Conda 安装Jupyter：使用Pyhive（Kerberos）

yum install gcc–c++ python–devel.x86_64 c y rus–sasl–devel.x86_64

Jup y t e r No t e book

conda install nb_conda_kernels

配置 jupyter，添加密码，允许root，设置 启动 目录

环境配置-为linux服务器配置可以远程访问的Jupyter – 知乎 (zhihu.com)

jupyter notebook 启动，以下报错可忽略

Attr i buteEr ro r: ‘Note bookApp‘ object has no attr i bute ‘io_loop‘

PyHi ve连接 开启Ker beros的Hive

jupyter notebook 部署的服务器为集群已配置Kerberos 认证的服务器，否则需要配置客户端认证

from pyhive import hive
import pandas as pd
import numpy as np
import time

def func_time(func):
    def wrapper(*args, **kwargs):
        start_time = time.time()
        result = func(*args, **kwargs)
        end_time = time.time()

        execution_time = end_time - start_time
        print(f"函数 {func.__name__} 的执行时间为：{execution_time} 秒")

        return result

    return wrapper


class HiveCursor:
    def __init__(self, host, port, db, auth, username, configuration={'hive.execution.engine': 'spark'}):
        self.host = host
        self.port = port
        self.db = db
        self.username = username
        self.auth = auth
        self.conn = None
        self.cursor = None
        self.configuration = configuration

    def __enter__(self):
        # 建立与 Hive 的连接
        if self.auth == "KERBEROS":
            self.conn = hive.Connection(host=self.host, port=self.port, database=self.db,
                                        kerberos_service_name=self.username,
                                        auth=self.auth, configuration=self.configuration)
        else:
            self.conn = hive.Connection(host=self.host, port=self.port, database=self.db, username=self.username,
                                        auth=self.auth, configuration=self.configuration)
        self.cursor = self.conn.cursor()
        return self

    def query(self, sql):
        self.cursor.execute(sql)
        # 将查询结果读取到 DataFrame
        df = pd.DataFrame(self.cursor.fetchall())
        # 设置 DataFrame 列名
        df.columns = [desc[0] for desc in self.cursor.description]
        return df

    def __exit__(self, exc_type, exc_val, exc_tb):
        # 关闭连接
        self.conn.close()


@func_time
def hive_kerberos():
    query = "show databases"

    with HiveCursor(host="master", port=10000, db="default", auth='KERBEROS',
                    username='hive') as _hive:
        result = _hive.query(sql)
        print(result)


@func_time
def hive_on_spark():
    query = "show databases"

    with HiveCursor(host="master", port=10000, db="default", auth='KERBEROS',
                    username='hive', configuration={'hive.execution.engine': 'spark'}) as _hive:
        df = _hive.query(sql)
        print(df)