yu-zhi-ran/scripts/outline.py

#!/usr/bin/env python3
"""
大纲阶段：基于选题和研究笔记，用 LLM 动态生成结构化大纲
"""

import json, datetime, logging, sys, re
from pathlib import Path
from typing import Dict

PROJECT_ROOT = Path(__file__).parent.parent
sys.path.insert(0, str(PROJECT_ROOT))
sys.path.insert(0, str(PROJECT_ROOT / "platform" / "backend"))

from db_helper import get_topic_by_id
from prompt_loader import get_prompt, get_prompt_params
try:
    from app.core.nvidia_client import call_llm
    HAVE_LLM = True
except ImportError:
    HAVE_LLM = False

DATA_DIR = PROJECT_ROOT / "automation" / "data"
RESEARCH_DIR = DATA_DIR / "research"
OUTPUT_DIR = DATA_DIR / "outlines"
LOGS_DIR = PROJECT_ROOT / "automation" / "logs"
TODAY = datetime.datetime.now().strftime("%Y-%m-%d")

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s',
                    handlers=[logging.FileHandler(LOGS_DIR / f"outline_{TODAY}.log"), logging.StreamHandler()])
logger = logging.getLogger(__name__)

class Outliner:
    def __init__(self, topic_id: str):
        self.topic_id = topic_id
        self.topic = self._load_topic()
        research_file = RESEARCH_DIR / TODAY / f"{topic_id}_research.md"
        self.research_notes = research_file.read_text(encoding='utf-8') if research_file.exists() else ""
        self.output_dir = OUTPUT_DIR / TODAY
        self.output_dir.mkdir(parents=True, exist_ok=True)

    def _load_topic(self) -> Dict:
        topic = get_topic_by_id(self.topic_id)
        if not topic: raise ValueError(f"Topic {self.topic_id} not found")
        return topic

    @staticmethod
    def _extract_seo_keywords(research_notes: str) -> str:
        """从研究笔记中提取 SEO 关键词"""
        if not research_notes:
            return "暂无"
        # 尝试匹配 "SEO关键词建议" 块
        m = re.search(r'(?:SEO关键词建议|SEO关键词|搜索词)[：:]\s*(.*?)(?:\n\n|\Z)', research_notes, re.DOTALL)
        if m:
            return m.group(1).strip()[:300]
        # 回退：取所有 # 标签或关键词模式
        keywords = re.findall(r'[#＃]([\u4e00-\u9fff\w]{2,6})', research_notes)
        if keywords:
            return "、".join(keywords[:5])
        return "暂无"

    def generate_outline(self) -> str:
        title = self.topic['title']
        field = self.topic.get('field', '')
        core = self.topic.get('core_concept', '')
        pain = self.topic.get('audience_pain', '')
        angle = self.topic.get('unique_angle', '')
        cases_summary = self.research_notes[:2000] if self.research_notes else "暂无研究笔记"
        seo_keywords = self._extract_seo_keywords(self.research_notes)

        if HAVE_LLM:
            _now = datetime.datetime.now()
            prompt = get_prompt("outline_generation",
                date=_now.strftime('%Y年%m月%d日'),
                year=_now.year,
                title=title,
                field=field,
                core=core,
                pain=pain,
                angle=angle,
                cases_summary=cases_summary,
                seo_keywords=seo_keywords,
            )
            try:
                params = get_prompt_params("outline_generation")
                outline = call_llm(prompt, temperature=params.get("temperature", 0.7), max_tokens=params.get("max_tokens", 4000), system_prompt="你是一个有经验的内容编辑，擅长为不同选题设计差异化的文章结构。")
                logger.info(f"LLM 大纲生成成功，长度：{len(outline)}")
                return f"# 文章大纲：{title}\n\n{outline}\n\n---\n*大纲生成时间：{TODAY}*"
            except Exception as e:
                logger.warning(f"LLM 大纲生成失败: {e}，使用模板")

        return self._template_outline(title, field, core, pain, angle)

    def _template_outline(self, title, field, core, pain, angle) -> str:
        case_count = self.research_notes.count('### 案例') if self.research_notes else 0
        case_section = f"""## 四、全球/行业趋势与案例
- 引用研究笔记中的 {case_count} 个案例，精选 2-3 个详述
- 数据支撑：提取研究笔记中的关键数据
- 趋势分析""" if case_count > 0 else ""
        return f"""# 文章大纲：{title}

## 一、引言
- 场景切入：{title}
- 点明文章价值

## 二、核心观点
{core}

## 三、受众痛点分析
{pain}
{case_section}

## {"五" if case_section else "四"}、本土落地建议
- 结合{field}领域特点
- 提供可执行的步骤
- 注意事项

## {"六" if case_section else "五"}、独特视角：{angle}

## {"七" if case_section else "六"}、行动指南
1. 了解现状 2. 制定方案 3. 小范围验证 4. 持续优化

## {"八" if case_section else "七"}、总结与鼓励

---

*大纲生成时间：{TODAY}*"""

    def save(self):
        outline_text = self.generate_outline()
        out_path = self.output_dir / f"{self.topic_id}_outline.md"
        out_path.write_text(outline_text, encoding='utf-8')
        logger.info(f"大纲已保存: {out_path}")
        return out_path

def main():
    import argparse
    parser = argparse.ArgumentParser()
    parser.add_argument('--topic-id', required=True)
    args = parser.parse_args()
    o = Outliner(args.topic_id)
    o.save()
    print(f"SUCCESS: Outline created for {args.topic_id}")
    sys.exit(0)

if __name__ == "__main__":
    main()