117 lines
3.5 KiB
Python
117 lines
3.5 KiB
Python
|
#!/usr/bin/env python3
|
|||
|
|
"""
|
|||
|
|
清理AI生成的各种内部标记和注释
|
|||
|
|
"""
|
|||
|
|
|
|||
|
|
import os
|
|||
|
|
import re
|
|||
|
|
|
|||
|
|
CHAPTERS_DIR = "/root/.openclaw/workspace/projects/末日重生_囤货/chapters"
|
|||
|
|
|
|||
|
|
def clean_ai_markers(content):
|
|||
|
|
"""
|
|||
|
|
清理AI生成的各种标记
|
|||
|
|
"""
|
|||
|
|
lines = content.split('\n')
|
|||
|
|
cleaned_lines = []
|
|||
|
|
|
|||
|
|
for line in lines:
|
|||
|
|
# 1. 移除特定的AI分析标记（但保留正常的心理描写）
|
|||
|
|
# 这些是明确的AI分析，应该移除
|
|||
|
|
ai_markers = [
|
|||
|
|
'展现重生者的先知优势',
|
|||
|
|
'利用未来信息获取利益',
|
|||
|
|
'展现主角的',
|
|||
|
|
'体现人物',
|
|||
|
|
'突出情节',
|
|||
|
|
'【爽点分析】',
|
|||
|
|
'[分析]',
|
|||
|
|
'<!-- 爽点分析：',
|
|||
|
|
]
|
|||
|
|
|
|||
|
|
has_ai_marker = any(marker in line for marker in ai_markers)
|
|||
|
|
|
|||
|
|
# 2. 检查是否是"谈判桌上"那段重复内容
|
|||
|
|
if '谈判桌上，陈末掌握着对手的所有底牌' in line:
|
|||
|
|
# 跳过这一行
|
|||
|
|
continue
|
|||
|
|
|
|||
|
|
# 3. 保留正常的心理描写
|
|||
|
|
# 正常的心理活动使用「」标记，应该保留
|
|||
|
|
if '「' in line and '」' in line and not has_ai_marker:
|
|||
|
|
# 这是正常的心理描写，保留
|
|||
|
|
cleaned_lines.append(line)
|
|||
|
|
continue
|
|||
|
|
|
|||
|
|
# 4. 移除爽点标题行
|
|||
|
|
if re.search(r'^#\s*【爽点[一二三四五六七八九十]?[：:]', line):
|
|||
|
|
continue
|
|||
|
|
|
|||
|
|
# 5. 移除HTML注释中的爽点分析
|
|||
|
|
if line.strip().startswith('<!--') and '爽点' in line:
|
|||
|
|
continue
|
|||
|
|
if line.strip() == '-->':
|
|||
|
|
continue
|
|||
|
|
|
|||
|
|
# 6. 如果没有AI标记，保留这一行
|
|||
|
|
if not has_ai_marker:
|
|||
|
|
cleaned_lines.append(line)
|
|||
|
|
|
|||
|
|
# 重新组合内容
|
|||
|
|
result = '\n'.join(cleaned_lines)
|
|||
|
|
|
|||
|
|
# 7. 清理多余的空白行
|
|||
|
|
result = re.sub(r'\n{3,}', '\n\n', result)
|
|||
|
|
|
|||
|
|
# 8. 确保章节以正确的内容结束
|
|||
|
|
# 移除末尾可能遗留的无关内容
|
|||
|
|
lines = result.split('\n')
|
|||
|
|
while lines and not lines[-1].strip():
|
|||
|
|
lines.pop()
|
|||
|
|
|
|||
|
|
result = '\n'.join(lines)
|
|||
|
|
|
|||
|
|
return result.strip()
|
|||
|
|
|
|||
|
|
def main():
|
|||
|
|
print("清理AI生成的各种标记...")
|
|||
|
|
|
|||
|
|
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"检查: {filename}")
|
|||
|
|
|
|||
|
|
with open(filepath, 'r', encoding='utf-8') as f:
|
|||
|
|
content = f.read()
|
|||
|
|
|
|||
|
|
# 检查是否需要清理
|
|||
|
|
needs_clean = (
|
|||
|
|
'展现重生者的先知优势' in content or
|
|||
|
|
'谈判桌上，陈末掌握着对手的所有底牌' in content or
|
|||
|
|
'<!-- 爽点分析：' in content
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
if needs_clean:
|
|||
|
|
print(f" ⚠ 需要清理")
|
|||
|
|
|
|||
|
|
# 创建备份
|
|||
|
|
backup_path = filepath + '.ai.bak'
|
|||
|
|
with open(backup_path, 'w', encoding='utf-8') as f:
|
|||
|
|
f.write(content)
|
|||
|
|
|
|||
|
|
# 清理内容
|
|||
|
|
cleaned_content = clean_ai_markers(content)
|
|||
|
|
|
|||
|
|
with open(filepath, 'w', encoding='utf-8') as f:
|
|||
|
|
f.write(cleaned_content)
|
|||
|
|
|
|||
|
|
print(f" ✓ 已清理AI标记")
|
|||
|
|
else:
|
|||
|
|
print(f" ✓ 无需清理")
|
|||
|
|
|
|||
|
|
print("\nAI标记清理完成！")
|
|||
|
|
|
|||
|
|
if __name__ == '__main__':
|
|||
|
|
main()
|