feat: 所有新闻/政策/研究摘要加入 pub_time 发布时间字段\n\n- summarize_news.py: AI摘要后用原始RSS时间按标题匹配回填pub_time\n- summarize_policy.py: 同上\n- summarize_research.py: 同上\n- 时间格式: 当天显示HH:MM, 非当天显示MM-DD HH:MM\n- 前端brief.html: 新闻卡片badge行右侧显示pub_time\n- 已用backfill脚本为现有数据补填pub_time(96/102, 8/15, 33/37)

scripts/summarize_research.py

@@ -1,6 +1,9 @@
-"""Use DeepSeek to summarize AI/quant research RSS into categorized briefs."""
+"""Use DeepSeek to summarize AI/quant research RSS into categorized briefs.
+v2: back-fills pub_time from raw RSS data after AI summarization.
+"""
 import json, os, requests, re
 from datetime import datetime, timezone, timedelta
+from dateutil import parser as dtparser
 
 API_KEY = "sk-bbca4a0380d549389f0d27cdea0b5228"
 API_URL = "https://api.deepseek.com/v1/chat/completions"
@@ -19,6 +22,46 @@ def load_raw():
     return data.get("items", [])
 
 
+def build_time_lookup(raw_items):
+    """Build lookup: title -> pub_time (Beijing time string)."""
+    lookup = {}
+    for item in raw_items:
+        title = item.get("title", "").strip()
+        published = item.get("published", "").strip()
+        if not title or not published:
+            continue
+        try:
+            dt = dtparser.parse(published)
+            if dt.tzinfo:
+                dt = dt.astimezone(tz)
+            else:
+                dt = dt.replace(tzinfo=tz)
+            now = datetime.now(tz)
+            if dt.date() == now.date():
+                time_str = dt.strftime("%H:%M")
+            else:
+                time_str = dt.strftime("%m-%d %H:%M")
+            lookup[title] = time_str
+        except Exception:
+            continue
+    return lookup
+
+
+def match_pub_time(items, lookup):
+    for item in items:
+        if "pub_time" in item:
+            continue
+        title = item.get("title", "").strip()
+        if title in lookup:
+            item["pub_time"] = lookup[title]
+        else:
+            for raw_title, time_val in lookup.items():
+                short = min(len(raw_title), len(title))
+                if short > 10 and (raw_title[:short] in title or title[:short] in raw_title):
+                    item["pub_time"] = time_val
+                    break
+
+
 def summarize(items):
     news_text = ""
     for i, item in enumerate(items[:100], 1):
@@ -41,7 +84,7 @@ def summarize(items):
 - 行业动态（AI 公司、产品发布、监管动态）
 
 ## 输出格式
-每条：rank, subtitle（15-30字）, title, source, link, summary（200-400字，说清楚这篇讲了什么、有什么用）
+每条：rank, subtitle（15-30字）, title（必须与原始标题完全一致，这是时间匹配的关键）, source, link, summary（200-400字，说清楚这篇讲了什么、有什么用）
 
 ## 原始内容
 {news_text}
@@ -72,9 +115,8 @@ JSON格式: {{"categories": [{{"name":"分类名","items":[{{"rank":1,"subtitle"
     try:
         result = json.loads(content)
     except:
-        import re as re_
-        content = re_.sub(r',\s*}', '}', content)
-        content = re_.sub(r',\s*]', ']', content)
+        content = re.sub(r',\s*}', '}', content)
+        content = re.sub(r',\s*]', ']', content)
         try:
             result = json.loads(content)
         except:
@@ -86,18 +128,26 @@ JSON格式: {{"categories": [{{"name":"分类名","items":[{{"rank":1,"subtitle"
 
 def run():
     now = datetime.now(tz).strftime("%Y-%m-%d %H:%M")
-    items = load_raw()
-    if not items:
+    raw_items = load_raw()
+    if not raw_items:
         print("No research data")
         exit(0)
 
-    print(f"Loaded {len(items)} research items. AI summarizing...")
-    data = summarize(items)
+    print(f"Loaded {len(raw_items)} research items. AI summarizing...")
+    data = summarize(raw_items)
 
     if not data:
         print("Summarization failed")
         exit(1)
 
+    # Back-fill pub_time
+    time_lookup = build_time_lookup(raw_items)
+    matched = 0
+    for cat in data.get("categories", []):
+        match_pub_time(cat["items"], time_lookup)
+        matched += sum(1 for item in cat["items"] if "pub_time" in item)
+    print(f"Matched pub_time for {matched} articles")
+
     result = {
         "updated_at": now,
         "categories": data.get("categories", []),