需求：数据仓库中所有表的定义结构保存到新的文件中，保存后类似下面数据，重复的数据只保留7月份即可
****************ods_log_info*****************
lid string
uid string
mb_uid string
operation string
module string
result string
ts string
remark1 string
remark2 string
remark3 string
****************ods_mbportal_201407*****************
data_time_thread string
data_module string
data_operation string
data_result string
data_ipaddess string
day string
****************************************************************************
#!/usr/bin/env python
import sys
import re
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
try:
transport = TSocket.TSocket(‘localhost‘, 10000)
transport = TTransport.TBufferedTransport(transport)
protocol = TBinaryProtocol.TBinaryProtocol(transport)
client = ThriftHive.Client(protocol)
transport.open()
query = ‘‘‘
show tables ‘‘‘
client.execute(query)
row = client.fetchAll()
fp = open(r"dw_struct.txt","w")
p = re.compile("201[34][01][0-6|8-9]")
print "Excuting ZZZZZZZZZZ"
for line in row:
m = p.search(line)
if m == None:
qq = "desc " + line
client.execute(qq)
result = client.fetchAll()
fp.write("****************" + line + "*****************\n")
for resLine in result:
if not resLine.startswith("col"):
fp.write(resLine + "\n")
fp.write("\n")
fp.close()
print "Excute OK"
transport.close()
except Thrift.TException, tx:
print ‘%s‘ % (tx.message)