方法一
from pyhive import hive
import traceback
class Hive_tool:
def __init__(self):
self.conn = hive.Connection(host="******", port=1****, database='ods')
self.cur = self.conn.cursor()
def execute(self, sql):
try:
if sql:
self.cur.execute(sql)
result = self.cur.fetchall()
return result
except:
traceback.print_exc()
finally:
self.cur.close()
self.conn.close()
方法二
import pandas as pd
from sqlalchemy import create_engine
engine = create_engine('hive://IP:port/dbname')
sql = """
你的hive sql内容
"""
data = pd.read_sql(sql,con=engine)
data.head()
len(data)
data.to_csv('文件名字.csv',index=False)