Scrittura di DAG di Airflow

Visualizza su GitHub Feedback

import datetime

from airflow import models
default_dag_args = {
    # The start_date describes when a DAG is valid / can be run. Set this to a
    # fixed point in time rather than dynamically, since it is evaluated every
    # time a DAG is parsed. See:
    # https://airflow.apache.org/faq.html#what-s-the-deal-with-start-date
    'start_date': datetime.datetime(2018, 1, 1),
}

# Define a DAG (directed acyclic graph) of tasks.
# Any task you create within the context manager is automatically added to the
# DAG object.
with models.DAG(
        'composer_sample_simple_greeting',
        schedule_interval=datetime.timedelta(days=1),
        default_args=default_dag_args) as dag:

Flusso d'aria 1

Visualizza su GitHub Feedback

import datetime

from airflow import models
default_dag_args = {
    # The start_date describes when a DAG is valid / can be run. Set this to a
    # fixed point in time rather than dynamically, since it is evaluated every
    # time a DAG is parsed. See:
    # https://airflow.apache.org/faq.html#what-s-the-deal-with-start-date
    'start_date': datetime.datetime(2018, 1, 1),
}

# Define a DAG (directed acyclic graph) of tasks.
# Any task you create within the context manager is automatically added to the
# DAG object.
with models.DAG(
        'composer_sample_simple_greeting',
        schedule_interval=datetime.timedelta(days=1),
        default_args=default_dag_args) as dag:

Operatori per descrivere il lavoro da svolgere. L'istanza di un operatore è chiamata attività.

Flusso d'aria 2

Visualizza su GitHub Feedback

from airflow.operators import bash_operator
from airflow.operators import python_operator
    def greeting():
        import logging
        logging.info('Hello World!')

    # An instance of an operator is called a task. In this case, the
    # hello_python task calls the "greeting" Python function.
    hello_python = python_operator.PythonOperator(
        task_id='hello',
        python_callable=greeting)

    # Likewise, the goodbye_bash task calls a Bash script.
    goodbye_bash = bash_operator.BashOperator(
        task_id='bye',
        bash_command='echo Goodbye.')

Flusso d'aria 1

Visualizza su GitHub Feedback

from airflow.operators import bash_operator
from airflow.operators import python_operator
    def greeting():
        import logging
        logging.info('Hello World!')

    # An instance of an operator is called a task. In this case, the
    # hello_python task calls the "greeting" Python function.
    hello_python = python_operator.PythonOperator(
        task_id='hello',
        python_callable=greeting)

    # Likewise, the goodbye_bash task calls a Bash script.
    goodbye_bash = bash_operator.BashOperator(
        task_id='bye',
        bash_command='echo Goodbye.')

Relazioni alle attività per descrivere l'ordine in cui completare il lavoro.

Flusso d'aria 2

Visualizza su GitHub Feedback

# Define the order in which the tasks complete by using the >> and <<
# operators. In this example, hello_python executes before goodbye_bash.
hello_python >> goodbye_bash

Flusso d'aria 1

Visualizza su GitHub Feedback

# Define the order in which the tasks complete by using the >> and <<
# operators. In this example, hello_python executes before goodbye_bash.
hello_python >> goodbye_bash

Esempio di flusso di lavoro completo di DAG in Python

Il seguente flusso di lavoro è un modello DAG funzionante completo composto da due attività: un'attività hello_python e un'attività goodbye_bash:

Flusso d'aria 2

Visualizza su GitHub Feedback

from __future__ import print_function

import datetime

from airflow import models
from airflow.operators import bash_operator
from airflow.operators import python_operator

default_dag_args = {
    # The start_date describes when a DAG is valid / can be run. Set this to a
    # fixed point in time rather than dynamically, since it is evaluated every
    # time a DAG is parsed. See:
    # https://airflow.apache.org/faq.html#what-s-the-deal-with-start-date
    'start_date': datetime.datetime(2018, 1, 1),
}

# Define a DAG (directed acyclic graph) of tasks.
# Any task you create within the context manager is automatically added to the
# DAG object.
with models.DAG(
        'composer_sample_simple_greeting',
        schedule_interval=datetime.timedelta(days=1),
        default_args=default_dag_args) as dag:
    def greeting():
        import logging
        logging.info('Hello World!')

    # An instance of an operator is called a task. In this case, the
    # hello_python task calls the "greeting" Python function.
    hello_python = python_operator.PythonOperator(
        task_id='hello',
        python_callable=greeting)

    # Likewise, the goodbye_bash task calls a Bash script.
    goodbye_bash = bash_operator.BashOperator(
        task_id='bye',
        bash_command='echo Goodbye.')

    # Define the order in which the tasks complete by using the >> and <<
    # operators. In this example, hello_python executes before goodbye_bash.
    hello_python >> goodbye_bash

Flusso d'aria 1

Visualizza su GitHub Feedback

from __future__ import print_function

import datetime

from airflow import models
from airflow.operators import bash_operator
from airflow.operators import python_operator

default_dag_args = {
    # The start_date describes when a DAG is valid / can be run. Set this to a
    # fixed point in time rather than dynamically, since it is evaluated every
    # time a DAG is parsed. See:
    # https://airflow.apache.org/faq.html#what-s-the-deal-with-start-date
    'start_date': datetime.datetime(2018, 1, 1),
}

# Define a DAG (directed acyclic graph) of tasks.
# Any task you create within the context manager is automatically added to the
# DAG object.
with models.DAG(
        'composer_sample_simple_greeting',
        schedule_interval=datetime.timedelta(days=1),
        default_args=default_dag_args) as dag:
    def greeting():
        import logging
        logging.info('Hello World!')

    # An instance of an operator is called a task. In this case, the
    # hello_python task calls the "greeting" Python function.
    hello_python = python_operator.PythonOperator(
        task_id='hello',
        python_callable=greeting)

    # Likewise, the goodbye_bash task calls a Bash script.
    goodbye_bash = bash_operator.BashOperator(
        task_id='bye',
        bash_command='echo Goodbye.')

    # Define the order in which the tasks complete by using the >> and <<
    # operators. In this example, hello_python executes before goodbye_bash.
    hello_python >> goodbye_bash

Tutorial e concetti di Airflow

Per ulteriori informazioni sulla definizione dei DAG Airflow, consulta il tutorial di Airflow e i concetti di Airflow.

Operatori Airflow

I seguenti esempi mostrano alcuni degli operatori Airflow più diffusi. Per un riferimento autorevole degli operatori Airflow, consulta la sezione Riferimento API AirApache o sfoglia il codice sorgente degli operatori core, contrib e provider.

Operatore bash

Utilizza BashOperator per eseguire programmi a riga di comando.

Flusso d'aria 2

Visualizza su GitHub Feedback

from airflow.operators import bash

    # Create BigQuery output dataset.
    make_bq_dataset = bash.BashOperator(
        task_id="make_bq_dataset",
        # Executing 'bq' command requires Google Cloud SDK which comes
        # preinstalled in Cloud Composer.
        bash_command=f"bq ls {bq_dataset_name} || bq mk {bq_dataset_name}",
    )

Flusso d'aria 1

Visualizza su GitHub Feedback

from airflow.operators import bash_operator

    # Create BigQuery output dataset.
    make_bq_dataset = bash_operator.BashOperator(
        task_id="make_bq_dataset",
        # Executing 'bq' command requires Google Cloud SDK which comes
        # preinstalled in Cloud Composer.
        bash_command="bq ls {} || bq mk {}".format(bq_dataset_name, bq_dataset_name),
    )

Cloud Composer esegue i comandi forniti in uno script Bash su un worker. Il worker è un container Docker basato su Debian e include diversi pacchetti.

Operatore Python

Utilizza PythonOperator per eseguire codice Python arbitrario.

Cloud Composer esegue il codice Python in un container che include i pacchetti per la versione immagine di Cloud Composer utilizzata nel tuo ambiente.

Per installare altri pacchetti Python, consulta Installazione di dipendenze Python.

Operatori Google Cloud

Utilizza gli operatori Google Cloud Airflow per eseguire attività che utilizzano i prodotti Google Cloud. Cloud Composer configura automaticamente una connessione Airflow al progetto dell'ambiente.

Gli operatori BigQuery interrompono i dati delle query e dei processi in BigQuery.

Flusso d'aria 2

Visualizza su GitHub Feedback

from airflow.providers.google.cloud.operators import bigquery
from airflow.providers.google.cloud.transfers import bigquery_to_gcs

    bq_recent_questions_query = bigquery.BigQueryInsertJobOperator(
        task_id="bq_recent_questions_query",
        configuration={
            "query": {
                "query": RECENT_QUESTIONS_QUERY,
                "useLegacySql": False,
                "destinationTable": {
                    "projectId": project_id,
                    "datasetId": bq_dataset_name,
                    "tableId": bq_recent_questions_table_id,
                },
            }
        },
        location=location,
    )

Flusso d'aria 1

Visualizza su GitHub Feedback

from airflow.contrib.operators import bigquery_operator

    # Query recent StackOverflow questions.
    bq_recent_questions_query = bigquery_operator.BigQueryOperator(
        task_id="bq_recent_questions_query",
        sql="""
        SELECT owner_display_name, title, view_count
        FROM `bigquery-public-data.stackoverflow.posts_questions`
        WHERE creation_date < CAST('{max_date}' AS TIMESTAMP)
            AND creation_date >= CAST('{min_date}' AS TIMESTAMP)
        ORDER BY view_count DESC
        LIMIT 100
        """.format(
            max_date=max_query_date, min_date=min_query_date
        ),
        use_legacy_sql=False,
        destination_dataset_table=bq_recent_questions_table_id,
    )

Gli operatori Dataflow eseguono i job Apache Beam in Dataflow.
Gli operatori Cloud Data Fusion gestiscono ed eseguono le pipeline Cloud Data Fusion.
Gli operatori Dataproc eseguono i job Hadoop e Spark in Dataproc.
Gli operatori del datastore leggono e scrivono i dati in Datastore.
Gli operatori di AI Platform eseguono job di addestramento e previsione in AI Platform.
Gli operatori Cloud Storage leggono e scrivono i dati in Cloud Storage.

Operatore email

Utilizza EmailOperator per inviare email da un DAG. Per inviare email da un ambiente Cloud Composer, devi configurare il tuo ambiente per l'utilizzo di SendGrid.

Flusso d'aria 2

Visualizza su GitHub Feedback

from airflow.operators import email

    # Send email confirmation (you will need to set up the email operator
    # See https://cloud.google.com/composer/docs/how-to/managing/creating#notification
    # for more info on configuring the email operator in Cloud Composer)
    email_summary = email.EmailOperator(
        task_id="email_summary",
        to="{{var.value.email}}",
        subject="Sample BigQuery notify data ready",
        html_content="""
        Analyzed Stack Overflow posts data from {min_date} 12AM to {max_date}
        12AM. The most popular question was '{question_title}' with
        {view_count} views. Top 100 questions asked are now available at:
        {export_location}.
        """.format(
            min_date=min_query_date,
            max_date=max_query_date,
            question_title=(
                "{{ ti.xcom_pull(task_ids='bq_read_most_popular', "
                "key='return_value')[0][0] }}"
            ),
            view_count=(
                "{{ ti.xcom_pull(task_ids='bq_read_most_popular', "
                "key='return_value')[0][1] }}"
            ),
            export_location=output_file,
        ),
    )

Flusso d'aria 1

Visualizza su GitHub Feedback

from airflow.operators import email_operator

    # Send email confirmation
    email_summary = email_operator.EmailOperator(
        task_id="email_summary",
        to="{{var.value.email}}",
        subject="Sample BigQuery notify data ready",
        html_content="""
        Analyzed Stack Overflow posts data from {min_date} 12AM to {max_date}
        12AM. The most popular question was '{question_title}' with
        {view_count} views. Top 100 questions asked are now available at:
        {export_location}.
        """.format(
            min_date=min_query_date,
            max_date=max_query_date,
            question_title=(
                "{{ ti.xcom_pull(task_ids='bq_read_most_popular', "
                "key='return_value')[0][0] }}"
            ),
            view_count=(
                "{{ ti.xcom_pull(task_ids='bq_read_most_popular', "
                "key='return_value')[0][1] }}"
            ),
            export_location=output_file,
        ),
    )

Notifiche

Imposta email_on_failure su True per inviare una notifica via email quando un operatore del DAG non riesce. Per inviare notifiche email da un ambiente Cloud Composer, devi configurare il tuo ambiente per l'utilizzo di SendGrid.

Flusso d'aria 2

Visualizza su GitHub Feedback

from airflow import models

default_dag_args = {
    "start_date": yesterday,
    # Email whenever an Operator in the DAG fails.
    "email": "{{var.value.email}}",
    "email_on_failure": True,
    "email_on_retry": False,
    "retries": 1,
    "retry_delay": datetime.timedelta(minutes=5),
    "project_id": project_id,
}

with models.DAG(
    "composer_sample_bq_notify",
    schedule_interval=datetime.timedelta(weeks=4),
    default_args=default_dag_args,
) as dag:

Flusso d'aria 1