bin/sqoop import \##連接的關(guān)系型數(shù)據(jù)庫(kù)的url,用戶名，密碼--connect jdbc:mysql://hadoop102:3306/test \--username root \--password 123 \##連接的表--table t_emp \##導(dǎo)出數(shù)據(jù)在hdfs上存放路徑--target-dir /sqoopTest \##如果路徑已存在則先刪除--delete-target-dir \##導(dǎo)入到Hdfs上后，每個(gè)字段使用什么參數(shù)進(jìn)行分割--fields-terminated-by "\t" \##要啟動(dòng)幾個(gè)MapTask，默認(rèn)4個(gè)--num-mappers 2 \##數(shù)據(jù)集根據(jù)哪個(gè)字段進(jìn)行切分，切分后每個(gè)MapTask負(fù)責(zé)一部分--split-by id \##要實(shí)現(xiàn)部分導(dǎo)入，加入下面的參數(shù)，表示導(dǎo)入哪些列##columns中如果涉及到多列，用逗號(hào)分隔，分隔時(shí)不要添加空格--columns id,name,age

bin/sqoop import \--connect jdbc:mysql://hadoop102:3306/test \--username root \--password 123 \--table t_emp \##指定過(guò)濾的where語(yǔ)句,where語(yǔ)句最好使用引號(hào)包裹--where 'id>6' \--target-dir /sqoopTest \--delete-target-dir \--fields-terminated-by "\t" \--num-mappers 1 \--split-by?id?

bin/sqoop import \--connect jdbc:mysql://hadoop102:3306/test \--username root \--password 123 \##查詢語(yǔ)句最好使用單引號(hào)##如果query后使用的是雙引號(hào)，則$CONDITIONS前必須加轉(zhuǎn)移符，防止shell識(shí)別為自己的變量--query 'select * from t_emp where id>3 and $CONDITIONS' \--target-dir /sqoopTest \--delete-target-dir \--fields-terminated-by "\t" \--num-mappers 1 \--split-by?id?

bin/sqoop import \--connect jdbc:mysql://hadoop102:3306/test \--username root \--password 123 \--query 'select * from t_emp where id>3 and $CONDITIONS' \--target-dir /sqoopTest \##如果不限定分隔符，那么hive存儲(chǔ)的數(shù)據(jù)將不帶分隔符，之后再想操作很麻煩，所以建議加上--fields-terminated-by "\t" \--delete-target-dir \##導(dǎo)入到hive--hive-import \##是否覆蓋寫(xiě)，不加這個(gè)參數(shù)就是追加寫(xiě)--hive-overwrite \##指定要導(dǎo)入的hive的表名--hive-table t_emp \--num-mappers 1 \--split-by?id

#!/bin/bashimport_data(){$sqoop import \--connect jdbc:mysql://hadoop102:3306/gmall \--username root \--password 123 \--target-dir /origin_data/gmall/db/$1/$do_date \--delete-target-dir \--query "$2 and  \$CONDITIONS" \--num-mappers 1 \--fields-terminated-by '\t' \# 使用壓縮，和指定壓縮格式為lzop--compress \--compression-codec lzop \#將String類(lèi)型和非String類(lèi)型的空值替換為\N,方便Hive讀取--null-string '\\N' \--null-non-string '\\N'}

bin/sqoop import \--connect jdbc:mysql://hadoop102:3306/test \--username root \--password 123 \--query 'select * from t_emp where id>3 and $CONDITIONS' \--target-dir /sqoopTest \--delete-target-dir \##表不存在是否創(chuàng)建--hbase-create-table \##hbase中的表名--hbase-table "t_emp" \##將導(dǎo)入數(shù)據(jù)的哪一列作為rowkey--hbase-row-key "id" \##導(dǎo)入的列族--column-family "info" \--num-mappers 2 \--split-by?id

bin/sqoop export \--connect 'jdbc:mysql://hadoop102:3306/test?useUnicode=true&characterEncoding=utf-8' \--username root \--password 123 \##導(dǎo)出的表名，需要自己提前創(chuàng)建好--table t_emp2 \--num-mappers 1 \##hdfs上導(dǎo)出的數(shù)據(jù)的路徑--export-dir /user/hive/warehouse/t_emp \##hdfs上數(shù)據(jù)的分隔符--input-fields-terminated-by?"\t"

INSERT INTO t_emp2 VALUE(5,'jack',30,3,1111) ON DUPLICATE KEY UPDATE NAME=VALUES(NAME),deptid=VALUES(deptid),empno=VALUES(empno);

bin/sqoop export \--connect 'jdbc:mysql://hadoop103:3306/mydb?useUnicode=true&characterEncoding=utf-8' \--username root \--password 123456 \--table t_emp2 \--num-mappers 1 \--export-dir /hive/t_emp \--input-fields-terminated-by "\t" \--update-key id

bin/sqoop export \--connect 'jdbc:mysql://hadoop103:3306/mydb?useUnicode=true&characterEncoding=utf-8' \--username root \--password 123456 \--table t_emp2 \--num-mappers 1 \--export-dir /hive/t_emp \--input-fields-terminated-by "\t" \--update-key id \--update-mode??allowinsert

bin/sqoop export \--connect 'jdbc:mysql://hadoop103:3306/mydb?useUnicode=true&characterEncoding=utf-8' \--username root \--password 123456 \--table t_emp2 \--num-mappers 1 \--export-dir /hive/t_emp \--input-fields-terminated-by "\t" \--update-key id \--update-mode??allowinsert

sudo mysqlbinlog mysql-bin.000001