datax离线同步不同数据库数据

##下载datax

cd?/home/yym/

wget http://datax-opensource.oss-cn-hangzhou.aliyuncs.com/datax.tar.gz

##解压

tar -zxvf datax.tar.gz

##配置环境变量

vim ~/.bashrc ##用户环境变量

export PATH=/home/yym/datax/openlogic-openjdk-11.0.21+9-linux-x64/bin:$PATH

source ~/.bashrc

##删除plugin

/home/yym/datax/datax/

rm -rf ./plugin/*/._*

##执行datax看下环境是否正常

cd /home/yym/datax/datax/bin

python3 datax.py ../job/job.json

##python与python3语法不一样，需要修改datax.py文件

python3执行报print错误，修改如下

举例

print >> sys.stderr, "DataX Process was killed ! you did ?"

改为

print ( sys.stderr, "DataX Process was killed ! you did ?")

##yym_data.json

{
    "job": {
        "content": [
            {
                "reader": {
                    "name": "oraclereader",
                    "parameter": {
                        "column": ["*"],
                        "connection": [
                            {
                                "jdbcUrl": ["jdbc:oracle:thin:@192.168.3.156:1522:lhrcdb1"],
                                "table": ["hp_assets_user_visit_count_d"]
                            }
                        ],
                        "password": "123456",
                        "username": "c##yym_admin"
                    }
                },
                "writer": {
                    "name": "postgresqlwriter",
                    "parameter": {
                        "column": ["*"],
                        "connection": [
                            {
                                "jdbcUrl": "jdbc:postgresql://192.168.3.156:17700/test",
                                "table": ["yym_admin.hp_assets_user_visit_count_d"]
                            }
                        ],
                        "password": "123456",
                        "postSql": [],
                        "preSql": [],
                        "username": "yym_admin"
                    }
                }
            },
            {
                "reader": {
                    "name": "oraclereader",
                    "parameter": {
                        "column": ["*"],
                        "connection": [
                            {
                                "jdbcUrl": ["jdbc:oracle:thin:@192.168.3.156:1522:lhrcdb1"],
                                "table": ["hp_assets_user_visit_detail"]
                            }
                        ],
                        "password": "123456",
                        "username": "c##yym_admin"
                    }
                },
                "writer": {
                    "name": "postgresqlwriter",
                    "parameter": {
                        "column": ["*"],
                        "connection": [
                            {
                                "jdbcUrl": "jdbc:postgresql://192.168.3.156:17700/test",
                                "table": ["yym_admin.hp_assets_user_visit_detail"]
                            }
                        ],
                        "password": "123456",
                        "postSql": [],
                        "preSql": [],
                        "username": "yym_admin"
                    }
                }
            }
        ],
        "setting": {
            "speed": {
                "channel": "2"
            }
        }
    }
}

##oracle表数据全量同步到postgresql

python3 /home/yym/datax/datax/bin/datax.py -r oraclereader -w postgresqlwriter