Athena on Python Demo

demo.py

import os

import pyathenajdbc as athena

conn = athena.connect(access_key=os.environ['AWS_ACCESS_KEY_ID'],
               secret_key=os.environ['AWS_SECRET_ACCESS_KEY'],
               s3_staging_dir='s3://aws-athena-query-results-123456789012345-us-west-2/',
               region_name=os.environ['AWS_REGION'])

try:
    with conn.cursor() as cursor:
        cursor.execute("""
            SELECT
                COUNT(created_at)
            FROM
                sampledb.events
            WHERE
                dt > '2017-03-02' AND dt < '2017-03-04'
            LIMIT 1000
        """)

        print(cursor)
        print(cursor.description)
        print(cursor.fetchall())
finally:
    conn.close()

Dockerfile

FROM openjdk:8u121-jre

WORKDIR /tmp

RUN echo "Install OS dependencies.." && \
    apt-get update && \
    apt-get -y install python python-dev python-pip && \
    echo "Fixing pip packaging with manual update.." && \
    apt-get purge -y python-pip && \
    wget https://bootstrap.pypa.io/get-pip.py && \
    python ./get-pip.py && \
    apt-get install python-pip

COPY requirements.txt .

RUN echo "Install app dependencies.." && \
    pip install -r requirements.txt

WORKDIR /athena

COPY run.sh /

CMD ["/run.sh"]

requirements.txt

PyAthenaJDBC==1.0.6

run.sh

#!/bin/sh

tail -f /dev/null