You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
42 lines
1.1 KiB
42 lines
1.1 KiB
# -*- coding: utf-8 -*-
|
|
|
|
"""
|
|
@Time : 2023/3/10 17:45
|
|
@Author :
|
|
@FileName:
|
|
@Software:
|
|
@Describe:
|
|
"""
|
|
import os
|
|
|
|
file = './data/10235513_大型商业建筑人员疏散设计研究_沈福禹/查重txt'
|
|
|
|
path_list = []
|
|
|
|
for root, dirs, files in os.walk(file):
|
|
for file in files:
|
|
path = os.path.join(root, file)
|
|
path_list.append(path)
|
|
|
|
|
|
for path in path_list:
|
|
with open(path, encoding="utf-8") as f:
|
|
text = f.read()
|
|
path_dan_list = path.split("\\")
|
|
root_path = path_dan_list[0]
|
|
file_path = path_dan_list[1]
|
|
root_pathdan_list = root_path.split("/")
|
|
root_pathdan_list = root_pathdan_list[:-1]
|
|
print(root_pathdan_list)
|
|
|
|
text_list = text.split("@@@@@@@@@@")
|
|
text_zhengwen = text_list[-1]
|
|
text_list = [i.lstrip("\n") for i in text_list[:-1]]
|
|
print(text_list)
|
|
text_zhengwen = text_zhengwen.strip().replace("\n", "").replace(" ", "").replace("。", "。\n")
|
|
text_list = text_list + [text_zhengwen]
|
|
text_str = "@@@@@@@@@@".join(text_list)
|
|
path_new = "/".join(root_pathdan_list + ["查重txt_new", file_path])
|
|
with open(path_new, "w") as f:
|
|
f.write(text_str)
|
|
f.close()
|
|
|