Scribd
Upload
4 views2 pages

2 Text 20241014

Uploaded by

www7474174haha
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
4 views2 pages

2 Text 20241014

Uploaded by

www7474174haha
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 2

#!

/usr/bin/env python
# -*- coding: utf-8 -*-
# haowen.zheng

import linecache

def has_ten_spaces(s):
return ' ' * 10 in s

path_temp_file = r"C:\Users\www74\Desktop\每日问题"

# 原始文件，移动办公复制出的聊天记录
file_path = path_temp_file + r'\processed_chat.txt'
# 中间文件,不关注
file_path_temp = path_temp_file + r'\temp.txt'
# 中间文件,不关注
new_file_path = path_temp_file + r'\modified_example.txt'

with open(file_path, 'r', encoding='utf-8') as file:


lines = file.read()
#看是否存在截图，进行替换处理
lines = lines.replace("\n \n\n", "截图\n")
#重新写入文件
with open(file_path_temp, 'w', encoding='utf-8') as file_temp:
file_temp.writelines(lines)

t = []
t1 = []

with open(file_path_temp, 'r',encoding='utf-8') as file:


lines = file.readlines()
with open(new_file_path, 'w', encoding='utf-8') as file1:
content = [line for line in lines if line.strip()]
# print(non_blank_lines)
# content = file.readlines()
j = 1
for i in content:
# print(i)
if has_ten_spaces(i) and len(i.strip()) > 0 and len(i.strip()) < 10:
y = {}
if i.strip() in q:
pass
else:
t.append(i.strip())
file1.writelines(i.strip() + '\n')
j = j + 1
else:
y1 = {}
y1["序号"] = j
y1["内容"] = i
t1.append(y1)
file1.writelines(i)
j = j + 1
def read_specific_line_using_linecache(file_path, line_number):

return linecache.getline(file_path, line_number)

with open(new_file_path, 'r', encoding='utf-8') as file:


content = [line for line in lines if line.strip()]
l = 1
list_text = {}
lists_text = []
for k in content:
if k.strip() in t:
line = read_specific_line_using_linecache(new_file_path, l + 1)
try:
list_text[k.strip()] = list_text[k.strip()] + "\问：" + line.strip()
except:
list_text[k.strip()] = line.strip()
elif k.strip() in q:
line = read_specific_line_using_linecache(new_file_path, l + 1)
lists_text_temp = []
lists_text_temp.append(k.strip())
lists_text_temp.append(line)
lists_text.append(lists_text_temp)
l = l + 1

list_pd_temp = {}
for key, value in list_text.items():
for t1 in lists_text:
if key in t1[1]:
try:
list_pd_temp[key] = list_pd_temp[key] + "\答：" + t1[0] + t1[1]
except:
list_pd_temp[key] = t1[0] + t1[1]

list_pd_a = []

import pandas as pd
# 创建 DataFrame
df = pd.DataFrame(list_pd_a)

# 将 DataFrame 写入 Excel 文件
excel_file_path = path_temp_file + r'\output.xlsx'
df.to_excel(excel_file_path, index=False) # index=False 表示不写入行索引

You might also like