99 lines
4.9 KiB
Python
99 lines
4.9 KiB
Python
#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:/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"])
|
||
|
||
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])
|
||
if __name__ == '__main__':
|
||
get_csv_weixin('D:/2020/新媒体监测/TASK_ALL.csv') |