newmediamonitoring/新媒体更新脚本/查找微博名称更改.py

# 更新新媒体脚本，结果为有出入的新媒体列表。
'''
1,将excel转为csv，使用utf-8编码集。
2、获取csv内容
3、与数据库中的数据逐项对比
'''
import csv
import uuid

import psycopg2 as psycopg2

# code = None
# alias = None
# attention = None
# remark = None
# identificationcode = None
# function = None
# articleurl = None
# weixinid = None
# type = None
G2 = 'host=210.77.68.250 port=5432 dbname=newmediaDB3 user=newmedia password=newmedia2020!@#'


def get_csv_weixin(path):
    with open("D:/2021/舆论监测平台/数据/数据库更新/新媒体对比结果_微博_账号名称更改.csv", "w", newline='',encoding='utf-8') as csvfile:
        writer = csv.writer(csvfile)
        writer.writerow(
            ["账号", "备注"])
        weibo_code_list = []
        csv_code_list = []
        with open(path, encoding='utf-8') as csvfile:
            reader = csv.reader(csvfile)
            for r in reader:
                if r[1] != '单位全称':
                    if '微博' in r[7]:
                        csv_code_list.append(r[4])
        with psycopg2.connect(G2) as connection:
            with connection.cursor() as cursor:
                try:
                    cursor.execute(
                        "select * from dashboard_weibo")
                    connection.commit()
                    for c in cursor:
                        weibo_code_list.append(c[1])
                except Exception as e:
                    print(e)
        print(len(weibo_code_list),len(csv_code_list))

        print( len(list(set( weibo_code_list ) ^ set( csv_code_list ))))
        for i in list(set( weibo_code_list ) ^ set( csv_code_list )):
            if i in weibo_code_list and i not in csv_code_list:
                writer.writerow(
                    [i,'删除'])
            elif i in csv_code_list and i not in weibo_code_list:
                writer.writerow(
                    [i, '新增'])
            else:
                writer.writerow(
                    [i, '异常'])
if __name__ == '__main__':
    get_csv_weixin('D:/2021/舆论监测平台/数据/Task_All.csv')