castor_extractor/visualization/looker_studio/client/looker_studio_api_client.py

@@ -16,7 +16,6 @@ from .credentials import LookerStudioCredentials
 from .endpoints import LookerStudioAPIEndpoint
 from .enums import LookerStudioAssetType
 from .pagination import LookerStudioPagination
-from .scopes import SCOPES
 
 
 @contextmanager
@@ -47,7 +46,8 @@ class LookerStudioAPIAuth(BearerAuth):
         that user and make requests on that user's behalf.
         """
         self._credentials = Credentials.from_service_account_info(
-            credentials.model_dump(), scopes=SCOPES
+            credentials.model_dump(),
+            scopes=credentials.scopes,
         )
         if subject:
             self._credentials = self._credentials.with_subject(subject)

{castor_extractor-0.24.15 → castor_extractor-0.24.21}/castor_extractor/visualization/looker_studio/extract.py

@@ -23,8 +23,14 @@ LOOKER_STUDIO_ADMIN_EMAIL = "CASTOR_LOOKER_STUDIO_ADMIN_EMAIL"
 
 def iterate_all_data(
     client: LookerStudioClient,
+    has_view_activity_logs: bool = True,
 ) -> Iterable[tuple[LookerStudioAsset, Union[list, dict]]]:
-    for asset in LookerStudioAsset:
+    assets_to_extract = LookerStudioAsset.mandatory
+
+    if has_view_activity_logs:
+        assets_to_extract.add(LookerStudioAsset.VIEW_ACTIVITY)
+
+    for asset in assets_to_extract:
         logger.info(f"Extracting {asset.name} from API")
         data = list(deep_serialize(client.fetch(asset)))
         yield asset, data
@@ -45,6 +51,8 @@ def _credentials(params: dict) -> LookerStudioCredentials:
         LOOKER_STUDIO_ADMIN_EMAIL
     )
     credentials["admin_email"] = admin_email
+    has_view_activity_logs = not params["skip_view_activity_logs"]
+    credentials["has_view_activity_logs"] = has_view_activity_logs
     return LookerStudioCredentials(**credentials)
 
 
@@ -68,7 +76,10 @@ def extract_all(**kwargs) -> None:
     the given output_directory.
     """
     output_directory = kwargs.get("output") or from_env(OUTPUT_DIR)
+
     credentials = _credentials(kwargs)
+    has_view_activity_logs = bool(credentials.has_view_activity_logs)
+
     bigquery_credentials = _bigquery_credentials_or_none(kwargs)
 
     client = LookerStudioClient(
@@ -77,7 +88,7 @@ def extract_all(**kwargs) -> None:
     )
     ts = current_timestamp()
 
-    for key, data in iterate_all_data(client):
+    for key, data in iterate_all_data(client, has_view_activity_logs):
         filename = get_output_filename(key.name.lower(), output_directory, ts)
         write_json(filename, data)
 

castor_extractor-0.24.21/castor_extractor/visualization/powerbi/__init__.py

@@ -0,0 +1,9 @@
+from .assets import PowerBiAsset
+from .client import (
+    CLIENT_APP_BASE,
+    DEFAULT_SCOPE,
+    REST_API_BASE_PATH,
+    PowerbiClient,
+    PowerbiCredentials,
+)
+from .extract import extract_all

castor_extractor-0.24.21/castor_extractor/visualization/powerbi/client/__init__.py

@@ -0,0 +1,7 @@
+from .client import PowerbiClient
+from .credentials import (
+    CLIENT_APP_BASE,
+    DEFAULT_SCOPE,
+    REST_API_BASE_PATH,
+    PowerbiCredentials,
+)

{castor_extractor-0.24.15 → castor_extractor-0.24.21}/castor_extractor/visualization/powerbi/client/authentication.py

@@ -9,7 +9,11 @@ from .endpoints import PowerBiEndpointFactory
 class PowerBiBearerAuth(BearerAuth):
     def __init__(self, credentials: PowerbiCredentials):
         self.credentials = credentials
-        authority = PowerBiEndpointFactory.authority(self.credentials.tenant_id)
+        endpoint_factory = PowerBiEndpointFactory(
+            login_url=self.credentials.login_url,
+            api_base=self.credentials.api_base,
+        )
+        authority = endpoint_factory.authority(self.credentials.tenant_id)
         self.app = msal.ConfidentialClientApplication(
             client_id=self.credentials.client_id,
             authority=authority,

{castor_extractor-0.24.15 → castor_extractor-0.24.21}/castor_extractor/visualization/powerbi/client/client.py

@@ -40,6 +40,10 @@ class PowerbiClient(APIClient):
             auth=auth,
             timeout=POWERBI_DEFAULT_TIMEOUT_S,
         )
+        self.endpoint_factory = PowerBiEndpointFactory(
+            login_url=credentials.login_url,
+            api_base=credentials.api_base,
+        )
 
     def _activity_events(self, day: Optional[date] = None) -> Iterator[dict]:
         """
@@ -49,7 +53,7 @@ class PowerbiClient(APIClient):
         """
         request = partial(
             self._get,
-            endpoint=PowerBiEndpointFactory.activity_events(day),
+            endpoint=self.endpoint_factory.activity_events(day),
         )
         yield from fetch_all_pages(request, PowerBiPagination)
 
@@ -58,28 +62,28 @@ class PowerbiClient(APIClient):
         Returns a list of datasets for the organization.
         https://learn.microsoft.com/en-us/rest/api/power-bi/admin/datasets-get-datasets-as-admin
         """
-        yield from self._get(PowerBiEndpointFactory.datasets())[Keys.VALUE]
+        yield from self._get(self.endpoint_factory.datasets())[Keys.VALUE]
 
     def _dashboards(self) -> Iterator[dict]:
         """
         Returns a list of dashboards for the organization.
         https://learn.microsoft.com/en-us/rest/api/power-bi/admin/dashboards-get-dashboards-as-admin
         """
-        yield from self._get(PowerBiEndpointFactory.dashboards())[Keys.VALUE]
+        yield from self._get(self.endpoint_factory.dashboards())[Keys.VALUE]
 
     def _reports(self) -> Iterator[dict]:
         """
         Returns a list of reports for the organization.
         https://learn.microsoft.com/en-us/rest/api/power-bi/admin/reports-get-reports-as-admin
         """
-        reports_endpoint = PowerBiEndpointFactory.reports()
+        reports_endpoint = self.endpoint_factory.reports()
         reports = self._get(reports_endpoint)[Keys.VALUE]
 
         for report in reports:
             report_id = report.get(Keys.ID)
 
             try:
-                pages_endpoint = PowerBiEndpointFactory.pages(report_id)
+                pages_endpoint = self.endpoint_factory.pages(report_id)
                 pages = self._get(pages_endpoint)[Keys.VALUE]
                 report["pages"] = pages
             except (requests.HTTPError, requests.exceptions.Timeout) as e:
@@ -99,14 +103,14 @@ class PowerbiClient(APIClient):
         }
 
         response = self._get(
-            PowerBiEndpointFactory.workspace_ids(),
+            self.endpoint_factory.workspace_ids(),
             params=params,
         )
 
         return [x[Keys.ID] for x in response]
 
     def _get_scan_result(self, scan_id: int) -> Iterator[dict]:
-        endpoint = PowerBiEndpointFactory.metadata_scan_result(scan_id)
+        endpoint = self.endpoint_factory.metadata_scan_result(scan_id)
         yield from self._get(endpoint)[Keys.WORKSPACES]
 
     def _wait_for_scan_result(self, scan_id: int) -> bool:
@@ -114,7 +118,7 @@ class PowerbiClient(APIClient):
         Periodically checks the status of the metadata scan until the results
         are ready.
         """
-        endpoint = PowerBiEndpointFactory.metadata_scan_status(scan_id)
+        endpoint = self.endpoint_factory.metadata_scan_status(scan_id)
         total_waiting_time_s = 0
 
         while total_waiting_time_s < POWERBI_DEFAULT_TIMEOUT_S:
@@ -152,7 +156,7 @@ class PowerbiClient(APIClient):
         }
         request_body = {"workspaces": workspaces_ids}
         scan_id = self._post(
-            PowerBiEndpointFactory.metadata_create_scan(),
+            self.endpoint_factory.metadata_create_scan(),
             params=params,
             data=request_body,
         )