007.PGSQL-python读取txt文件，将数据转化为dataFrame,dataFrame数据插入到pgsql; dataframe去掉索引，指定列为索引；python读取pgsql数据,读取数据库表导成excel

import numpy as np
import pandas as pd
from sqlalchemy import create_engine

#查看文件
list(open(‘C:/Users/James Murray/Desktop/test0001.txt‘))

#读取txt 
df_news = pd.read_table(‘C:/Users/James Murray/Desktop/test0001.txt‘,sep=‘\s+‘)
df=pd.DataFrame(df_news)
#指定某一列为索引
df.set_index(‘rid‘,inplace=True)
df
# 初始化引擎
connect = create_engine(‘postgresql+psycopg2://‘+‘yonghu‘+‘:‘+‘mima‘+‘@ip‘+‘:‘+str(duankou) + ‘/‘ + ‘kuming‘)
# 写入数据 
pd.io.sql.to_sql(df,‘test0001‘,connect,schema=‘ioc_dw_second‘, if_exists=‘append‘)
connect.dispose()

import pandas as pd
from sqlalchemy import create_engine

df_news = pd.read_table(‘C:/Users/James Murray/Desktop/test0001.txt‘,sep=‘\s+‘)
df=pd.DataFrame(df_news)
#指定某一列为索引
df.set_index(‘rid‘,inplace=True)
df
engine = create_engine(‘postgresql+psycopg2://‘ + ‘yonghu‘ + ‘:‘ + ‘mima‘ + ‘@‘ + ‘ip‘ + ‘:‘ + str(duankou) + ‘/‘ + ‘kuming‘)


# 配合pandas的to_sql方法使用十分方便（dataframe对象直接入库）
#df.to_sql(table, engine, if_exists=‘replace‘, index=False) #覆盖入库
# index=False ，索引行不插入表
df.to_sql(‘test0001‘, engine,schema=‘ioc_dw_second‘, if_exists=‘append‘, index=False)  #增量入库

from string import Template
import numpy as np
import pandas as pd
from sqlalchemy import create_engine

#创建连接引擎
engine = create_engine(‘postgresql+psycopg2://‘ + ‘yonghu‘ + ‘:‘ + ‘mima‘ + ‘@‘ + ‘xx.xx.xx.xx‘ + ‘:‘ + str(duabkou) + ‘/‘ + ‘kuming‘)

#sql语句
=====================================
query_sql = """
       select * from ioc_dw_second.$arg1
       """
=====================================

query_sql = Template(query_sql) # template方法 字符串格式化

#表名
tablename = ‘test0001‘
df1 = pd.read_sql_query(query_sql .substitute(arg1=tablename),engine) # 配合pandas的方法读取数据库值
df1

import psycopg2
import openpyxl

conn = psycopg2.connect(database=‘xx‘,user=‘xxx‘,password=‘xx‘,host=‘xx.xx.xx.xx‘,port=‘xxx‘)

cur= conn.cursor()
cur.execute("select database_name,proc_name,proc_detail from ioc_ods.ud_ioc_proc_beifen limit 1" )
rows = cur.fetchall()

for row in rows:
    print("database_name = ",row[0])
    print("proc_name = ",row[1])
    print("proc_detail = ",row[2])
print("operation done succcessful") 
conn.close()

# encoding:utf-8
import psycopg2
import openpyxl
from datetime import datetime

def database_excel():
    # 建立数据库连接
    conn = psycopg2.connect(database=‘kuming‘,user=‘yonghu‘,password=‘mima‘,host=‘ip‘,port=‘duankou‘)
    # 读取数据
    cur= conn.cursor()
    sql = ‘‘‘
        SELECT  nspname ,proname  , prosrc , CURRENT_TIMESTAMP as update_time 
        FROM    pg_catalog.pg_namespace n 
        JOIN    pg_catalog.pg_proc p 
        ON      pronamespace = n.oid 
        WHERE   nspname in (     
            ‘ioc_ods‘,  ‘ioc_support‘,‘ioc_standard‘,‘ioc_dm‘,‘ioc_dw‘,‘ioc_theme‘  
        )order by nspname
    ‘‘‘
    cur.execute(sql) 
    rows = cur.fetchall()

    wb = openpyxl.Workbook()
    wb.create_sheet(‘SHEET1‘,0)
    sheet = wb.get_sheet_by_name("SHEET1")

    today = datetime.today()
    today_date = datetime.date(today)

    myAlphbet = [‘A‘,‘B‘,‘C‘,‘D‘,‘E‘,‘F‘,‘G‘,‘H‘,‘I‘,‘J‘,‘K‘,‘L‘,‘M‘,‘N‘,‘O‘,‘P‘,‘Q‘,‘R‘,‘S‘,‘T‘,‘U‘,‘V‘,‘W‘,‘X‘,‘Y‘,‘Z‘]

    # 各列对应
    column_name = [‘库名‘,‘存储过程名称‘, ‘存储过程‘,‘更新时间‘]
    path = ‘E:\\龙岗IOC10.101.27.15PGsql存储过程备份\\备份proc\\‘
    # 列名
    for i in range(len(column_name)) :
        loc = myAlphbet[i]+str(1)
        sheet[loc] = column_name[i]

    for i in range(len(rows)) :
        for j in range(len(rows[i])):
            loc = myAlphbet[j]+str(i+2)
            sheet[loc] = rows[i][j]

    wb.save(path+‘SHEET‘+‘_‘+str(today_date)+‘.xlsx‘)

if __name__ == ‘__main__‘:

    database_excel()

    print("succeed")