Airflow Slack 연동 실습

mkdir airflow && cd airflow

conda create -n airflow-practice python=3.8

# Dockerfile FROM apache/airflow:2.5.1 USER root RUN apt-get update && apt-get install -y build-essential RUN apt-get install -y default-libmysqlclient-dev CMD ["webserver"]

# docker-compose.yaml # Licensed to the Apache Software Foundation (ASF) under one # or more contributor license agreements. See the NOTICE file # distributed with this work for additional information # regarding copyright ownership. The ASF licenses this file # to you under the Apache License, Version 2.0 (the # "License"); you may not use this file except in compliance # with the License. You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, # software distributed under the License is distributed on an # "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY # KIND, either express or implied. See the License for the # specific language governing permissions and limitations # under the License. # # Basic Airflow cluster configuration for CeleryExecutor with Redis and PostgreSQL. # # WARNING: This configuration is for local development. Do not use it in a production deployment. # # This configuration supports basic configuration using environment variables or an .env file # The following variables are supported: # # AIRFLOW_IMAGE_NAME - Docker image name used to run Airflow. # Default: apache/airflow:2.5.1 # AIRFLOW_UID - User ID in Airflow containers # Default: 50000 # AIRFLOW_PROJ_DIR - Base path to which all the files will be volumed. # Default: . # Those configurations are useful mostly in case of standalone testing/running Airflow in test/try-out mode # # _AIRFLOW_WWW_USER_USERNAME - Username for the administrator account (if requested). # Default: airflow # _AIRFLOW_WWW_USER_PASSWORD - Password for the administrator account (if requested). # Default: airflow # _PIP_ADDITIONAL_REQUIREMENTS - Additional PIP requirements to add when starting all containers. # Default: '' # # Feel free to modify this file to suit your needs. --- version: '3' x-airflow-common: &airflow-common # In order to add custom dependencies or upgrade provider packages you can use your extended image. # Comment the image line, place your Dockerfile in the directory where you placed the docker-compose.yaml # and uncomment the "build" line below, Then run `docker-compose build` to build the images. image: ${AIRFLOW_IMAGE_NAME:-apache/airflow:2.5.1} # build: # context: . # dockerfile: Dockerfile environment: &airflow-common-env AIRFLOW__CORE__EXECUTOR: CeleryExecutor AIRFLOW__DATABASE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow # For backward compatibility, with Airflow <2.3 AIRFLOW__CORE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow AIRFLOW__CELERY__RESULT_BACKEND: db+postgresql://airflow:airflow@postgres/airflow AIRFLOW__CELERY__BROKER_URL: redis://:@redis:6379/0 AIRFLOW__CORE__FERNET_KEY: '' AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION: 'true' AIRFLOW__CORE__LOAD_EXAMPLES: 'true' AIRFLOW__API__AUTH_BACKENDS: 'airflow.api.auth.backend.basic_auth,airflow.api.auth.backend.session' _PIP_ADDITIONAL_REQUIREMENTS: ${_PIP_ADDITIONAL_REQUIREMENTS:- pandas numpy beautifulsoup4 } volumes: - ${AIRFLOW_PROJ_DIR:-.}/dags:/opt/airflow/dags - ${AIRFLOW_PROJ_DIR:-.}/logs:/opt/airflow/logs - ${AIRFLOW_PROJ_DIR:-.}/plugins:/opt/airflow/plugins - ${AIRFLOW_PROJ_DIR:-.}/data:/opt/airflow/data user: "${AIRFLOW_UID:-50000}:0" depends_on: &airflow-common-depends-on redis: condition: service_healthy postgres: condition: service_healthy services: postgres: image: postgres:13 environment: POSTGRES_USER: airflow POSTGRES_PASSWORD: airflow POSTGRES_DB: airflow volumes: - postgres-db-volume:/var/lib/postgresql/data healthcheck: test: ["CMD", "pg_isready", "-U", "airflow"] interval: 5s retries: 5 restart: always redis: image: redis:latest expose: - 6379 healthcheck: test: ["CMD", "redis-cli", "ping"] interval: 5s timeout: 30s retries: 50 restart: always airflow-webserver: <<: *airflow-common command: webserver ports: - 8080:8080 healthcheck: test: ["CMD", "curl", "--fail", "http://localhost:8080/health"] interval: 10s timeout: 10s retries: 5 restart: always depends_on: <<: *airflow-common-depends-on airflow-init: condition: service_completed_successfully airflow-scheduler: <<: *airflow-common command: scheduler healthcheck: test: ["CMD-SHELL", 'airflow jobs check --job-type SchedulerJob --hostname "$${HOSTNAME}"'] interval: 10s timeout: 10s retries: 5 restart: always depends_on: <<: *airflow-common-depends-on airflow-init: condition: service_completed_successfully airflow-worker: <<: *airflow-common command: celery worker healthcheck: test: - "CMD-SHELL" - 'celery --app airflow.executors.celery_executor.app inspect ping -d "celery@$${HOSTNAME}"' interval: 10s timeout: 10s retries: 5 environment: <<: *airflow-common-env # Required to handle warm shutdown of the celery workers properly # See https://airflow.apache.org/docs/docker-stack/entrypoint.html#signal-propagation DUMB_INIT_SETSID: "0" restart: always depends_on: <<: *airflow-common-depends-on airflow-init: condition: service_completed_successfully airflow-triggerer: <<: *airflow-common command: triggerer healthcheck: test: ["CMD-SHELL", 'airflow jobs check --job-type TriggererJob --hostname "$${HOSTNAME}"'] interval: 10s timeout: 10s retries: 5 restart: always depends_on: <<: *airflow-common-depends-on airflow-init: condition: service_completed_successfully airflow-init: <<: *airflow-common entrypoint: /bin/bash # yamllint disable rule:line-length command: - -c - | function ver() { printf "%04d%04d%04d%04d" $${1//./ } } airflow_version=$$(AIRFLOW__LOGGING__LOGGING_LEVEL=INFO && gosu airflow airflow version) airflow_version_comparable=$$(ver $${airflow_version}) min_airflow_version=2.2.0 min_airflow_version_comparable=$$(ver $${min_airflow_version}) if (( airflow_version_comparable < min_airflow_version_comparable )); then echo echo -e "\033[1;31mERROR!!!: Too old Airflow version $${airflow_version}!\e[0m" echo "The minimum Airflow version supported: $${min_airflow_version}. Only use this or higher!" echo exit 1 fi if [[ -z "${AIRFLOW_UID}" ]]; then echo echo -e "\033[1;33mWARNING!!!: AIRFLOW_UID not set!\e[0m" echo "If you are on Linux, you SHOULD follow the instructions below to set " echo "AIRFLOW_UID environment variable, otherwise files will be owned by root." echo "For other operating systems you can get rid of the warning with manually created .env file:" echo " See: https://airflow.apache.org/docs/apache-airflow/stable/howto/docker-compose/index.html#setting-the-right-airflow-user" echo fi one_meg=1048576 mem_available=$$(($$(getconf _PHYS_PAGES) * $$(getconf PAGE_SIZE) / one_meg)) cpus_available=$$(grep -cE 'cpu[0-9]+' /proc/stat) disk_available=$$(df / | tail -1 | awk '{print $$4}') warning_resources="false" if (( mem_available < 4000 )) ; then echo echo -e "\033[1;33mWARNING!!!: Not enough memory available for Docker.\e[0m" echo "At least 4GB of memory required. You have $$(numfmt --to iec $$((mem_available * one_meg)))" echo warning_resources="true" fi if (( cpus_available < 2 )); then echo echo -e "\033[1;33mWARNING!!!: Not enough CPUS available for Docker.\e[0m" echo "At least 2 CPUs recommended. You have $${cpus_available}" echo warning_resources="true" fi if (( disk_available < one_meg * 10 )); then echo echo -e "\033[1;33mWARNING!!!: Not enough Disk space available for Docker.\e[0m" echo "At least 10 GBs recommended. You have $$(numfmt --to iec $$((disk_available * 1024 )))" echo warning_resources="true" fi if [[ $${warning_resources} == "true" ]]; then echo echo -e "\033[1;33mWARNING!!!: You have not enough resources to run Airflow (see above)!\e[0m" echo "Please follow the instructions to increase amount of resources available:" echo " https://airflow.apache.org/docs/apache-airflow/stable/howto/docker-compose/index.html#before-you-begin" echo fi mkdir -p /sources/logs /sources/dags /sources/plugins /sources/data chown -R "${AIRFLOW_UID}:0" /sources/{logs,dags,plugins} exec /entrypoint airflow version # yamllint enable rule:line-length environment: <<: *airflow-common-env _AIRFLOW_DB_UPGRADE: 'true' _AIRFLOW_WWW_USER_CREATE: 'true' _AIRFLOW_WWW_USER_USERNAME: ${_AIRFLOW_WWW_USER_USERNAME:-airflow} _AIRFLOW_WWW_USER_PASSWORD: ${_AIRFLOW_WWW_USER_PASSWORD:-airflow} _PIP_ADDITIONAL_REQUIREMENTS: '' user: "0:0" volumes: - ${AIRFLOW_PROJ_DIR:-.}:/sources airflow-cli: <<: *airflow-common profiles: - debug environment: <<: *airflow-common-env CONNECTION_CHECK_MAX_COUNT: "0" # Workaround for entrypoint issue. See: https://github.com/apache/airflow/issues/16252 command: - bash - -c - airflow # You can enable flower by adding "--profile flower" option e.g. docker-compose --profile flower up # or by explicitly targeted on the command line e.g. docker-compose up flower. # See: https://docs.docker.com/compose/profiles/ flower: <<: *airflow-common command: celery flower profiles: - flower ports: - 5555:5555 healthcheck: test: ["CMD", "curl", "--fail", "http://localhost:5555/"] interval: 10s timeout: 10s retries: 5 restart: always depends_on: <<: *airflow-common-depends-on airflow-init: condition: service_completed_successfully volumes: postgres-db-volume:

docker compose up -d

# boaz_simple_etl.py from datetime import datetime, timedelta from airflow import DAG from airflow.models import Variable import requests from bs4 import BeautifulSoup import csv # 사용할 Operator Import from airflow.providers.postgres.operators.postgres import PostgresOperator from airflow.operators.python import PythonOperator from airflow.operators.bash import BashOperator def extract(link): f = requests.get(link) return f.text def transform(text): soup = BeautifulSoup(text, 'html.parser') titles = [] tmp = soup.select(".title") for title in tmp: titles.append(title.get_text()) return titles def load(titles): with open("job_search_result.csv", "w") as file: writer = csv.writer(file) writer.writerow(titles) def etl(): link = "https://kr.indeed.com/jobs?q=airflow" text = extract(link) titles = transform(text) load(titles) # DAG 설정 dag = DAG( dag_id="boaz_simple_etl", schedule_interval="@daily", start_date=datetime(2022,6,15), #원래 시작했어야 한 날짜 하지만 명시적으로 시작 안 해주면 dag는 시작 안 함 default_args = { 'retries': 1, 'retry_delay': timedelta(minutes=3), }, #dag 밑에 속한 task에 적용되는 파라미터 tags=["BOAZ"], #팀별로, 태스크별로 tag 붙일 수 있음 (DAG 수백개 되면 하나하나 기억할 수 없음. tag 필수) catchup=False #start_date와 실제 시작일 사이에 실행 안 된 것을 한 번에 실행해주는 옵션 (모르겠으면 false…) ) # Operator 만들기 creating_table = PostgresOperator( task_id="creating_table", postgres_conn_id="postgres_conn_id", # 웹UI에서 connection을 등록해줘야 함. sql=''' CREATE TABLE IF NOT EXISTS job_search_result ( title TEXT ) ''', dag = dag ) etl = PythonOperator( task_id = "etl", python_callable = etl, # 실행할 파이썬 함수 dag = dag ) # 저장되었다는 사실 echo store_result = BashOperator( task_id="store_result", bash_command= "echo 'ETL Done'", dag=dag ) # 파이프라인 구성하기 creating_table >> etl >> store_result

from slack_sdk import WebClient from datetime import datetime class SlackAlert: def __init__(self, channel, token): self.channel = channel self.client = WebClient(token=token) def success_msg(self, msg): text = f""" date : {datetime.today().strftime('%Y-%m-%d')} alert : Success! task id : {msg.get('task_instance').task_id}, dag id : {msg.get('task_instance').dag_id}, log url : {msg.get('task_instance').log_url} """ self.client.chat_postMessage(channel=self.channel, text=text) def fail_msg(self, msg): text = f""" date : {datetime.today().strftime('%Y-%m-%d')} alert : Fail! task id : {msg.get('task_instance').task_id}, dag id : {msg.get('task_instance').dag_id}, log url : {msg.get('task_instance').log_url} """ self.client.chat_postMessage(channel=self.channel, text=text)

# boaz_simple_etl.py from datetime import datetime, timedelta from airflow import DAG from airflow.models import Variable from plugins.slack import SlackAlert import requests from bs4 import BeautifulSoup import csv # 사용할 Operator Import from airflow.providers.postgres.operators.postgres import PostgresOperator from airflow.operators.python import PythonOperator from airflow.operators.bash import BashOperator def extract(link): f = requests.get(link) return f.text def transform(text): soup = BeautifulSoup(text, 'html.parser') titles = [] tmp = soup.select(".title") for title in tmp: titles.append(title.get_text()) return titles def load(titles): with open("job_search_result.csv", "w") as file: writer = csv.writer(file) writer.writerow(titles) def etl(): link = "https://kr.indeed.com/jobs?q=airflow" text = extract(link) titles = transform(text) load(titles) # SLACK 정의 slack = SlackAlert("#채널 이름", "발급받은 token") # DAG 설정 dag = DAG( dag_id="boaz_simple_etl", schedule_interval="@daily", start_date=datetime(2022,6,15), #원래 시작했어야 한 날짜 하지만 명시적으로 시작 안 해주면 dag는 시작 안 함 default_args = { 'retries': 1, 'retry_delay': timedelta(minutes=3), 'on_success_callback': slack.success_msg, # 성공시 SLACK 함수 요청 'on_failure_callback': slack.fail_msg, # 실패시 SLACK 함수 요청 }, #dag 밑에 속한 task에 적용되는 파라미터 tags=["BOAZ"], #팀별로, 태스크별로 tag 붙일 수 있음 (DAG 수백개 되면 하나하나 기억할 수 없음. tag 필수) catchup=False #start_date와 실제 시작일 사이에 실행 안 된 것을 한 번에 실행>해주는 옵션 (모르겠으면 false…) ) # Operator 만들기 creating_table = PostgresOperator( task_id="creating_table", postgres_conn_id="postgres_conn_id", # 웹UI에서 connection을 등록해줘야 함. sql=''' CREATE TABLE IF NOT EXISTS job_search_result ( title TEXT ) ''', dag = dag ) etl = PythonOperator( task_id = "etl", python_callable = etl, # 실행할 파이썬 함수 dag = dag ) # 저장되었다는 사실 echo store_result = BashOperator( task_id="store_result", bash_command= "echo 'ETL Done'", dag=dag ) # 파이프라인 구성하기 creating_table >> etl >> store_result