xhs_factory/services/hotspot.py

"""
services/hotspot.py
热点探测、热点生成、笔记列表缓存（供评论管家主动评论使用）
"""
import threading
import logging

import gradio as gr

from llm_service import LLMService
from mcp_client import get_mcp_client
from services.connection import _get_llm_config
from services.persona import _resolve_persona

logger = logging.getLogger("autobot")

# ==================================================
#                Tab 2: 热点探测
# ==================================================


def search_hotspots(keyword, sort_by, mcp_url):
    """搜索小红书热门内容"""
    if not keyword:
        return "❌ 请输入搜索关键词", ""
    try:
        client = get_mcp_client(mcp_url)
        result = client.search_feeds(keyword, sort_by=sort_by)
        if "error" in result:
            return f"❌ 搜索失败: {result['error']}", ""
        text = result.get("text", "无结果")
        return "✅ 搜索完成", text
    except Exception as e:
        logger.error("热点搜索失败: %s", e)
        return f"❌ 搜索失败: {e}", ""


def analyze_and_suggest(model, keyword, search_result):
    """AI 分析热点并给出建议"""
    if not search_result:
        return "❌ 请先搜索", "", ""
    api_key, base_url, _ = _get_llm_config()
    if not api_key:
        return "❌ 请先配置 LLM 提供商", "", ""
    try:
        svc = LLMService(api_key, base_url, model)
        analysis = svc.analyze_hotspots(search_result)

        topics = "\n".join(f"• {t}" for t in analysis.get("hot_topics", []))
        patterns = "\n".join(f"• {p}" for p in analysis.get("title_patterns", []))
        suggestions = "\n".join(
            f"**{s['topic']}** - {s['reason']}"
            for s in analysis.get("suggestions", [])
        )
        structure = analysis.get("content_structure", "")

        summary = (
            f"## 🔥 热门选题\n{topics}\n\n"
            f"## 📝 标题套路\n{patterns}\n\n"
            f"## 📐 内容结构\n{structure}\n\n"
            f"## 💡 推荐选题\n{suggestions}"
        )
        return "✅ 分析完成", summary, keyword
    except Exception as e:
        logger.error("热点分析失败: %s", e)
        return f"❌ 分析失败: {e}", "", ""


def generate_from_hotspot(model, topic_from_hotspot, style, search_result, sd_model_name, persona_text):
    """基于热点分析生成文案（自动适配 SD 模型，支持人设）"""
    if not topic_from_hotspot:
        return "", "", "", "", "❌ 请先选择或输入选题"
    api_key, base_url, _ = _get_llm_config()
    if not api_key:
        return "", "", "", "", "❌ 请先配置 LLM 提供商"
    try:
        svc = LLMService(api_key, base_url, model)
        persona = _resolve_persona(persona_text) if persona_text else None
        data = svc.generate_copy_with_reference(
            topic=topic_from_hotspot,
            style=style,
            reference_notes=search_result[:2000],
            sd_model_name=sd_model_name,
            persona=persona,
        )
        tags = data.get("tags", [])
        return (
            data.get("title", ""),
            data.get("content", ""),
            data.get("sd_prompt", ""),
            ", ".join(tags),
            "✅ 基于热点的文案已生成",
        )
    except Exception as e:
        return "", "", "", "", f"❌ 生成失败: {e}"


# ==================================================
#              Tab 3: 评论管家
# ==================================================

# ---- 共用: 笔记列表缓存（线程安全）----

# 主动评论缓存
_cached_proactive_entries: list[dict] = []
# 我的笔记评论缓存
_cached_my_note_entries: list[dict] = []
# 缓存互斥锁，防止并发回调产生竞态
_cache_lock = threading.RLock()


def _set_cache(name: str, entries: list):
    """线程安全地更新笔记列表缓存"""
    global _cached_proactive_entries, _cached_my_note_entries
    with _cache_lock:
        if name == "proactive":
            _cached_proactive_entries = list(entries)
        else:
            _cached_my_note_entries = list(entries)


def _get_cache(name: str) -> list:
    """线程安全地获取笔记列表缓存快照（返回副本）"""
    with _cache_lock:
        if name == "proactive":
            return list(_cached_proactive_entries)
        return list(_cached_my_note_entries)


def _fetch_and_cache(keyword, mcp_url, cache_name="proactive"):
    """通用: 获取笔记列表并线程安全地缓存"""
    try:
        client = get_mcp_client(mcp_url)
        if keyword and keyword.strip():
            entries = client.search_feeds_parsed(keyword.strip())
            src = f"搜索「{keyword.strip()}」"
        else:
            entries = client.list_feeds_parsed()
            src = "首页推荐"

        _set_cache(cache_name, entries)

        if not entries:
            return gr.update(choices=[], value=None), f"⚠️ 从{src}未找到笔记"

        choices = []
        for i, e in enumerate(entries):
            title_short = (e["title"] or "无标题")[:28]
            label = f"[{i+1}] {title_short}  |  @{e['author'] or '未知'}  |  ❤ {e['likes']}"
            choices.append(label)

        return (
            gr.update(choices=choices, value=choices[0]),
            f"✅ 从{src}获取 {len(entries)} 条笔记",
        )
    except Exception as e:
        _set_cache(cache_name, [])
        return gr.update(choices=[], value=None), f"❌ {e}"


def _pick_from_cache(selected, cache_name="proactive"):
    """通用: 从缓存中提取选中条目的 feed_id / xsec_token / title（线程安全快照）"""
    cache = _get_cache(cache_name)
    if not selected or not cache:
        return "", "", ""
    try:
        # 尝试从 [N] 前缀提取序号
        idx = int(selected.split("]")[0].replace("[", "")) - 1
        if 0 <= idx < len(cache):
            e = cache[idx]
            return e["feed_id"], e["xsec_token"], e.get("title", "")
    except (ValueError, IndexError):
        pass
    # 回退: 模糊匹配标题
    for e in cache:
        if e.get("title", "")[:15] in selected:
            return e["feed_id"], e["xsec_token"], e.get("title", "")
    return "", "", ""


# ---- 模块 A: 主动评论他人 ----

def fetch_proactive_notes(keyword, mcp_url):
    return _fetch_and_cache(keyword, mcp_url, "proactive")


def on_proactive_note_selected(selected):
    return _pick_from_cache(selected, "proactive")