我正在尝试用python连接AWS雅典娜。我正在尝试使用pyathenajdbc来完成这个任务。我现在的问题是获得一种联系。当我运行下面的代码时,我会收到一条错误消息,说明它找不到AthenaDriver。( java.lang.RuntimeException:未找到类com.amazonaws.athena.jdbc.AthenaDriver )。我从AWS下载了这个文件,并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)回溯(最近一次调用):文件“/usr/lib64 64/python2.7/runpy.py”,第174行,在_run_module_as_main "main“中,fname,,pkg_name) File”/usr/lib64 64/python2.7/runpy.py“,第72行,在run_globals文件第53行中的_run_code exec代码在rtn = main() "/home/ec2-user/jason_testing/mdpbi/rsi/athena/main.py",第39行中,在主driver_path=athena_jdbc_driver_path文件"/opt/mdpbi/Python_Envs/2.7.10/local/lib/python2.7/dist-packages/pyathenajdbc/init.py",第65行中,在connect driver_path中,**kwargs)文件"/opt/mdpbi/Python_Envs/2.7.10/local/lib/python2.7/dist-packages/pyathenajdbc/connection.py",第68行,init jpype.JClass(ATHENA_DRIVER_CLASS_NAME) File jpype.JClass(ATHENA_DRIVER_CLASS_NAME) File JClass _RUNTIMEEXCEPTION.PYEXC("Class %s not“% name)
发布于 2017-03-27 17:03:04
JDBC驱动程序需要Java 8。我目前正在运行Java 7。我能够在EC2实例上安装另一个版本的Java。
https://tecadmin.net/install-java-8-on-centos-rhel-and-fedora/#
我还必须在代码中设置java版本。通过这些更改,代码现在按预期运行。
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)发布于 2017-03-27 09:19:18
试试这个:
pyathenajdbc.ATHENA_JAR = ATHENA_JDBC_CLASSPATH您不需要在连接方法中指定driver_path参数
https://stackoverflow.com/questions/43006368
复制相似问题