def get_target_workbook_df(conn_target, workbook_names=None):
"""
Query details for all workbooks on the source site, or only the workbooks listed in 'workbook_names'.
:param class conn_target: the Tableau Server connection object
:param list workbook_names: a list of the desired workbook names whose details will be queried
:return: Pandas DataFrame
"""
try:
workbook_df = get_workbooks_dataframe(conn_target)
workbook_df.fillna(value='', inplace=True)
if workbook_names:
workbook_df = workbook_df[workbook_df['name'].isin(workbook_names)]
workbook_df = flatten_dict_column(workbook_df,
keys=['id', 'name'],
col_name='project')
workbook_df = flatten_dict_column(workbook_df,
keys=['id', 'name', 'email'],
col_name='owner')
workbook_df.columns = [
"target_" + column for column in workbook_df.columns
]
workbook_df['target_project_name_lower'] = workbook_df[
'target_project_name'].apply(lambda x: str(x).lower())
except KeyError:
workbook_df = pd.DataFrame()
return workbook_df
def get_subscriptions_dataframe(conn):
subscriptions_df = pd.DataFrame(get_all_subscription_fields(conn))
subscriptions_df = flatten_dict_column(subscriptions_df,
keys=['id', 'type'],
col_name='content')
subscriptions_df = flatten_dict_column(subscriptions_df,
keys=['id', 'name'],
col_name='schedule')
subscriptions_df = flatten_dict_column(subscriptions_df,
keys=['id', 'name'],
col_name='user')
return subscriptions_df
def get_source_datasource_df(conn_source, datasource_ids):
datasource_df = get_datasources_dataframe(conn_source)
if datasource_ids:
datasource_df = datasource_df.loc[datasource_df['id'].isin(
datasource_ids)]
datasource_df = flatten_dict_column(datasource_df,
keys=['id', 'name'],
col_name='project')
datasource_df = flatten_dict_column(datasource_df,
keys=['id', 'name'],
col_name='owner')
datasource_df.columns = [
"source_" + column for column in datasource_df.columns
]
datasource_df['source_project_name_lower'] = datasource_df[
'source_project_name'].apply(lambda x: x.lower())
return datasource_df
def get_views_dataframe(conn, site_id=None):
if not site_id:
site_id = conn.site_id
views_df = pd.DataFrame(get_all_view_fields(conn, site_id))
views_df = flatten_dict_column(views_df,
keys=['totalViewCount'],
col_name='usage')
return views_df
def get_views_dataframe(conn: TableauServerConnection,
site_id: Optional[str] = None) -> pd.DataFrame:
"""Returns a DataFrame describing all available views. If none are available, an empty DataFrame is returned."""
if not site_id:
site_id = conn.site_id
views_df = pd.DataFrame(get_all_view_fields(conn, site_id))
if not views_df.empty:
views_df = flatten_dict_column(views_df,
keys=["totalViewCount"],
col_name="usage")
return views_df
def get_workbook_connections_dataframe(conn, workbook_id):
try:
connections_json = conn.query_workbook_connections(
workbook_id).json()['connections']['connection']
connections_df = pd.DataFrame(connections_json)
connections_df = flatten_dict_column(connections_df,
keys=['id', 'name'],
col_name='datasource')
return connections_df
except KeyError:
raise ContentNotFound('workbook', workbook_id)
def get_workbook_connections_dataframe(conn: TableauServerConnection,
workbook_id: str) -> pd.DataFrame:
"""Returns a DataFrame describing the connections associated with the specified workbook."""
try:
connections_json = conn.query_workbook_connections(
workbook_id).json()["connections"]["connection"]
connections_df = pd.DataFrame(connections_json)
connections_df = flatten_dict_column(connections_df,
keys=["id", "name"],
col_name="datasource")
except KeyError:
connections_df = pd.DataFrame()
return connections_df