159 lines
5.2 KiB
Python
159 lines
5.2 KiB
Python
|
#!/usr/bin/env python3
|
|||
|
|
"""
|
|||
|
|
从正文中移除爽点分析内容
|
|||
|
|
将爽点分析提取到单独的注释部分
|
|||
|
|
"""
|
|||
|
|
|
|||
|
|
import os
|
|||
|
|
import re
|
|||
|
|
|
|||
|
|
CHAPTERS_DIR = "/root/.openclaw/workspace/projects/末日重生_囤货/chapters"
|
|||
|
|
|
|||
|
|
def remove_shuangdian_from_content(content):
|
|||
|
|
"""
|
|||
|
|
从正文中移除爽点分析内容
|
|||
|
|
"""
|
|||
|
|
# 1. 移除正文中的爽点分析句子
|
|||
|
|
patterns_to_remove = [
|
|||
|
|
r'展现重生者的先知优势[，。]?',
|
|||
|
|
r'利用未来信息获取利益[，。]?',
|
|||
|
|
r'展现主角的[^，。]+[，。]?',
|
|||
|
|
r'体现[^，。]+的[^，。]+[，。]?',
|
|||
|
|
r'突出[^，。]+的[^，。]+[，。]?',
|
|||
|
|
]
|
|||
|
|
|
|||
|
|
for pattern in patterns_to_remove:
|
|||
|
|
content = re.sub(pattern, '', content)
|
|||
|
|
|
|||
|
|
# 2. 移除正文中的AI分析标记
|
|||
|
|
ai_patterns = [
|
|||
|
|
r'【[^】]+】', # 移除【爽点分析】等标记
|
|||
|
|
r'\[[^\]]+\]', # 移除[分析]等标记
|
|||
|
|
r'「[^」]+」', # 移除「分析」等标记
|
|||
|
|
]
|
|||
|
|
|
|||
|
|
for pattern in ai_patterns:
|
|||
|
|
# 但保留章节标题中的【爽点X：XXX】
|
|||
|
|
lines = content.split('\n')
|
|||
|
|
cleaned_lines = []
|
|||
|
|
for line in lines:
|
|||
|
|
if line.startswith('# 第'):
|
|||
|
|
# 保留章节标题
|
|||
|
|
cleaned_lines.append(line)
|
|||
|
|
else:
|
|||
|
|
# 移除正文中的分析标记
|
|||
|
|
cleaned_line = re.sub(pattern, '', line)
|
|||
|
|
cleaned_lines.append(cleaned_line)
|
|||
|
|
content = '\n'.join(cleaned_lines)
|
|||
|
|
|
|||
|
|
# 3. 提取爽点分析部分（如果存在）
|
|||
|
|
shuangdian_sections = []
|
|||
|
|
main_content_lines = []
|
|||
|
|
|
|||
|
|
lines = content.split('\n')
|
|||
|
|
in_shuangdian_section = False
|
|||
|
|
current_shuangdian = []
|
|||
|
|
|
|||
|
|
for line in lines:
|
|||
|
|
# 检测爽点部分开始
|
|||
|
|
if re.search(r'【爽点[一二三四五六七八九十]?[：:]', line):
|
|||
|
|
in_shuangdian_section = True
|
|||
|
|
current_shuangdian.append(line)
|
|||
|
|
elif in_shuangdian_section:
|
|||
|
|
if line.strip() and not line.startswith('#') and not re.search(r'【爽点[一二三四五六七八九十]?[：:]', line):
|
|||
|
|
current_shuangdian.append(line)
|
|||
|
|
else:
|
|||
|
|
# 爽点部分结束
|
|||
|
|
if current_shuangdian:
|
|||
|
|
shuangdian_sections.append('\n'.join(current_shuangdian))
|
|||
|
|
current_shuangdian = []
|
|||
|
|
in_shuangdian_section = False
|
|||
|
|
if line.strip():
|
|||
|
|
main_content_lines.append(line)
|
|||
|
|
else:
|
|||
|
|
main_content_lines.append(line)
|
|||
|
|
|
|||
|
|
# 处理最后一个爽点部分
|
|||
|
|
if current_shuangdian:
|
|||
|
|
shuangdian_sections.append('\n'.join(current_shuangdian))
|
|||
|
|
|
|||
|
|
# 4. 重新组合内容
|
|||
|
|
result = '\n'.join(main_content_lines)
|
|||
|
|
|
|||
|
|
# 5. 清理重复的爽点标题
|
|||
|
|
# 移除正文中重复的爽点标题部分
|
|||
|
|
result_lines = result.split('\n')
|
|||
|
|
cleaned_result_lines = []
|
|||
|
|
i = 0
|
|||
|
|
while i < len(result_lines):
|
|||
|
|
line = result_lines[i]
|
|||
|
|
# 检查是否是重复的爽点内容
|
|||
|
|
if '谈判桌上，陈末掌握着对手的所有底牌' in line:
|
|||
|
|
# 跳过这几行
|
|||
|
|
i += 3 # 跳过这一行和后面的两行
|
|||
|
|
continue
|
|||
|
|
cleaned_result_lines.append(line)
|
|||
|
|
i += 1
|
|||
|
|
|
|||
|
|
result = '\n'.join(cleaned_result_lines)
|
|||
|
|
|
|||
|
|
# 6. 清理多余的空白行
|
|||
|
|
result = re.sub(r'\n{3,}', '\n\n', result)
|
|||
|
|
|
|||
|
|
# 7. 如果有爽点分析，添加到末尾作为注释
|
|||
|
|
if shuangdian_sections:
|
|||
|
|
result += '\n\n<!-- 爽点分析：\n'
|
|||
|
|
for section in shuangdian_sections:
|
|||
|
|
result += section + '\n\n'
|
|||
|
|
result += '-->'
|
|||
|
|
|
|||
|
|
return result.strip()
|
|||
|
|
|
|||
|
|
def main():
|
|||
|
|
print("从正文中移除爽点分析内容...")
|
|||
|
|
|
|||
|
|
chapter_files = [f for f in os.listdir(CHAPTERS_DIR) if f.endswith('.md')]
|
|||
|
|
|
|||
|
|
fixed_count = 0
|
|||
|
|
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()
|
|||
|
|
|
|||
|
|
# 检查是否需要修复
|
|||
|
|
needs_fix = False
|
|||
|
|
if '展现重生者的先知优势' in content:
|
|||
|
|
needs_fix = True
|
|||
|
|
if re.search(r'【爽点[一二三四五六七八九十]?[：:]', content):
|
|||
|
|
needs_fix = True
|
|||
|
|
if '谈判桌上，陈末掌握着对手的所有底牌' in content:
|
|||
|
|
needs_fix = True
|
|||
|
|
|
|||
|
|
if not needs_fix:
|
|||
|
|
print(f" ✓ 无需修复")
|
|||
|
|
continue
|
|||
|
|
|
|||
|
|
# 创建备份
|
|||
|
|
backup_path = filepath + '.shuangdian.bak'
|
|||
|
|
with open(backup_path, 'w', encoding='utf-8') as f:
|
|||
|
|
f.write(content)
|
|||
|
|
|
|||
|
|
# 修复内容
|
|||
|
|
fixed_content = remove_shuangdian_from_content(content)
|
|||
|
|
|
|||
|
|
# 检查是否有变化
|
|||
|
|
if content != fixed_content:
|
|||
|
|
with open(filepath, 'w', encoding='utf-8') as f:
|
|||
|
|
f.write(fixed_content)
|
|||
|
|
print(f" ✓ 已移除爽点分析内容")
|
|||
|
|
fixed_count += 1
|
|||
|
|
else:
|
|||
|
|
print(f" ✓ 无需修复")
|
|||
|
|
|
|||
|
|
print(f"\n修复完成！共处理了 {len(chapter_files)} 个文件，修复了 {fixed_count} 个文件的爽点分析问题。")
|
|||
|
|
|
|||
|
|
if __name__ == '__main__':
|
|||
|
|
main()
|