【无标题】

最新推荐文章于 2024-09-11 18:01:31 发布

weixin_48843478

最新推荐文章于 2024-09-11 18:01:31 发布

阅读量484

点赞数 7

文章标签： python json

本文链接：https://blog.csdn.net/weixin_48843478/article/details/136822047

版权

文章详细描述了使用Python编写的脚本如何生成DataX配置，用于从MySQL数据库向HDFS进行数据迁移，涉及数据库列映射和配置文件生成。

摘要由CSDN通过智能技术生成

1.HDFSReader和MySQLWriter

# coding=utf-8
import json
import getopt
import os
import sys
import MySQLdb

#MySQL相关配置，需根据实际情况作出修改
mysql_host = "hadoop102"
mysql_port = "3306"
mysql_user = "root"
mysql_passwd = "123456"

#HDFS NameNode相关配置，需根据实际情况作出修改
hdfs_nn_host = "hadoop102"
hdfs_nn_port = "8020"

#生成配置文件的目标路径，可根据实际情况作出修改
output_path = "/opt/module/datax/job/import"


def get_connection():
    return MySQLdb.connect(host=mysql_host, port=int(mysql_port), user=mysql_user, passwd=mysql_passwd)


def get_mysql_meta(database, table):
    connection = get_connection()
    cursor = connection.cursor()
    sql = "SELECT COLUMN_NAME,DATA_TYPE from information_schema.COLUMNS WHERE TABLE_SCHEMA=%s AND TABLE_NAME=%s ORDER BY ORDINAL_POSITION"
    cursor.execute(sql, [database, table])
    fetchall = cursor.fetchall()
    cursor.close()
    connection.close()
    return fetchall


def get_mysql_columns(database, table):
    return map(lambda x: x[0], get_mysql_meta(database, table))


def get_hive_columns(database, table):
    def type_mapping(mysql_type):
        mappings = {
            "bigint": "bigint",
            "int": "bigint",
            "smallint": "bigint",
            "tinyint": "bigint",
            "decimal": "string",
            "double": "double",
            "float": "float",
            "binary": "string",
            "char": "string",
            "varchar": "string",
            "datetime": "string",
            "time": "string",
            "timestamp": "string",
            "date": "string",
            "text": "string"
        }
        return mappings[mysql_type]

    meta = get_mysql_meta(database, table)
    return map(lambda x: {"name": x[0], "type": type_mapping(x[1].lower())}, meta)


def generate_json(source_database, source_table):
    job = {
        "job": {
            "setting": {
                "speed": {
                    "channel": 3
                },
                "errorLimit": {
                    "record": 0,
                    "percentage": 0.02
                }
            },
            "content": [{
                "reader": {
                    "name": "mysqlreader",
                    "parameter": {
                        "username": mysql_user,
                        "password": mysql_passwd,
                        "column": get_mysql_columns(source_database, source_table),
                        "splitPk": "",
                        "connection": [{
                            "table": [source_table],
                            "jdbcUrl": ["jdbc:mysql://" + mysql_host + ":" + mysql_port + "/" + source_database]
                        }]
                    }
                },
                "writer": {
                    "name": "hdfswriter",
                    "parameter": {
                        "defaultFS": "hdfs://" + hdfs_nn_host + ":" + hdfs_nn_port,
                        "fileType": "text",
                        "path": "${targetdir}",
                        "fileName": source_table,
                        "column": get_hive_columns(source_database, source_table),
                        "writeMode": "append",
                        "fieldDelimiter": "\t",
                        "compress": "gzip"
                    }
                }
            }]
        }
    }
    if not os.path.exists(output_path):
        os.makedirs(output_path)
    with open(os.path.join(output_path, ".".join([source_database, source_table, "json"])), "w") as f:
        json.dump(job, f)


def main(args):
    source_database = ""
    source_table = ""

    options, arguments = getopt.getopt(args, '-d:-t:', ['sourcedb=', 'sourcetbl='])
    for opt_name, opt_value in options:
        if opt_name in ('-d', '--sourcedb'):
            source_database = opt_value
        if opt_name in ('-t', '--sourcetbl'):
            source_table = opt_value

    generate_json(source_database, source_table)


if __name__ == '__main__':
    main(sys.argv[1:])

使用说明

python gen_export_config.py -d database -t table

datax执行执行：

python /opt/module/datax/bin/datax.py -p"-Dtargetdir=/origin_data/gmall/db/activity_info_full/2020-06-14" /opt/module/datax/job/import/gmall.activity_info.json

HFDS目标路径出现数据。