getnote_interactive.py

#!/usr/bin/env python3
"""
Get 笔记知识库交互式浏览工具
支持序号选择、完整内容查看和公众号文章适配性评估
"""

import os
import sys
from pathlib import Path
from typing import List, Dict

# 加载环境变量
config_dir = Path(__file__).parent / "config"
getnote_env = config_dir / "getnote.env"

if getnote_env.exists():
    with open(getnote_env, 'r', encoding='utf-8') as f:
        for line in f:
            line = line.strip()
            if line and not line.startswith('#') and '=' in line:
                key, value = line.split('=', 1)
                os.environ[key.strip()] = value.strip()

from mcp_tools.getnote import GetNoteAPI


class GetNoteInteractive:
    """Get 笔记交互式浏览器"""

    def __init__(self):
        self.client = GetNoteAPI()
        self.all_notes = []
        self.all_files = {}

    def fetch_all_content(self):
        """获取所有知识库内容"""
        print("🔍 正在加载知识库内容...\n")

        keywords = ['文章', '教程', '指南', 'AI', '开发', '学习']
        all_items = {}

        for kw in keywords:
            try:
                materials = self.client.recall(kw, top_k=30)
                for m in materials:
                    item_id = m.get('id')
                    if item_id and item_id not in all_items:
                        all_items[item_id] = m
            except:
                continue

        # 分类
        self.all_notes = [m for m in all_items.values() if m.get('type') == 'NOTE']
        self.all_notes.sort(key=lambda x: x.get('title', ''))

        for m in all_items.values():
            if m.get('type') == 'FILE':
                title = m.get('title', '无标题')
                if title not in self.all_files:
                    self.all_files[title] = []
                self.all_files[title].append(m)

    def show_all_titles(self):
        """显示所有笔记标题"""
        print("=" * 70)
        print("📚 Get 笔记知识库 - 全部内容")
        print("=" * 70)
        print()

        print(f"📝 笔记（NOTE）: {len(self.all_notes)} 条\n")

        for i, note in enumerate(self.all_notes, 1):
            title = note.get('title', '无标题')
            extra = note.get('extra', {})
            url = extra.get('url', '') if isinstance(extra, dict) else ''

            print(f"{i:2d}. {title}")
            if url:
                print(f"    🔗 {url}")

        if self.all_files:
            print(f"\n📄 文档（FILE）: {len(self.all_files)} 份\n")
            for i, (title, fragments) in enumerate(self.all_files.items(), len(self.all_notes) + 1):
                print(f"{i:2d}. {title}")
                print(f"    （共 {len(fragments)} 个片段）")

        print()
        print("=" * 70)

    def get_full_content(self, index: int) -> Dict:
        """获取完整内容（处理多片段情况）"""
        total_notes = len(self.all_notes)

        if index <= total_notes:
            # 选择的是笔记
            note = self.all_notes[index - 1]
            title = note.get('title', '无标题')

            # 检查是否有多个片段
            print(f"\n🔍 正在获取《{title}》的完整内容...\n")

            # 搜索同标题的所有片段
            all_fragments = self.client.recall(title, top_k=50)
            fragments = [f for f in all_fragments if f.get('title') == title]

            if len(fragments) > 1:
                print(f"✅ 发现 {len(fragments)} 个片段，正在合并...\n")

                # 合并内容
                full_content = ""
                for frag in fragments:
                    content = frag.get('content', '')
                    if content and content not in full_content:
                        full_content += content + "\n\n"

                return {
                    'title': title,
                    'content': full_content.strip(),
                    'type': note.get('type'),
                    'url': note.get('extra', {}).get('url', ''),
                    'fragments': len(fragments)
                }
            else:
                return {
                    'title': title,
                    'content': note.get('content', ''),
                    'type': note.get('type'),
                    'url': note.get('extra', {}).get('url', ''),
                    'fragments': 1
                }
        else:
            # 选择的是文档
            file_index = index - total_notes - 1
            file_titles = list(self.all_files.keys())

            if file_index < len(file_titles):
                title = file_titles[file_index]
                fragments = self.all_files[title]

                print(f"\n🔍 正在合并《{title}》的 {len(fragments)} 个片段...\n")

                # 合并所有片段
                full_content = ""
                for frag in fragments:
                    content = frag.get('content', '')
                    if content:
                        full_content += content + "\n\n"

                return {
                    'title': title,
                    'content': full_content.strip(),
                    'type': 'FILE',
                    'url': '',
                    'fragments': len(fragments)
                }

        return None

    def evaluate_for_wechat(self, content_data: Dict) -> Dict:
        """评估内容是否适合写公众号文章"""
        title = content_data.get('title', '')
        content = content_data.get('content', '')
        url = content_data.get('url', '')

        # 基础指标
        word_count = len(content)
        has_url = bool(url)
        content_type = content_data.get('type', '')

        # 评估结果
        evaluation = {
            'suitable': False,
            'score': 0,
            'reasons': [],
            'suggestions': []
        }

        # 1. 长度评估
        if word_count >= 500:
            evaluation['score'] += 25
            evaluation['reasons'].append(f"✅ 内容长度充足（约{word_count}字）")
        elif word_count >= 300:
            evaluation['score'] += 15
            evaluation['reasons'].append(f"⚠️  内容长度适中（约{word_count}字），建议扩充")
        else:
            evaluation['reasons'].append(f"❌ 内容过短（约{word_count}字），需要大量扩充")
            evaluation['suggestions'].append("补充更多案例、故事或实践经验")

        # 2. 结构评估
        has_structure = any(keyword in content for keyword in ['一、', '二、', '1.', '2.', '##', '###'])
        if has_structure:
            evaluation['score'] += 20
            evaluation['reasons'].append("✅ 内容有清晰结构")
        else:
            evaluation['reasons'].append("⚠️  建议添加明确的章节结构")
            evaluation['suggestions'].append("使用小标题划分内容层次")

        # 3. 实践性评估
        practical_keywords = ['方法', '技巧', '步骤', '如何', '实践', '案例', '经验', '教程']
        practical_count = sum(1 for kw in practical_keywords if kw in content)

        if practical_count >= 3:
            evaluation['score'] += 25
            evaluation['reasons'].append("✅ 内容具有实践性和可操作性")
        elif practical_count >= 1:
            evaluation['score'] += 15
            evaluation['reasons'].append("⚠️  有一定实践性，可增强可操作性")
            evaluation['suggestions'].append("添加更多具体方法和步骤")
        else:
            evaluation['reasons'].append("❌ 缺少实践指导")
            evaluation['suggestions'].append("补充具体的操作方法和案例")

        # 4. 话题热度评估
        hot_topics = ['AI', 'Claude', '提示词', '效率', '时间管理', '职场', '创业', '学习']
        has_hot_topic = any(topic in title or topic in content[:200] for topic in hot_topics)

        if has_hot_topic:
            evaluation['score'] += 15
            evaluation['reasons'].append("✅ 话题有热度和关注度")
        else:
            evaluation['reasons'].append("⚠️  话题可以更贴近热点")
            evaluation['suggestions'].append("结合当前热门话题或痛点")

        # 5. 原创性评估
        if has_url:
            evaluation['score'] += 15
            evaluation['reasons'].append(f"✅ 有原文链接，可作为参考素材")
        else:
            evaluation['reasons'].append("⚠️  无原文链接，注意版权问题")

        # 综合评估
        if evaluation['score'] >= 75:
            evaluation['suitable'] = True
            evaluation['level'] = "🌟🌟🌟 强烈推荐"
            evaluation['summary'] = "内容质量优秀，非常适合改编为公众号文章"
        elif evaluation['score'] >= 60:
            evaluation['suitable'] = True
            evaluation['level'] = "🌟🌟 推荐"
            evaluation['summary'] = "内容基础较好，稍作优化即可发布"
        elif evaluation['score'] >= 40:
            evaluation['suitable'] = False
            evaluation['level'] = "🌟 可考虑"
            evaluation['summary'] = "内容有潜力，但需要较多改进和扩充"
        else:
            evaluation['suitable'] = False
            evaluation['level'] = "❌ 不推荐"
            evaluation['summary'] = "当前内容不太适合，建议寻找其他素材"

        return evaluation

    def show_content_and_evaluation(self, content_data: Dict, evaluation: Dict):
        """显示完整内容和评估结果"""
        print("=" * 70)
        print(f"📄 《{content_data['title']}》")
        print("=" * 70)
        print()

        # 基本信息
        print("【基本信息】")
        print(f"类型: {content_data.get('type', '未知')}")
        if content_data.get('fragments', 1) > 1:
            print(f"片段数: {content_data['fragments']} 个")
        if content_data.get('url'):
            print(f"原文: {content_data['url']}")
        print()

        # 内容预览
        content = content_data.get('content', '')
        print("【内容预览】")
        print("-" * 70)
        # 显示前1000字
        preview_length = min(1000, len(content))
        print(content[:preview_length])
        if len(content) > preview_length:
            print(f"\n... （还有 {len(content) - preview_length} 字）")
        print("-" * 70)
        print()

        # 核心摘要
        print("【核心摘要】")
        # 提取前300字作为摘要
        summary = content[:300].replace('\n', ' ')
        print(f"{summary}...")
        print()

        # 公众号适配性评估
        print("=" * 70)
        print("📊 公众号文章适配性评估")
        print("=" * 70)
        print()

        print(f"【综合评分】{evaluation['score']}/100")
        print(f"【推荐等级】{evaluation['level']}")
        print(f"【评估结论】{evaluation['summary']}")
        print()

        print("【详细分析】")
        for reason in evaluation['reasons']:
            print(f"  {reason}")

        if evaluation['suggestions']:
            print()
            print("【优化建议】")
            for suggestion in evaluation['suggestions']:
                print(f"  • {suggestion}")

        print()
        print("=" * 70)

    def run(self):
        """运行交互式流程"""
        # 1. 获取所有内容
        self.fetch_all_content()

        # 2. 显示标题列表
        self.show_all_titles()

        # 3. 提示用户输入
        print()
        print("💡 请输入文章序号查看完整内容和评估（输入 0 退出）")

        while True:
            try:
                user_input = input("\n请选择 [0-%d]: " % (len(self.all_notes) + len(self.all_files))).strip()

                if not user_input:
                    continue

                choice = int(user_input)

                if choice == 0:
                    print("\n👋 再见！")
                    break

                max_index = len(self.all_notes) + len(self.all_files)
                if choice < 1 or choice > max_index:
                    print(f"❌ 无效选择，请输入 1-{max_index} 之间的数字")
                    continue

                # 4. 获取完整内容
                content_data = self.get_full_content(choice)

                if not content_data:
                    print("❌ 获取内容失败")
                    continue

                # 5. 评估适配性
                evaluation = self.evaluate_for_wechat(content_data)

                # 6. 显示结果
                print()
                self.show_content_and_evaluation(content_data, evaluation)

                # 继续或退出
                print()
                continue_choice = input("按 Enter 继续选择，输入 q 退出: ").strip().lower()
                if continue_choice == 'q':
                    print("\n👋 再见！")
                    break

                # 重新显示标题列表
                print()
                self.show_all_titles()

            except ValueError:
                print("❌ 请输入有效的数字")
            except KeyboardInterrupt:
                print("\n\n👋 已取消")
                break
            except Exception as e:
                print(f"\n❌ 错误: {e}")
                import traceback
                traceback.print_exc()


def main():
    """主函数"""
    try:
        browser = GetNoteInteractive()
        browser.run()
    except KeyboardInterrupt:
        print("\n\n👋 已取消")
        sys.exit(0)
    except Exception as e:
        print(f"\n❌ 程序错误: {e}")
        import traceback
        traceback.print_exc()
        sys.exit(1)


if __name__ == "__main__":
    main()