資源簡(jiǎn)介
hive spark hadoop

代碼片段和文件信息
#!/usr/bin/env?python2.7
#?-*-?coding:?utf-8?-*-
#coding=utf-8
#===============================================================================
#
#?????????FILE:?collect_sms_ready_snowball.py
#
#????????USAGE:?python?collect_sms_ready_snowball.py?時(shí)間參數(shù)1(YYYYMMDD)?時(shí)間參數(shù)2(YYYYMMDD)
#
#??DEscriptION:
#
#??????OPTIONS:?---
#?REQUIREMENTS:
#?????????BUGS:?---
#????????NOTES:?---
#???????AUTHOR:?penghao.qiao
#??????COMPANY:?MSXF
#??????VERSION:?1.0
#??????CREATED:?
#?????REVIEWER:
#?????REVISION:?---
#????TGT_TABLE:
#===============================================================================
import?MySQLdb
import?sys
import?os
import?string
import?datetime
import?time
sys.path.append(os.getenv(‘BDP_CONN‘));import?aes?as?ConfigParser
from?BdpConnector?import?*
from?Calendar?import?*
from?HiveTasks?import?*
import?traceback
reload(sys)
sys.setdefaultencoding(?“utf-8“?)
config=ConfigParser.ConfigParser()
config.read(“/home/hadoop/edw/etl/conf/etl.ini“)
tag_db?=?‘x_sell‘
tag_tab?=?‘collect_sms_ready_snowball‘
src_db=?‘fdl‘
src_tab?=?‘fdl_cust_info_chainfdl_acct_det_chainfdl_loanrpy_plan_chainfdl_loanbor_term_chain‘
hts?=?HiveTasks(tag_dbtag_tab)
dte=Calendar(datetime.datetime.today())
#字符型起始日期
v_statbgdate?=?sys.argv[1]
#字符型結(jié)束日期
v_stateddate?=?sys.argv[2]
#日期型起始日期
v_start_date?=?datetime.datetime.strptime(v_statbgdate‘%Y%m%d‘).date()
#日期型結(jié)束日期
v_end_date???=?datetime.datetime.strptime(v_stateddate‘%Y%m%d‘).date()
#當(dāng)前時(shí)間
v_run_time?=?datetime.datetime.now().strftime(“%Y-%m-%d?%H:%M:%S“)
#當(dāng)前日期
v_run_date?=?datetime.datetime.now().strftime(“%Y%m%d“)
#etl抽數(shù)日期
v_etl_date??=?datetime.datetime.now().strftime(“%Y-%m-%d?%H:%M:%S“)
#T+1統(tǒng)計(jì)日期
v_yest_date?=?dte.getDayBefore(‘‘)
#前天日期
v_bf_yest_date?=?dte.getDayBeforeN(‘‘2)
#對(duì)時(shí)間參數(shù)進(jìn)行處理
if?v_statbgdate.strip()==‘‘?and?v_stateddate.strip()==‘‘:
????v_statbgdate=v_yest_date
????v_stateddate=v_yest_date
elif?v_statbgdate.strip()!=‘‘?and?v_stateddate.strip()==‘‘:
????v_stateddate=v_statbgdate
elif?v_statbgdate.strip()==‘‘?and?v_stateddate.strip()!=‘‘:
????v_statbgdate=v_stateddate
#定義lzo數(shù)據(jù)索引路徑
lzo_index_path=None
#定義該表數(shù)據(jù)是否要壓縮
lzo_compress?=?False
#定義是否有分區(qū)
is_partition?=?True
#定義數(shù)據(jù)文件是否要做合并
merge_flag?=?False
#合并文件路徑
merge_part_dir?=?None
#定義是否需要做表解析
parse_flag?=?False
#################Need?user?configure?the?parameters####################
v_begin_time=datetime.datetime.now().strftime(“%Y-%m-%d?%H:%M:%S“)
conn=MySQLdb.connect(host=config.get(“MYSQL_DB““IP“)port=int(config.get(“MYSQL_DB““PORT“))user=config.get(“MYSQL_DB““USERNAME“)passwd=config.get(“MYSQL_DB““PASSWORD“)db=config.get(“MYSQL_DB““DB“))
cur=conn.cursor()
v_sql?=?“““
????set?hive.exec.max.dynamic.partitions=100000;
????set?hive.exec.max.dynamic.partitions.pernode=100000;
????set?fs.hdfs.impl.disable.cache?=?true;
????use?fdl;
????-------篩選出一對(duì)一,一對(duì)多(合同)數(shù)據(jù)去除和包產(chǎn)品----------
????drop?table?if?exists??tmp.tmp_collect_sms_ready_snowball_01;
??
?屬性????????????大小?????日期????時(shí)間???名稱
-----------?---------??----------?-----??----
?????文件?????????25??2018-03-01?11:35??edwsc
?????文件????????303??2018-03-01?11:34??edwsc
?????文件?????????73??2018-03-01?11:34??edwsc
?????文件?????????23??2018-03-01?11:34??edwsc
?????文件????????478??2018-03-01?11:34??edwsc
?????文件????????896??2018-03-01?11:34??edwsc
?????文件????????189??2018-03-01?11:34??edwsc
?????文件????????424??2018-03-01?11:34??edwsc
?????文件???????1642??2018-03-01?11:34??edwsc
?????文件???????1348??2018-03-01?11:34??edwsc
?????文件???????4951??2018-03-01?11:34??edwsc
?????文件????????544??2018-03-01?11:34??edwsc
?????文件???????1239??2018-03-01?11:34??edwsc
?????文件???????3610??2018-03-01?11:34??edwsc
?????文件?????142544??2018-03-01?11:35??edwsc
?????文件????????240??2018-03-01?11:34??edwsc
?????文件????????350??2018-03-01?11:35??edwsc
?????文件????????350??2018-03-01?11:35??edwsc
?????文件????????185??2018-03-01?11:34??edwsc
?????文件????????147??2018-03-01?11:35??edwsc
?????文件???????1929??2018-03-01?11:35??edwsc
?????文件????????268??2018-03-01?11:35??edwsc
?????文件????????189??2018-03-01?11:35??edwsc
?????文件????????165??2018-03-01?11:35??edwsc
?????文件????????282??2018-03-01?11:35??edwsc
?????文件????????325??2018-03-01?11:35??edwsc
?????文件?????365688??2018-03-01?11:34??edwsc
?????文件????4953896??2018-03-01?11:34??edwsc
?????文件????????594??2018-03-01?11:34??edwsc
?????文件?????????41??2018-03-01?11:35??edwsc
............此處省略1374個(gè)文件信息
評(píng)論
共有 條評(píng)論