Support monthly source rollover; update data - 8/29-8/31

The 2609 file carries only 8/31 and has no 投手 sheet, so build_data.py
now globs every *每日数据-武汉萌奇熊.xlsx, merges 平台消耗统计 per date
(newer filename wins for a repeated date), and takes the roster from the
newest file that still has a 投手 sheet. Future month rollovers need no
code change.

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

build_data.py

@@ -5,10 +5,14 @@
 # 规则：@某某 == 某某；未填投放人的 Adpingid 丢弃；
 #       exclude.json 的 packages（按包名）与 adpings（按 Adpingid）永久剔除，均为精确匹配。
 # 每个 package 明细：Geo 后缀 = 该 package 花费最高的地区；Adpingid = 该地区内花费最高的 Adping。
-import openpyxl, collections, json, datetime, os, sys
+import openpyxl, collections, json, datetime, os, sys, glob
 
 HERE = os.path.dirname(os.path.abspath(__file__))
-SRC  = os.path.join(HERE, '2608每日数据-武汉萌奇熊.xlsx')
+# 源文件按月滚动（2608 -> 2609 -> ...）。全部读进来合并：
+# 同一天出现在多个文件时，以文件名较新的为准（源表会修订历史数据）。
+SRC_FILES = sorted(glob.glob(os.path.join(HERE, '*每日数据-武汉萌奇熊.xlsx')))
+if not SRC_FILES:
+    sys.exit('ERROR: 仓库里找不到 *每日数据-武汉萌奇熊.xlsx')
 _cfg = json.load(open(os.path.join(HERE, 'exclude.json')))
 EXCL      = set(_cfg['packages'])            # 按包名剔除
 EXCL_ADP  = set(_cfg.get('adpings', {}))     # 按 Adpingid 剔除
@@ -20,12 +24,20 @@ def key(v):
         return str(int(v))
     return str(v).strip()
 
-wb = openpyxl.load_workbook(SRC, data_only=True)
+books = [(f, openpyxl.load_workbook(f, data_only=True)) for f in SRC_FILES]
+
+# --- 投手表：取最新一个带「投手」sheet 的文件（月度文件可能不含该表）---
+roster_file, roster = None, None
+for f, wb_ in reversed(books):
+    if '投手' in wb_.sheetnames:
+        roster_file, roster = f, wb_['投手']
+        break
+if roster is None:
+    sys.exit('ERROR: 所有源文件都没有「投手」sheet，无法归属投放人')
 
-# --- 投手表：Adpingid -> 投放人 ---
 amap = {}
 dropped_ids = set(EXCL_ADP)   # 先纳入按 Adpingid 剔除的，再补上按包名命中的
-for r in wb['投手'].iter_rows(min_row=2, values_only=True):
+for r in roster.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
@@ -42,19 +54,25 @@ for r in wb['投手'].iter_rows(min_row=2, values_only=True):
 
 owned = collections.Counter(amap.values())   # 每位投手名下的 Adpingid 数（已扣除排除包名）
 
-# --- 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, geo, spend = r[1], r[2], r[3], r[4], r[8]
-    if d is None or adp is None or not isinstance(d, datetime.datetime):
+# --- 平台消耗统计：逐文件读取，按日期归组，新文件覆盖同一天的旧数据 ---
+by_date = {}
+for f, wb_ in books:
+    if '平台消耗统计' not in wb_.sheetnames:
         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)'),
-                 (str(geo).strip() if geo else ''), s))
+    day = collections.defaultdict(list)
+    for r in wb_['平台消耗统计'].iter_rows(min_row=2, values_only=True):
+        d, adp, pkg, geo, spend = r[1], r[2], r[3], r[4], 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
+        day[d.date()].append((d.date(), key(adp), (str(pkg).strip() if pkg else '(未知)'),
+                              (str(geo).strip() if geo else ''), s))
+    by_date.update(day)          # books 已按文件名升序，后者覆盖前者
 
+rows = [r for day_rows in by_date.values() for r in day_rows]
 if not rows:
     sys.exit('ERROR: 平台消耗统计 无有效数据行')
 
@@ -132,6 +150,8 @@ data = {
 }
 json.dump(data, open(os.path.join(HERE, 'data.json'), 'w'), ensure_ascii=False, indent=2)
 
+print('源文件:', ', '.join(os.path.basename(f) for f in SRC_FILES))
+print('投手表取自:', os.path.basename(roster_file))
 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']}")