jupyter_presto.py

# !pip install git+https://github.com/dropbox/PyHive.git@437eefa7bceda1fd27051e5146e66cb8e4bdfea1
# !pip install requests-kerberos

import os
import socket
from pyhive import presto

def get_presto_cursor(
    host="an-coord1001.eqiad.wmnet",
    port=8281,
    catalog='analytics_hive',
    protocol='https',
    source='Presto Jupyter - {}@{}'.format(os.geteuid, socket.gethostname()),
    ca_crt='/etc/presto/ca.crt.pem',
    KerberosConfigPath="/etc/krb5.conf",
    KerberosPrincipal="{}@WIKIMEDIA".format(os.getenv('USER')),
    KerberosRemoteServiceName="presto",
    KerberosCredentialCachePath='/tmp/krb5cc_{}'.format(os.geteuid())
):

    requests_kwargs = {
        proxies: {
            'http': None, 'https': None
        }
    }
    if ca_crt:
        requests_kwargs['verify'] = ca_crt


    presto_cursor = presto.Cursor(
        host=host,
        port=port,
        catalog=catalog,
        protocol=protocol,
        requests_kwargs=requests_kwargs,
        KerberosConfigPath=KerberosConfigPath,
        KerberosPrincipal=KerberosPrincipal,
        KerberosRemoteServiceName=KerberosRemoteServiceName,
        KerberosCredentialCachePath=KerberosCredentialCachePath
    )

    return presto_cursor