from airflow.operators import BranchPythonOperator, DummyOperator
from airflow.models import DAG
from datetime import datetime, timedelta
import random
seven_days_ago = datetime.combine(datetime.today() - timedelta(7),
datetime.min.time())
args = {
'owner': 'airflow',
'start_date': seven_days_ago,
}
dag = DAG(dag_id='example_branch_operator', default_args=args)
cmd = 'ls -l'
run_this_first = DummyOperator(task_id='run_this_first', dag=dag)
options = ['branch_a', 'branch_b', 'branch_c', 'branch_d']
branching = BranchPythonOperator(
task_id='branching',
python_callable=lambda: random.choice(options),
dag=dag)
branching.set_upstream(run_this_first)
for option in options:
t = DummyOperator(task_id=option, dag=dag)
t.set_upstream(branching)
dummy_follow = DummyOperator(task_id='follow_' + option, dag=dag)
t.set_downstream(dummy_follow)
t3 = PythonOperator(task_id='compare_result',
provide_context=True,
python_callable=compare_result,
trigger_rule="all_done",
dag=dag)
t3.set_upstream(t1)
t3.set_upstream(t2)
options = ['hadoop_jar_cmd', 'presto_cmd', 'db_query', 'spark_cmd']
branching = BranchPythonOperator(
task_id='branching',
python_callable=lambda: random.choice(options),
dag=dag)
branching.set_upstream(t3)
join = DummyOperator(task_id='join', trigger_rule='one_success', dag=dag)
t4 = QuboleOperator(
task_id='hadoop_jar_cmd',
command_type='hadoopcmd',
sub_command=
'jar s3://paid-qubole/HadoopAPIExamples/jars/hadoop-0.20.1-dev-streaming.jar -mapper wc -numReduceTasks 0 -input s3://paid-qubole/HadoopAPITests/data/3.tsv -output s3://paid-qubole/HadoopAPITests/data/3_wc',
cluster_label='default',
fetch_logs=True,
dag=dag)
t5 = QuboleOperator(
task_id='pig_cmd',
command_type="pigcmd",
html_content='Check out the latest!!',
files=['{}/latest_links.txt'.format(RAW_TWEET_DIR)],
dag=dag)
sub = SubDagOperator(subdag=subdag,
task_id='insert_and_id_pop',
trigger_rule='one_success',
dag=dag)
clear_latest = BashOperator(bash_command='rm -rf {}/latest_links.txt'.format(
RAW_TWEET_DIR), task_id='clear_latest', dag=dag)
gen_search_terms.set_upstream(fill_search_terms)
for term in SEARCH_TERMS:
term_without_punctuation = re.sub(r'\W+', '', term)
simple_search = PythonOperator(
task_id='search_{}_twitter'.format(term_without_punctuation),
provide_context=True,
python_callable=search_twitter,
dag=dag,
params={'query': term})
simple_search.set_upstream(gen_search_terms)
simple_search.set_downstream(sub)
sub.set_downstream(email_links)
email_links.set_downstream(clear_latest)
task_id='compare_result',
provide_context=True,
python_callable=compare_result,
trigger_rule="all_done",
dag=dag)
t3.set_upstream(t1)
t3.set_upstream(t2)
options = ['hadoop_jar_cmd', 'presto_cmd', 'db_query', 'spark_cmd']
branching = BranchPythonOperator(
task_id='branching',
python_callable=lambda: random.choice(options),
dag=dag)
branching.set_upstream(t3)
join = DummyOperator(
task_id='join',
trigger_rule='one_success',
dag=dag
)
t4 = QuboleOperator(
task_id='hadoop_jar_cmd',
command_type='hadoopcmd',
sub_command='jar s3://paid-qubole/HadoopAPIExamples/jars/hadoop-0.20.1-dev-streaming.jar -mapper wc -numReduceTasks 0 -input s3://paid-qubole/HadoopAPITests/data/3.tsv -output s3://paid-qubole/HadoopAPITests/data/3_wc',
cluster_label='default',
fetch_logs=True,
subject='Latest popular links',
html_content='Check out the latest!!',
files=['{}/latest_links.txt'.format(RAW_TWEET_DIR)],
dag=dag)
sub = SubDagOperator(subdag=subdag,
task_id='insert_and_id_pop',
trigger_rule='one_success',
dag=dag)
clear_latest = BashOperator(
bash_command='rm -rf {}/latest_links.txt'.format(RAW_TWEET_DIR),
task_id='clear_latest',
dag=dag)
gen_search_terms.set_upstream(fill_search_terms)
for term in SEARCH_TERMS:
term_without_punctuation = re.sub(r'\W+', '', term)
simple_search = PythonOperator(
task_id='search_{}_twitter'.format(term_without_punctuation),
provide_context=True,
python_callable=search_twitter,
dag=dag,
params={'query': term})
simple_search.set_upstream(gen_search_terms)
simple_search.set_downstream(sub)
sub.set_downstream(email_links)
email_links.set_downstream(clear_latest)
def create_dag(dag_id, schedule, start_date, delta_sensor, airpots_codes,
default_args):
dag = DAG(dag_id,
schedule_interval=schedule,
start_date=start_date,
default_args=default_args)
dag.doc_md = """
# DAG fetching data from smiles.com.ar
### procesing and dumping on postgresql
"""
"""start = TimeDeltaSensor(
task_id='wait_to_start',
delta=timedelta(minutes=delta_sensor),
dag=dag)"""
start = DummyOperator(task_id="start", dag=dag)
branches = []
def return_dates_branches(**kwargs):
return branches
gen_url_branch = BranchPythonOperator(
task_id='generate_url_dates',
provide_context=True,
python_callable=return_dates_branches,
dag=dag)
def transform_data(**kwargs):
ti = kwargs['ti']
raw_data = ti.xcom_pull(task_ids=return_dates_branches())
data = []
logging.info(raw_data)
if raw_data is not None:
flat_list = [item for sublist in raw_data for item in sublist]
for row in flat_list:
row = list(row)
# add À-ÿ for spanish accents
date = '/'.join(
list(
re.compile("([A-ZÀ-ÿ]+)(\d+)([A-ZÀ-ÿ]+)").split(
row[1]))[2:4])
date = dateparser.parse(date,
languages=['pt', 'es'],
date_formats=['%d/%b'
]).strftime('%Y-%m-%d')
row[1] = date
td = row[4].split(':')
row[4] = str(timedelta(hours=int(td[0]), minutes=int(td[1])))
row[5] = int(row[5].replace('.', ''))
row[6] = int(row[6].replace('.', ''))
row[8] = row[8].split(' ')[-1]
row.insert(0, datetime.now().strftime('%Y-%m-%d'))
data.append(tuple(row))
return data
else:
print('No se recibio datos')
t2 = PythonOperator(
task_id='transform_data',
python_callable=transform_data,
depends_on_past=True,
trigger_rule=TriggerRule.ALL_SUCCESS,
provide_context=True,
dag=dag,
)
t2.doc_md = """
#### Task Documentation
Transform fetched data
@return a list of tuples
"""
# def gen_url_dates(**kwargs):
date_start = read_scraped_date(airpots_codes)
date_end = date_start + timedelta(days=AMOUNT_DAYS)
date_generated = [
date_start + timedelta(days=x)
for x in range(0, (date_end - date_start).days)
]
for i, date in enumerate(date_generated):
date_ml = str(date.timestamp())[:8] + '00000'
url_dated = """https://www.smiles.com.ar/emission?originAirportCode={}&destinationAirportCode={}&departureDate={}&adults=1&children=0&infants=0&isFlexibleDateChecked=false&tripType=3¤cyCode=BRL&segments=2&departureDate2={}&originAirportCode2={}&destinationAirportCode2={}""".format(
airpots_codes[0][0], airpots_codes[1], date_ml, date_ml,
airpots_codes[0][1], airpots_codes[1])
get_data_op = PythonOperator(
task_id='get_data_{}and{}to{}_{}'.format(airpots_codes[0][0],
airpots_codes[0][1],
airpots_codes[1], i),
python_callable=get_data_URL,
op_kwargs={'URL': url_dated},
trigger_rule=TriggerRule.ONE_SUCCESS,
provide_context=True,
dag=dag,
)
branches.append(get_data_op.task_id)
get_data_op.set_upstream(gen_url_branch)
get_data_op.set_downstream(t2)
get_data_op.doc_md = """
#### Task Documentation
Fetch data from passed url
return list of semi-parsed data
"""
insert_data = PythonOperator(
task_id='insert_data',
python_callable=insert_into_table,
provide_context=True,
dag=dag,
)
insert_data.doc_md = """
#### Task Documentation
Insert parsed and transformed data into table
"""
t2.set_downstream(insert_data)
gen_url_branch.set_upstream(start)
return dag
