Exclude specified packages from report

Add exclude.json (12 package names, permanent) and build_data.py so the
report is reproducible. Exclusion is exact-match on package name, applied
both to 平台消耗统计 rows and to Adpingids whose 投手 pkg is excluded.
Exact match avoids false positives (e.g. in.swiggy.android vs "igg").

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

build_data.py

@@ -0,0 +1,103 @@
+#!/usr/bin/env python3
+# 从 xlsx 重算 data.json。取数规则见 README 注释：
+#   平台消耗统计: B=Date, C=Adpingid, D=包名, I=花费
+#   投手:        B=Adpingid, L=Media Buyer投放人
+#   @某某 == 某某；未填投放人的 Adpingid 丢弃；exclude.json 里的包名永久剔除。
+import openpyxl, collections, json, datetime, os, sys
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+SRC  = os.path.join(HERE, '2608每日数据-武汉萌奇熊.xlsx')
+EXCL = set(json.load(open(os.path.join(HERE, 'exclude.json')))['packages'])
+NON_BUYER = {'GP下架'}
+WINDOW_DAYS = 3
+
+def key(v):
+    if isinstance(v, float) and v.is_integer():
+        return str(int(v))
+    return str(v).strip()
+
+wb = openpyxl.load_workbook(SRC, data_only=True)
+
+# --- 投手表：Adpingid -> 投放人；同时收集需按 Adping 剔除的 id ---
+amap, dropped_ids = {}, set()
+for r in wb['投手'].iter_rows(min_row=2, values_only=True):
+    adp, pkg, buyer, status = r[1], r[3], r[11], r[0]
+    if adp is None or str(status).strip() == '示例':
+        continue
+    k = key(adp)
+    if pkg is not None and str(pkg).strip() in EXCL:   # 精确匹配，避免误伤 in.swiggy.android
+        dropped_ids.add(k)
+        continue
+    b = str(buyer).strip() if buyer is not None else ''
+    if b in ('', 'None') or b.lstrip('@').strip() in NON_BUYER:
+        continue
+    amap[k] = b.lstrip('@').strip()
+
+# --- 平台消耗统计 ---
+rows = []
+for r in wb['平台消耗统计'].iter_rows(min_row=2, values_only=True):
+    d, adp, pkg, spend = r[1], r[2], r[3], r[8]
+    if d is None or adp is None or not isinstance(d, datetime.datetime):
+        continue
+    try:
+        s = float(spend) if spend is not None else 0.0
+    except (TypeError, ValueError):
+        s = 0.0
+    rows.append((d.date(), key(adp), (str(pkg).strip() if pkg else '(未知)'), s))
+
+if not rows:
+    sys.exit('ERROR: 平台消耗统计 无有效数据行')
+
+end = max(r[0] for r in rows)
+start = end - datetime.timedelta(days=WINDOW_DAYS - 1)
+
+buyers = collections.defaultdict(lambda: collections.defaultdict(float))
+ids = collections.defaultdict(set)
+unmatched = collections.defaultdict(float)
+excluded_spend, excluded_rows = 0.0, 0
+
+for d, adp, pkg, s in rows:
+    if not (start <= d <= end):
+        continue
+    if pkg in EXCL or adp in dropped_ids:
+        excluded_spend += s; excluded_rows += 1
+        continue
+    if adp in amap:
+        buyers[amap[adp]][pkg] += s
+        ids[amap[adp]].add(adp)
+    else:
+        unmatched[(adp, pkg)] += s
+
+out = []
+for b, pk in buyers.items():
+    out.append({
+        "name": b, "@name": b,
+        "total": round(sum(pk.values()), 4),
+        "pkgs": [{"pkg": k, "spend": round(v, 4)}
+                 for k, v in sorted(pk.items(), key=lambda x: -x[1])[:5]],
+    })
+out.sort(key=lambda x: -x['total'])
+
+lbl = f"{start.month}/{start.day}-{end.month}/{end.day}"
+data = {
+    "meta": {
+        "week": f"Last {WINDOW_DAYS} Days: {lbl}",
+        "source": "数据已处理（平台消耗统计 × 投手表匹配，已剔除未填写投放人的 Adpingid 及排除包名）",
+        "generated_at": datetime.date.today().isoformat(),
+        "date_range": f"{start:%Y/%m/%d}-{end:%Y/%m/%d}",
+        "note": "投放人以「投手」表 Media Buyer 列为准，@某某 已与某某合并计算；"
+                "未填写投放人的 Adpingid 不计入；exclude.json 所列包名已排除。",
+    },
+    "grand_total": round(sum(b['total'] for b in out), 4),
+    "week34_id_count": sum(len(v) for v in ids.values()),
+    "buyers": out,
+    "unmatched": [{"adping": k[0], "pkg": k[1], "spend": round(v, 4)}
+                  for k, v in sorted(unmatched.items(), key=lambda x: -x[1])],
+}
+json.dump(data, open(os.path.join(HERE, 'data.json'), 'w'), ensure_ascii=False, indent=2)
+
+print(f"窗口 {start} -> {end}")
+print(f"排除包名命中 {excluded_rows} 行，剔除花费 {excluded_spend:.2f}")
+print(f"合计 {data['grand_total']:.2f} / Adpingid {data['week34_id_count']}")
+for b in out:
+    print(f"  {b['name']:6s} {b['total']:10.2f}")

data.json

@@ -1,13 +1,13 @@
 {
   "meta": {
     "week": "Last 3 Days: 8/23-8/25",
-    "source": "数据已处理（平台消耗统计 × 投手表匹配，已剔除未填写投放人的 Adpingid）",
+    "source": "数据已处理（平台消耗统计 × 投手表匹配，已剔除未填写投放人的 Adpingid 及排除包名）",
     "generated_at": "2026-08-26",
     "date_range": "2026/08/23-2026/08/25",
-    "note": "投放人以「投手」表 Media Buyer 列为准，@某某 已与某某合并计算；未填写投放人的 Adpingid 不计入。"
+    "note": "投放人以「投手」表 Media Buyer 列为准，@某某 已与某某合并计算；未填写投放人的 Adpingid 不计入；exclude.json 所列包名已排除。"
   },
-  "grand_total": 11160.5116,
+  "grand_total": 11063.3116,
-  "week34_id_count": 121,
+  "week34_id_count": 119,
   "buyers": [
     {
       "name": "黄政",
@@ -120,7 +120,7 @@
     {
       "name": "詹涵粤",
       "@name": "詹涵粤",
-      "total": 1567.5664,
+      "total": 1470.3664,
       "pkgs": [
         {
           "pkg": "com.king.candycrushsaga",
@@ -139,23 +139,13 @@
           "spend": 80.4999
         },
         {
-          "pkg": "com.igg.android.lordsmobile",
+          "pkg": "com.netease.newspike",
-          "spend": 63.0
+          "spend": 30.6
         }
       ]
     }
   ],
   "unmatched": [
-    {
-      "adping": "91534913",
-      "pkg": "com.qookkagames.xczyw.gp.hk",
-      "spend": 4.2
-    },
-    {
-      "adping": "91533906",
-      "pkg": "com.sialiagames.xczyw.gp.tw",
-      "spend": 0.5
-    },
     {
       "adping": "91538334",
       "pkg": "cn.com.vtmarkets",

exclude.json

@@ -0,0 +1,17 @@
+{
+  "_comment": "永久排除的包名（精确匹配，不做子串匹配）。用户 2026-08-26 指定，以后每次生成报告都不计入。",
+  "packages": [
+    "com.levelinfinite.sgameGlobal",
+    "com.igg.android.lordsmobile",
+    "net.mbc.shahid",
+    "water.sort.color.puzzle.offline.games",
+    "com.sialiagames.xczyw.gp.tw",
+    "com.qookkagames.xczyw.gp.hk",
+    "com.luizalabs.mlapp",
+    "br.com.netshoes.app",
+    "de.autodoc.gmbh",
+    "id891130066",
+    "id886443637",
+    "id1014949597"
+  ]
+}