唐天洛
2003fa15ef
✅ 修复关键标题问题： 1. 筹码_手动修复 → 致命筹码 2. 修复 → 心灵修复 3. 对峙（2） → 生死对峙 ✅ 创建完整质量检查与修复工具集： 1. chapter_title_qc.py - 标题质量分析系统 2. apply_title_fixes.py - 自动修复工具 3. clean_ai_markers.py - AI标记清理工具 4. final_format_fix.py - 最终格式修复工具 5. improve_all_titles.py - 全面标题改进工具 ✅ 所有29个章节标题质量均已优化，评分A级以上 ✅ 移除爽点分析内容，确保正文纯净 ✅ 提升标题吸引力和阅读体验
183 lines
5.8 KiB
Python
183 lines
5.8 KiB
Python
#!/usr/bin/env python3
|
||
"""
|
||
最终质量检查脚本
|
||
检查章节格式是否已经修复
|
||
"""
|
||
|
||
import os
|
||
import re
|
||
|
||
CHAPTERS_DIR = "/root/.openclaw/workspace/projects/末日重生_囤货/chapters"
|
||
|
||
def check_chapter_quality(filename, content):
|
||
"""
|
||
检查章节质量
|
||
返回问题列表
|
||
"""
|
||
problems = []
|
||
|
||
# 1. 检查是否有爽点分析混入正文
|
||
if '展现重生者的先知优势' in content:
|
||
problems.append("仍有'展现重生者的先知优势'在正文中")
|
||
|
||
if '利用未来信息获取利益' in content:
|
||
problems.append("仍有'利用未来信息获取利益'在正文中")
|
||
|
||
if '谈判桌上，陈末掌握着对手的所有底牌' in content:
|
||
problems.append("仍有重复的'谈判桌上'段落")
|
||
|
||
# 2. 检查是否有爽点标题
|
||
if re.search(r'^#\s*【爽点[一二三四五六七八九十]?[：:]', content, re.MULTILINE):
|
||
problems.append("仍有爽点标题在正文中")
|
||
|
||
# 3. 检查章节标题格式
|
||
if not content.startswith('# 第'):
|
||
problems.append("章节标题格式不正确")
|
||
|
||
# 4. 检查是否有HTML注释中的爽点分析
|
||
if '<!-- 爽点分析：' in content:
|
||
problems.append("仍有HTML注释中的爽点分析")
|
||
|
||
# 5. 检查重复的章节标题
|
||
lines = content.split('\n')
|
||
if len(lines) > 1:
|
||
# 检查第二行是否包含章节标题
|
||
title_match = re.search(r'第\d+章\s+(.+)', lines[0])
|
||
if title_match:
|
||
chapter_title = title_match.group(1)
|
||
if chapter_title in lines[1] and len(lines[1]) < 50:
|
||
problems.append("第二行有重复的章节标题")
|
||
|
||
return problems
|
||
|
||
def main():
|
||
print("最终质量检查...\n")
|
||
|
||
chapter_files = [f for f in os.listdir(CHAPTERS_DIR) if f.endswith('.md')]
|
||
|
||
all_problems = []
|
||
good_chapters = 0
|
||
|
||
for filename in sorted(chapter_files, key=lambda x: int(re.search(r'ch(\d+)', x).group(1)) if re.search(r'ch(\d+)', x) else 0):
|
||
filepath = os.path.join(CHAPTERS_DIR, filename)
|
||
|
||
with open(filepath, 'r', encoding='utf-8') as f:
|
||
content = f.read()
|
||
|
||
problems = check_chapter_quality(filename, content)
|
||
|
||
if problems:
|
||
print(f"❌ {filename}")
|
||
for problem in problems:
|
||
print(f" - {problem}")
|
||
all_problems.append((filename, problems))
|
||
else:
|
||
print(f"✅ {filename} - 格式正确")
|
||
good_chapters += 1
|
||
|
||
print(f"\n检查完成！")
|
||
print(f"✅ 格式正确的章节: {good_chapters}/{len(chapter_files)}")
|
||
print(f"❌ 需要修复的章节: {len(all_problems)}/{len(chapter_files)}")
|
||
|
||
if all_problems:
|
||
print("\n需要修复的文件:")
|
||
for filename, problems in all_problems:
|
||
print(f" - {filename}: {', '.join(problems)}")
|
||
|
||
# 创建修复脚本
|
||
if all_problems:
|
||
create_fix_script(all_problems)
|
||
|
||
def create_fix_script(problem_files):
|
||
"""
|
||
创建修复脚本
|
||
"""
|
||
script_content = """#!/usr/bin/env python3
|
||
"""
|
||
自动修复章节格式问题
|
||
"""
|
||
|
||
import os
|
||
import re
|
||
|
||
CHAPTERS_DIR = "/root/.openclaw/workspace/projects/末日重生_囤货/chapters"
|
||
|
||
def final_fix_content(content):
|
||
\"\"\"
|
||
最终修复内容
|
||
\"\"\"
|
||
# 1. 移除所有爽点分析内容
|
||
content = re.sub(r'展现重生者的先知优势[，。]?', '', content)
|
||
content = re.sub(r'利用未来信息获取利益[，。]?', '', content)
|
||
content = re.sub(r'谈判桌上，陈末掌握着对手的所有底牌[^。]*。', '', content)
|
||
|
||
# 2. 移除爽点标题
|
||
content = re.sub(r'^#\s*【爽点[一二三四五六七八九十]?[：:][^】]+】', '', content, flags=re.MULTILINE)
|
||
|
||
# 3. 移除HTML注释中的爽点分析
|
||
lines = content.split('\\n')
|
||
cleaned_lines = []
|
||
skip = False
|
||
for line in lines:
|
||
if '<!-- 爽点分析：' in line:
|
||
skip = True
|
||
continue
|
||
if skip and line.strip() == '-->':
|
||
skip = False
|
||
continue
|
||
if not skip:
|
||
cleaned_lines.append(line)
|
||
|
||
content = '\\n'.join(cleaned_lines)
|
||
|
||
# 4. 确保章节标题格式正确
|
||
if not content.startswith('# 第'):
|
||
# 从内容中提取章节标题
|
||
first_line = content.split('\\n')[0] if content else ''
|
||
match = re.search(r'第(\\d+)章\\s+(.+)', first_line)
|
||
if match:
|
||
chapter_num = match.group(1)
|
||
chapter_title = match.group(2)
|
||
content = f'# 第{chapter_num}章 {chapter_title}\\n\\n' + '\\n'.join(content.split('\\n')[1:])
|
||
|
||
# 5. 清理多余的空白行
|
||
content = re.sub(r'\\n{3,}', '\\n\\n', content)
|
||
|
||
return content.strip()
|
||
|
||
# 需要修复的文件列表
|
||
problem_files = %s
|
||
|
||
for filename in problem_files:
|
||
filepath = os.path.join(CHAPTERS_DIR, filename)
|
||
|
||
print(f"修复: {filename}")
|
||
|
||
with open(filepath, 'r', encoding='utf-8') as f:
|
||
content = f.read()
|
||
|
||
# 创建备份
|
||
backup_path = filepath + '.final.bak'
|
||
with open(backup_path, 'w', encoding='utf-8') as f:
|
||
f.write(content)
|
||
|
||
# 应用修复
|
||
fixed_content = final_fix_content(content)
|
||
|
||
with open(filepath, 'w', encoding='utf-8') as f:
|
||
f.write(fixed_content)
|
||
|
||
print(f" ✓ 已修复")
|
||
|
||
print("\\n所有文件修复完成！")
|
||
""" % str([filename for filename, _ in problem_files])
|
||
|
||
script_path = os.path.join(CHAPTERS_DIR, "tools", "apply_final_fixes.py")
|
||
with open(script_path, 'w', encoding='utf-8') as f:
|
||
f.write(script_content)
|
||
|
||
print(f"\n已创建修复脚本: tools/apply_final_fixes.py")
|
||
print(f"运行命令: cd /root/.openclaw/workspace/projects/末日重生_囤货 && python3 tools/apply_final_fixes.py")
|
||
|
||
if __name__ == '__main__':
|
||
main() |