newmediamonitoring/敏感词查找.py

31 lines
1.1 KiB
Python

import csv
def get_weixin_cuominzi(cuominzi):
with open('D:/2021/新媒体/微信错敏字.csv','w', newline='',encoding='utf-8') as csvfile:
writer = csv.writer(csvfile)
writer.writerow(
[ "错敏字","标题","日期", "链接", "公众号","位置"])
with open('D:/2021/新媒体/WX_LX.csv',encoding='utf8') as csvfile:
reader_wx = csv.reader(csvfile)
for r_w in reader_wx:
for c in cuominzi:
if str(c[0]) in str(r_w[4]) and str(c[1]) not in str(r_w[4]):
print(str(r_w[4]).index(str(c[0])))
writer.writerow([c[0], r_w[3], r_w[2], r_w[1], r_w[0],
str(r_w[4])[str(r_w[4]).index(str(c[0])) - 10:str(r_w[4]).index(str(c[0])) + 10]])
if __name__ == '__main__':
cuominzi = []
with open('D:/2021/新媒体/错敏字.csv') as csvfile:
reader = csv.reader(csvfile)
for r in reader:
if r[0] != '错敏字' and r[0] != '':
cuominzi.append(r)
print(cuominzi)
get_weixin_cuominzi(cuominzi)