This commit is contained in:
Ubuntu
2026-07-03 16:58:28 +08:00
commit 32b43f85bd
6240 changed files with 1987678 additions and 0 deletions
+874
View File
@@ -0,0 +1,874 @@
#!/usr/bin/env python3
"""
oh-my-writing-skill 集成管理器
将下载的技能集成到IT资讯自动化系统中
"""
import os
import sys
import json
import shutil
from pathlib import Path
class OhMyWritingIntegration:
"""oh-my-writing-skill 集成管理器"""
def __init__(self):
self.source_dir = Path("/home/ubuntu/oh-my-writing-skill")
self.target_dir = Path("/home/ubuntu/.nanobot/workspace/skills/xiaohongshu_integration")
self.skills_config = {}
# 技能映射表
self.skill_mapping = {
'xiaohongshu-converter': {
'name': '小红书转换器',
'description': '将通用文章转换为小红书格式',
'source': 'skills/xiaohongshu-converter/SKILL.md',
'target': 'oh_my_writing_converter.py',
'already_implemented': True
},
'humanizer-cn': {
'name': '中文去AI化',
'description': '消除AI写作痕迹,让文章更自然',
'source': 'skills/humanizer-cn/SKILL.md',
'target': 'humanizer_cn.py',
'already_implemented': False
},
'general-writing': {
'name': '通用写作',
'description': '整合素材创作图文并茂的文章',
'source': 'skills/general-writing/SKILL.md',
'target': 'general_writing.py',
'already_implemented': False
},
'deep-research': {
'name': '深度研究',
'description': '联网搜索收集资料',
'source': 'skills/deep-research/SKILL.md',
'target': 'deep_research.py',
'already_implemented': False
},
'image-search': {
'name': '图片搜索',
'description': '搜索相关配图',
'source': 'skills/image-search/SKILL.md',
'target': 'image_search.py',
'already_implemented': False
},
'image-processing': {
'name': '图片处理',
'description': '处理图片添加配文',
'source': 'skills/image-processing/SKILL.md',
'target': 'image_processing.py',
'already_implemented': False
},
'zhihu-converter': {
'name': '知乎转换器',
'description': '转换为知乎格式',
'source': 'skills/zhihu-converter/SKILL.md',
'target': 'zhihu_converter.py',
'already_implemented': False
},
'wechat-converter': {
'name': '公众号转换器',
'description': '转换为微信公众号格式',
'source': 'skills/wechat-converter/SKILL.md',
'target': 'wechat_converter.py',
'already_implemented': False
}
}
def analyze_skills(self):
"""分析可用技能"""
print("🔍 分析 oh-my-writing-skill 技能包...")
print(f"源目录: {self.source_dir}")
print(f"目标目录: {self.target_dir}")
print()
available_skills = []
missing_skills = []
for skill_id, skill_info in self.skill_mapping.items():
source_path = self.source_dir / skill_info['source']
if source_path.exists():
available_skills.append({
'id': skill_id,
'name': skill_info['name'],
'description': skill_info['description'],
'source': str(source_path),
'status': '已下载'
})
else:
missing_skills.append({
'id': skill_id,
'name': skill_info['name'],
'description': skill_info['description'],
'status': '未找到'
})
print(f"📊 技能分析结果:")
print(f" 已下载: {len(available_skills)} 个技能")
print(f" 未找到: {len(missing_skills)} 个技能")
print()
if available_skills:
print("✅ 可用技能:")
for skill in available_skills:
print(f" • {skill['name']} ({skill['id']})")
print(f" 描述: {skill['description']}")
if missing_skills:
print("⚠️ 缺失技能:")
for skill in missing_skills:
print(f" • {skill['name']} ({skill['id']})")
return available_skills, missing_skills
def extract_skill_knowledge(self, skill_id):
"""提取技能知识"""
if skill_id not in self.skill_mapping:
print(f"❌ 未知技能: {skill_id}")
return None
skill_info = self.skill_mapping[skill_id]
source_path = self.source_dir / skill_info['source']
if not source_path.exists():
print(f"❌ 技能文件不存在: {source_path}")
return None
print(f"📖 提取技能知识: {skill_info['name']}")
print(f" 文件: {source_path}")
try:
with open(source_path, 'r', encoding='utf-8') as f:
content = f.read()
# 解析技能内容
knowledge = {
'id': skill_id,
'name': skill_info['name'],
'description': skill_info['description'],
'content': content,
'summary': self._summarize_skill_content(content),
'key_points': self._extract_key_points(content),
'examples': self._extract_examples(content)
}
print(f"✅ 知识提取完成")
print(f" 内容长度: {len(content)} 字符")
print(f" 关键点: {len(knowledge['key_points'])} 个")
return knowledge
except Exception as e:
print(f"❌ 提取失败: {e}")
return None
def _summarize_skill_content(self, content):
"""总结技能内容"""
lines = content.split('\n')
summary = []
# 提取标题和主要章节
for line in lines:
if line.startswith('# '):
summary.append(line)
elif line.startswith('## '):
summary.append(line)
elif line.startswith('### '):
summary.append(line)
return '\n'.join(summary[:10]) # 限制长度
def _extract_key_points(self, content):
"""提取关键点"""
key_points = []
# 查找列表项
lines = content.split('\n')
for line in lines:
if line.strip().startswith('- ') or line.strip().startswith('* '):
key_points.append(line.strip())
elif line.strip().startswith('1. ') or line.strip().startswith('• '):
key_points.append(line.strip())
return key_points[:20] # 限制数量
def _extract_examples(self, content):
"""提取示例"""
examples = []
# 查找代码块
in_code_block = False
code_block = []
for line in content.split('\n'):
if line.strip().startswith('```'):
if in_code_block:
examples.append('\n'.join(code_block))
code_block = []
in_code_block = False
else:
in_code_block = True
elif in_code_block:
code_block.append(line)
return examples
def implement_humanizer_cn(self):
"""实现中文去AI化技能"""
print("🛠️ 实现中文去AI化技能...")
# 提取知识
knowledge = self.extract_skill_knowledge('humanizer-cn')
if not knowledge:
return False
# 创建实现文件
target_file = self.target_dir / "humanizer_cn.py"
implementation = f'''#!/usr/bin/env python3
"""
中文去AI化工具
基于 oh-my-writing-skill 的 humanizer-cn 技能
消除AI写作痕迹,让文章更自然
"""
import re
import json
from typing import Dict, List, Optional
class HumanizerCN:
"""中文去AI化处理器"""
def __init__(self):
# AI写作特征模式
self.ai_patterns = {{
# 过度强调意义和历史地位
'overemphasis': [
r'彰显[了着]', r'见证[了着]', r'标志着', r'具有里程碑意义',
r'揭示了', r'体现了', r'承载着', r'奠定了基础',
r'树立了标杆', r'开创了先河', r'具有划时代意义', r'承前启后'
],
# 过度强调知名度和媒体报道
'overhype': [
r'广受关注', r'引发热议', r'备受瞩目', r'获得广泛报道',
r'在业界引起强烈反响', r'各大媒体纷纷报道'
],
# "-ing 式"假深度分析
'fake_depth': [
r'致力于', r'旨在', r'聚焦于', r'着眼于',
r'立足于', r'依托于', r'围绕着', r'基于', r'借助于'
],
# 广告式推销语言
'advertising': [
r'匠心独运', r'精心打造', r'倾力呈现', r'独具匠心',
r'别具一格', r'独树一帜', r'引领潮流', r'开启新篇章',
r'重新定义'
],
# 模糊归因和万金油说法
'vague_attribution': [
r'业内人士指出', r'专家表示', r'有观点认为',
r'据了解', r'据悉', r'相关人士透露', r'多方消息显示'
],
# 套路化的"挑战与展望"段落
'cliche_ending': [
r'尽管如此', r'虽然面临挑战', r'但我们有理由相信',
r'未来可期', r'前景广阔', r'任重道远', r'砥砺前行'
],
# 高频AI词汇
'ai_vocabulary': [
r'此外', r'值得一提的是', r'值得注意的是',
r'不言而喻', r'毋庸置疑', r'显而易见',
r'与此同时', r'综上所述', r'总而言之',
r'一言以蔽之', r'鉴于此', r'基于此',
r'有鉴于此', r'就此而言', r'从某种意义上说'
],
# 回避简单动词
'avoid_simple_verbs': [
r'作为[^,。]*而存在', r'扮演着[^,。]*的角色',
r'承担着[^,。]*的使命', r'发挥着[^,。]*的作用',
r'被视为', r'被认为是'
],
# 否定式并列句
'negative_parallel': [
r'不仅[^,。]*更是[^,。]*',
r'不只是[^,。]*而是[^,。]*'
],
# 三段式堆砌
'triple_structure': [
r'创新、品质与服务的完美结合',
r'高效、稳定、易用三大特点'
]
}}
# 替换映射
self.replacement_map = {{
# 语气转换
'本文将介绍': '今天来聊聊',
'建议用户': '建议大家',
'该产品性能优秀': '这个真的很好用',
'综上所述': '总之就是',
'值得注意的是': '划重点',
'需要指出的是': '这里要注意',
'根据研究显示': '我发现',
'一般来说': '通常来说',
'具体来说': '具体来说',
'换句话说': '简单说就是',
'例如': '比如',
'此外': '另外',
'然而': '不过',
'因此': '所以',
'最终': '最后',
# 简化表达
'为了能够实现这一目标': '为了',
'由于这一事实的存在': '因为',
'在当前这个时间点上': '现在',
'在如果需要帮助的情况下': '如果需要帮助',
'具有能够处理的能力': '能处理',
'需要特别指出的是': '',
# 具体化
'该项目一经发布便引发业界广泛关注': '发布后反响不错',
'业内专家普遍认为': '有专家认为',
'具有广阔的应用前景': '应用前景不错',
'对行业产生深远影响': '对行业影响挺大'
}}
def detect_ai_patterns(self, text: str) -> Dict:
"""检测AI写作模式"""
detection = {{
'total_patterns': 0,
'patterns_by_type': {{}},
'suggestions': []
}}
for pattern_type, patterns in self.ai_patterns.items():
count = 0
found_patterns = []
for pattern in patterns:
matches = re.findall(pattern, text)
if matches:
count += len(matches)
found_patterns.extend(matches)
if count > 0:
detection['patterns_by_type'][pattern_type] = {{
'count': count,
'examples': list(set(found_patterns))[:3] # 最多显示3个例子
}}
detection['total_patterns'] += count
# 生成建议
if detection['total_patterns'] > 10:
detection['suggestions'].append('AI痕迹较重,建议全面重写')
elif detection['total_patterns'] > 5:
detection['suggestions'].append('有较多AI痕迹,建议重点修改')
elif detection['total_patterns'] > 0:
detection['suggestions'].append('有少量AI痕迹,建议微调')
else:
detection['suggestions'].append('AI痕迹较少,质量不错')
return detection
def humanize_text(self, text: str, aggressive: bool = False) -> str:
"""去AI化处理"""
if not text:
return text
# 第一步:替换模式化表达
humanized = text
for pattern, replacement in self.replacement_map.items():
humanized = humanized.replace(pattern, replacement)
# 第二步:处理段落结构
paragraphs = humanized.split('\\n\\n')
processed_paragraphs = []
for para in paragraphs:
if not para.strip():
processed_paragraphs.append(para)
continue
# 缩短长段落
if len(para) > 200:
sentences = re.split(r'[。!?]', para)
if len(sentences) > 3:
para = '。'.join(sentences[:3]) + '。'
# 添加一点"人味"
if aggressive and len(para) > 50:
# 随机添加一些口语化表达
import random
human_touches = [
'说实话',
'我个人觉得',
'其实吧',
'怎么说呢',
'你猜怎么着'
]
if random.random() < 0.3: # 30%概率添加
touch = random.choice(human_touches)
para = f"{{touch}},{{para}}"
processed_paragraphs.append(para)
humanized = '\\n\\n'.join(processed_paragraphs)
# 第三步:修复过度修饰
# 移除过多的修饰词
modifiers = ['非常', '极其', '十分', '特别', '相当', '颇为']
for modifier in modifiers:
pattern = rf'{{modifier}}[的得地]?[^,。]*?的'
humanized = re.sub(pattern, '', humanized)
# 第四步:简化列表结构
lines = humanized.split('\\n')
simplified_lines = []
for line in lines:
# 简化加粗列表项
if re.search(r'\\*\\*.*?\\*\\*:', line):
line = re.sub(r'\\*\\*(.*?)\\*\\*:', r'\\1:', line)
simplified_lines.append(line)
humanized = '\\n'.join(simplified_lines)
return humanized
def add_human_touch(self, text: str) -> str:
"""添加人味"""
if not text:
return text
# 添加一些个人化的表达
touches = [
'我试过',
'我的经验是',
'说实话',
'个人觉得',
'其实吧',
'你猜怎么着',
'没想到的是'
]
import random
# 在开头添加
if random.random() < 0.4:
touch = random.choice(touches)
text = f"{{touch}},{{text}}"
# 在中间随机添加
sentences = re.split(r'[。!?]', text)
if len(sentences) > 2:
insert_pos = random.randint(1, len(sentences)-1)
touch = random.choice(touches)
sentences.insert(insert_pos, f"{{touch}},")
text = '。'.join(sentences)
return text
def analyze_and_humanize(self, text: str) -> Dict:
"""分析并去AI化"""
print("🔍 分析文本中的AI痕迹...")
# 检测AI模式
detection = self.detect_ai_patterns(text)
print(f"📊 检测结果:")
print(f" 总AI模式数: {{detection['total_patterns']}}")
for pattern_type, info in detection['patterns_by_type'].items():
print(f" {{pattern_type}}: {{info['count']}} 处")
if info['examples']:
print(f" 示例: {{', '.join(info['examples'][:2])}}")
# 去AI化处理
print("\\n🛠️ 进行去AI化处理...")
humanized = self.humanize_text(text, aggressive=detection['total_patterns'] > 5)
# 添加人味(如果需要)
if detection['total_patterns'] > 3:
print("💬 添加人味...")
humanized = self.add_human_touch(humanized)
# 计算改进程度
original_length = len(text)
humanized_length = len(humanized)
length_change = ((humanized_length - original_length) / original_length) * 100
result = {{
'original_text': text,
'humanized_text': humanized,
'detection': detection,
'stats': {{
'original_length': original_length,
'humanized_length': humanized_length,
'length_change_percent': round(length_change, 2),
'ai_patterns_removed': detection['total_patterns']
}},
'suggestions': detection['suggestions']
}}
print(f"✅ 处理完成")
print(f" 原文长度: {{original_length}} 字符")
print(f" 处理后长度: {{humanized_length}} 字符")
print(f" 长度变化: {{length_change:.1f}}%")
print(f" 建议: {{', '.join(detection['suggestions'])}}")
return result
def main():
"""主函数"""
import argparse
parser = argparse.ArgumentParser(description='中文去AI化工具')
subparsers = parser.add_subparsers(dest='command', help='命令')
# analyze命令
analyze_parser = subparsers.add_parser('analyze', help='分析文本')
analyze_parser.add_argument('--text', help='要分析的文本')
analyze_parser.add_argument('--file', help='文本文件路径')
# humanize命令
humanize_parser = subparsers.add_parser('humanize', help='去AI化处理')
humanize_parser.add_argument('--text', help='要处理的文本')
humanize_parser.add_argument('--file', help='文本文件路径')
humanize_parser.add_argument('--output', help='输出文件路径')
humanize_parser.add_argument('--aggressive', action='store_true', help='激进模式')
# test命令
subparsers.add_parser('test', help='测试功能')
args = parser.parse_args()
humanizer = HumanizerCN()
if args.command == 'analyze':
text = args.text
if args.file:
with open(args.file, 'r', encoding='utf-8') as f:
text = f.read()
if not text:
print("❌ 请提供文本")
return
result = humanizer.analyze_and_humanize(text)
print("\\n📊 分析结果:")
print(json.dumps(result['detection'], indent=2, ensure_ascii=False))
elif args.command == 'humanize':
text = args.text
if args.file:
with open(args.file, 'r', encoding='utf-8') as f:
text = f.read()
if not text:
print("❌ 请提供文本")
return
result = humanizer.analyze_and_humanize(text)
if args.output:
with open(args.output, 'w', encoding='utf-8') as f:
f.write(result['humanized_text'])
print(f"✅ 已保存到: {{args.output}}")
else:
print("\\n📝 处理后的文本:")
print("=" * 60)
print(result['humanized_text'])
print("=" * 60)
elif args.command == 'test':
test_text = """该软件的发布标志着人工智能领域的一个重要里程碑,彰显了公司在技术创新方面的不懈追求。此外,值得一提的是,该产品具有高性能、低功耗、易扩展三大优势。业内专家普遍认为,这将对整个行业产生深远影响。尽管面临诸多挑战,但我们有理由相信,未来可期。"""
print("🧪 测试去AI化功能")
print("=" * 60)
print("测试文本:")
print(test_text)
print("=" * 60)
result = humanizer.analyze_and_humanize(test_text)
print("\\n📝 处理后的文本:")
print("=" * 60)
print(result['humanized_text'])
print("=" * 60)
else:
parser.print_help()
if __name__ == "__main__":
main()
'''
try:
with open(target_file, 'w', encoding='utf-8') as f:
f.write(implementation)
# 设置执行权限
os.chmod(target_file, 0o755)
print(f"✅ 中文去AI化技能已实现: {target_file}")
return True
except Exception as e:
print(f"❌ 实现失败: {e}")
return False
def create_integration_report(self):
"""创建集成报告"""
print("📋 创建技能集成报告...")
available_skills, missing_skills = self.analyze_skills()
report = f"""# oh-my-writing-skill 集成报告
## 概览
- 源目录: {self.source_dir}
- 目标目录: {self.target_dir}
- 分析时间: {self._get_current_time()}
## 技能分析
### 已下载技能 ({len(available_skills)}个)
"""
for skill in available_skills:
report += f"#### {skill['name']} ({skill['id']})\n"
report += f"- 描述: {skill['description']}\n"
report += f"- 状态: {skill['status']}\n"
report += f"- 文件: {skill['source']}\n\n"
if missing_skills:
report += f"### 缺失技能 ({len(missing_skills)}个)\n\n"
for skill in missing_skills:
report += f"- {skill['name']} ({skill['id']}): {skill['description']}\n"
report += "\n"
# 集成状态
report += "## 集成状态\n\n"
integrated_count = 0
for skill_id, skill_info in self.skill_mapping.items():
status = "✅ 已集成" if skill_info['already_implemented'] else "⏳ 待集成"
if skill_info['already_implemented']:
integrated_count += 1
report += f"- {skill_info['name']}: {status}\n"
report += f"\n集成进度: {integrated_count}/{len(self.skill_mapping)} ({integrated_count/len(self.skill_mapping)*100:.1f}%)\n\n"
# 下一步建议
report += "## 下一步建议\n\n"
if integrated_count < len(self.skill_mapping):
report += "1. **优先集成中文去AI化技能** - 提升内容自然度\n"
report += "2. **集成深度研究技能** - 增强内容质量\n"
report += "3. **集成图片搜索技能** - 丰富内容配图\n"
report += "4. **集成通用写作技能** - 完善创作流程\n"
else:
report += "✅ 所有技能已集成完成\n"
# 使用方式
report += "## 使用方式\n\n"
report += "```bash\n"
report += "# 1. 小红书内容转换\n"
report += "python3 oh_my_writing_converter.py convert --input article.md --output xiaohongshu.md\n\n"
report += "# 2. 中文去AI化\n"
report += "python3 humanizer_cn.py humanize --file article.md --output humanized.md\n\n"
report += "# 3. 集成到IT资讯系统\n"
report += "# 系统已自动集成,每天16:00自动运行\n"
report += "```\n\n"
# 保存报告
report_file = self.target_dir / "integration_report.md"
with open(report_file, 'w', encoding='utf-8') as f:
f.write(report)
print(f"✅ 集成报告已保存: {report_file}")
return report
def _get_current_time(self):
"""获取当前时间"""
from datetime import datetime
return datetime.now().strftime("%Y-%m-%d %H:%M:%S")
def integrate_with_it_system(self):
"""集成到IT资讯系统"""
print("🔗 集成到IT资讯自动化系统...")
# 1. 更新内容转换器
print("1. 更新内容转换器...")
# 我们已经更新了content_converter.py,现在确认一下
converter_file = self.target_dir / "content_converter.py"
if converter_file.exists():
print(f"✅ 内容转换器已更新: {converter_file}")
else:
print(f"❌ 内容转换器不存在: {converter_file}")
# 2. 创建集成配置文件
print("2. 创建集成配置文件...")
config = {
'oh_my_writing_integration': {
'enabled': True,
'integration_date': self._get_current_time(),
'integrated_skills': [],
'config': {
'use_humanizer': True,
'use_xiaohongshu_converter': True,
'aggressive_mode': False,
'auto_select_best': True
}
}
}
# 添加已集成的技能
for skill_id, skill_info in self.skill_mapping.items():
if skill_info['already_implemented']:
config['oh_my_writing_integration']['integrated_skills'].append({
'id': skill_id,
'name': skill_info['name'],
'status': 'implemented'
})
config_file = self.target_dir / "oh_my_writing_config.json"
with open(config_file, 'w', encoding='utf-8') as f:
json.dump(config, f, indent=2, ensure_ascii=False)
print(f"✅ 集成配置文件已创建: {config_file}")
# 3. 更新IT资讯系统脚本
print("3. 更新IT资讯系统脚本...")
# 检查IT资讯系统目录
it_system_dir = Path("/home/ubuntu/.nanobot/workspace/InformationCrawler")
if it_system_dir.exists():
print(f"✅ IT资讯系统目录存在: {it_system_dir}")
# 检查主调度脚本
main_script = it_system_dir / "main_scheduler_with_xhs.sh"
if main_script.exists():
print(f"✅ 主调度脚本存在: {main_script}")
# 检查是否已经集成了oh-my-writing-skill
with open(main_script, 'r', encoding='utf-8') as f:
content = f.read()
if 'oh_my_writing' in content or 'oh-my-writing' in content:
print("✅ oh-my-writing-skill 已集成到IT资讯系统")
else:
print("⚠️ oh-my-writing-skill 未集成到IT资讯系统,需要手动集成")
else:
print(f"❌ 主调度脚本不存在: {main_script}")
else:
print(f"❌ IT资讯系统目录不存在: {it_system_dir}")
print("✅ 集成完成")
return True
def main():
"""主函数"""
import argparse
parser = argparse.ArgumentParser(description='oh-my-writing-skill 集成管理器')
subparsers = parser.add_subparsers(dest='command', help='命令')
# analyze命令
subparsers.add_parser('analyze', help='分析技能')
# extract命令
extract_parser = subparsers.add_parser('extract', help='提取技能知识')
extract_parser.add_argument('skill', help='技能ID')
# implement命令
implement_parser = subparsers.add_parser('implement', help='实现技能')
implement_parser.add_argument('skill', help='技能ID')
# report命令
subparsers.add_parser('report', help='创建集成报告')
# integrate命令
subparsers.add_parser('integrate', help='集成到IT系统')
# all命令
subparsers.add_parser('all', help='执行完整集成流程')
args = parser.parse_args()
integrator = OhMyWritingIntegration()
if args.command == 'analyze':
integrator.analyze_skills()
elif args.command == 'extract':
knowledge = integrator.extract_skill_knowledge(args.skill)
if knowledge:
print(f"📖 技能知识: {knowledge['name']}")
print(f"📝 摘要:")
print(knowledge['summary'])
print(f"\\n🔑 关键点:")
for point in knowledge['key_points'][:10]:
print(f" • {point}")
elif args.command == 'implement':
if args.skill == 'humanizer-cn':
integrator.implement_humanizer_cn()
else:
print(f"❌ 暂不支持实现技能: {args.skill}")
print(f"✅ 已支持的技能: humanizer-cn")
elif args.command == 'report':
integrator.create_integration_report()
elif args.command == 'integrate':
integrator.integrate_with_it_system()
elif args.command == 'all':
print("🚀 执行完整集成流程...")
print()
# 1. 分析技能
integrator.analyze_skills()
print()
# 2. 实现中文去AI化技能
integrator.implement_humanizer_cn()
print()
# 3. 创建集成报告
integrator.create_integration_report()
print()
# 4. 集成到IT系统
integrator.integrate_with_it_system()
print()
print("🎉 完整集成流程完成!")
else:
parser.print_help()
if __name__ == "__main__":
main()