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>
This commit is contained in:
FANGKK
2026-09-01 13:29:22 +08:00
co-authored by Claude Opus 5
parent e6ec3e1d22
commit e6061d1286
3 changed files with 90 additions and 70 deletions
Binary file not shown.
+36 -16
View File
@@ -5,10 +5,14 @@
# 规则:@某某 == 某某;未填投放人的 Adpingid 丢弃; # 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。 # 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。 # 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__)) 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'))) _cfg = json.load(open(os.path.join(HERE, 'exclude.json')))
EXCL = set(_cfg['packages']) # 按包名剔除 EXCL = set(_cfg['packages']) # 按包名剔除
EXCL_ADP = set(_cfg.get('adpings', {})) # 按 Adpingid 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(int(v))
return str(v).strip() 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 = {} amap = {}
dropped_ids = set(EXCL_ADP) # 先纳入按 Adpingid 剔除的,再补上按包名命中的 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] adp, pkg, buyer, status = r[1], r[3], r[11], r[0]
if adp is None or str(status).strip() == '示例': if adp is None or str(status).strip() == '示例':
continue 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) 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 --- # --- 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 ---
rows = [] by_date = {}
for r in wb['平台消耗统计'].iter_rows(min_row=2, values_only=True): for f, wb_ in books:
d, adp, pkg, geo, spend = r[1], r[2], r[3], r[4], r[8] if '平台消耗统计' not in wb_.sheetnames:
if d is None or adp is None or not isinstance(d, datetime.datetime):
continue continue
try: day = collections.defaultdict(list)
s = float(spend) if spend is not None else 0.0 for r in wb_['平台消耗统计'].iter_rows(min_row=2, values_only=True):
except (TypeError, ValueError): d, adp, pkg, geo, spend = r[1], r[2], r[3], r[4], r[8]
s = 0.0 if d is None or adp is None or not isinstance(d, datetime.datetime):
rows.append((d.date(), key(adp), (str(pkg).strip() if pkg else '(未知)'), continue
(str(geo).strip() if geo else ''), s)) 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: if not rows:
sys.exit('ERROR: 平台消耗统计 无有效数据行') 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) 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"窗口 {start} -> {end}")
print(f"排除包名命中 {excluded_rows} 行,剔除花费 {excluded_spend:.2f}") 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']}") print(f"合计 {data['grand_total']:.2f} / Adpingid {data['week34_id_count']}")
+54 -54
View File
@@ -1,19 +1,19 @@
{ {
"meta": { "meta": {
"week": "Last 3 Days: 8/28-8/30", "week": "Last 3 Days: 8/29-8/31",
"source": "萌奇熊日报", "source": "萌奇熊日报",
"generated_at": "2026-08-31", "generated_at": "2026-09-01",
"date_range": "2026/08/28-2026/08/30", "date_range": "2026/08/29-2026/08/31",
"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。Package 后缀为该 Package 花费最高的投放地区,Adpingid 为该地区内花费最高的 Adping。" "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。Package 后缀为该 Package 花费最高的投放地区,Adpingid 为该地区内花费最高的 Adping。"
}, },
"grand_total": 11581.3293, "grand_total": 11872.5278,
"week34_id_count": 123, "week34_id_count": 119,
"buyers": [ "buyers": [
{ {
"name": "黄政", "name": "黄政",
"@name": "黄政", "@name": "黄政",
"total": 3344.4122, "total": 3480.3241,
"active_ids": 32, "active_ids": 31,
"owned_ids": 133, "owned_ids": 133,
"pkgs": [ "pkgs": [
{ {
@@ -21,42 +21,42 @@
"geo": "SA", "geo": "SA",
"label": "com.amazon.mShop.android.shopping_SA", "label": "com.amazon.mShop.android.shopping_SA",
"adping": "2732727", "adping": "2732727",
"spend": 1145.5168 "spend": 1220.3056
}, },
{ {
"pkg": "com.king.candycrushsodasaga", "pkg": "com.king.candycrushsodasaga",
"geo": "BR", "geo": "DE",
"label": "com.king.candycrushsodasaga_BR", "label": "com.king.candycrushsodasaga_DE",
"adping": "8460883", "adping": "6951594",
"spend": 1098.694 "spend": 1089.63
}, },
{ {
"pkg": "com.yandex.lavka", "pkg": "com.yandex.lavka",
"geo": "RU", "geo": "RU",
"label": "com.yandex.lavka_RU", "label": "com.yandex.lavka_RU",
"adping": "8156506", "adping": "8156506",
"spend": 360.9953 "spend": 340.0207
}, },
{ {
"pkg": "com.fxpro.direct.application", "pkg": "com.fxpro.direct.application",
"geo": "PK", "geo": "PK",
"label": "com.fxpro.direct.application_PK", "label": "com.fxpro.direct.application_PK",
"adping": "7202934", "adping": "7202934",
"spend": 234.09 "spend": 233.96
}, },
{ {
"pkg": "ru.banki.banki", "pkg": "tech.jm",
"geo": "RU", "geo": "RU",
"label": "ru.banki.banki_RU", "label": "tech.jm_RU",
"adping": "91548044", "adping": "1745925",
"spend": 137.5186 "spend": 156.7521
} }
] ]
}, },
{ {
"name": "万科", "name": "万科",
"@name": "万科", "@name": "万科",
"total": 2426.0128, "total": 2318.8753,
"active_ids": 24, "active_ids": 24,
"owned_ids": 112, "owned_ids": 112,
"pkgs": [ "pkgs": [
@@ -65,42 +65,42 @@
"geo": "TH", "geo": "TH",
"label": "com.king.candycrushsaga_TH", "label": "com.king.candycrushsaga_TH",
"adping": "5497580", "adping": "5497580",
"spend": 1059.413 "spend": 968.234
}, },
{ {
"pkg": "ru.aliexpress.buyer", "pkg": "ru.aliexpress.buyer",
"geo": "RU", "geo": "RU",
"label": "ru.aliexpress.buyer_RU", "label": "ru.aliexpress.buyer_RU",
"adping": "6607117", "adping": "6607117",
"spend": 953.539 "spend": 938.279
}, },
{ {
"pkg": "ru.mobstudio.andgalaxy", "pkg": "ru.mobstudio.andgalaxy",
"geo": "RU", "geo": "RU",
"label": "ru.mobstudio.andgalaxy_RU", "label": "ru.mobstudio.andgalaxy_RU",
"adping": "7953512", "adping": "7953512",
"spend": 152.69 "spend": 144.16
}, },
{ {
"pkg": "ru.kinopoisk", "pkg": "ru.kinopoisk",
"geo": "RU", "geo": "RU",
"label": "ru.kinopoisk_RU", "label": "ru.kinopoisk_RU",
"adping": "10599681", "adping": "10599681",
"spend": 126.88 "spend": 126.23
}, },
{ {
"pkg": "com.edadeal.android", "pkg": "com.edadeal.android",
"geo": "RU", "geo": "RU",
"label": "com.edadeal.android_RU", "label": "com.edadeal.android_RU",
"adping": "10599157", "adping": "10599157",
"spend": 81.2 "spend": 85.55
} }
] ]
}, },
{ {
"name": "谭超", "name": "谭超",
"@name": "谭超", "@name": "谭超",
"total": 2250.706, "total": 2311.848,
"active_ids": 23, "active_ids": 23,
"owned_ids": 124, "owned_ids": 124,
"pkgs": [ "pkgs": [
@@ -109,43 +109,43 @@
"geo": "ID", "geo": "ID",
"label": "com.kwai.bulldog_ID", "label": "com.kwai.bulldog_ID",
"adping": "7815836", "adping": "7815836",
"spend": 1148.97 "spend": 1149.95
}, },
{ {
"pkg": "com.vitastudio.mahjong", "pkg": "com.vitastudio.mahjong",
"geo": "ID", "geo": "ID",
"label": "com.vitastudio.mahjong_ID", "label": "com.vitastudio.mahjong_ID",
"adping": "91467820", "adping": "91467820",
"spend": 465.14 "spend": 519.33
}, },
{ {
"pkg": "astrum.ent.m2alyona", "pkg": "astrum.ent.m2alyona",
"geo": "RU", "geo": "RU",
"label": "astrum.ent.m2alyona_RU", "label": "astrum.ent.m2alyona_RU",
"adping": "11690181", "adping": "11690181",
"spend": 273.82 "spend": 263.12
}, },
{ {
"pkg": "tech.jm", "pkg": "tech.jm",
"geo": "RU", "geo": "RU",
"label": "tech.jm_RU", "label": "tech.jm_RU",
"adping": "9297014", "adping": "9297014",
"spend": 116.73 "spend": 196.63
}, },
{ {
"pkg": "in.startv.hotstar.dplus", "pkg": "in.startv.hotstar.dplus",
"geo": "ID", "geo": "ID",
"label": "in.startv.hotstar.dplus_ID", "label": "in.startv.hotstar.dplus_ID",
"adping": "9096620", "adping": "9096620",
"spend": 71.95 "spend": 73.74
} }
] ]
}, },
{ {
"name": "周梓君", "name": "周梓君",
"@name": "周梓君", "@name": "周梓君",
"total": 1860.5323, "total": 1954.4797,
"active_ids": 27, "active_ids": 26,
"owned_ids": 119, "owned_ids": 119,
"pkgs": [ "pkgs": [
{ {
@@ -153,14 +153,14 @@
"geo": "KZ", "geo": "KZ",
"label": "ru.ozon.app.android_KZ", "label": "ru.ozon.app.android_KZ",
"adping": "5963354", "adping": "5963354",
"spend": 974.2013 "spend": 1000.9987
}, },
{ {
"pkg": "ru.kinopoisk", "pkg": "ru.kinopoisk",
"geo": "RU", "geo": "RU",
"label": "ru.kinopoisk_RU", "label": "ru.kinopoisk_RU",
"adping": "8291713", "adping": "8291713",
"spend": 575.96 "spend": 630.0
}, },
{ {
"pkg": "com.edadeal.android", "pkg": "com.edadeal.android",
@@ -174,22 +174,22 @@
"geo": "RU", "geo": "RU",
"label": "com.yandex.bank_RU", "label": "com.yandex.bank_RU",
"adping": "2937658", "adping": "2937658",
"spend": 65.721 "spend": 75.981
}, },
{ {
"pkg": "com.appteka.lapy", "pkg": "com.appteka.lapy",
"geo": "RU", "geo": "RU",
"label": "com.appteka.lapy_RU", "label": "com.appteka.lapy_RU",
"adping": "5623760", "adping": "5623760",
"spend": 17.2 "spend": 21.2
} }
] ]
}, },
{ {
"name": "詹涵粤", "name": "詹涵粤",
"@name": "詹涵粤", "@name": "詹涵粤",
"total": 1699.666, "total": 1807.0007,
"active_ids": 17, "active_ids": 15,
"owned_ids": 144, "owned_ids": 144,
"pkgs": [ "pkgs": [
{ {
@@ -197,50 +197,50 @@
"geo": "MY", "geo": "MY",
"label": "com.king.candycrushsaga_MY", "label": "com.king.candycrushsaga_MY",
"adping": "5464039", "adping": "5464039",
"spend": 1144.35 "spend": 1154.11
}, },
{ {
"pkg": "com.esprit.rpg.lttlefirykng", "pkg": "com.esprit.rpg.lttlefirykng",
"geo": "RU", "geo": "RU",
"label": "com.esprit.rpg.lttlefirykng_RU", "label": "com.esprit.rpg.lttlefirykng_RU",
"adping": "10514860", "adping": "10514860",
"spend": 311.45 "spend": 359.1
}, },
{ {
"pkg": "com.reefgames.fabletown", "pkg": "com.reefgames.fabletown",
"geo": "RU", "geo": "RU",
"label": "com.reefgames.fabletown_RU", "label": "com.reefgames.fabletown_RU",
"adping": "91532857", "adping": "91532857",
"spend": 70.9804 "spend": 63.8392
},
{
"pkg": "net.peakgames.Yuzbir",
"geo": "TR",
"label": "net.peakgames.Yuzbir_TR",
"adping": "91550293",
"spend": 38.75
}, },
{ {
"pkg": "com.netease.newspike", "pkg": "com.netease.newspike",
"geo": "US", "geo": "US",
"label": "com.netease.newspike_US", "label": "com.netease.newspike_US",
"adping": "91551388", "adping": "91551388",
"spend": 36.6713 "spend": 62.3091
},
{
"pkg": "net.peakgames.Yuzbir",
"geo": "TR",
"label": "net.peakgames.Yuzbir_TR",
"adping": "91550293",
"spend": 45.85
} }
] ]
} }
], ],
"unmatched": [ "unmatched": [
{
"adping": "11729927",
"pkg": "com.amazon.mShop.android.shopping",
"spend": 13.5
},
{ {
"adping": "11729830", "adping": "11729830",
"pkg": "com.amazon.mShop.android.shopping", "pkg": "com.amazon.mShop.android.shopping",
"spend": 0.002 "spend": 0.002
}, },
{
"adping": "11729927",
"pkg": "com.amazon.mShop.android.shopping",
"spend": 0.0
},
{ {
"adping": "11729820", "adping": "11729820",
"pkg": "com.amazon.mShop.android.shopping", "pkg": "com.amazon.mShop.android.shopping",