pyxecm 1.6__py3-none-any.whl → 2.0.1__py3-none-any.whl

pyxecm/otmm.py

@@ -1,53 +1,61 @@
-"""
-OTMM Module to interact with the OpenText Media Management API
-See: 
-
-Class: OTMM
-Methods:
-
-__init__ : class initializer
-config : Returns config data set
-get_data: Get the Data object that holds all processed Media Management base Assets
-credentials: Returns the token data
-request_header: Returns the request header for ServiceNow API calls
-parse_request_response: Parse the REST API responses and convert
-                        them to Python dict in a safe way
-exist_result_item: Check if an dict item is in the response
-                   of the ServiceNow API call
-get_result_value: Check if a defined value (based on a key) is in the ServiceNow API response
-
-authenticate : Authenticates at ServiceNow API
+"""OTMM Module to interact with the OpenText Media Management API.
+
+The documentation for the used REST APIs can be found here:
+    - [https://developer.opentext.com](https://developer.opentext.com/ce/products/media-management)
 """
 
 __author__ = "Dr. Marc Diefenbruch"
-__copyright__ = "Copyright 2024, OpenText"
+__copyright__ = "Copyright (C) 2024-2025, OpenText"
 __credits__ = ["Kai-Philip Gatzweiler"]
 __maintainer__ = "Dr. Marc Diefenbruch"
 __email__ = "mdiefenb@opentext.com"
 
-from json import JSONDecodeError
-import os
+import json
 import logging
-import urllib.parse
+import os
+import platform
+import sys
 import threading
 import traceback
+import urllib.parse
+from collections.abc import Callable
+from datetime import datetime, timezone
+from importlib.metadata import version
+from json import JSONDecodeError
 
 import requests
+from requests.adapters import HTTPAdapter
 from requests.exceptions import HTTPError, RequestException
 
-from pyxecm.helper.data import Data
+from pyxecm.helper import Data
 
-logger = logging.getLogger("pyxecm.otmm")
+APP_NAME = "pyxecm"
+APP_VERSION = version("pyxecm")
+MODULE_NAME = APP_NAME + ".otmm"
 
-REQUEST_HEADERS = {"Accept": "application/json", "Content-Type": "application/json"}
+PYTHON_VERSION = f"{sys.version_info.major}.{sys.version_info.minor}.{sys.version_info.micro}"
+OS_INFO = f"{platform.system()} {platform.release()}"
+ARCH_INFO = platform.machine()
+REQUESTS_VERSION = requests.__version__
 
+USER_AGENT = (
+    f"{APP_NAME}/{APP_VERSION} ({MODULE_NAME}/{APP_VERSION}; "
+    f"Python/{PYTHON_VERSION}; {OS_INFO}; {ARCH_INFO}; Requests/{REQUESTS_VERSION})"
+)
+
+REQUEST_HEADERS = {
+    "User-Agent": USER_AGENT,
+    "Content-Type": "application/x-www-form-urlencoded",
+}
 REQUEST_TIMEOUT = 60
 
-ASSET_BASE_PATH = "/tmp/mediaassets"
+default_logger = logging.getLogger(MODULE_NAME)
 
 
 class OTMM:
-    """Used to retrieve and automate data extraction from OTMM."""
+    """Class OTMM is used to automate data extraction from OTMM."""
+
+    logger: logging.Logger = default_logger
 
     _config: dict
     _access_token = None
@@ -55,7 +63,11 @@ class OTMM:
     _thread_number = 3
     _download_dir = ""
     _business_unit_exclusions = None
+    _business_unit_inclusions = None
     _product_exclusions = None
+    _product_inclusions = None
+    _asset_exclusions = None
+    _asset_inclusions = None
 
     def __init__(
         self,
@@ -67,8 +79,51 @@ class OTMM:
         thread_number: int,
         download_dir: str,
         business_unit_exclusions: list | None = None,
+        business_unit_inclusions: list | None = None,
         product_exclusions: list | None = None,
-    ):
+        product_inclusions: list | None = None,
+        asset_exclusions: list | None = None,
+        asset_inclusions: list | None = None,
+        logger: logging.Logger = default_logger,
+    ) -> None:
+        """Initialize for the OTMM object.
+
+        Args:
+            base_url (str):
+                The base URL for accessing OTMM.
+            username (str):
+                The name of the user.
+            password (str):
+                The password of the user.
+            client_id (str):
+                The client ID for the credentials.
+            client_secret (str):
+                The client secret for the credentials.
+            thread_number (int):
+                The number of threads for parallel processing for data loads.
+            download_dir (str):
+                The filesystem directory to download the OTMM assets to.
+            business_unit_exclusions (list | None, optional):
+                An optional list of business units to exclude. Defaults to None.
+            business_unit_inclusions (list | None, optional):
+                An optional list of business units to include. Defaults to None.
+            product_exclusions (list | None, optional):
+                An optional list of products to exclude. Defaults to None.
+            product_inclusions (list | None, optional):
+                An optional list of products to include. Defaults to None.
+            asset_exclusions (list | None, optional):
+                An optional list of asset (IDs) to exclude. Defaults to None.
+            asset_inclusions (list | None, optional):
+                An optional list of asset (IDs) to include. Defaults to None.
+            logger (logging.Logger, optional):
+                The logging object to use for all log messages. Defaults to default_logger.
+
+        """
+
+        if logger != default_logger:
+            self.logger = logger.getChild("otmm")
+            for logfilter in logger.filters:
+                self.logger.addFilter(logfilter)
 
         # Initialize otcs_config as an empty dictionary
         otmm_config = {}
@@ -80,7 +135,8 @@ class OTMM:
         otmm_config["clientId"] = client_id
         otmm_config["clientSecret"] = client_secret
 
-        otmm_config["restUrl"] = otmm_config["baseUrl"] + "/otmmapi/v6"
+        # Make sure we don't have double-slashes if base_url comes with a trailing slash:
+        otmm_config["restUrl"] = urllib.parse.urljoin(base_url, "/otmmapi/v6")
         otmm_config["tokenUrl"] = otmm_config["restUrl"] + "/sessions/oauth2/token"
         otmm_config["domainUrl"] = otmm_config["restUrl"] + "/lookupdomains"
         otmm_config["assetsUrl"] = otmm_config["restUrl"] + "/assets"
@@ -89,44 +145,75 @@ class OTMM:
         self._config = otmm_config
 
         self._session = requests.Session()
+        self._session.headers.update({"User-Agent": USER_AGENT})
 
-        self._data = Data()
+        self._adapter = HTTPAdapter(
+            pool_connections=thread_number,
+            pool_maxsize=thread_number,
+        )
+        self._session.mount("http://", self._adapter)
+        self._session.mount("https://", self._adapter)
+
+        self._data = Data(logger=self.logger)
 
         self._thread_number = thread_number
 
         self._download_dir = download_dir
 
         self._business_unit_exclusions = business_unit_exclusions
+        self._business_unit_inclusions = business_unit_inclusions
         self._product_exclusions = product_exclusions
+        self._product_inclusions = product_inclusions
+        self._asset_exclusions = asset_exclusions
+        self._asset_inclusions = asset_inclusions
 
     # end method definition
 
-    def thread_wrapper(self, target, *args, **kwargs):
-        """Function to wrap around threads to catch exceptions during exection"""
+    def thread_wrapper(self, target: Callable, *args: tuple, **kwargs: dict) -> None:
+        """Wrap around threads to catch exceptions during exection.
+
+        Args:
+            target (Callable):
+                The method (callable) the Thread should run.
+            args (tuple):
+                The arguments for the method.
+            kwargs (dict):
+                Keyword arguments for the method.
+
+        """
+
         try:
             target(*args, **kwargs)
-        except Exception as e:
+        except Exception:
             thread_name = threading.current_thread().name
-            logger.error("Thread '%s': failed with exception -> %s", thread_name, e)
-            logger.error(traceback.format_exc())
+            self.logger.error(
+                "Thread '%s' failed!",
+                thread_name,
+            )
+            self.logger.error(traceback.format_exc())
 
     # end method definition
 
     def config(self) -> dict:
-        """Returns the configuration dictionary
+        """Return the configuration dictionary.
 
         Returns:
-            dict: Configuration dictionary
+            dict:
+                The configuration dictionary.
+
         """
+
         return self._config
 
     # end method definition
 
     def get_data(self) -> Data:
-        """Get the Data object that holds all processed Media Management base Assets
+        """Get the data frame that holds all processed Media Management assets.
 
         Returns:
-            Data: Datastructure with all processed assets.
+            Data:
+                Data frame with all processed assets.
+
         """
 
         return self._data
@@ -134,10 +221,18 @@ class OTMM:
     # end method definition
 
     def authenticate(self) -> str | None:
-        """Authenticate at OTMM with client ID and client secret or with basic authentication."""
+        """Authenticate at OTMM.
+
+        Supports authentication with client ID and client secret
+        or with basic authentication.
+
+        Returns:
+            str | None:
+                The access token for OTMM.
+
+        """
 
         request_url = self.config()["tokenUrl"]
-        headers = {"Content-Type": "application/x-www-form-urlencoded"}
         payload = {
             "username": self.config()["username"],
             "password": self.config()["password"],
@@ -149,154 +244,369 @@ class OTMM:
         try:
             response = self._session.post(
                 request_url,
-                headers=headers,
+                headers=REQUEST_HEADERS,
                 data=urllib.parse.urlencode(payload),
             )
             response.raise_for_status()
 
-            self._access_token = (
-                response.json().get("token_info").get("oauth_token").get("accessToken")
-            )
+            self._access_token = response.json().get("token_info").get("oauth_token").get("accessToken")
             self._session.headers.update(
-                {"Authorization": f"Bearer {self._access_token}"}
+                {"Authorization": f"Bearer {self._access_token}"},
+            )
+
+        except requests.exceptions.HTTPError as http_error:
+            self.logger.error("HTTP error requesting -> %s; error -> %s", request_url, str(http_error))
+            self.logger.debug("HTTP request header -> %s", str(REQUEST_HEADERS))
+            return None
+        except requests.exceptions.ConnectionError:
+            self.logger.error("Connection error requesting -> %s", request_url)
+            return None
+        except requests.exceptions.Timeout:
+            self.logger.error("Timeout error requesting -> %s", request_url)
+            return None
+        except requests.exceptions.RequestException:
+            self.logger.error("Request error requesting -> %s", request_url)
+            return None
+        except Exception:
+            self.logger.error("Unexpected error requesting -> %s", request_url)
+            return None
+
+        return self._access_token
+
+    # end method definition
+
+    def get_lookup_domains(self) -> dict | None:
+        """Get all OTMM lookup domains.
+
+        Args:
+            None
+
+        Returns:
+            dict | None:
+                All OTMM lookup domains.
+
+        Example:
+            {
+                'lookup_domains_resource': {
+                    'lookup_domains': [
+                        {
+                            'cacheable': True,
+                            'datatype': 'CHAR',
+                            'domainId': 'ARTESIA.DOMAIN.MEDIA_ANALYSIS.SOURCE.LANGUAGE',
+                            'domainValues': [
+                                {
+                                    'display_value': 'Hausa (Ghana)',
+                                    'expired_value': False,
+                                    'field_value': {...}
+                                },
+                                ...
+                            ]
+                        },
+                        ...
+                    ]
+                }
+            }
+
+        """
+
+        request_url = self.config()["domainUrl"]
+
+        try:
+            response = self._session.get(
+                request_url,
             )
 
-            return self._access_token
+            response.raise_for_status()
 
-        except requests.exceptions.HTTPError as http_err:
-            logger.error("HTTP error occurred: %s", http_err)
-        except requests.exceptions.ConnectionError as conn_err:
-            logger.error("Connection error occurred: %s", conn_err)
-        except requests.exceptions.Timeout as timeout_err:
-            logger.error("Timeout error occurred: %s", timeout_err)
-        except requests.exceptions.RequestException as req_err:
-            logger.error("Request error occurred: %s", req_err)
-        except Exception as e:
-            logger.error("An unexpected error occurred: %s", e)
+        except requests.exceptions.HTTPError as http_error:
+            self.logger.error("HTTP error requesting -> %s; error -> %s", request_url, str(http_error))
+            return None
+        except requests.exceptions.ConnectionError:
+            self.logger.error("Connection error requesting -> %s", request_url)
+            return None
+        except requests.exceptions.Timeout:
+            self.logger.error("Timeout error requesting -> %s", request_url)
+            return None
+        except requests.exceptions.RequestException:
+            self.logger.error("Request error requesting -> %s", request_url)
+            return None
+        except Exception:
+            self.logger.error("Unexpected error requesting -> %s", request_url)
+            return None
 
-        return None
+        return response.json()
 
     # end method definition
 
-    def get_products(self, domain: str = "OTMM.DOMAIN.OTM_PRODUCT") -> dict:
-        """Get a dictionary with product names (keys) and IDs (values)
+    def get_lookup_domain(self, domain: str) -> dict | None:
+        """Get OTMM lookup domain with a given name.
 
         Args:
-            domain (str, optional): Domain. Defaults to "OTMM.DOMAIN.OTM_PRODUCT".
+            domain (str):
+                The name / identifier of the domain.
+
         Returns:
-            dict: Dictionary of all known products.
+            dict | None:
+                The response includes data for the given lookup domain
+                or None if the request fails.
+
+        Example:
+            {
+                'lookup_domain_resource': {
+                    'lookup_domain': {
+                        'cacheable': True,
+                        'datatype': 'CHAR',
+                        'domainId': 'OTMM.DOMAIN.OTM_PRODUCT',
+                        'domainValues': [
+                            {
+                                'active_from': '',
+                                'active_to': '',
+                                'description': 'Active Access',
+                                'display_value': 'Active Access',
+                                'expired_value': False,
+                                'field_value': {
+                                    'type': 'string',
+                                    'value': '213'
+                                }
+                            },
+                            ...
+                        ]
+                    }
+                }
+            }
+
         """
 
-        lookup_products = self.lookup_domains(domain)
+        request_url = self.config()["domainUrl"] + "/" + domain
 
-        result = {}
-        for product in lookup_products:
-            result[product.get("display_value")] = product.get("field_value").get(
-                "value"
+        try:
+            response = self._session.get(
+                request_url,
             )
 
-        return result
+            response.raise_for_status()
+
+        except requests.exceptions.HTTPError as http_error:
+            self.logger.error("HTTP error requesting -> %s; error -> %s", request_url, str(http_error))
+            return None
+        except requests.exceptions.ConnectionError:
+            self.logger.error("Connection error requesting -> %s", request_url)
+            return None
+        except requests.exceptions.Timeout:
+            self.logger.error("Timeout error requesting -> %s", request_url)
+            return None
+        except requests.exceptions.RequestException:
+            self.logger.error("Request error requesting -> %s", request_url)
+            return None
+        except Exception:
+            self.logger.error("Unexpected error requesting -> %s", request_url)
+            return None
+
+        return response.json()
 
     # end method definition
 
-    def get_business_units(
-        self, domain: str = "OTMM.DOMAIN.OTM_BUSINESS_UNIT.LU"
-    ) -> dict:
-        """Get a dictionary with product names (keys) and IDs (values)
+    def get_lookup_domain_values(self, domain: str) -> list | None:
+        """Get values of an OTMM lookup domain with a given name.
 
         Args:
-            domain (str, optional): Domain. Defaults to "OTMM.DOMAIN.OTM_BUSINESS_UNIT.LU".
+            domain (str):
+                The name / identifier of the domain.
 
         Returns:
-            dict: Dictionary of all known business units.
+            list | None:
+                The list of domain values or None if the request fails.
+
         """
 
-        lookup_bus = self.lookup_domains(domain)
-        result = {}
-        for bu in lookup_bus:
-            result[bu.get("display_value")] = bu.get("field_value").get("value")
+        lookup_domain = self.get_lookup_domain(domain=domain)
+        if not lookup_domain:
+            self.logger.error(
+                "Cannot get lookup domain values for domain -> '%s'",
+                domain,
+            )
+            return None
 
-        return result
+        values = lookup_domain.get("lookup_domain_resource").get("lookup_domain").get("domainValues")
+
+        return values
 
     # end method definition
 
-    def lookup_domains(self, domain: str):
-        """Lookup domain values in a given OTMM domain
+    def get_products(self, domain: str = "OTMM.DOMAIN.OTM_PRODUCT") -> dict:
+        """Get a dictionary with product names (keys) and IDs (values).
 
         Args:
-            domain (str): name / identifier of the domain.
+            domain (str, optional):
+                The identifier of the Domain. Defaults to "OTMM.DOMAIN.OTM_PRODUCT".
 
         Returns:
-            _type_: _description_
+            dict:
+                Dictionary of all known products.
+
         """
 
-        request_url = self.config()["domainUrl"] + "/" + domain
+        lookup_products = self.get_lookup_domain_values(domain) or []
 
-        try:
-            response = self._session.get(
-                request_url,
+        # Comprehension to create a dictionary.
+        # Keys are the product names, values the product IDs.
+        # We remove leading and trailing spaces -
+        # OTMM data seems to have this in some places.
+        return {
+            product.get("display_value").strip(): product.get("field_value").get(
+                "value",
             )
+            for product in lookup_products
+        }
 
-            response.raise_for_status()
+    # end method definition
 
-        except requests.exceptions.HTTPError as http_err:
-            logger.error("HTTP error occurred: %s", http_err)
-        except requests.exceptions.ConnectionError as conn_err:
-            logger.error("Connection error occurred: %s", conn_err)
-        except requests.exceptions.Timeout as timeout_err:
-            logger.error("Timeout error occurred: %s", timeout_err)
-        except requests.exceptions.RequestException as req_err:
-            logger.error("Request error occurred: %s", req_err)
-        except Exception as e:
-            logger.error("An unexpected error occurred: %s", e)
-
-        response = (
-            response.json()
-            .get("lookup_domain_resource")
-            .get("lookup_domain")
-            .get("domainValues")
-        )
+    def get_business_units(
+        self,
+        domain: str = "OTMM.DOMAIN.OTM_BUSINESS_UNIT.LU",
+    ) -> dict:
+        """Get a dictionary with business unit names (keys) and business unit IDs (values).
+
+        Args:
+            domain (str, optional):
+                The domain. Defaults to "OTMM.DOMAIN.OTM_BUSINESS_UNIT.LU".
+
+        Returns:
+            dict:
+                Dictionary of all known business units.
+
+        """
 
-        return response
+        lookup_bus = self.get_lookup_domain_values(domain) or []
+
+        # Comprehension to create a dictionary.
+        # Keys are the product names, values the product IDs:
+        return {bu.get("display_value").strip(): bu.get("field_value").get("value") for bu in lookup_bus}
 
     # end method definition
 
-    def get_asset(self, asset_id: str) -> dict:
-        """Get an asset based on its ID
+    def get_asset(self, asset_id: str) -> dict | None:
+        """Get an asset based on its ID.
 
         Args:
-            asset_id (str): Asset ID
+            asset_id (str):
+                The ID of the asset.
 
         Returns:
-            dict: dictionary with asset data
+            dict | None:
+                A dictionary with asset data or None if the asset is not found.
+
+        Example:
+            {
+                'asset_resource': {
+                    'asset': {
+                        'access_control_descriptor': {
+                            'permissions_map': {...}
+                        },
+                        'asset_content_info': {
+                            'master_content': {...}
+                        },
+                        'asset_id': 'e064571da79c926ee14b0850734b49edf42d9ba5',
+                        'asset_lock_state_last_update_date': '2024-04-16T15:03:48Z',
+                        'asset_lock_state_user_id': '153',
+                        'asset_state': 'NORMAL',
+                        'asset_state_last_update_date': '2024-04-16T15:03:48Z',
+                        'asset_state_user_id': '153',
+                        'checked_out': False,
+                        'content_editable': True,
+                        'content_lock_state_last_update_date': '2023-12-11T20:56:26Z',
+                        'content_lock_state_user_id': '202',
+                        'content_lock_state_user_name': 'ajohnson3',
+                        'content_size': 95873,
+                        'content_state': 'NORMAL',
+                        'content_state_last_update_date': '2023-12-11T20:56:26Z',
+                        'content_state_user_id': '202',
+                        'content_state_user_name': 'Amanda Johnson',
+                        'content_type': 'ACROBAT',
+                        'creator_id': '202',
+                        'date_imported': '2023-12-11T20:56:26Z',
+                        'date_last_updated': '2024-04-16T15:03:48Z',
+                        'deleted': False,
+                        'delivery_service_url': 'https://assets.opentext.com/adaptivemedia/rendition?id=726d14f14bb1ae93c3efda5a870399a20c991770',
+                        'expired': False,
+                        'import_job_id': 5776,
+                        'import_user_name': 'ajohnson3',
+                        'latest_version': True,
+                        'legacy_model_id': 104,
+                        'locked': False,
+                        'master_content_info': {
+                            'content_checksum': '2a31defcf7ad2feb7c557acb068a5c22',
+                            'content_data': {...},
+                            'content_kind': 'MASTER',
+                            'content_manager_id': 'ARTESIA.CONTENT.GOOGLE.CLOUD',
+                            'content_size': 95873,
+                            'height': -1,
+                            'id': 'b563035e050a89e58a921df8a4047a0673ad9691',
+                            'mime_type': 'application/pdf',
+                            'name': 'a-business-case-for-arcsight-soar-wp.pdf',
+                            'unit_of_size': 'BYTES',
+                            'url': '/otmmapi/v6/renditions/b563035e050a89e58a921df8a4047a0673ad9691',
+                            'width': -1
+                        },
+                        'metadata_lock_state_user_name': 'ababigian',
+                        'metadata_model_id': 'OTM.MARKETING.MODEL',
+                        'metadata_state_user_name': 'Andra Babigian',
+                        'mime_type': 'application/pdf',
+                        'name': 'a-business-case-for-arcsight-soar-pp-en.pdf',
+                        'original_asset_id': '726d14f14bb1ae93c3efda5a870399a20c991770',
+                        'product_associations': False,
+                        'rendition_content': {
+                            'pdf_preview_content': {
+                                'content_checksum': '2a31defcf7ad2feb7c557acb068a5c22',
+                                'content_data': {
+                                    'data_source': 'NO_CONTENT',
+                                    'temp_file': False
+                                },
+                                'content_kind': 'MASTER',
+                                'content_manager_id': 'ARTESIA.CONTENT.GOOGLE.CLOUD',
+                                'content_size': 95873,
+                                'height': -1,
+                                'id': 'b563035e050a89e58a921df8a4047a0673ad9691',
+                                'mime_type': 'application/pdf',
+                                'name': 'a-business-case-for-arcsight-soar-wp.pdf',
+                                'unit_of_size': 'BYTES',
+                                'url': '/otmmapi/v6/renditions/b563035e050a89e58a921df8a4047a0673ad9691',
+                                'width': -1
+                            }
+                        },
+                        'subscribed_to': False,
+                        'version': 3
+                    }
+                }
+            }
+
         """
 
         request_url = self.config()["assetsUrl"] + "/" + asset_id
 
-        headers = {"Content-Type": "application/x-www-form-urlencoded"}
-
         try:
             response = self._session.get(
                 request_url,
-                headers=headers,
+                headers=REQUEST_HEADERS,
             )
 
             response.raise_for_status()
 
-        except requests.exceptions.HTTPError as http_err:
-            logger.error("HTTP error occurred: %s", http_err)
+        except requests.exceptions.HTTPError as http_error:
+            self.logger.error("HTTP error requesting -> %s; error -> %s", request_url, str(http_error))
+            self.logger.debug("HTTP request header -> %s", str(REQUEST_HEADERS))
             return None
-        except requests.exceptions.ConnectionError as conn_err:
-            logger.error("Connection error occurred: %s", conn_err)
+        except requests.exceptions.ConnectionError:
+            self.logger.error("Connection error requesting -> %s", request_url)
             return None
-        except requests.exceptions.Timeout as timeout_err:
-            logger.error("Timeout error occurred: %s", timeout_err)
+        except requests.exceptions.Timeout:
+            self.logger.error("Timeout error requesting -> %s", request_url)
             return None
-        except requests.exceptions.RequestException as req_err:
-            logger.error("Request error occurred: %s", req_err)
+        except requests.exceptions.RequestException:
+            self.logger.error("Request error requesting -> %s", request_url)
             return None
-        except Exception as e:
-            logger.error("An unexpected error occurred: %s", e)
+        except Exception:
+            self.logger.error("Unexpected error requesting -> %s", request_url)
             return None
 
         return response.json()
@@ -304,17 +614,26 @@ class OTMM:
     # end method definition
 
     def get_business_unit_assets(
-        self, bu_id: int, offset: int = 0, limit: int = 200
+        self,
+        bu_id: str,
+        offset: int = 0,
+        limit: int = 200,
     ) -> list | None:
         """Get all Media Assets for a given Business Unit (ID) that are NOT related to a product.
 
         Args:
-            bu_id (int): Identifier of the Business Unit.
-            offset (int, optional): Result pagination. Starting ID. Defaults to 0.
-            limit (int, optional): Result pagination. Page length. Defaults to 200.
+            bu_id (str):
+                Identifier of the Business Unit. DON'T USE INT HERE! OTMM delivers
+                strings for get_business_units()
+            offset (int, optional):
+                Result pagination. Starting ID. Defaults to 0.
+            limit (int, optional):
+                Result pagination. Page length. Defaults to 200.
 
         Returns:
-            dict: Search Results
+            dict:
+                Search Results
+
         """
 
         payload = {
@@ -327,22 +646,57 @@ class OTMM:
             "search_config_id": ["3"],
             "preference_id": ["ARTESIA.PREFERENCE.GALLERYVIEW.DISPLAYED_FIELDS"],
             "metadata_to_return": ["ARTESIA.FIELD.TAG"],
-            "facet_restriction_list": '{"facet_restriction_list":{"facet_field_restriction":[{"type":"com.artesia.search.facet.FacetSimpleFieldRestriction","facet_generation_behavior":"EXCLUDE","field_id":"PRODUCT_CHAR_ID","value_list":[null]}]}}',
+            "facet_restriction_list": json.dumps(
+                {
+                    "facet_restriction_list": {
+                        "facet_field_restriction": [
+                            {
+                                "type": "com.artesia.search.facet.FacetSimpleFieldRestriction",
+                                "facet_generation_behavior": "EXCLUDE",
+                                "field_id": "PRODUCT_CHAR_ID",
+                                "value_list": [None],
+                            },
+                        ],
+                    },
+                },
+            ),
             "search_condition_list": [
-                '{"search_condition_list":{"search_condition":[{"type":"com.artesia.search.SearchTabularCondition","metadata_table_id":"OTMM.FIELD.BUSINESS_UNIT.TAB","tabular_field_list":[{"type":"com.artesia.search.SearchTabularFieldCondition","metadata_field_id":"OTMM.COLUMN.BUSINESS_UNIT.TAB","relational_operator_id":"ARTESIA.OPERATOR.CHAR.CONTAINS","value":"'
-                + str(bu_id)
-                + '","left_paren":"(","right_paren":")"}]}]}}'
+                json.dumps(
+                    {
+                        "search_condition_list": {
+                            "search_condition": [
+                                {
+                                    "type": "com.artesia.search.SearchTabularCondition",
+                                    "metadata_table_id": "OTMM.FIELD.BUSINESS_UNIT.TAB",
+                                    "tabular_field_list": [
+                                        {
+                                            "type": "com.artesia.search.SearchTabularFieldCondition",
+                                            "metadata_field_id": "OTMM.COLUMN.BUSINESS_UNIT.TAB",
+                                            "relational_operator_id": "ARTESIA.OPERATOR.CHAR.CONTAINS",
+                                            "value": str(bu_id),
+                                            "left_paren": "(",
+                                            "right_paren": ")",
+                                        },
+                                    ],
+                                },
+                            ],
+                        },
+                    },
+                ),
             ],
         }
 
-        flattened_data = {
-            k: v if not isinstance(v, list) else ",".join(v) for k, v in payload.items()
-        }
+        # Convert list values into comma-separated strings:
+        flattened_data = {k: v if not isinstance(v, list) else ",".join(v) for k, v in payload.items()}
 
+        # Use OTMM's search to find the assets for the business unit:
         search_result = self.search_assets(flattened_data)
 
-        if not search_result or not "search_result_resource" in search_result:
-            logger.error("No assets found via search!")
+        if not search_result or "search_result_resource" not in search_result:
+            self.logger.error(
+                "No assets found via search for business unit with ID -> '%s'!",
+                bu_id,
+            )
             return None
         search_result = search_result.get("search_result_resource")
 
@@ -357,7 +711,7 @@ class OTMM:
             flattened_data["after"] += hits
             search_result = self.search_assets(flattened_data)
 
-            if not search_result or not "search_result_resource" in search_result:
+            if not search_result or "search_result_resource" not in search_result:
                 break
 
             search_result = search_result.get("search_result_resource")
@@ -372,17 +726,29 @@ class OTMM:
     # end method definition
 
     def get_product_assets(
-        self, product_id: int, offset: int = 0, limit: int = 200
+        self,
+        product_id: str,
+        offset: int = 0,
+        limit: int = 200,
     ) -> list | None:
         """Get all Media Assets for a given product (ID).
 
+        This does currently NOT include the asset metadata even though lead type
+        is set to "metadata" below as "metadata_to_return" is set to a single field.
+
         Args:
-            product_id (int): Identifier of the product.
-            offset (int, optional): Result pagination. Starting ID. Defaults to 0.
-            limit (int, optional): Result pagination. Page length. Defaults to 200.
+            product_id (str):
+                Identifier of the product. DON'T USE `int` HERE!
+                OTMM delivers strings for get_products()
+            offset (int, optional):
+                Result pagination. Starting ID. Defaults to 0.
+            limit (int, optional):
+                Result pagination. Page length. Defaults to 200.
 
         Returns:
-            dict: Search Results
+            dict:
+                Search Results
+
         """
 
         payload = {
@@ -396,20 +762,39 @@ class OTMM:
             "preference_id": ["ARTESIA.PREFERENCE.GALLERYVIEW.DISPLAYED_FIELDS"],
             "metadata_to_return": ["ARTESIA.FIELD.TAG"],
             "search_condition_list": [
-                '{"search_condition_list":{"search_condition":[{"type":"com.artesia.search.SearchTabularCondition","metadata_table_id":"OTM.TABLE.PRODUCT_TABLE_FIELD","tabular_field_list":[{"type":"com.artesia.search.SearchTabularFieldCondition","metadata_field_id":"PRODUCT_CHAR_ID","relational_operator_id":"ARTESIA.OPERATOR.CHAR.CONTAINS","value":"'
-                + str(product_id)
-                + '","left_paren":"(","right_paren":")"}]}]}}'
+                json.dumps(
+                    {
+                        "search_condition_list": {
+                            "search_condition": [
+                                {
+                                    "type": "com.artesia.search.SearchTabularCondition",
+                                    "metadata_table_id": "OTM.TABLE.PRODUCT_TABLE_FIELD",
+                                    "tabular_field_list": [
+                                        {
+                                            "type": "com.artesia.search.SearchTabularFieldCondition",
+                                            "metadata_field_id": "PRODUCT_CHAR_ID",
+                                            "relational_operator_id": "ARTESIA.OPERATOR.CHAR.CONTAINS",
+                                            "value": str(product_id),
+                                            "left_paren": "(",
+                                            "right_paren": ")",
+                                        },
+                                    ],
+                                },
+                            ],
+                        },
+                    },
+                ),
             ],
         }
 
-        flattened_data = {
-            k: v if not isinstance(v, list) else ",".join(v) for k, v in payload.items()
-        }
+        # Convert list values into comma-separated strings:
+        flattened_data = {k: v if not isinstance(v, list) else ",".join(v) for k, v in payload.items()}
 
-        search_result = self.search_assets(flattened_data)
+        # Use OTMM's search to find the assets for the product:
+        search_result = self.search_assets(payload=flattened_data)
 
-        if not search_result or not "search_result_resource" in search_result:
-            logger.error("No assets found via search!")
+        if not search_result or "search_result_resource" not in search_result:
+            self.logger.error("No assets found via search!")
             return None
         search_result = search_result.get("search_result_resource")
 
@@ -420,11 +805,12 @@ class OTMM:
 
         hits_remaining = hits_total - hits
 
+        # Iterate through all result pages:
         while hits_remaining > 0:
             flattened_data["after"] += hits
-            search_result = self.search_assets(flattened_data)
+            search_result = self.search_assets(payload=flattened_data)
 
-            if not search_result or not "search_result_resource" in search_result:
+            if not search_result or "search_result_resource" not in search_result:
                 break
 
             search_result = search_result.get("search_result_resource")
@@ -443,39 +829,53 @@ class OTMM:
         asset_id: str,
         asset_name: str,
         download_url: str = "",
-        skip_existing: bool = True,
+        asset_modification_date: str | None = None,
     ) -> bool:
-        """Download a given Media Asset
+        """Download a given media asset.
 
         Args:
-            asset_id (str): ID of the asset to download
-            asset_name (str): Name of the assets - becomes the file name.
-            download_url (str, optiona): URL to download the asset (optional).
+            asset_id (str):
+                ID of the asset to download. This becomes the file name.
+            asset_name (str):
+                The name of the asset.
+            download_url (str, optiona):
+                URL to download the asset (optional).
+            asset_modification_date (str | None, optional):
+                The last asset modification in OpenText Media Management.
 
         Returns:
-            bool: True = success, False = failure
+            bool:
+                True = success, False = failure
+
         """
-        #        url = f"{self.base_url}/assets/v1/{asset_id}/download"
 
-        if download_url:
-            request_url = download_url
-        else:
-            request_url = self.config()["assetsUrl"] + "/" + asset_id + "/contents"
+        request_url = download_url if download_url else self.config()["assetsUrl"] + "/" + asset_id + "/contents"
 
+        # We use the Asset ID as the filename to avoid name collisions:
         file_name = os.path.join(self._download_dir, asset_id)
 
         if os.path.exists(file_name):
-            if skip_existing:
-                logger.debug(
-                    "OpenText Media Management asset has been downloaded before skipping download -> '%s' (%s) to -> %s...",
+            if asset_modification_date:
+                file_mod_time = datetime.fromtimestamp(os.path.getmtime(file_name), tz=timezone.utc)
+                date_last_updated = datetime.strptime(
+                    asset_modification_date,
+                    "%Y-%m-%dT%H:%M:%SZ",
+                ).replace(tzinfo=timezone.utc)
+                download_up_to_date: bool = file_mod_time >= date_last_updated
+            else:
+                download_up_to_date = True
+
+            if download_up_to_date:
+                self.logger.debug(
+                    "Asset -> '%s' (%s) has been downloaded before and is up to date. Skipping download to -> %s...",
                     asset_name,
                     asset_id,
                     file_name,
                 )
                 return True
             else:
-                logger.debug(
-                    "OpenText Media Management asset has been downloaded before. Update download -> '%s' (%s) to -> %s...",
+                self.logger.debug(
+                    "Asset -> '%s' (%s) has been downloaded before, but it is outdated. Updating download to -> %s...",
                     asset_name,
                     asset_id,
                     file_name,
@@ -487,8 +887,8 @@ class OTMM:
                 # Create the directory
                 os.makedirs(self._download_dir)
 
-            logger.info(
-                "Downloading OpenText Media Management asset -> '%s' (%s) to -> %s...",
+            self.logger.info(
+                "Downloading asset -> '%s' (%s) to -> %s...",
                 asset_name,
                 asset_id,
                 file_name,
@@ -498,161 +898,516 @@ class OTMM:
             with open(file_name, "wb") as f:
                 for chunk in response.iter_content(chunk_size=8192):
                     f.write(chunk)
+        except HTTPError as http_error:
+            self.logger.error("HTTP error requesting -> %s; error -> %s", request_url, str(http_error))
+            return False
+        except RequestException:
+            self.logger.error("Request error requesting -> %s!", request_url)
+            return False
+        except Exception:
+            self.logger.error("Unexpected error requesting -> %s!", request_url)
+            return False
+
+        return True
+
+    # end method definition
+
+    def remove_stale_download(
+        self,
+        asset_id: str,
+        asset_name: str = "",
+    ) -> bool:
+        """Remove stale download file for an expired or deleted asset.
+
+        Args:
+            asset_id (str):
+                The ID of the asset to delete in the file system.
+            asset_name (str, optional):
+                The name of the assets. Just uswed for logging.
+
+        Returns:
+            bool: True = success, False = failure
+
+        """
+
+        file_name = os.path.join(self._download_dir, asset_id)
+
+        if os.path.exists(file_name):
+            self.logger.debug(
+                "Deleting stale download file -> '%s' for asset %s...",
+                file_name,
+                "-> '{}' ({})".format(asset_name, asset_id) if asset_name else "-> {}".format(asset_id),
+            )
+            os.remove(file_name)
             return True
-        except HTTPError as http_err:
-            logger.error("HTTP error occurred -> %s!", str(http_err))
-        except RequestException as req_err:
-            logger.error("Request error occurred -> %s!", str(req_err))
-        except Exception as err:
-            logger.error("An error occurred -> %s!", str(err))
 
         return False
 
     # end method definition
 
-    def search_assets(self, payload: dict):
+    def search_assets(self, payload: dict) -> dict | None:
         """Search an asset based on the given parameters / criterias.
 
         Args:
-            payload (dict): in the format of:
-                            payload = {
-                                "PRODUCT_CHAR_ID": "Extended ECM for Engineering",
-                                "BUSINESS_AREA_CHAR_ID": "Content",
-                                "keyword_query": "*",
-                                "limit": "5",
-                            }
+            payload (dict):
+                In the format of:
+                payload = {
+                    "PRODUCT_CHAR_ID": "Extended ECM for Engineering",
+                    "BUSINESS_AREA_CHAR_ID": "Content",
+                    "keyword_query": "*",
+                    "limit": "5",
+                }
 
         Returns:
-            _type_: JSON search results
+            dict | None:
+                The search results.
+
+        Example:
+            {
+                'search_result_resource': {
+                    'search_result': {
+                        'asset_group_count': {
+                            'entry': [...]
+                        },
+                        'asset_id_list': [
+                            '00084f808d1331bca1f24134bde9cd8e742fe24a',
+                            '000af201d7130d1bb2778af672f3bfb554ea965a',
+                            '000f9594985b766ee495c27172446d5c9c4e0ebf',
+                            '0012d344dc39d4d23aaeb04fbe9db3b21daee6e0',
+                            '00135d36232d66b6f11e0020f317244d08a613d1'
+                        ],
+                        'contains_invalid_conditions': False,
+                        'facet_field_response_list': [
+                            {...},
+                            {...},
+                            ...
+                        ],
+                        'hit_count': 5,
+                        'offset': 0,
+                        'total_hit_count': 11886
+                    },
+                    'asset_list': [
+                        {
+                            'access_control_descriptor': {...},
+                            'asset_content_info': {...},
+                            'asset_id': '00084f808d1331bca1f24134bde9cd8e742fe24a',
+                            'asset_lock_state_last_update_date': '2024-01-03T16:47:22Z',
+                            'asset_lock_state_user_id': '166',
+                            'asset_state': 'NORMAL',
+                            'asset_state_last_update_date': '2024-01-03T16:47:22Z',
+                            'asset_state_user_id': '166',
+                            'checked_out': False,
+                            'content_editable': True,
+                            'content_lock_state_last_update_date': '2021-11-22T16:32:59Z',
+                            'content_lock_state_user_id': '49',
+                            'content_lock_state_user_name': 'sspasik',
+                            'content_size': 3103,
+                            'content_state': 'NORMAL',
+                            'content_state_last_update_date': '2021-11-22T16:32:57Z',
+                            'content_state_user_id': '49',
+                            'content_state_user_name': 'Srgjan Spasik',
+                            'content_type': 'BITMAP',
+                            ...
+                        },
+                        ...
+                    ]
+                }
+            }
+
         """
 
         request_url = self.config()["searchUrl"]
 
-        headers = {"Content-Type": "application/x-www-form-urlencoded"}
-
         encoded_payload = urllib.parse.urlencode(payload, safe="/:")
 
         try:
             response = self._session.post(
                 request_url,
-                headers=headers,
+                headers=REQUEST_HEADERS,
                 data=encoded_payload,
             )
 
             response.raise_for_status()
 
-        except requests.exceptions.HTTPError as http_err:
-            logger.error("HTTP error occurred: %s", http_err)
-        except requests.exceptions.ConnectionError as conn_err:
-            logger.error("Connection error occurred: %s", conn_err)
-        except requests.exceptions.Timeout as timeout_err:
-            logger.error("Timeout error occurred: %s", timeout_err)
-        except requests.exceptions.RequestException as req_err:
-            logger.error("Request error occurred: %s", req_err)
-        except Exception as e:
-            logger.error("An unexpected error occurred: %s", e)
+        except requests.exceptions.HTTPError as http_error:
+            self.logger.error("HTTP error requesting -> %s; error -> %s", request_url, str(http_error))
+            self.logger.debug("HTTP request header -> %s", str(REQUEST_HEADERS))
+            return None
+        except requests.exceptions.ConnectionError:
+            self.logger.error("Connection error requesting -> %s", request_url)
+            return None
+        except requests.exceptions.Timeout:
+            self.logger.error("Timeout error requesting -> %s", request_url)
+            return None
+        except requests.exceptions.RequestException:
+            self.logger.error("Request error requesting -> %s", request_url)
+            return None
+        except Exception:
+            self.logger.error("Unexpected error requesting -> %s", request_url)
+            return None
 
         return response.json()
 
     # end method definition
 
-    def get_asset_metadata(self, asset_id: str) -> dict:
-        """Retrieve metadata of an asset based on the given parameters / criterias.
+    def get_asset_details(
+        self,
+        asset_id: str,
+        level_of_detail: str = "slim",
+        load_multilingual_field_values: bool = True,
+        load_subscribed_to: bool = True,
+        load_asset_content_info: bool = True,
+        load_metadata: bool = True,
+        load_inherited_metadata: bool = True,
+        load_thumbnail_info: bool = True,
+        load_preview_info: bool = True,
+        load_pdf_preview_info: bool = True,
+        load_3d_preview_info: bool = True,
+        load_destination_links: bool = True,
+        load_security_policies: bool = True,
+        load_path: bool = True,
+        load_deep_zoom_info: bool = True,
+    ) -> dict | None:
+        """Retrieve details of an asset based on the given parameters / criterias.
 
         Args:
-            asset_id (str): asset_id of the asset to query
+            asset_id (str):
+                The ID of the asset to query.
+            level_of_detail (str, optional):
+                Can either be "slim" or "full". "slim" is the default.
+            load_multilingual_field_values (bool, optional):
+                If True, load multilingual fields, default = True.
+            load_subscribed_to (bool, optional):
+                If True, load subscriber information, default = True.
+            load_asset_content_info (bool, optional):
+                If True, load content information, default = True.
+            load_metadata (bool, optional):
+                If True, load metadata, default = True.
+            load_inherited_metadata (bool, optional):
+                If True, load inherited metadata, default = True.
+            load_thumbnail_info (bool, optional):
+                If True, load thumbnail information, default = True.
+            load_preview_info (bool, optional):
+                If True, load preview information, default = True.
+            load_pdf_preview_info (bool, optional):
+                If true, load PDF preview information, default = True.
+            load_3d_preview_info (bool, optional):
+                If True, load 3D preview information, default = True.
+            load_destination_links (bool, optional):
+                If true, load destination links, default = True.
+            load_security_policies (bool, optional):
+                If True, load security policies, default = True.
+            load_path (bool, optional):
+                If True, load path, default = True.
+            load_deep_zoom_info(bool, optional):
+                If True, load deep zoom information, default = True.
 
         Returns:
-            dict: Metadata information as dict with values as list
-
-                  example:
-                  {
-                    'OTMM.CUSTOM.FIELD_TITLE': [],
-                    'OTMM.CUSTOM.FIELD_DESCRIPTION': [],
-                    'OTMM.CUSTOM.FIELD_KEYWORDS': [],
-                    'CONTENT_TYPE_COMBO_CHAR_ID': [],
-                    'OTM.TABLE.APPROVED_USAGE_FIELD': [],
-                    'OTMM.FIELD.RESOURCE_LIBRARY.TAB': [],
-                    'LANGUAGE_COMBO_CHAR_ID': [],
-                    'OTMM.CUSTOM.FIELD_PART_NUMBER': [],
-                    'OTMM.FIELD.BUSINESS_UNIT.TAB': ['Content'],
-                    'OTM.TABLE.PRODUCT_TABLE_FIELD': ['Vendor Invoice Management for SAP'],
-                    'OTM.TABLE.INDUSTRY_TABLE_FIELD': [],
-                    'OTMM.CUSTOM.FIELD_URL': [],
-                    'OTMM.CUSTOM.FIELD_PREVIOUS_URL': [],
-                    'OTMM.CUSTOM.FIELD_CONTENT_OWNER': [],
-                    'OTMM.CUSTOM.FIELD_EMAIL': [],
-                    'OTMM.CUSTOM.FIELD_JOB_NUMBER': [],
-                    'OTM.TABLE.BUSINESS_AREA_TABLE_FIELD': [],
-                    'OTM.TABLE.JOURNEY_TABLE_FIELD': ['Buy', 'Try', 'Learn'],
-                    'OTMM.FIELD.PERSONA.TAB': [],
-                    'OTMM.FIELD.SERVICES.TAB': [],
-                    'OTMM.FIELD.REGION.TAB': [],
-                    'OTMM.FIELD.PURPOSE.TAB': [],
-                    'AODA_CHAR_ID': [],
-                    'REVIEW_CADENCE_CHAR_ID': [],
-                    'CONTENT_CREATED_DATE_ID': [],
-                    'ARTESIA.FIELD.EXPIRATION DATE': [],
-                    'OTMM.CUSTOM.FIELD_REAL_COMMENTS': []
-                  }
+            dict | None:
+                Metadata information as dict with values as list
+
+        Example:
+            {
+                'asset_resource': {
+                    'asset': {
+                        'access_control_descriptor': {
+                            'permissions_map': {...}
+                        },
+                        'asset_content_info': {
+                            'master_content': {...}
+                        },
+                        'asset_id': 'e064571da79c926ee14b0850734b49edf42d9ba5',
+                        'asset_lock_state_last_update_date': '2024-04-16T15:03:48Z',
+                        'asset_lock_state_user_id': '153',
+                        'asset_state': 'NORMAL',
+                        'asset_state_last_update_date': '2024-04-16T15:03:48Z',
+                        'asset_state_user_id': '153',
+                        'checked_out': False,
+                        'content_editable': True,
+                        'content_lock_state_last_update_date': '2023-12-11T20:56:26Z',
+                        'content_lock_state_user_id': '202',
+                        'content_lock_state_user_name': 'ajohnson3',
+                        'content_size': 95873,
+                        'content_state': 'NORMAL',
+                        'content_state_last_update_date': '2023-12-11T20:56:26Z',
+                        'content_state_user_id': '202',
+                        'content_state_user_name': 'Amanda Johnson',
+                        'content_type': 'ACROBAT',
+                        'creator_id': '202',
+                        'date_imported': '2023-12-11T20:56:26Z',
+                        'date_last_updated': '2024-04-16T15:03:48Z',
+                        'deleted': False,
+                        'delivery_service_url': 'https://assets.opentext.com/adaptivemedia/rendition?id=726d14f14bb1ae93c3efda5a870399a20c991770',
+                        'expired': False,
+                        'import_job_id': 5776,
+                        'import_user_name': 'ajohnson3',
+                        'latest_version': True,
+                        'legacy_model_id': 104,
+                        'links': {
+                            'links': [...],
+                            'source_id': 'e064571da79c926ee14b0850734b49edf42d9ba5'
+                        },
+                        'locked': False,
+                        'master_content_info': {
+                            'content_checksum': '2a31defcf7ad2feb7c557acb068a5c22',
+                            'content_data': {...},
+                            'content_kind': 'MASTER',
+                            'content_manager_id': 'ARTESIA.CONTENT.GOOGLE.CLOUD',
+                            'content_size': 95873,
+                            'height': -1,
+                            'id': 'b563035e050a89e58a921df8a4047a0673ad9691',
+                            'mime_type': 'application/pdf',
+                            'name': 'a-business-case-for-arcsight-soar-wp.pdf',
+                            'unit_of_size': 'BYTES',
+                            'url': '/otmmapi/v6/renditions/b563035e050a89e58a921df8a4047a0673ad9691',
+                            'width': -1
+                        },
+                        'metadata': {
+                            'type': 'com.artesia.metadata.MetadataModel',
+                            'id': 'OTM.MARKETING.MODEL',
+                            'name': 'OTM Marketing Tags',
+                            'metadata_element_list': [...],
+                            'has_multilingual_fields': False,
+                            'legacy_id': 104
+                        },
+                        'metadata_lock_state_user_name': 'ababigian',
+                        'metadata_model_id': 'OTM.MARKETING.MODEL',
+                        'metadata_state_user_name': 'Andra Babigian',
+                        'mime_type': 'application/pdf',
+                        'name': 'a-business-case-for-arcsight-soar-pp-en.pdf',
+                        'original_asset_id': '726d14f14bb1ae93c3efda5a870399a20c991770',
+                        'path_list': [
+                            {...}
+                        ],
+                        'product_associations': False,
+                        'rendition_content': {
+                            'pdf_preview_content': {...}
+                        },
+                        'security_policy_list': [
+                            {...}
+                        ],
+                        'subscribed_to': False,
+                        'version': 3
+                    }
+                }
+            }
+
         """
 
-        request_url = self.config()["assetsUrl"] + f"/{asset_id}"
-        headers = {"Content-Type": "application/x-www-form-urlencoded"}
+        request_url = self.config()["assetsUrl"] + "/" + asset_id
 
         params = {
             "load_type": "custom",
-            "level_of_detail": "slim",
-            "data_load_request": '{"data_load_request":{"load_multilingual_field_values":"true","load_subscribed_to":"true","load_asset_content_info":"true","load_metadata":"true","load_inherited_metadata":"true","load_thumbnail_info":"true","load_preview_info":"true", "load_pdf_preview_info":"true", "load_3d_preview_info" : "true","load_destination_links":"true", "load_security_policies":"true","load_path":"true","load_deep_zoom_info":"true"}}',
+            "level_of_detail": level_of_detail,
+            "data_load_request": json.dumps(
+                {
+                    "data_load_request": {
+                        "load_multilingual_field_values": load_multilingual_field_values,
+                        "load_subscribed_to": load_subscribed_to,
+                        "load_asset_content_info": load_asset_content_info,
+                        "load_metadata": load_metadata,
+                        "load_inherited_metadata": load_inherited_metadata,
+                        "load_thumbnail_info": load_thumbnail_info,
+                        "load_preview_info": load_preview_info,
+                        "load_pdf_preview_info": load_pdf_preview_info,
+                        "load_3d_preview_info": load_3d_preview_info,
+                        "load_destination_links": load_destination_links,
+                        "load_security_policies": load_security_policies,
+                        "load_path": load_path,
+                        "load_deep_zoom_info": load_deep_zoom_info,
+                    },
+                },
+            ),
         }
 
         try:
-            response = self._session.get(request_url, headers=headers, params=params)
+            response = self._session.get(
+                request_url,
+                headers=REQUEST_HEADERS,
+                params=params,
+            )
 
             response.raise_for_status()
 
-        except requests.exceptions.HTTPError as http_err:
-            logger.error("HTTP error occurred: %s", http_err)
-        except requests.exceptions.ConnectionError as conn_err:
-            logger.error("Connection error occurred: %s", conn_err)
-        except requests.exceptions.Timeout as timeout_err:
-            logger.error("Timeout error occurred: %s", timeout_err)
-        except requests.exceptions.RequestException as req_err:
-            logger.error("Request error occurred: %s", req_err)
-        except Exception as e:
-            logger.error("An unexpected error occurred: %s", e)
+        except requests.exceptions.HTTPError as http_error:
+            self.logger.error("HTTP error requesting -> %s; error -> %s", request_url, str(http_error))
+            self.logger.debug("HTTP request header -> %s", str(REQUEST_HEADERS))
+            return None
+        except requests.exceptions.ConnectionError:
+            self.logger.error("Connection error requesting -> %s", request_url)
+            return None
+        except requests.exceptions.Timeout:
+            self.logger.error("Timeout error requesting -> %s", request_url)
+            return None
+        except requests.exceptions.RequestException:
+            self.logger.error("Request error requesting -> %s", request_url)
+            return None
+        except Exception:
+            self.logger.error("Unexpected error requesting -> %s", request_url)
+            return None
+
+        return response.json()
+
+    # end method definition
+
+    def prepare_asset_data(self, asset_id: str, asset: dict | None = None) -> dict:
+        """Prepare the asset data for the Pandas Data frame.
+
+        The asset data is either provided with the asset parameter or
+        retrieved by the method.
+
+        Args:
+            asset_id (str):
+                The ID of the asset.
+            asset (dict | None, optional):
+                If the asset data structure is already available pass it
+                with this parameter. Make sure the asset data was retrieved
+                to include the metadata. If None is provided then the method
+                will retrieve the asset data (including metadata) on the fly.
+
+        Returns:
+            dict | None:
+                The simplified / flat structure for the Pandas data frame.
+
+        Example:
+            {
+                'OTMM_CUSTOM_FIELD_TITLE': 'A Business Case for ArcSight SOAR',
+                'OTMM_CUSTOM_FIELD_DESCRIPTION': 'Cybersecurity is a complex problem.',
+                'OTMM_CUSTOM_FIELD_KEYWORDS': 'SOAR, SIEM, cybersecurity, SecOps, SOC, cybersecurity automation',
+                'CONTENT_TYPE_COMBO_CHAR_ID': None,
+                'OTMM_FIELD_IMAGE_TYPE': None,
+                'OTM_TABLE_APPROVED_USAGE_FIELD': None,
+                'OTMM_FIELD_RESOURCE_LIBRARY_TAB': ['Resource Library'],
+                'LANGUAGE_COMBO_CHAR_ID': 'English',
+                'OTMM_CUSTOM_FIELD_PART_NUMBER': '762-000033-003',
+                'OTMM_FIELD_AVIATOR': None,
+                'OTMM_FIELD_BUSINESS_UNIT_TAB': ['Cybersecurity'],
+                'OTM_TABLE_PRODUCT_TABLE_FIELD': ['ArcSight Enterprise Security Manager', 'Arcsight Intelligence'],
+                'OTMM_FIELD_PRODUCT_NEW_TAB': [],
+                'OTMM_FIELD_MARKET_SEGMENT_TAB': [],
+                'OTM_TABLE_INDUSTRY_TABLE_FIELD': [],
+                'OTMM_CUSTOM_FIELD_URL': None,
+                'OTMM_CUSTOM_FIELD_PREVIOUS_URL': 'https://www.microfocus.com/media/white-paper/a-business-case-for-arcsight-soar-wp.pdf',
+                'OTMM_CUSTOM_FIELD_CONTENT_OWNER': 'Steve Jones',
+                'OTMM_CUSTOM_FIELD_EMAIL': 'sjones2@opentext.com',
+                'OTMM_CUSTOM_FIELD_JOB_NUMBER': [],
+                'OTM_TABLE_BUSINESS_AREA_TABLE_FIELD': [],
+                'OTM_TABLE_JOURNEY_TABLE_FIELD': [],
+                'OTMM_FIELD_PERSONA_TAB': [],
+                'OTMM_FIELD_SERVICES_TAB': [],
+                'OTMM_FIELD_REGION_TAB': [],
+                'OTMM_FIELD_PURPOSE_TAB': ['Marketing'],
+                'AODA_CHAR_ID': 'Yes',
+                'REVIEW_CADENCE_CHAR_ID': 'Quarterly',
+                'CONTENT_CREATED_DATE_ID': '2023-10-18T07:00:00Z',
+                'ARTESIA_FIELD_EXPIRATIONDATE': None,
+                'OTMM_CUSTOM_FIELD_REAL_COMMENTS': None
+            }
+
+        """
+
+        # If the asset dictionary is not already provided
+        # we retrieve it here:
+        if not asset:
+            asset = self.get_asset_details(asset_id=asset_id)
+            if asset is None:
+                self.logger.error(
+                    "Cannot get asset details for asset with ID -> %s",
+                    asset_id,
+                )
+                return {}
+
+        # We drill down to the actual asset data:
+        if "asset_resource" in asset:
+            asset = asset["asset_resource"]
+        if "asset" in asset:
+            asset = asset["asset"]
+
+        if "metadata" not in asset:
+            self.logger.error(
+                "The provided data for asset with ID -> '%s' was retrieved without metadata - cannot prepare metadata fields.",
+                asset_id,
+            )
+            return {}
 
         # Read Metadata from nested structure
         try:
-            metadata = (
-                response.json()
-                .get("asset_resource", {})
-                .get("asset", {})
-                .get("metadata", {})
-                .get("metadata_element_list", [])[0]
-                .get("metadata_element_list", [])
+            """
+            metadata is a list of dictionaries. Each item has these keys:
+            * type (str)
+            * id (str)
+            * name (str)
+            * value (dict)
+              - cascading_domain_value (bool)
+              - domain_value (bool)
+              - is_locked (bool)
+              - value (dict)
+                  + type (str)
+                  + value (str)
+            * metadata_element_list (list)
+            * display_value
+            """
+            metadata_list = (
+                asset.get("metadata", {}).get("metadata_element_list", [])[0].get("metadata_element_list", [])
             )
         except JSONDecodeError:
-            logger.error("Cannot decode JSON response for assset_id -> %s", asset_id)
+            self.logger.error(
+                "Cannot decode JSON response for asset with ID -> %s",
+                asset_id,
+            )
+            return {}
+        except IndexError:
+            self.logger.error(
+                "Cannot find metadata in asset with ID -> %s",
+                asset_id,
+            )
             return {}
 
-        # Generate empty result dict
+        # Initialize empty result dict
         result = {}
 
-        # Extract Metadata fields with values as list
-        for data in metadata:
-            index = data.get("id").replace(" ", "").replace(".", "_")
-
-            try:
-                result[index] = data.get("value").get("value").get("value")
-            except AttributeError:
+        # Extract Metadata fields with values as list and build up
+        # a dictionary:
+        for metadata in metadata_list:
+            # IDs may have dots and spaces that we don't want as dictionary keys.
+            # We remove spaces and replace dots with underscores
+            # (example: OTMM.CUSTOM.FIELD_ PART_NUMBER -> OTMM_CUSTOM_FIELD_PART_NUMBER):
+            dict_key = metadata.get("id").replace(" ", "").replace(".", "_")
+
+            # OTMM has a variety of metadata field types.
+            # This includes list values, drop-down lists and strings.
+            # Each of these have a different representation in
+            # the 'metadata' structure:
+            if "value" in metadata and "value" in metadata["value"]:  # do we have a scalar value (plain string)?
+                value_dict = metadata.get("value").get("value")
+                if "value" in value_dict:
+                    result[dict_key] = value_dict.get("value")
+                elif "display_value" in value_dict:  # is to a domain value?
+                    result[dict_key] = value_dict.get("display_value")
+                else:
+                    result[dict_key] = None
+            elif "metadata_element_list" in metadata:  # do we have a list value?
+                # Create list with a comprehension:
+                value_list = [
+                    value.get("value").get("display_value")
+                    for element in metadata.get("metadata_element_list", [])  # outer loop
+                    for value in element.get("values", [])  # inner loop
+                ]
+                result[dict_key] = value_list
+            else:  # it may also be that there's no value:
+                self.logger.debug(
+                    "No value field in metadata -> %s for key -> '%s'",
+                    str(metadata),
+                    dict_key,
+                )
+                result[dict_key] = None
 
-                infos = []
-                for element in data.get("metadata_element_list", []):
-                    for value in element.get("values", []):
-                        infos.append(value.get("value").get("display_value"))
+        self.logger.debug(
+            "Retrieved asset details for asset with ID -> %s: %s",
+            asset_id,
+            str(result),
+        )
 
-                result[index] = infos
         return result
 
     # end method definition
@@ -663,17 +1418,21 @@ class OTMM:
         load_business_units: bool = True,
         download_assets: bool = True,
     ) -> bool:
-        """Load all Media Assets for Products and Business Units
+        """Load all Media Assets for Products and Business Units into a Pandas data frame.
 
         Args:
-            load_products (bool, optional): If true load assets on Business Unit level. Defaults to True.
-            load_business_units (bool, optional): If true load assets on Product level. Defaults to True.
-            download_assets (bool, optional): Should assets been downloaded. Defaults to True.
+            load_products (bool, optional):
+                If True, load assets on Business Unit level.
+                Defaults to True.
+            load_business_units (bool, optional):
+                If True, load assets on Product level. Defaults to True.
+            download_assets (bool, optional):
+                Only if True assets will be downloaded. Defaults to True.
 
         Returns:
             bool: True = Success, False = Failure
 
-        Example Asset:
+        Example:
         {
             'access_control_descriptor': {
                 'permissions_map': {...}
@@ -714,7 +1473,7 @@ class OTMM:
                 'content_data': {...},
                 'content_kind': 'MASTER',
                 'content_manager_id': 'ARTESIA.CONTENT.GOOGLE.CLOUD',
-                'content_path': 'data/repository/original/generative-ai-governance-essentials-wp-en_56cbbfe270593ba1a5ab6551d2c8b373469cc1a9.pdf',
+                'content_path': 'data/repository/original/generative-ai-governance-essentials-wp-en_56cbbfe.pdf',
                 'content_size': 18474085,
                 'height': -1,
                 'id': '56cbbfe270593ba1a5ab6551d2c8b373469cc1a9',
@@ -740,78 +1499,113 @@ class OTMM:
             'thumbnail_content_id': '70aef1a5b5e480337bc115e47443884432c355ff',
             'version': 1
         }
+
         """
 
         asset_list = []
 
         if load_products:
-
             products = self.get_products()  # dictionary with key = name and value = ID
 
+            if self._product_inclusions is not None:
+                products_filtered = {}
+                self.logger.info(
+                    "Apply include filter on products -> %s",
+                    str(self._product_inclusions),
+                )
+                for key in self._product_inclusions:
+                    if key in products:
+                        products_filtered[key] = products[key]
+
+                products = products_filtered
+
             if self._product_exclusions:
-                logger.info("Excluding products -> %s", str(self._product_exclusions))
+                self.logger.info(
+                    "Excluding products -> %s",
+                    str(self._product_exclusions),
+                )
                 for key in self._product_exclusions:
-                    products.pop(
-                        key, None
-                    )  # pop(key, None) will remove the key if it exists, and do nothing if it doesn't
+                    # pop(key, None) will remove the key if it exists,
+                    # and do nothing if it doesn't:
+                    products.pop(key, None)
 
             for product_name, product_id in products.items():
                 if "DO NOT USE" in product_name:
                     continue
 
-                logger.info("Processing product -> '%s'...", product_name)
+                self.logger.info(
+                    "Processing assets for product -> '%s'...",
+                    product_name,
+                )
 
                 assets = self.get_product_assets(product_id)
 
                 if not assets:
-                    logger.info("Found no assets for product -> '%s'", product_name)
+                    self.logger.info(
+                        "Found no assets for product -> '%s'. Skipping it...",
+                        product_name,
+                    )
                     continue
 
+                # We enrich the dictionary with tags for workspace type and
+                # workspace name for later bulk processing:
                 for asset in assets:
                     asset["workspace_type"] = "Product"
                     asset["workspace_name"] = product_name
 
+                # Filter out assets that are not files - we use the content size
+                # attribute for this:
                 asset_list += [asset for asset in assets if "content_size" in asset]
 
         if load_business_units:
-
             business_units = self.get_business_units()
 
+            if self._business_unit_inclusions is not None:
+                business_units_filtered = {}
+                self.logger.info(
+                    "Apply include filter on business units -> %s",
+                    str(self._business_unit_inclusions),
+                )
+                for key in self._business_unit_inclusions:
+                    if key in business_units:
+                        business_units_filtered[key] = business_units[key]
+
+                business_units = business_units_filtered
+
             if self._business_unit_exclusions:
-                logger.info(
+                self.logger.info(
                     "Excluding business units -> %s",
                     str(self._business_unit_exclusions),
                 )
                 for key in self._business_unit_exclusions:
-                    business_units.pop(
-                        key, None
-                    )  # pop(key, None) will remove the key if it exists, and do nothing if it doesn't
+                    # pop(key, None) will remove the key if it exists,
+                    # and do nothing if it doesn't:
+                    business_units.pop(key, None)
 
             for bu_name, bu_id in business_units.items():
-                logger.debug(bu_name)
+                self.logger.info("Processing assets for business unit -> '%s'", bu_name)
                 assets = self.get_business_unit_assets(bu_id)
 
                 if not assets:
-                    logger.info("Found no assets for business unit -> '%s'", bu_name)
+                    self.logger.info(
+                        "Found no assets for business unit -> '%s'. Skipping it...",
+                        bu_name,
+                    )
                     continue
 
+                # We enrich the dictionary with tags for workspace type and name for
+                # later bulk processing:
                 for asset in assets:
                     asset["workspace_type"] = "Business Unit"
                     asset["workspace_name"] = bu_name
 
+                # Filter out assets that are not files - we use the content size
+                # attribute for this:
                 asset_list += [asset for asset in assets if "content_size" in asset]
+
             # end for bu_name...
         # end if load_business_units
 
-        # WE DON'T WANT TO DO THIS HERE ANY MORE!
-        # This is now done in the bulk document processing
-        # using conditions_delete and conditions_create
-        # asset_list = [
-        #     item
-        #     for item in asset_list
-        #     if not item.get("deleted", False) and not item.get("expired", False)
-        # ]
-
         total_count = len(asset_list)
 
         number = self._thread_number
@@ -824,11 +1618,11 @@ class OTMM:
             number = 1
             remainder = 0
 
-        logger.info(
-            "Processing -> %s Media Assets, thread number -> %s, partition size -> %s",
+        self.logger.info(
+            "Processing -> %s media assets, thread number -> %s, partition size -> %s",
             str(total_count),
-            number,
-            partition_size,
+            str(number),
+            str(partition_size),
         )
 
         threads = []
@@ -868,16 +1662,114 @@ class OTMM:
         partition_size: int,
         offset: int = 0,
         download_assets: bool = True,
-    ):
-        """Worker Method for multi-threading
+    ) -> None:
+        """Worker Method for multi-threading.
 
         Args:
-            asset_list (list): List of assets to process
-            business_unit (str, optional): Name of business unit. Defaults to "".
+            asset_list (list):
+                Complete list of assets. The thread uses offset an partition size
+                to pick its working subset of it.
+            partition_size (int):
+                The size of the partition.
+            offset (int, optional):
+                The starting offset for the worker. The default is 0.
+            download_assets (bool, optional):
+                Whether the thread should download the assets. Default is True.
+
+        Example asset that get's added to the Data Frame:
+            {
+                'access_control_descriptor': {
+                    'permissions_map': {...}
+                },
+                'asset_content_info': {'master_content': {...}},
+                'asset_id': '3eefc89705f53f0540d409cf866f1bc8119f65c0',
+                'asset_lock_state_last_update_date': '2024-06-26T22:15:00Z',
+                'asset_lock_state_user_id': '153',
+                'asset_state': 'NORMAL',
+                'asset_state_last_update_date': '2024-06-26T22:15:00Z',
+                'asset_state_user_id': '153',
+                'checked_out': False,
+                'content_editable': True,
+                'content_lock_state_last_update_date': '2021-11-22T05:33:46Z',
+                'content_lock_state_user_id': '76',
+                'content_lock_state_user_name': 'dgoyal',
+                'content_size': 25986,
+                'content_state': 'NORMAL',
+                'content_state_last_update_date': '2021-11-22T05:33:45Z',
+                'content_state_user_id': '76',
+                'content_state_user_name': 'Dignesh Goyal',
+                'content_type': 'BITMAP',
+                'creator_id': '76',
+                'date_imported': '2021-11-22T05:33:44Z',
+                'date_last_updated': '2024-06-26T22:15:00Z',
+                'deleted': False,
+                'delivery_service_url': 'https://assets.opentext.com/adaptivemedia/rendition?id=3eefc89705f53f0540d409cf866f1bc8119f65c0',
+                'expired': False,
+                'import_job_id': 381,
+                'import_user_name': 'dgoyal',
+                'latest_version': True,
+                'legacy_model_id': 104,
+                'locked': False,
+                'master_content_info': {
+                    'content_checksum': '2cf0db34b37b2af71c516259c6b8287e',
+                    'content_data': {...},
+                    'content_kind': 'MASTER',
+                    'content_manager_id': 'ARTESIA.CONTENT.GOOGLE.CLOUD',
+                    'content_path': 'data/repository/original/co-op-food-logo-ss (1)_21d529dea732.jpg',
+                    'content_size': 25986,
+                    'height': 192,
+                    'id': '21d529dea7324e54b2c00df8573951fcb3f4ebb2',
+                    'mime_type': 'image/jpeg',
+                    'name': 'co-op-food-logo-ss (1).jpg',
+                    'unit_of_size': 'BYTES',
+                    'url': '/otmmapi/v6/renditions/21d529dea7324e54b2c00df8573951fcb3f4ebb2',
+                    'width': 192
+                },
+                'metadata_lock_state_user_name': 'ababigian',
+                'metadata_model_id': 'OTM.MARKETING.MODEL',
+                'metadata_state_user_name': 'Andra Babigian',
+                'mime_type': 'image/jpeg',
+                'name': 'co-op-food-logo-ss (1).jpg',
+                'original_asset_id': '3eefc89705f53f0540d409cf866f1bc8119f65c0',
+                'product_associations': False,
+                'rendition_content': {
+                    'thumbnail_content': {...},
+                    'preview_content': {...}
+                },
+                'subscribed_to': False,
+                'thumbnail_content_id': '94d71e6ac14890e89931f2bbfc2da74ffab8db5f',
+                'version': 1,
+                'workspace_type': 'Product',
+                'workspace_name': 'Trading Grid',
+                'asset_name': 'co-op-food-logo-ss (1).jpg',
+                'OTMM_CUSTOM_FIELD_TITLE': None,
+                'OTMM_CUSTOM_FIELD_DESCRIPTION': None,
+                'OTMM_CUSTOM_FIELD_KEYWORDS': None,
+                'CONTENT_TYPE_COMBO_CHAR_ID': 'Image',
+                'OTMM_FIELD_IMAGE_TYPE': None,
+                'OTM_TABLE_APPROVED_USAGE_FIELD': 'Internal',
+                'OTMM_FIELD_RESOURCE_LIBRARY_TAB': [],
+                'LANGUAGE_COMBO_CHAR_ID': 'English',
+                'OTMM_CUSTOM_FIELD_PART_NUMBER': None,
+                'OTMM_FIELD_AVIATOR': None,
+                'OTMM_FIELD_BUSINESS_UNIT_TAB': ['Business Network'],
+                'OTM_TABLE_PRODUCT_TABLE_FIELD': ['Trading Grid'],
+                'OTMM_FIELD_PRODUCT_NEW_TAB': ['Trading Grid'],
+                'OTMM_FIELD_MARKET_SEGMENT_TAB': [],
+                'OTM_TABLE_INDUSTRY_TABLE_FIELD': ['Retail'],
+                'OTMM_CUSTOM_FIELD_URL': None,
+                ...,
+                'OTM_TABLE_JOURNEY_TABLE_FIELD': ['Buy', 'Try', 'Learn'],
+                ...,
+                'REVIEW_CADENCE_CHAR_ID': 'Quarterly',
+                'CONTENT_CREATED_DATE_ID': '2021-11-08T00:00:00Z',
+                ...
+            }
+
         """
 
-        logger.info(
-            "Processing Media Assets in range from -> %s to -> %s...",
+        self.logger.info(
+            "Processing media assets in range from -> %s to -> %s...",
             offset,
             offset + partition_size,
         )
@@ -886,43 +1778,98 @@ class OTMM:
 
         for asset in worker_asset_list:
             asset_id = asset.get("asset_id")
+            if self._asset_exclusions and asset_id in self._asset_exclusions:
+                self.logger.info(
+                    "Asset with ID -> %s is in exclusion list. Skipping it...",
+                    asset_id,
+                )
+                asset["included"] = False
+                continue
+            if self._asset_inclusions and asset_id not in self._asset_inclusions:
+                self.logger.info(
+                    "Asset with ID -> %s is not in inclusion list. Skipping it...",
+                    asset_id,
+                )
+                asset["included"] = False
+                continue
+            if self._asset_exclusions or self._asset_inclusions:
+                asset["included"] = True
             asset_name = asset.get("name")
             # Store name as asset_name
             asset["asset_name"] = asset_name
-            asset_download_url = asset.get("delivery_service_url")
+            # We cannot fully trust the deliver_service_url -
+            # instead we construct a URL that should always work:
+            asset_download_url = self.config()["assetsUrl"] + "/" + asset_id + "/contents"
+            # We also store the correct download URL to make it available
+            # for the data frame and in bulkDocuments:
+            asset["download_url"] = asset_download_url
             asset_deleted = asset.get("deleted", False)
             asset_expired = asset.get("expired", False)
-            if asset_deleted or asset_expired:
-                logger.info(
-                    "Asset -> '%s' is deleted or expired. Skipping...",
-                    asset_name,
-                )
-                continue
 
-            if download_assets and asset.get("content_size", 0) > 0:
+            # We can skip the_download_ of deleted or expired assets,
+            # but we still want to have them in the Data Frame for
+            # bulk processing (to remove them from OTCS)
+            if download_assets and asset.get("content_size", 0) > 0 and not asset_deleted and not asset_expired:
                 success = self.download_asset(
                     asset_id=asset_id,
                     asset_name=asset_name,
                     download_url=asset_download_url,
+                    asset_modification_date=asset.get("date_last_updated"),
                 )
                 if not success:
-                    logger.error(
+                    self.logger.error(
                         "Failed to download asset -> '%s' (%s) to '%s'",
                         asset_name,
                         asset_id,
                         self._download_dir,
                     )
                 else:
-                    logger.info(
+                    self.logger.info(
                         "Successfully downloaded asset -> '%s' (%s) to '%s'",
                         asset_name,
                         asset_id,
                         self._download_dir,
                     )
+            elif asset_deleted or asset_expired:
+                success = self.remove_stale_download(
+                    asset_id=asset_id,
+                    asset_name=asset_name,
+                )
+                if not success:
+                    self.logger.info(
+                        "No stale download for asset -> '%s' (%s) in directory -> '%s'. Nothing to clean up.",
+                        asset_name,
+                        asset_id,
+                        self._download_dir,
+                    )
+                else:
+                    self.logger.info(
+                        "Deleted stale download for asset -> '%s' (%s) in directory -> '%s'",
+                        asset_name,
+                        asset_id,
+                        self._download_dir,
+                    )
 
-            ## Add metadata to asset and add to new list
-            asset.update(self.get_asset_metadata(asset_id))
+            # Add additional metadata to asset and add to new list
+            asset.update(self.prepare_asset_data(asset_id=asset_id))
 
-        # Now we add the article to the Pandas Data Frame in the Data class:
+        # Now we add the assets processed by the worker
+        # to the Pandas Data Frame in the Data class:
         with self._data.lock():
-            self._data.append(worker_asset_list)
+            # Check if we have added the temporary key "included"
+            # to handle inclusions or exclusions. Then we want to
+            # a) remove the excluded items
+            # b) remove the "included" key to avoid polluting the
+            #    data frame with an additional temp column
+            if self._asset_exclusions or self._asset_inclusions:
+                self._data.append(
+                    [
+                        {k: v for k, v in item.items() if k != "included"}
+                        for item in worker_asset_list
+                        if item.get("included")
+                    ],
+                )
+            else:
+                self._data.append(worker_asset_list)
+
+    # end method definition