初始化红餐观察库项目

2026-07-19 18:11:08 +08:00
commit c663539548
22 changed files with 1261 additions and 0 deletions
@@ -0,0 +1,106 @@
+#!/usr/bin/env python3
+"""Extract cross-article restaurant industry signals from cached Qwen analyses."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import os
+import sqlite3
+import urllib.error
+import urllib.request
+from datetime import datetime, timedelta
+
+from app import DB_PATH, ensure_schema, now_iso
+
+
+def call_qwen(items: list[dict], model: str) -> list[dict]:
+    key = os.getenv("DASHSCOPE_API_KEY", "").strip()
+    if not key:
+        raise RuntimeError("尚未配置 DASHSCOPE_API_KEY")
+    prompt = f"""你是餐饮产业首席分析师。根据以下多篇文章的结构化分析，识别跨文章、可验证、有经营意义的行业信号。
+只返回合法 JSON：{{"signals":[...]}}。每个 signal 必须包含：title（短标题）、summary（100-180字）、trend（emerging/accelerating/stable/declining）、confidence（0到1）、article_ids（至少2个证据文章ID；确实只有单篇强信号时可为1个）、implications（2-4条经营启示）、tags（3-6个标签）。
+不要把单一品牌新闻简单改写成行业信号；合并重复主题；最多输出8条；没有充分证据就少输出。
+输入：{json.dumps(items, ensure_ascii=False)}"""
+    body = json.dumps({
+        "model": model,
+        "messages": [
+            {"role": "system", "content": "你进行基于证据的餐饮行业趋势聚类，避免空泛结论。"},
+            {"role": "user", "content": prompt},
+        ],
+        "temperature": 0.2,
+        "response_format": {"type": "json_object"},
+    }, ensure_ascii=False).encode("utf-8")
+    req = urllib.request.Request(
+        "https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions",
+        data=body,
+        headers={"Authorization": f"Bearer {key}", "Content-Type": "application/json"},
+        method="POST",
+    )
+    try:
+        with urllib.request.urlopen(req, timeout=120) as response:
+            result = json.loads(response.read().decode("utf-8"))
+    except urllib.error.HTTPError as exc:
+        raise RuntimeError(f"千问接口返回 {exc.code}：{exc.read().decode('utf-8', errors='replace')[:500]}") from exc
+    text = result["choices"][0]["message"]["content"].strip()
+    if text.startswith("```"):
+        text = text.strip("`").removeprefix("json").strip()
+    return json.loads(text).get("signals", [])
+
+
+def run(days: int) -> int:
+    ensure_schema()
+    model = os.getenv("QWEN_MODEL", "qwen-plus")
+    cutoff = (datetime.now() - timedelta(days=days)).strftime("%Y-%m-%dT%H:%M:%S")
+    conn = sqlite3.connect(DB_PATH)
+    conn.row_factory = sqlite3.Row
+    rows = conn.execute(
+        """
+        SELECT a.id,a.title,a.published_at,x.result_json
+        FROM articles a JOIN ai_analyses x ON x.article_id=a.id
+        WHERE a.crawl_status='success' AND a.published_at>=?
+        ORDER BY a.published_at DESC
+        """,
+        (cutoff,),
+    ).fetchall()
+    items = []
+    for row in rows:
+        analysis = json.loads(row["result_json"])
+        items.append({
+            "article_id": row["id"], "title": row["title"], "published_at": row["published_at"],
+            "summary": analysis.get("summary"), "key_points": analysis.get("key_points", []),
+            "industry_signal": analysis.get("industry_signal"), "tags": analysis.get("tags", []),
+        })
+    if not items:
+        print(json.dumps({"status": "skipped", "reason": "没有已分析文章"}, ensure_ascii=False))
+        return 0
+    signals = call_qwen(items, model)
+    signal_date = datetime.now().astimezone().date().isoformat()
+    timestamp = now_iso()
+    conn.execute("DELETE FROM industry_signals WHERE signal_date=?", (signal_date,))
+    for signal in signals:
+        conn.execute(
+            """
+            INSERT INTO industry_signals
+              (signal_date,title,summary,trend,confidence,implications_json,article_ids_json,tags_json,model,created_at,updated_at)
+            VALUES (?,?,?,?,?,?,?,?,?,?,?)
+            """,
+            (
+                signal_date, signal["title"], signal["summary"], signal.get("trend", "emerging"),
+                float(signal.get("confidence", 0.5)), json.dumps(signal.get("implications", []), ensure_ascii=False),
+                json.dumps(signal.get("article_ids", [])), json.dumps(signal.get("tags", []), ensure_ascii=False),
+                model, timestamp, timestamp,
+            ),
+        )
+    conn.commit()
+    conn.close()
+    print(json.dumps({"status": "success", "input_articles": len(items), "signals": len(signals), "date": signal_date}, ensure_ascii=False))
+    return 0
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="提炼红餐文章跨文行业信号")
+    parser.add_argument("--days", type=int, default=30, help="聚合最近多少天的文章")
+    args = parser.parse_args()
+    raise SystemExit(run(args.days))
+