# 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_抖音_账号名称更改.csv", "w", newline='',encoding='utf-8') as csvfile: writer = csv.writer(csvfile) writer.writerow( ["账号", "备注"]) douyin_code_list = [] csv_code_list = [] r = None with open(path, encoding='utf-8') as csvfile: reader = csv.reader(csvfile) for r in reader: if r[1] != '单位全称': if '抖音' 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_douyin") connection.commit() for c in cursor: douyin_code_list.append(c[1]) except Exception as e: print(e) print(len(douyin_code_list),len(csv_code_list)) print( len(list(set( douyin_code_list ) ^ set( csv_code_list )))) for i in list(set( douyin_code_list ) ^ set( csv_code_list )): if i in douyin_code_list and i not in csv_code_list: writer.writerow( [i,'删除']) elif i in csv_code_list and i not in douyin_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')