使用 Python 和 pyathenajdbc 连接 Athena

Connecting with Athena using Python and pyathenajdbc

我正在尝试使用 python 连接到 AWS Athena。我正在尝试使用 pyathenajdbc 来完成这项任务。我遇到的问题是获得连接。当我 运行 下面的代码时,我收到一条错误消息,指出找不到 AthenaDriver。 ( java.lang.RuntimeException: Class com.amazonaws.athena.jdbc.AthenaDriver 未找到)。我确实从 AWS 下载了这个文件,我已经确认它位于该目录中。

from mdpbi.rsi.config import *
from mdpbi.tools.functions import mdpLog
from pkg_resources import resource_string
import argparse
import os
import pyathenajdbc
import sys

SCRIPT_NAME = "Athena_Export"

ATHENA_JDBC_CLASSPATH = "/opt/amazon/athenajdbc/AthenaJDBC41-1.0.0.jar"
EXPORT_OUTFILE = "RSI_Export.txt"
EXPORT_OUTFILE_PATH = os.path.join(WORKINGDIR, EXPORT_OUTFILE)


def get_arg_parser():
    """This function returns the argument parser object to be used with this script"""
    parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)

    return parser


def main():
    args = get_arg_parser().parse_args(sys.argv[1:])
    logger = mdpLog(SCRIPT_NAME, LOGDIR)

    SQL = resource_string("mdpbi.rsi.athena.resources", "athena.sql")

    conn = pyathenajdbc.connect(
        s3_staging_dir="s3://athena",
        access_key=AWS_ACCESS_KEY_ID,
        secret_key=AWS_SECRET_ACCESS_KEY,
        region_name="us-east-1",
        log_path=LOGDIR,
        driver_path=ATHENA_JDBC_CLASSPATH
    )
    try:
        with conn.cursor() as cursor:
            cursor.execute(SQL)
            logger.info(cursor.description)
            logger.info(cursor.fetchall())
    finally:
        conn.close()

    return 0


if __name__ == '__main__':
    rtn = main()
    sys.exit(rtn)

Traceback (most recent call last): File "/usr/lib64/python2.7/runpy.py", line 174, in _run_module_as_main "main", fname, loader, pkg_name) File "/usr/lib64/python2.7/runpy.py", line 72, in _run_code exec code in run_globals File "/home/ec2-user/jason_testing/mdpbi/rsi/athena/main.py", line 53, in rtn = main() File "/home/ec2-user/jason_testing/mdpbi/rsi/athena/main.py", line 39, in main driver_path=athena_jdbc_driver_path File "/opt/mdpbi/Python_Envs/2.7.10/local/lib/python2.7/dist-packages/pyathenajdbc/init.py", line 65, in connect driver_path, **kwargs) File "/opt/mdpbi/Python_Envs/2.7.10/local/lib/python2.7/dist-packages/pyathenajdbc/connection.py", line 68, in init jpype.JClass(ATHENA_DRIVER_CLASS_NAME) File "/opt/mdpbi/Python_Envs/2.7.10/lib64/python2.7/dist-packages/jpype/_jclass.py", line 55, in JClass raise _RUNTIMEEXCEPTION.PYEXC("Class %s not found" % name)

试试这个:

    pyathenajdbc.ATHENA_JAR = ATHENA_JDBC_CLASSPATH

您将不需要在连接方法中指定 driver_path 参数

JDBC 驱动程序需要 Java 8. 我目前是 运行 Java 7. 我能够在 EC2 上安装另一个版本的 Java实例.

https://tecadmin.net/install-java-8-on-centos-rhel-and-fedora/#

我还必须在我的代码中设置 java 版本。通过这些更改,代码现在可以按预期运行。

from mdpbi.rsi.config import *
from mdpbi.tools.functions import mdpLog
from pkg_resources import resource_string
import argparse
import os
import pyathenajdbc
import sys

SCRIPT_NAME = "Athena_Export"


def get_arg_parser():
    """This function returns the argument parser object to be used with this script"""
    parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)

    return parser


def main():
    args = get_arg_parser().parse_args(sys.argv[1:])
    logger = mdpLog(SCRIPT_NAME, LOGDIR)

    SQL = resource_string("mdpbi.rsi.athena.resources", "athena.sql")

    os.environ["JAVA_HOME"] = "/opt/jdk1.8.0_121"
    os.environ["JRE_HOME"] = "/opt/jdk1.8.0_121/jre"
    os.environ["PATH"] = "/opt/jdk1.8.0_121/bin:/opt/jdk1.8.0_121/jre/bin"

    conn = pyathenajdbc.connect(
        s3_staging_dir="s3://mdpbi.data.rsi.out/",
        access_key=AWS_ACCESS_KEY_ID,
        secret_key=AWS_SECRET_ACCESS_KEY,
        schema_name="rsi",
        region_name="us-east-1"
    )
    try:
        with conn.cursor() as cursor:
            cursor.execute(SQL)
            logger.info(cursor.description)
            logger.info(cursor.fetchall())
    finally:
        conn.close()

    return 0


if __name__ == '__main__':
    rtn = main()
    sys.exit(rtn)