实例讲解hadoop中的hive查询(python语言实现) 实践检验真理 51CTO技术博客

from hive_service import ThriftHive
from hive_service.ttypes import HiveServerException
from thrift import Thrift
from thrift.transport import TSocket
from thrift.transport import TTransport
from thrift.protocol import TBinaryProtocol

def hiveExe(hsql,dbname):
#定义hive查询函数
try:
transport = TSocket.TSocket('192.168.10.1', 10000)
transport = TTransport.TBufferedTransport(transport)
protocol = TBinaryProtocol.TBinaryProtocol(transport)

client = ThriftHive.Client(protocol)
transport.open()

client.execute('ADD jar /opt/modules/hive/hive-0.7.1/lib/hive-contrib-0.7.1.jar')

client.execute("use "+dbname)
row = client.fetchOne()
#使用库名，只需一次fetch，用fetchOne

client.execute(hsql)
return client.fetchAll()
#查询所有数据，用fetchAll()

transport.close()

except Thrift.TException, tx:
print '%s' % (tx.message)

def mysqlExe(sql):
try:
conn = MySQLdb.connect(user="test",passwd="test123",host="127.0.0.1",db="active2_ip",port=5029)
except Exception,data:
print "Could not connect to MySQL server.:",data
try:
cursor = conn.cursor()
cursor.execute(sql)
return row
cursor.commit()
cursor.close()
conn.close()
except Exception,data:
print "Could not Fetch anything:",data

dbname = "active2"
date = os.popen("date -d '1 day ago' +%Y%m%d").read().strip()
#shell方式取昨天日期，读取并去前后\n
date.close()

sql = "create table IF NOT EXISTS "+dbname+"_group_ip_"+date+" like "+dbname+"_group_ip;load data infile '/tmp/"+dbname+"_"+date+".csv' into table "+dbname+"_group_ip_"+date+" FIELDS TERMINATED BY ','"
#以模板表创建日期表，并load data到该表中

hsql = "insert overwrite local directory '/tmp/"+dbname+"_"+date+"' select count(version) as vc,stat_hour,type,version,province,city,isp from "+dbname+"_"+date+" group by province,city,version,type,stat_hour,isp"
#hive查询，并将查询结果导出到本地/tmp/active2_20111129目录下，可能生成多个文件

hiveExe(hsql, dbname)
#执行查询

os.system("sudo cat /tmp/"+dbname+"_"+date+"/* > /tmp/tmplog ")
#将多个文件通过shell合并为一个文件tmplog

file1 = open("/tmp/tmplog", 'r')
#打开合并后的临时文件
file2 = open("/tmp/"+dbname+"_"+date+".csv",'w')
#打开另一个文件，做文字替换。因为hive导出结果，其分隔符为特殊字符。所以需要做替换，格式为csv，故用逗号分隔
sep = ','
for line in file1:
tmp = line[:-1].split('\x01')
#hive导出文件分隔符为ascii中的001，\x01是16进制，但其实也就是十进制的1
replace = sep.join(tmp)
file2.write(replace+"\n")

file1.close()
file2.close()

os.system("sudo rm -f /tmp/tmplog")
#删除临时的tmplog

mysqlExe(sql)
#执行mysql查询，创建表和加载数据。
os.system("sudo rm -f /tmp/"+dbname+"_"+date)