2020-12-05 06:52:28 +00:00
|
|
|
|
#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
|
2020-12-05 16:39:07 +00:00
|
|
|
|
import uuid
|
2020-12-05 06:52:28 +00:00
|
|
|
|
|
2020-12-05 16:39:07 +00:00
|
|
|
|
import psycopg2 as psycopg2
|
2020-12-05 06:52:28 +00:00
|
|
|
|
|
2020-12-05 16:39:07 +00:00
|
|
|
|
# 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!@#'
|
2020-12-05 06:52:28 +00:00
|
|
|
|
|
2020-12-05 16:39:07 +00:00
|
|
|
|
def get_csv_weixin(path):
|
|
|
|
|
|
with open("D:/2020/新媒体监测/新媒体对比结果_其他.csv", "w", newline='') as csvfile:
|
|
|
|
|
|
writer = csv.writer(csvfile)
|
|
|
|
|
|
writer.writerow(
|
|
|
|
|
|
["序号", "冲突账号"])
|
2020-12-05 06:52:28 +00:00
|
|
|
|
|
2020-12-05 16:39:07 +00:00
|
|
|
|
with psycopg2.connect(G2) as connection:
|
|
|
|
|
|
with open(path, encoding='utf-8') as csvfile:
|
|
|
|
|
|
reader = csv.reader(csvfile)
|
|
|
|
|
|
for r in reader:
|
|
|
|
|
|
if r[1] != '单位全称':
|
|
|
|
|
|
if '头条' not in r[7] and '微信' not in r[7] and '微博' not in r[7] and '抖音' not in r[7]:
|
|
|
|
|
|
name = r[1]
|
|
|
|
|
|
code = r[4]
|
|
|
|
|
|
identificationcode = r[3]
|
|
|
|
|
|
function = r[8]
|
|
|
|
|
|
articleurl = r[12]
|
|
|
|
|
|
biz = r[13]
|
|
|
|
|
|
province = None
|
|
|
|
|
|
cities = None
|
|
|
|
|
|
district = None
|
|
|
|
|
|
d_name = None
|
|
|
|
|
|
c_name = None
|
|
|
|
|
|
p_name = None
|
|
|
|
|
|
|
|
|
|
|
|
print(r)
|
|
|
|
|
|
try:
|
|
|
|
|
|
with connection.cursor() as cursor_p:
|
|
|
|
|
|
cursor_p.execute(
|
|
|
|
|
|
"select * from dashboard_area_code_2020 where name = '%s'" % (r[9]))
|
|
|
|
|
|
for p in cursor_p:
|
|
|
|
|
|
province = p[1]
|
|
|
|
|
|
p_name = p[2]
|
|
|
|
|
|
with connection.cursor() as cursor_c:
|
|
|
|
|
|
cursor_c.execute(
|
|
|
|
|
|
"select * from dashboard_area_code_2020 where name = '%s'" % (r[10]))
|
|
|
|
|
|
for c in cursor_c:
|
|
|
|
|
|
cities = c[1]
|
|
|
|
|
|
c_name = c[2]
|
|
|
|
|
|
with connection.cursor() as cursor_d:
|
|
|
|
|
|
cursor_d.execute(
|
|
|
|
|
|
"select * from dashboard_area_code_2020 where name = '%s'" % (r[11]))
|
|
|
|
|
|
for d in cursor_d:
|
|
|
|
|
|
district = d[1]
|
|
|
|
|
|
d_name = d[2]
|
|
|
|
|
|
print(code)
|
|
|
|
|
|
with connection.cursor() as cursor:
|
|
|
|
|
|
cursor.execute(
|
|
|
|
|
|
"select * from dashboard_qita where code = '%s'" % (code))
|
|
|
|
|
|
# connection.commit()
|
|
|
|
|
|
|
|
|
|
|
|
for c in cursor:
|
|
|
|
|
|
print(str(c[10]) + "1111111111111111111111")
|
|
|
|
|
|
with connection.cursor() as cursor2:
|
|
|
|
|
|
cursor2.execute(
|
|
|
|
|
|
"select * from dashboard_organization where id = '%s'" % (c[10]))
|
|
|
|
|
|
for c2 in cursor2:
|
|
|
|
|
|
print(str(c2[0]) + "55555555555555555555555")
|
|
|
|
|
|
|
|
|
|
|
|
if str(name) == str(c2[1]) and str(province) == str(c2[3]) and str(
|
|
|
|
|
|
cities) == str(c2[4]) and str(district) == str(c2[5]) and str(
|
|
|
|
|
|
code) == str(c[1]) and str(identificationcode) == str(
|
|
|
|
|
|
c[13]) and str(biz) == str(c[9]):
|
|
|
|
|
|
print(c2)
|
|
|
|
|
|
else:
|
|
|
|
|
|
writer.writerow(
|
|
|
|
|
|
[r[0], name, code, identificationcode, biz, p_name, c_name,
|
|
|
|
|
|
d_name])
|
|
|
|
|
|
writer.writerow(
|
|
|
|
|
|
[r[0], c2[1], c[1], c[13], c[9], c2[3], c2[4], c2[5]])
|
|
|
|
|
|
|
|
|
|
|
|
except:
|
|
|
|
|
|
writer.writerow(
|
|
|
|
|
|
[r[0], name, code, identificationcode, biz, p_name, c_name,
|
|
|
|
|
|
d_name])
|
2020-12-05 06:52:28 +00:00
|
|
|
|
if __name__ == '__main__':
|
2020-12-05 16:39:07 +00:00
|
|
|
|
get_csv_weixin('D:/2020/新媒体监测/TASK_ALL.csv')
|
