Apache Airflow Python Client.DatasetApi

All URIs are relative to http://localhost/api/v1

Method	HTTP request	Description
get_dataset	GET /datasets/{uri}	Get a dataset
get_dataset_events	GET /datasets/events	Get dataset events
get_datasets	GET /datasets	List datasets
get_upstream_dataset_events	GET /dags/{dag_id}/dagRuns/{dag_run_id}/upstreamDatasetEvents	Get dataset events for a DAG run

get_dataset

Dataset get_dataset(uri)

Get a dataset

Get a dataset by uri.

Example

Basic Authentication (Basic):

import time
import airflow_client.client
from airflow_client.client.api import dataset_api
from airflow_client.client.model.error import Error
from airflow_client.client.model.dataset import Dataset
from pprint import pprint
# Defining the host is optional and defaults to http://localhost/api/v1
# See configuration.py for a list of all supported configuration parameters.
configuration = client.Configuration(
    host = "http://localhost/api/v1"
)

# The client must configure the authentication and authorization parameters
# in accordance with the API server security policy.
# Examples for each auth method are provided below, use the example that
# satisfies your auth use case.

# Configure HTTP basic authorization: Basic
configuration = client.Configuration(
    username = 'YOUR_USERNAME',
    password = 'YOUR_PASSWORD'
)

# Enter a context with an instance of the API client
with client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = dataset_api.DatasetApi(api_client)
    uri = "uri_example" # str | The encoded Dataset URI

    # example passing only required values which don't have defaults set
    try:
        # Get a dataset
        api_response = api_instance.get_dataset(uri)
        pprint(api_response)
    except client.ApiException as e:
        print("Exception when calling DatasetApi->get_dataset: %s\n" % e)

Parameters

Name	Type	Description	Notes
uri	str	The encoded Dataset URI

Return type

Dataset

Authorization

Basic, Kerberos

HTTP request headers

Content-Type: Not defined
Accept: application/json

HTTP response details

Status code	Description	Response headers
200	Success.	-
401	Request not authenticated due to missing, invalid, authentication info.	-
403	Client does not have sufficient permission.	-
404	A specified resource is not found.	-

[Back to top] [Back to API list] [Back to Model list] [Back to README]

get_dataset_events

DatasetEventCollection get_dataset_events()

Get dataset events

Example

Basic Authentication (Basic):

import time
import airflow_client.client
from airflow_client.client.api import dataset_api
from airflow_client.client.model.dataset_event_collection import DatasetEventCollection
from airflow_client.client.model.error import Error
from pprint import pprint
# Defining the host is optional and defaults to http://localhost/api/v1
# See configuration.py for a list of all supported configuration parameters.
configuration = client.Configuration(
    host = "http://localhost/api/v1"
)

# The client must configure the authentication and authorization parameters
# in accordance with the API server security policy.
# Examples for each auth method are provided below, use the example that
# satisfies your auth use case.

# Configure HTTP basic authorization: Basic
configuration = client.Configuration(
    username = 'YOUR_USERNAME',
    password = 'YOUR_PASSWORD'
)

# Enter a context with an instance of the API client
with client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = dataset_api.DatasetApi(api_client)
    limit = 100 # int | The numbers of items to return. (optional) if omitted the server will use the default value of 100
    offset = 0 # int | The number of items to skip before starting to collect the result set. (optional)
    order_by = "order_by_example" # str | The name of the field to order the results by. Prefix a field name with `-` to reverse the sort order.  *New in version 2.1.0*  (optional)
    dataset_id = 1 # int | The Dataset ID that updated the dataset. (optional)
    source_dag_id = "source_dag_id_example" # str | The DAG ID that updated the dataset. (optional)
    source_task_id = "source_task_id_example" # str | The task ID that updated the dataset. (optional)
    source_run_id = "source_run_id_example" # str | The DAG run ID that updated the dataset. (optional)
    source_map_index = 1 # int | The map index that updated the dataset. (optional)

    # example passing only required values which don't have defaults set
    # and optional values
    try:
        # Get dataset events
        api_response = api_instance.get_dataset_events(limit=limit, offset=offset, order_by=order_by, dataset_id=dataset_id, source_dag_id=source_dag_id, source_task_id=source_task_id, source_run_id=source_run_id, source_map_index=source_map_index)
        pprint(api_response)
    except client.ApiException as e:
        print("Exception when calling DatasetApi->get_dataset_events: %s\n" % e)

Parameters

Name	Type	Description	Notes
limit	int	The numbers of items to return.	[optional] if omitted the server will use the default value of 100
offset	int	The number of items to skip before starting to collect the result set.	[optional]
order_by	str	The name of the field to order the results by. Prefix a field name with `-` to reverse the sort order. New in version 2.1.0	[optional]
dataset_id	int	The Dataset ID that updated the dataset.	[optional]
source_dag_id	str	The DAG ID that updated the dataset.	[optional]
source_task_id	str	The task ID that updated the dataset.	[optional]
source_run_id	str	The DAG run ID that updated the dataset.	[optional]
source_map_index	int	The map index that updated the dataset.	[optional]

Return type

DatasetEventCollection

Authorization

Basic, Kerberos

HTTP request headers

Content-Type: Not defined
Accept: application/json

HTTP response details

Status code	Description	Response headers
200	Success.	-
401	Request not authenticated due to missing, invalid, authentication info.	-
403	Client does not have sufficient permission.	-
404	A specified resource is not found.	-

[Back to top] [Back to API list] [Back to Model list] [Back to README]

get_datasets

DatasetCollection get_datasets()

List datasets

Example

Basic Authentication (Basic):

import time
import airflow_client.client
from airflow_client.client.api import dataset_api
from airflow_client.client.model.dataset_collection import DatasetCollection
from airflow_client.client.model.error import Error
from pprint import pprint
# Defining the host is optional and defaults to http://localhost/api/v1
# See configuration.py for a list of all supported configuration parameters.
configuration = client.Configuration(
    host = "http://localhost/api/v1"
)

# The client must configure the authentication and authorization parameters
# in accordance with the API server security policy.
# Examples for each auth method are provided below, use the example that
# satisfies your auth use case.

# Configure HTTP basic authorization: Basic
configuration = client.Configuration(
    username = 'YOUR_USERNAME',
    password = 'YOUR_PASSWORD'
)

# Enter a context with an instance of the API client
with client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = dataset_api.DatasetApi(api_client)
    limit = 100 # int | The numbers of items to return. (optional) if omitted the server will use the default value of 100
    offset = 0 # int | The number of items to skip before starting to collect the result set. (optional)
    order_by = "order_by_example" # str | The name of the field to order the results by. Prefix a field name with `-` to reverse the sort order.  *New in version 2.1.0*  (optional)
    uri_pattern = "uri_pattern_example" # str | If set, only return datasets with uris matching this pattern.  (optional)

    # example passing only required values which don't have defaults set
    # and optional values
    try:
        # List datasets
        api_response = api_instance.get_datasets(limit=limit, offset=offset, order_by=order_by, uri_pattern=uri_pattern)
        pprint(api_response)
    except client.ApiException as e:
        print("Exception when calling DatasetApi->get_datasets: %s\n" % e)

Parameters

Name	Type	Description	Notes
limit	int	The numbers of items to return.	[optional] if omitted the server will use the default value of 100
offset	int	The number of items to skip before starting to collect the result set.	[optional]
order_by	str	The name of the field to order the results by. Prefix a field name with `-` to reverse the sort order. New in version 2.1.0	[optional]
uri_pattern	str	If set, only return datasets with uris matching this pattern.	[optional]

Return type

DatasetCollection

Authorization

Basic, Kerberos

HTTP request headers

Content-Type: Not defined
Accept: application/json

HTTP response details

Status code	Description	Response headers
200	Success.	-
401	Request not authenticated due to missing, invalid, authentication info.	-
403	Client does not have sufficient permission.	-

[Back to top] [Back to API list] [Back to Model list] [Back to README]

get_upstream_dataset_events

DatasetEventCollection get_upstream_dataset_events(dag_id, dag_run_id)

Get dataset events for a DAG run

Get datasets for a dag run. New in version 2.4.0

Example

Basic Authentication (Basic):

import time
import airflow_client.client
from airflow_client.client.api import dataset_api
from airflow_client.client.model.dataset_event_collection import DatasetEventCollection
from airflow_client.client.model.error import Error
from pprint import pprint
# Defining the host is optional and defaults to http://localhost/api/v1
# See configuration.py for a list of all supported configuration parameters.
configuration = client.Configuration(
    host = "http://localhost/api/v1"
)

# The client must configure the authentication and authorization parameters
# in accordance with the API server security policy.
# Examples for each auth method are provided below, use the example that
# satisfies your auth use case.

# Configure HTTP basic authorization: Basic
configuration = client.Configuration(
    username = 'YOUR_USERNAME',
    password = 'YOUR_PASSWORD'
)

# Enter a context with an instance of the API client
with client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = dataset_api.DatasetApi(api_client)
    dag_id = "dag_id_example" # str | The DAG ID.
    dag_run_id = "dag_run_id_example" # str | The DAG run ID.

    # example passing only required values which don't have defaults set
    try:
        # Get dataset events for a DAG run
        api_response = api_instance.get_upstream_dataset_events(dag_id, dag_run_id)
        pprint(api_response)
    except client.ApiException as e:
        print("Exception when calling DatasetApi->get_upstream_dataset_events: %s\n" % e)

Parameters

Name	Type	Description	Notes
dag_id	str	The DAG ID.
dag_run_id	str	The DAG run ID.

Return type

DatasetEventCollection

Authorization

Basic, Kerberos

HTTP request headers

Content-Type: Not defined
Accept: application/json

HTTP response details

Status code	Description	Response headers
200	Success.	-
401	Request not authenticated due to missing, invalid, authentication info.	-
403	Client does not have sufficient permission.	-
404	A specified resource is not found.	-

[Back to top] [Back to API list] [Back to Model list] [Back to README]