53 lines
1.5 KiB
Python
53 lines
1.5 KiB
Python
#!/usr/bin/env python
|
||
# -*- coding: utf-8 -*-
|
||
"""
|
||
合并1.md到6.md文件，在合并处添加分隔标注
|
||
"""
|
||
|
||
import re
|
||
|
||
def remove_line_numbers(content):
|
||
"""移除每行开头的行号格式（如 ' 1→'）"""
|
||
lines = content.split('\n')
|
||
cleaned_lines = []
|
||
for line in lines:
|
||
# 匹配并移除行号格式：空格+数字+→
|
||
cleaned = re.sub(r'^\s*\d+→', '', line)
|
||
cleaned_lines.append(cleaned)
|
||
return '\n'.join(cleaned_lines)
|
||
|
||
def main():
|
||
output_lines = []
|
||
|
||
for i in range(1, 7):
|
||
filename = f"{i}.md"
|
||
|
||
try:
|
||
with open(filename, 'r', encoding='utf-8') as f:
|
||
content = f.read()
|
||
|
||
# 移除行号
|
||
cleaned_content = remove_line_numbers(content)
|
||
|
||
# 添加分隔标注（第一个文件不需要）
|
||
if i > 1:
|
||
separator = "\n\n---\n\n**【以下为下一页，发言者的区分将重记】**\n\n---\n\n"
|
||
output_lines.append(separator)
|
||
|
||
output_lines.append(cleaned_content)
|
||
print(f"已处理: {filename}")
|
||
|
||
except FileNotFoundError:
|
||
print(f"文件不存在: {filename}")
|
||
return
|
||
|
||
# 写入合并后的文件
|
||
output_filename = "会议转写_合并版.md"
|
||
with open(output_filename, 'w', encoding='utf-8') as f:
|
||
f.write(''.join(output_lines))
|
||
|
||
print(f"\n合并完成！输出文件: {output_filename}")
|
||
|
||
if __name__ == "__main__":
|
||
main()
|