1.搜集数据
upload.job
#upload.job
type=command
command=bash upload.sh
upload.sh
#!/bin/bash
#set java env
export JAVA_HOME=/soft/jdk/
export JRE_HOME=${JAVA_HOME}/jre
export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib
export PATH=${JAVA_HOME}/bin:$PATH
#set hadoop env
export HADOOP_HOME=/soft/hadoop/
export PATH=${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin:$PATH
#日志文件存放的目录
log_src_dir=/home/centos/logs/log/
#待上传文件存放的目录
log_toupload_dir=/home/centos/logs/toupload/
#得到昨天的日期
day_01=`date -d'-1 day' +%Y-%m-%d`
#得到昨天的年份
syear=`date --date=$day_01 +%Y`
#得到昨天的月份
smonth=`date --date=$day_01 +%m`
#得到昨天的日份
sday=`date --date=$day_01 +%d`
#日志文件上传到hdfs的根路径
hdfs_root_dir=/data/clickLog/$syear/$smonth/$sday
#创建hdfs上的路径文件夹
hadoop fs -mkdir -p $hdfs_root_dir
#读取日志文件的目录,判断是否有需要上传的文件
ls $log_src_dir | while read fileName
do
if [[ "$fileName" == access.log ]]; then
# if [ "access.log" = "$fileName" ];then
date=`date +%Y_%m_%d_%H_%M_%S`
#将文件移动到待上传目录并重命名
mv $log_src_dir$fileName $log_toupload_dir"xxxxx_click_log_$fileName"$date
#将待上传的文件path写入一个列表文件willDoing
echo $log_toupload_dir"xxxxx_click_log_$fileName"$date >> $log_toupload_dir"willDoing."$date
fi
done
#找到列表文件willDoing
ls $log_toupload_dir | grep will |grep -v "_COPY_" | grep -v "_DONE_" | while read line
do
#将待上传文件列表willDoing改名为willDoing_COPY_
mv $log_toupload_dir$line $log_toupload_dir$line"_COPY_"
#读列表文件willDoing_COPY_的内容(一个一个的待上传文件名) ,此处的line 就是列表中的一个待上传文件的path
cat $log_toupload_dir$line"_COPY_" |while read line
do
hadoop fs -put $line $hdfs_root_dir
done
mv $log_toupload_dir$line"_COPY_" $log_toupload_dir$line"_DONE_"
done
2.清洗数据
clean.job
# clean.job
type=command
dependencies=upload
command=bash clean.sh
clean.sh
#!/bin/bash
#set java env
export JAVA_HOME=/soft/jdk
export JRE_HOME=${JAVA_HOME}/jre
export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib
export PATH=${JAVA_HOME}/bin:$PATH
#set hadoop env
export HADOOP_HOME=/soft/hadoop
export PATH=${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin:$PATH
#获取昨天的日期
day_01=`date -d'-1 day' +%Y-%m-%d`
#获取昨天的年份
syear=`date --date=$day_01 +%Y`
#获取昨天的月份
smonth=`date --date=$day_01 +%m`
#获取昨天的日份
sday=`date --date=$day_01 +%d`
#日志在hdfs上的路径
log_hdfs_dir=/data/clickLog/$syear/$smonth/$sday
#mapreduce程序的入口路径
click_log_clean=clickLog.AccessLogDriver
#清洗后的数据路径
clean_dir=/cleaup/$syear/$smonth/$sday
#清洗后的数据路径不可存在(删除操作)
hadoop fs -rm -r -f $clean_dir
#运行mapreduce程序的jar文件(jar文件的位置;程序的入口路径;数据输入路径;数据输出路径)
hadoop jar /home/centos/hivedemo/mrclick.jar $click_log_clean $log_hdfs_dir $clean_dir
3.数据绑定到hive
hivesql.job
# hivesql.job
type=command
dependencies=clean
command=bash hivesql.sh
hivesql.sh
#!/bin/bash
#set java env
export JAVA_HOME=/soft/jdk
export JRE_HOME=${JAVA_HOME}/jre
export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib
export PATH=${JAVA_HOME}/bin:$PATH
#set hadoop env
export HADOOP_HOME=/soft/hadoop
export PATH=${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin:$PATH
#set hive env
export HIVE_HOME=/soft/hive
export PATH=${HIVE_HOME}/bin:$PATH
#获取昨天的日期
day_01=`date -d'-1 day' +%Y-%m-%d`
#获取昨天的年份
syear=`date --date=$day_01 +%Y`
#获取昨天的月份
smonth=`date --date=$day_01 +%m`
#获取昨天的日份
sday=`date --date=$day_01 +%d`
#清洗后的数据在hdfs上的路径
clean_dir=/cleaup/$syear/$smonth/$sday
#hive sql 导入数据到hive
HQL_origin="load data inpath '$clean_dir' into table mydb.accesslog"
#执行sql语句
hive -e "$HQL_origin"
4.查询数据
ip.job
# ip.job
type=command
dependencies=hivesqljob
command=bash ip.sh
ip.sh
#!/bin/bash
#set java env
export JAVA_HOME=/soft/jdk
export JRE_HOME=${JAVA_HOME}/jre
export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib
export PATH=${JAVA_HOME}/bin:$PATH
#set hadoop env
export HADOOP_HOME=/soft/hadoop
export PATH=${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin:$PATH
#set hive env
export HIVE_HOME=/soft/hive
export PATH=${HIVE_HOME}/bin:$PATH
#hive sql 从一张表查询出数据放到结果集表中
HQL_origin="insert into mydb.upflow select ip,sum(upflow) as sum from mydb.accesslog group by ip order by sum desc "
#执行sql语句
hive -e "$HQL_origin"
5.导出到mysql
mysql.job
# mysql.job
type=command
dependencies=ipjob
command=bash mysql.sh
mysql.sh
#!/bin/bash
#set java env
export JAVA_HOME=/soft/jdk
export JRE_HOME=${JAVA_HOME}/jre
export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib
export PATH=${JAVA_HOME}/bin:$PATH
#set hadoop env
export HADOOP_HOME=/soft/hadoop
export PATH=${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin:$PATH
#set hive env
export HIVE_HOME=/soft/hive
export PATH=${HIVE_HOME}/bin:$PATH
#set sqoop env
export SQOOP_HOME=/soft/sqoop
export PATH=${SQOOP_HOME}/bin:$PATH
#sqoop语句 从hive导出到mysql(导出到mysql的表中从hive的路径文件下)
sqoop export --connect jdbc:mysql://s201:3306/userdb --username sqoop --password sqoop --table upflow --export-dir /user/hive/warehouse/mydb.db/upflow --input-fields-terminated-by ','
五个job有依赖关系