Files
Lakehouse/config/spark-jobs/consumer.py
T
Lakehouse Admin df5ec93dc3 Full lab documentation and infrastructure as code
- Trino catalogs, Grafana, Spark jobs, LDAP LDIF, NPM compose
- Airflow DAG scripts, Proxmox VM inventory, network docs
- Ansible playbook, Gitea CI validate workflow
- Backup and health-check scripts, cron documentation
- Homepage DOCS tab with links to all documentation
- Extended collect-fleet-config.sh and populate-repo.py
2026-05-19 23:12:41 +02:00

39 lines
1013 B
Python

from kafka import KafkaConsumer
import boto3
import json
from datetime import datetime
KAFKA_BROKER = "10.0.21.36:9092"
KAFKA_TOPIC = "test-lakehouse"
S3_ENDPOINT = "http://10.0.20.111:9020"
S3_BUCKET = "data"
S3_ACCESS_KEY = "REDACTED"
S3_SECRET_KEY = "REDACTED"
print("Starting consumer...")
print(f"Kafka: {KAFKA_BROKER}, Topic: {KAFKA_TOPIC}")
print(f"S3: {S3_ENDPOINT}, Bucket: {S3_BUCKET}")
s3 = boto3.client(
's3',
endpoint_url=S3_ENDPOINT,
aws_access_key_id=S3_ACCESS_KEY,
aws_secret_access_key=S3_SECRET_KEY,
use_ssl=False,
verify=False
)
consumer = KafkaConsumer(
KAFKA_TOPIC,
bootstrap_servers=[KAFKA_BROKER],
auto_offset_reset='earliest',
value_deserializer=lambda x: json.loads(x.decode('utf-8'))
)
print("Waiting for messages...")
for msg in consumer:
ts = datetime.now().strftime('%Y%m%d_%H%M%S_%f')
key = f"kafka/{KAFKA_TOPIC}/msg_{ts}.json"
s3.put_object(Bucket=S3_BUCKET, Key=key, Body=json.dumps(msg.value))
print(f"Written: {key}")