69 lines
2.1 KiB
Python
69 lines
2.1 KiB
Python
|
#!/usr/bin/env python3
|
||
|
|
"""
|
||
|
|
清理重复的章节标题
|
||
|
|
"""
|
||
|
|
|
||
|
|
import os
|
||
|
|
import re
|
||
|
|
|
||
|
|
CHAPTERS_DIR = "/root/.openclaw/workspace/projects/末日重生_囤货/chapters"
|
||
|
|
|
||
|
|
def clean_duplicate_titles(content, filename):
|
||
|
|
"""
|
||
|
|
清理重复的章节标题
|
||
|
|
"""
|
||
|
|
# 从文件名提取章节标题
|
||
|
|
match = re.search(r'ch\d+-第\d+章\s+(.+)\.md', filename)
|
||
|
|
if not match:
|
||
|
|
return content
|
||
|
|
|
||
|
|
chapter_title = match.group(1).strip()
|
||
|
|
|
||
|
|
lines = content.split('\n')
|
||
|
|
if not lines:
|
||
|
|
return content
|
||
|
|
|
||
|
|
# 第一行应该是章节标题
|
||
|
|
if lines[0].startswith('# 第'):
|
||
|
|
# 检查第一行是否包含重复的章节标题
|
||
|
|
first_line = lines[0]
|
||
|
|
title_pattern = f"# 第\\d+章 {re.escape(chapter_title)}"
|
||
|
|
|
||
|
|
# 如果第一行已经正确，就检查第二行
|
||
|
|
if re.match(title_pattern, first_line):
|
||
|
|
# 检查第二行是否也包含章节标题
|
||
|
|
if len(lines) > 1 and chapter_title in lines[1]:
|
||
|
|
# 移除第二行的重复标题
|
||
|
|
lines[1] = lines[1].replace(chapter_title, '').strip()
|
||
|
|
# 如果第二行变成空或只剩下空格，移除它
|
||
|
|
if not lines[1] or lines[1].isspace():
|
||
|
|
lines.pop(1)
|
||
|
|
|
||
|
|
return '\n'.join(lines)
|
||
|
|
|
||
|
|
def main():
|
||
|
|
print("清理重复的章节标题...")
|
||
|
|
|
||
|
|
chapter_files = [f for f in os.listdir(CHAPTERS_DIR) if f.endswith('.md')]
|
||
|
|
|
||
|
|
for filename in sorted(chapter_files):
|
||
|
|
filepath = os.path.join(CHAPTERS_DIR, filename)
|
||
|
|
|
||
|
|
print(f"处理: {filename}")
|
||
|
|
|
||
|
|
with open(filepath, 'r', encoding='utf-8') as f:
|
||
|
|
content = f.read()
|
||
|
|
|
||
|
|
cleaned_content = clean_duplicate_titles(content, filename)
|
||
|
|
|
||
|
|
if content != cleaned_content:
|
||
|
|
with open(filepath, 'w', encoding='utf-8') as f:
|
||
|
|
f.write(cleaned_content)
|
||
|
|
print(f" ✓ 已清理重复标题")
|
||
|
|
else:
|
||
|
|
print(f" ✓ 无需清理")
|
||
|
|
|
||
|
|
print("\n清理完成！")
|
||
|
|
|
||
|
|
if __name__ == '__main__':
|
||
|
|
main()
|