利用python将excel文件转成txt文件，再将txt文件上传hdfs，最后传入hive中

将excel文件转成txt文件，再将txt文件上传hdfs，最后传入hive中

1.利用python将excel转成txt文件

#!/user/bin env python
import pandas as pd
import sys


def excel_to_txt(dt):
        df = pd.read_excel('data/excel/%s.xlsx'%(dt), header=None)  # 使用pandas模块读取数据， header 默认0，指定表头行，None:不取表头
        print('开始写入txt文件')
        df.to_csv('data/txt/%s.txt' % (dt), header=None, sep='\t', index=False)  # 写入txt中，tab分隔
        print('文件写入成功!')


if __name__ == '__main__':
    excel_to_txt('IS_GS_Recruitment_Data_20231211')

2.上传到hdfs
3.在hive中创建表

drop table if exists ticket.test_text;
create external table IF NOT EXISTS ticket.test_text
(
    name string,
    age int
) comment ''
      row format delimited fields terminated by '\t'
    lines terminated by '\n'
    NULL DEFINED AS ''
    stored as textfile
    LOCATION '/warehouse/ticket/ods/test_text';

4.将hdfs数据写入hive

load data inpath '/origin_data/test.txt' overwrite into table ticket.test_text;