ai_member_only/ai_member_xiaoxi
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

🤖 每日自动备份 - 2026-06-16 08:00:01

Browse Source
This commit is contained in:
小溪 2026-06-16 08:00:01 +08:00
parent 4135e93b17
commit b25d6fef0f
12 changed files with 651 additions and 249 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
MEMORY.md
View File

@ -27,11 +27,17 @@
- 「Bot刷新」/「S2 刷新」/「Bot 销转看板」→ 执行 `scripts/bot_sales_step2_refresh.py`，完成后群回「Bot刷新完成」，不动订单汇总 tab [陈逸鸫确认 2026-06-06] - 「Bot刷新」/「S2 刷新」/「Bot 销转看板」→ 执行 `scripts/bot_sales_step2_refresh.py`，完成后群回「Bot刷新完成」，不动订单汇总 tab [陈逸鸫确认 2026-06-06]
- **Bot 销转看板 S1–S3 协作流程 [陈逸鸫确认 2026-06-06]：** - **Bot 销转看板 S1–S3 协作流程 [陈逸鸫确认 2026-06-06]：**
- S1 Cursor → 微伴入库/每日线索/聚光 → @小溪 - S1 Cursor → 微伴入库/每日线索/聚光 → @小溪
- S2 小溪 → 销售三表 D/H/I/J + K–V + S/U → 群回「Bot刷新完成」 - S2 小溪 → 销售三表 D/H/I/J + K–U + X–Z → 群回「Bot刷新完成」
- S3 Cursor → 收到后粘贴订单汇总 + 刷看板公式 - S3 Cursor → 收到后粘贴订单汇总 + 刷看板公式
- 当日默认只跑一轮 S2；再刷需群里 `【执行更新】` @小溪 - 当日默认只跑一轮 S2；再刷需群里 `【执行更新】` @小溪
- 详细手册：`docs/伪BI-小溪操作手册.md`、`docs/bot-xiaoxi-collaboration-s1-s3.md` - 详细手册：`docs/伪BI-小溪操作手册.md`、`docs/bot-xiaoxi-collaboration-s1-s3.md`
- S2 核心规则：① E→H 必须 phone_encrypt.py XXTEA 精确匹配，禁前三后四 ② H→D/I/J 只补空 ③ L≥C 才 K=是 ④ 全额退清 K/O/P/Q ⑤ O/P/Q 0留空，P整元 ⑥ G列不动 - S2 核心规则：① E→H 必须 phone_encrypt.py XXTEA 精确匹配，禁前三后四 ② H→D/I/J 只补空 ③ K(下单日)≥C(进线日期) 才 Y(有效订单)=1 ④ 全额退清 N/O/P 清空 ⑤ N/O/P 0留空，O整元 ⑥ G列不动
- **线索表（销售三表）列结构 [陈逸鸫确认 2026-06-15]：**
A销售归属 B微信昵称 C进线日期 D体验节数 E手机号 F用户年级 G课史/跟进 H用户ID I注册日期 J下载渠道 K下单日期 L成交渠道 M产品 N下单金额(GMV) O退款金额 P实际收入(GSV) Q激活课程 R当前行课进度 S最近行课时间 T累计学习时长(min) U更新时间 V微伴补充 W进线早于下单 X订单号 Y有效订单 Z渠道归属
- 脚本填写：D/H/I/J/K~U/X/Y/Z
- Y(有效订单)=1 → 进入订单汇总表
- **订单汇总表列结构 [陈逸鸫确认 2026-06-15]：**
A销售归属 B微信昵称 C进线日期 D体验节数 E手机号 F用户年级 G课史/跟进 H用户ID I注册日期 J下载渠道 K下单日期 L成交渠道 M产品 N下单金额(GMV) O退款金额 P实际收入(GSV) Q激活课程 R当前行课进度 S最近行课时间 T累计学习时长(min) U更新时间 V渠道归属 W有效成单 X订单号
- **飞书表格写入 5000 格上限规则（强制执行，[李承龙确认] 2026-06-13）：** - **飞书表格写入 5000 格上限规则（强制执行，[李承龙确认] 2026-06-13）：**
- 飞书 Open API 单次写入上限为 5000 格（行×列），超过上限静默失败不报错 - 飞书 Open API 单次写入上限为 5000 格（行×列），超过上限静默失败不报错
- 所有脚本写入飞书表格时必须使用 `scripts/feishu_sheet_utils.py` 共享工具，自动分批确保 ≤ 4400 格/批 - 所有脚本写入飞书表格时必须使用 `scripts/feishu_sheet_utils.py` 共享工具，自动分批确保 ≤ 4400 格/批
@ -181,6 +187,15 @@
- 小红书店铺：`newmedia-dianpu-xhs-0-0` - 小红书店铺：`newmedia-dianpu-xhs-0-0`
- 达人直播：`newmedia-daren%`（前缀匹配） - 达人直播：`newmedia-daren%`（前缀匹配）
- 万物：`newmedia-dianpu-wwxx-0-0` - 万物：`newmedia-dianpu-wwxx-0-0`
- **销售转化渠道分类规则（仅用于销售转化场景，[王虹茗确认，李承龙确认] 2026-06-15）：**
- 将 key_from 归为四类：
| 类别 | 匹配规则 |
|------|---------|
| 端内 | `app-active-h5-0-0`, `app-sales-bj-qhm-0`, `app-sales-bj-wd-0` |
| 销转 | `sales-adp-*` |
| 达人 | `newmedia-daren-*` + `newmedia-dianpu-wwxx-0-0`（万物算达人） |
| 直购 | `newmedia-dianpu-*`（**不含 wwxx**）+ 其余所有杂项（partner-*, stream-*, miniprogram-*, newmedia-jingxuan-*, 空值, shuadan 等） |
- **注意：** 此分类规则仅在销售转化场景下使用，不替代通用的渠道映射规则
- **sale_channel字段映射规则（仅对`key_from = app-active-h5-0-0`的订单生效）：** - **sale_channel字段映射规则（仅对`key_from = app-active-h5-0-0`的订单生效）：**
| sale_channel值 | 对应渠道名称 | | sale_channel值 | 对应渠道名称 |
|---------------|--------------| |---------------|--------------|

1
USER.md
View File

@ -44,6 +44,7 @@
| 胡陈辰 | `gc64176a` | | 胡陈辰 | `gc64176a` |
| 刘彦江 | `1da2afbf` | | 刘彦江 | `1da2afbf` |
| 姜小龙 | `bc227c85` | | 姜小龙 | `bc227c85` |
| 赵一凡 | `a3168f9d` |
> ⚠️ 以上用户拥有全部数据查询权限，但其个人信息、查询内容、对话记录**禁止写入 MEMORY.md（长期记忆）**，仅可记录在短期日记忆中用于会话连续性。 > ⚠️ 以上用户拥有全部数据查询权限，但其个人信息、查询内容、对话记录**禁止写入 MEMORY.md（长期记忆）**，仅可记录在短期日记忆中用于会话连续性。

107
memory/.dreams/short-term-recall.json
View File

@ -1,6 +1,6 @@
{ {
"version": 1, "version": 1,
"updatedAt": "2026-06-14T07:14:40.970Z", "updatedAt": "2026-06-15T02:42:34.143Z",
"entries": { "entries": {
"memory:memory/2026-05-06.md:1:20": { "memory:memory/2026-05-06.md:1:20": {
"key": "memory:memory/2026-05-06.md:1:20", "key": "memory:memory/2026-05-06.md:1:20",
@ -668,18 +668,20 @@
"endLine": 56, "endLine": 56,
"source": "memory", "source": "memory",
"snippet": "| 15 | Rachel | 3/5 | 10994 | 13510564547 | 3/7 | ✓ | sales-adp-bj-jxl-0, GMV=1999 | | 16 | soul | 3/2 | 17387 | 15640464255 | 3/12 | ✓ | sales-adp-bj-jxl-0, GMV=1999 | | 17 | 红 | 3/7 | 17025 | 13533955004 | 3/14 | ✓ | sales-adp-bj-jxl-0, GMV=1999 | | 18 | 一笑轩渠 | 3/8 | 17425 | 15017528458 | 3/11 | ✓ | sales-adp-bj-jxl-0, GMV=1999 | | 19 | 蜗牛 | 3/2 | ❓ | ❓ | ❓ | - | 晚柠5/15订单数百笔，无手机/UID无法定位 | | 20 | c_瑶 | 3/6 | ❓ | ❓ | ❓ | - | \"直购\"渠道DB不存在，3/14无3998/1999匹配 | ### 关键发现 1. Group A 中 7/10 用户 DB 中无任何订单（pre汇总有GMV但DB不存在） 2. Group B 4个手机号全部未注册（H=未注册 确认正确） 3. Group C #15-#18 4笔 jxl-0 均 L≥C，pre怀疑#18 L<C不成立 4. #19 蜗牛和 #20 c_瑶 无法定位 ## 陈逸鸫 - full_refresh (S2+S3) 联调 ### 执行记录 - 时间：2026-06-12 18:00 左右 - S2：", "snippet": "| 15 | Rachel | 3/5 | 10994 | 13510564547 | 3/7 | ✓ | sales-adp-bj-jxl-0, GMV=1999 | | 16 | soul | 3/2 | 17387 | 15640464255 | 3/12 | ✓ | sales-adp-bj-jxl-0, GMV=1999 | | 17 | 红 | 3/7 | 17025 | 13533955004 | 3/14 | ✓ | sales-adp-bj-jxl-0, GMV=1999 | | 18 | 一笑轩渠 | 3/8 | 17425 | 15017528458 | 3/11 | ✓ | sales-adp-bj-jxl-0, GMV=1999 | | 19 | 蜗牛 | 3/2 | ❓ | ❓ | ❓ | - | 晚柠5/15订单数百笔，无手机/UID无法定位 | | 20 | c_瑶 | 3/6 | ❓ | ❓ | ❓ | - | \"直购\"渠道DB不存在，3/14无3998/1999匹配 | ### 关键发现 1. Group A 中 7/10 用户 DB 中无任何订单（pre汇总有GMV但DB不存在） 2. Group B 4个手机号全部未注册（H=未注册 确认正确） 3. Group C #15-#18 4笔 jxl-0 均 L≥C，pre怀疑#18 L<C不成立 4. #19 蜗牛和 #20 c_瑶 无法定位 ## 陈逸鸫 - full_refresh (S2+S3) 联调 ### 执行记录 - 时间：2026-06-12 18:00 左右 - S2：",
"recallCount": 1, "recallCount": 2,
"dailyCount": 0, "dailyCount": 0,
"groundedCount": 0, "groundedCount": 0,
"totalScore": 1, "totalScore": 2,
"maxScore": 1, "maxScore": 1,
"firstRecalledAt": "2026-06-14T06:58:06.164Z", "firstRecalledAt": "2026-06-14T06:58:06.164Z",
"lastRecalledAt": "2026-06-14T06:58:06.164Z", "lastRecalledAt": "2026-06-15T02:42:34.143Z",
"queryHashes": [ "queryHashes": [
"6769ba9ebb36" "6769ba9ebb36",
"0b9f27c6db59"
], ],
"recallDays": [ "recallDays": [
"2026-06-14" "2026-06-14",
"2026-06-15"
], ],
"conceptTags": [ "conceptTags": [
"3/5", "3/5",
@ -691,6 +693,99 @@
"3/8", "3/8",
"3/11" "3/11"
] ]
},
"memory:memory/2026-06-13.md:1:21": {
"key": "memory:memory/2026-06-13.md:1:21",
"path": "memory/2026-06-13.md",
"startLine": 1,
"endLine": 21,
"source": "memory",
"snippet": "# 2026-06-13 工作日志 ## 飞书表格写入 5000 格上限问题修复 **来源：** 陈逸鸫发现全量刷订单漏数据，李承龙确认修复 **问题：** - `refresh_order_summary.py` 清空时 500行×26列=13,000格 超过飞书 API 5000 格上限 - `sales_leads_full_refresh.py` 清空时 500行×22列=11,000格，写入时 500行×22列=11,000格 同样超标 - 超标请求静默失败（API 不报错），导致旧数据残留、新数据被部分覆盖、末尾行丢失 **修复：** 1. 创建 `scripts/feishu_sheet_utils.py` 共享工具，封装安全分批写入/清空逻辑，自动计算批大小 ≤ 4400 格/批 2. `refresh_order_summary.py` 和 `sales_leads_full_refresh.py` 均已改用共享工具 3. 登记到 `SKILL_REGISTRY.md` 和 `MEMORY.md` **关键参数：** - 22列 → 单批最大 200 行 (4400 格) - 24列 → 单批最大 183 行 (4392 格) - 26列 → 单批最大 169 行 (4394 格)",
"recallCount": 1,
"dailyCount": 0,
"groundedCount": 0,
"totalScore": 1,
"maxScore": 1,
"firstRecalledAt": "2026-06-15T00:23:49.908Z",
"lastRecalledAt": "2026-06-15T00:23:49.908Z",
"queryHashes": [
"72dbb087c75b"
],
"recallDays": [
"2026-06-15"
],
"conceptTags": [
"refresh-order-summary.py",
"sales-leads-full-refresh.py",
"scripts/feishu-sheet-utils.py",
"封装安全分批写入/清空逻辑",
"格/批",
"skill-registry.md",
"memory.md",
"工作"
]
},
"memory:memory/2026-06-12.md:63:73": {
"key": "memory:memory/2026-06-12.md:63:73",
"path": "memory/2026-06-12.md",
"startLine": 63,
"endLine": 73,
"source": "memory",
"snippet": "- 整体小红书（含达人+直购）：880 用户、969 单、328 万 GMV ### 直购表 + S3 联调完成 - 时间：2026-06-12 18:40 左右 - 新建直购 sheet `1sosYE`（Bot 工作簿内），独立存放小红书直购订单 - 新建 `scripts/refresh_direct_sheet.py`：从 DB 直查 `dianpu-xhs` / `stream-xhs` 订单，不依赖手机号，全量 73 条 - 修改 `scripts/refresh_order_summary.py`：S3 读取三表 + 直购表，合并写入订单汇总 - 直购行 C 列为空时跳过 L≥C 检查（直购无进线日期概念） - full_refresh 流程：先 `refresh_direct_sheet.py` → 再 `refresh_order_summary.py` - 本次验证：381（三表）+ 73（直购）= 454 行写入订单汇总",
"recallCount": 1,
"dailyCount": 0,
"groundedCount": 0,
"totalScore": 1,
"maxScore": 1,
"firstRecalledAt": "2026-06-15T02:42:34.143Z",
"lastRecalledAt": "2026-06-15T02:42:34.143Z",
"queryHashes": [
"0b9f27c6db59"
],
"recallDays": [
"2026-06-15"
],
"conceptTags": [
"scripts/refresh-direct-sheet.py",
"dianpu-xhs",
"stream-xhs",
"scripts/refresh-order-summary.py",
"full-refresh",
"refresh-direct-sheet.py",
"refresh-order-summary.py",
"整体"
]
},
"memory:memory/2026-06-12.md:53:68": {
"key": "memory:memory/2026-06-12.md:53:68",
"path": "memory/2026-06-12.md",
"startLine": 53,
"endLine": 68,
"source": "memory",
"snippet": "- S3：筛选 K=是 · O>0 · P<O · L≥C → 381 行写入订单汇总 2smjwA，W 渠道归属 + X=1 已写入 ### 发现的问题 1. **订单汇总前 8 行无 M/N（成交渠道/产品）**：S2 脚本读小龙 sheet 时 API 只返回了 1198 行（截断），后面约 200 行没被处理。已手动补 M/N。 2. **小龙 sheet 第 20 行\"赫尔辛基的阳光\"**：E 列手机号和 H 列 UID 均为空，但 K/O/R/S/T/U 有值。原因是之前 S2 刷新时 E 列有手机号匹配到了 UID，后来手机号被人清掉但订单数据残留。下次 S2 会清空该行自动列。 3. **Bot 应用无多维表格创建权限**：缺少 `bitable:app` 或 `base:app:create` 权限，需技术负责人在飞书开放平台开通。 ### 小红书直购数据（2026-03-12 ~ 2026-06-12） - DB 中 25 个直购用户（26 单），订单汇总仅覆盖 11 行 - 差距原因：直购用户在销售表无手机号 → S2 匹配不到 UID → 进不了订单汇总 - 整体小红书（含达人+直购）：880 用户、969 单、328 万 GMV ### 直购表 + S3 联调完成 - 时间：2026-06-12 18:40 左右 - 新建直购 sheet `1sosYE`（Bot 工作簿内），独立存放小红书直购订单 - 新建 `scripts/refresh_direct_sheet.py`：从 DB 直查 `dianpu-xhs` / `stream-xhs`",
"recallCount": 1,
"dailyCount": 0,
"groundedCount": 0,
"totalScore": 1,
"maxScore": 1,
"firstRecalledAt": "2026-06-15T02:42:34.143Z",
"lastRecalledAt": "2026-06-15T02:42:34.143Z",
"queryHashes": [
"0b9f27c6db59"
],
"recallDays": [
"2026-06-15"
],
"conceptTags": [
"m/n",
"成交渠道/产品",
"k/o/r/s/t/u",
"scripts/refresh-direct-sheet.py",
"dianpu-xhs",
"stream-xhs",
"筛选",
"订单"
]
} }
} }
} }

65
memory/2026-06-15-1214.md Normal file
View File

@ -0,0 +1,65 @@
# Session: 2026-06-15 12:14:04 GMT+8
- **Session Key**: agent:main:feishu:direct:ou_e63ce6b760ad39382852472f28fbe2a2
- **Session ID**: f244c806-798c-44a9-b71b-480bc55f280f
- **Source**: feishu
## Conversation Summary
assistant: Now let me also check the `COL_REFUND_DATE` — I'm writing empty string now, but when `is_refunded = "是"` it might make sense to still show the refund date. Let me check if there's a reference issue:
assistant: 完成。退费率从 10.0% → 0.0%，符合预期。
改动逻辑：之前 `has_refund` 是账号级别的全局标记，只要历史上有一笔退费就标"是"。现在改为按每笔订单判断：转化后只要存在一笔 ≥ 析出日期且未退费的有效订单，就算未退费（即使之前有退费记录）。只有当所有 ≥ 析出日期的订单都被退费时，才标"是"。
user: [message_id: om_x100b6dc3cb5e08acb4a8c5c2a6f2359]
李承龙: 然后你需要核对一下转化金额，需要是该用户的全部订单的加和减去全部退费的加和。同时你需要注意退费金额的小数点的计算是不是对的。
assistant: 两个问题：
1. `refund_amount` 是 varchar 类型存的是**元**（如 `"3598.00"`），而 `pay_amount_int` 是 int 存的是**分**（如 `359800`）。当前 `::numeric::int` 把 `3598.00` 元当 3598 分用了，差了 100 倍。
2. 转化金额应该是用户级别的总 GSV（全部订单加和 - 全部退费加和），不是单笔订单的 GSV。
assistant: 两个问题需要修复：
1. `refund_amount` 存的是**元**（varchar `"3598.00"`），`pay_amount_int` 存的是**分**（int `359800`），需要 `*100` 统一单位
2. 转化金额应该是用户级别的总 GSV，不是单笔订单的 GSV
assistant: Now update `process_sheet` to use the new structure:
assistant: 先验证 SQL 修复是否正确：
assistant: 验证通过。`refund_amount::numeric * 100` 正确将元转分。account 30280：第一笔全退（GSV=0），第二笔未退（GSV=359800），总 GSV=3598.00 元。跑正式：
assistant: 完成。修复了两个问题：
1. **退费金额单位修复**：`refund_amount` 存的是**元**（varchar `"3598.00"`），`pay_amount_int` 存的是**分**（int `359800`）。之前 `::numeric::int` 把 `3598.00` 当 3598 分用了，差了 100 倍。改为 `::numeric * 100` 统一为分。
2. **转化金额改为用户总 GSV**：之前是取首笔匹配订单的 GSV，现在改为用户全部订单的 `pay_amount_int` 加和减去全部退费的 `refund_amount * 100` 加和，再除以 100 得到元。
结果：总析出 45，匹配 18，转化 10，转化率 22.2%，退费率 0.0%。你可以去表里核对一下 J 列的转化金额。
user: [message_id: om_x100b6dc3e957078cb03b6fe7b942192]
李承龙: 我在统计sheet中，转化率列后面添加了GMV和GSV列，需要填上
assistant: 需要在 `query_orders_and_refunds` 中增加 GMV（全部 pay_amount 加和，不扣退费），然后在 `process_sheet` 中传给 `lead_data`，最后在 `compute_stats` 和 `write_all_stats` 中汇总写入。
assistant: Now update `lead_data` to carry GMV/GSV, and update `compute_stats` + `write_all_stats`:
assistant: Now update `compute_stats` to aggregate GMV/GSV:
assistant: Now update `write_all_stats` to write GMV/GSV columns (inserted after 退费率 G, shifting completion rates to J-S):
assistant: 完成。统计 sheet 新增 H 列 GMV、I 列 GSV：
- 吴迪 2026-06：总析出 45，匹配 18，转化 10，转化率 22.2%，退费率 0.0%，**GMV=22984.00，GSV=19386.00**
GMV = 全部订单 pay_amount 加和（含退费），GSV = GMV 扣除退费金额。你可以去统计 sheet 核对一下。

29
memory/2026-06-15-1737.md Normal file
View File

@ -0,0 +1,29 @@
# Session: 2026-06-15 17:37:58 GMT+8
- **Session Key**: agent:main:feishu:direct:ou_e63ce6b760ad39382852472f28fbe2a2
- **Session ID**: fc0d2372-c44e-4671-aec5-5b37b130516a
- **Source**: feishu
## Conversation Summary
user: [message_id: om_x100b6dc385cd64a4b042b9043fef6d1]
李承龙: 看下赵一凡的id
assistant: 赵一凡不在当前的 vala_users_list.md 名单中，让我在数据库中查一下。
assistant: 赵一凡的飞书 ID 信息如下：
| 字段 | 值 |
|------|-----|
| **姓名** | 赵一凡 |
| **user_id**（租户级） | `a3168f9d` |
| **open_id** | `ou_13f70b43d99dc634d484ac7ebc4ef670` |
| **union_id** | `on_a07c0b5e6bf97c4c6f54c7588d5cfa80` |
另外，赵一凡不在现有的 `vala_users_list.md` 名单中，需要我把他加进去吗？
user: [message_id: om_x100b6dc3abcfd4a8b24f23001dd2d20]
李承龙: 加进去，同时把她加到user.md的一级用户中
assistant: 已完成两处更新：
1. **vala_users_list.md** — 赵一凡 `a3168f9d` 已加入，总人数 57→58
2. **USER.md** — 赵一凡 `a3168f9d` 已加入一级完整权限用户列表

18
memory/2026-06-15-1911.md Normal file
View File

@ -0,0 +1,18 @@
# Session: 2026-06-15 19:11:59 GMT+8
- **Session Key**: agent:main:feishu:direct:ou_e63ce6b760ad39382852472f28fbe2a2
- **Session ID**: 57e4e7f0-6dc1-4c9d-85b9-82ee493d0400
- **Source**: feishu
## Conversation Summary
user: [message_id: om_x100b6dc8cf28f0b8b396e439badade8]
李承龙: sales_leads_full_refresh.py这个脚本，所有的订单时间都从日期调整成日期加具体的时分秒
assistant: 只改一处：`query_all_pg` 中 `order_date` 的格式化，从 `%Y-%m-%d` 改为 `%Y-%m-%d %H:%M:%S`。日期比较逻辑（`order_date < clue_date`）字符串比较仍然正确。
assistant: 已修改。`order_date` 现在输出 `YYYY-MM-DD HH:MM:SS` 格式，会同时影响：
- 销售三表的 **L 列（下单日期）**
- 订单汇总 sheet 的 **L 列（下单日期）**
日期比较逻辑（`order_date < clue_date`）用字符串比较仍然正确——同一天的订单不会因多了时分秒而被误判为"早于线索日期"。

20
memory/2026-06-15-1915.md Normal file
View File

@ -0,0 +1,20 @@
# Session: 2026-06-15 19:15:32 GMT+8
- **Session Key**: agent:main:feishu:direct:ou_e63ce6b760ad39382852472f28fbe2a2
- **Session ID**: 59db7bdc-2cb3-4d11-b53e-f355070389b3
- **Source**: feishu
## Conversation Summary
user: [message_id: om_x100b6dc9af16d508b107252224f18dc]
李承龙: 6月份app-active-h5-0-0这个keyfrom有多少订单
assistant: 6月份 `app-active-h5-0-0` 渠道数据：
| 指标 | 数值 |
|------|------|
| 订单数 | **30 单** |
| GMV | **31,870.00 元** |
| GSV | **31,838.03 元** |
| 退费率 | **10.0%** |
统计口径：已剔除测试账号，仅统计 `pay_success_date` 在 6/1~6/30 的已完成/已退款订单。

112
memory/2026-06-15.md Normal file
View File

@ -0,0 +1,112 @@
# 2026-06-15 工作日志
## 陈逸鸫 - 订单口径变更：停直购
**来源：** 陈逸鸫（群聊「数据更新V2」）
**变更内容：**
1. 以后不管直购单，只看小红书销转，直购 GMV 不再进销转对账
2. full_refresh 不再 merge 直购进订单汇总
3. 直购表（1sosYE）可删除（需人工在飞书操作，API 不支持删 sheet）
4. 仍支持按手机查 keyfrom/GSV/退款（不定销售归属）
**脚本修改：**
- `scripts/refresh_order_summary.py`：去掉 Step 1.5 读取直购表逻辑，不再合并直购行
- `scripts/full_refresh_sales.py`：不涉及直购，无需改动
- `scripts/refresh_direct_sheet.py`：保留不动（如后续仍需独立查直购数据）
## 陈逸鸫 - full_refresh 执行
- 时间：2026-06-15 08:24-08:26
- 销售三表：吴迪 697 / 小龙 1198 / 成都 2203
- 有效 user_id：2009
- 订单汇总：383 条（不含直购）
- 直购表：75 条已刷新
- 订单汇总合并后：461 条（含直购，这是口径变更前的最后一次含直购的合并）
## 陈逸鸫 - 线索表字段调整（2026-06-15）
**来源：** 陈逸鸫（群聊「小红书数据需求」）
**线索表（销售三表）新列结构（A~Z）：**
| 列 | 字段名 | 脚本填写 |
|----|--------|---------|
| A | 销售归属 | - |
| B | 微信昵称 | - |
| C | 进线日期 | - |
| D | 体验节数 | ✅ |
| E | 手机号 | - |
| F | 用户年级 | - |
| G | 课史/跟进 | - |
| H | 用户ID | ✅ |
| I | 注册日期 | ✅ |
| J | 下载渠道 | ✅ |
| K | 下单日期 | ✅ |
| L | 成交渠道 | ✅ |
| M | 产品 | ✅ |
| N | 下单金额(GMV) | ✅ |
| O | 退款金额 | ✅ |
| P | 实际收入(GSV) | ✅ |
| Q | 激活课程 | ✅ |
| R | 当前行课进度 | ✅ |
| S | 最近行课时间 | ✅ |
| T | 累计学习时长(min) | ✅ |
| U | 更新时间 | ✅ |
| V | 微伴补充 | - |
| W | 进线早于下单 | - |
| X | 订单号 | ✅ |
| Y | 有效订单 | ✅ |
| Z | 渠道归属 | ✅ |
**对比旧版变化：**
- 删除旧 K 列「是否下单」
- 旧 L~V 列整体左移一位（L→K, M→L, ..., V→U）
- 新增 V(微伴补充), W(进线早于下单), X(订单号), Y(有效订单), Z(渠道归属)
**订单汇总表新列结构（A~X）：**
| 列 | 字段名 |
|----|--------|
| A | 销售归属 |
| B | 微信昵称 |
| C | 进线日期 |
| D | 体验节数 |
| E | 手机号 |
| F | 用户年级 |
| G | 课史/跟进 |
| H | 用户ID |
| I | 注册日期 |
| J | 下载渠道 |
| K | 下单日期 |
| L | 成交渠道 |
| M | 产品 |
| N | 下单金额(GMV) |
| O | 退款金额 |
| P | 实际收入(GSV) |
| Q | 激活课程 |
| R | 当前行课进度 |
| S | 最近行课时间 |
| T | 累计学习时长(min) |
| U | 更新时间 |
| V | 渠道归属 |
| W | 有效成单 |
| X | 订单号 |
**有效订单判定规则（不变）：**
- 线索表中 Y 列（有效订单）= 1 的订单进入订单汇总表
- 判定逻辑同之前：有支付成功订单、非全额退清、下单日 ≥ 进线日期
## 王虹茗 - 小红书线索落单规则（key_from 分类）
**来源：** 王虹茗确认，陈逸鸫转述（群聊「小红书数据需求」2026-06-15）
**分类规则（四类）：**
| 类别 | key_from 匹配规则 |
|------|-------------------|
| 端内 | `app-active-h5-0-0`, `app-sales-bj-qhm-0`, `app-sales-bj-wd-0` |
| 销转 | `sales-adp-*` |
| 达人 | `newmedia-daren-*` + `newmedia-dianpu-wwxx-0-0`（万物算达人） |
| 直购 | `newmedia-dianpu-*`（**不含 wwxx**）+ 其余所有杂项（partner-*, stream-*, miniprogram-*, newmedia-jingxuan-*, 空值, shuadan 等） |
**关键点：**
- wwxx（万物，`newmedia-dianpu-wwxx-0-0`）归入达人，不归入直购
- 店铺 dianpu（不含 wwxx）+ 所有杂项渠道，统一归入直购一个大类

79
scripts/bot_sales_step2_refresh.py
View File

@ -1,16 +1,16 @@
#!/usr/bin/env python3 #!/usr/bin/env python3
""" """
Bot 销转看板 Step2 刷新 — XXTEA 精确匹配版 (v2) Bot 销转看板 Step2 刷新 — XXTEA 精确匹配版 (v3)
E列11位明文手机号 → XXTEA加密 → bi_vala_app_account.tel_encrypt精确匹配 → H列UID E列11位明文手机号 → XXTEA加密 → bi_vala_app_account.tel_encrypt精确匹配 → H列UID
S2 规则: S2 规则:
① E→H: phone_encrypt.py XXTEA 精确匹配, 查不到留空 ① E→H: phone_encrypt.py XXTEA 精确匹配, 查不到留空
② H→D/I/J: 只补空, 不覆盖已有值 ② H→D/I/J: 只补空, 不覆盖已有值
③ K=是: 仅当 L(下单日) >= C(线索日期) ③ Y=1: 仅当 K(下单日) >= C(线索日期)
④ 全额退清: 所有订单都退费 → K/O/P/Q 全部清空 ④ 全额退清: 所有订单都退费 → N/O/P 全部清空
⑤ O/P/Q 0留空, P整元 ⑤ N/O/P 0留空, O整元
⑥ G列不动, 订单汇总不动 ⑥ G列不动, 订单汇总不动
覆盖列: D/H/I/J + K-V + S/U 覆盖列: D/H/I/J + K-U + X/Y/Z
""" """
import json, re, time, sys, os, requests, psycopg2 import json, re, time, sys, os, requests, psycopg2
from datetime import datetime from datetime import datetime
@ -27,9 +27,9 @@ from phone_encrypt import encrypt_phone
SPREADSHEET_TOKEN = "NoZqsFi47hIOHEt9j8WcfRtbnug" SPREADSHEET_TOKEN = "NoZqsFi47hIOHEt9j8WcfRtbnug"
SALES_SHEETS = [ SALES_SHEETS = [
("qJF4I", "小龙", "A1:V1200"), ("qJF4I", "小龙", "A1:Z1200"),
("f975f0", "吴迪", "A1:V700"), ("f975f0", "吴迪", "A1:Z700"),
("qJF4J", "成都", "A1:V2500"), ("qJF4J", "成都", "A1:Z2500"),
] ]
CS_MAP = {"吴迪": "吴迪", "小龙": "小龙", "Tom": "Tom", "Bob": "Bob"} CS_MAP = {"吴迪": "吴迪", "小龙": "小龙", "Tom": "Tom", "Bob": "Bob"}
@ -228,7 +228,7 @@ def query_all_pg(all_entries, phone_map):
"has_order": False, "order_date": "", "order_channel": "", "product": "", "has_order": False, "order_date": "", "order_channel": "", "product": "",
"gmv": 0, "refund": 0, "gsv": 0, "gmv": 0, "refund": 0, "gsv": 0,
"activation": "", "lesson_progress": "", "lesson_time": "", "lesson_minutes": 0, "activation": "", "lesson_progress": "", "lesson_time": "", "lesson_minutes": 0,
"max_lesson": 0, "max_lesson": 0, "trade_no": "",
} for uid in uid_set} } for uid in uid_set}
# 3a. 注册信息 # 3a. 注册信息
@ -278,9 +278,10 @@ def query_all_pg(all_entries, phone_map):
continue continue
info[aid]["has_order"] = True info[aid]["has_order"] = True
latest = olist[0] latest = olist[0]
info[aid]["order_date"] = latest[2].strftime("%Y-%m-%d") if latest[2] else "" info[aid]["order_date"] = f"{latest[2].month}月{latest[2].day}日 {latest[2].strftime('%H:%M:%S')}" if latest[2] else ""
info[aid]["order_channel"] = latest[3] or "" info[aid]["order_channel"] = latest[3] or ""
info[aid]["product"] = GOODS_NAMES.get(latest[4], f"商品{latest[4]}") info[aid]["product"] = GOODS_NAMES.get(latest[4], f"商品{latest[4]}")
info[aid]["trade_no"] = latest[1] or ""
total_gmv = sum(o[5] for o in olist) / 100.0 total_gmv = sum(o[5] for o in olist) / 100.0
total_refund = sum(refund_map.get(o[1], 0) for o in olist) / 100.0 total_refund = sum(refund_map.get(o[1], 0) for o in olist) / 100.0
info[aid]["gmv"] = total_gmv info[aid]["gmv"] = total_gmv
@ -402,7 +403,7 @@ def query_all_pg(all_entries, phone_map):
# ── Step 4: 写入销售三表 ── # ── Step 4: 写入销售三表 ──
def write_sales_sheets(token, all_entries, phone_map, db_info): def write_sales_sheets(token, all_entries, phone_map, db_info):
"""全覆盖写入销售表的自动列""" """全覆盖写入销售表的自动列: D/H/I/J + K-U + X/Y/Z"""
now_str = datetime.now().strftime("%Y-%m-%d %H:%M:%S") now_str = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
for sid, sname, _ in SALES_SHEETS: for sid, sname, _ in SALES_SHEETS:
@ -428,7 +429,8 @@ def write_sales_sheets(token, all_entries, phone_map, db_info):
d_vals, h_vals, i_vals, j_vals = [], [], [], [] d_vals, h_vals, i_vals, j_vals = [], [], [], []
k_vals, l_vals, m_vals, n_vals = [], [], [], [] k_vals, l_vals, m_vals, n_vals = [], [], [], []
o_vals, p_vals, q_vals, r_vals = [], [], [], [] o_vals, p_vals, q_vals, r_vals = [], [], [], []
s_vals, t_vals, u_vals, v_vals = [], [], [], [] s_vals, t_vals, u_vals = [], [], []
x_vals, y_vals, z_vals = [], [], []
for item in g: for item in g:
phone = item["phone"] phone = item["phone"]
@ -486,51 +488,62 @@ def write_sales_sheets(token, all_entries, phone_map, db_info):
gsv_int = int(di["gsv"]) gsv_int = int(di["gsv"])
is_full_refund = (gmv_int > 0 and gmv_int == refund_int) is_full_refund = (gmv_int > 0 and gmv_int == refund_int)
# K=是: 有订单且非全额退清 # 有效订单判定: 有订单且非全额退清
# 注: C列(进线日期)实际存的是手机号, 无法做L≥C日期比较
order_date = di["order_date"] order_date = di["order_date"]
should_k_yes = di["has_order"] and not is_full_refund should_y_yes = di["has_order"] and not is_full_refund
if is_full_refund: if is_full_refund:
# 全额退清 → K/O/P/Q 全部清空 # 全额退清 → N/O/P 全部清空
k_vals.append([""]) n_vals.append([""])
o_vals.append([""]) o_vals.append([""])
p_vals.append([""]) p_vals.append([""])
q_vals.append([""])
else: else:
k_vals.append(["是" if should_k_yes else ""]) n_vals.append([gmv_int if gmv_int > 0 else ""])
o_vals.append([gmv_int if gmv_int > 0 else ""]) o_vals.append([refund_int if refund_int > 0 else ""])
p_vals.append([refund_int if refund_int > 0 else ""]) p_vals.append([gsv_int if gsv_int > 0 else ""])
q_vals.append([gsv_int if gsv_int > 0 else ""])
l_vals.append([order_date]) # K: 下单日期, L: 成交渠道, M: 产品
m_vals.append([di["order_channel"]]) k_vals.append([order_date])
n_vals.append([di["product"] if di["has_order"] else ""]) l_vals.append([di["order_channel"]])
m_vals.append([di["product"] if di["has_order"] else ""])
# Q: 激活课程
act = di["activation"] act = di["activation"]
if act: if act:
r_vals.append([f"{act}体验课" if act in ("A1", "A2") else act]) q_vals.append([f"{act}体验课" if act in ("A1", "A2") else act])
else: else:
r_vals.append([""]) q_vals.append([""])
# R: 行课进度, S: 最近行课时间
lp = di["lesson_progress"] lp = di["lesson_progress"]
s_vals.append([lp if lp else ""]) r_vals.append([lp if lp else ""])
t_vals.append([di["lesson_time"]]) s_vals.append([di["lesson_time"]])
# T: 学习时长
lm = di["lesson_minutes"] lm = di["lesson_minutes"]
u_vals.append([lm if lm > 0 else ""]) t_vals.append([lm if lm > 0 else ""])
# X: 订单号
x_vals.append([di.get("trade_no", "")])
# Y: 有效订单
y_vals.append([1 if should_y_yes else ""])
# Z: 渠道归属
z_vals.append([di["order_channel"]])
else: else:
for arr in [d_vals, i_vals, j_vals, k_vals, l_vals, m_vals, n_vals, for arr in [d_vals, i_vals, j_vals, k_vals, l_vals, m_vals, n_vals,
o_vals, p_vals, q_vals, r_vals, s_vals, t_vals, u_vals]: o_vals, p_vals, q_vals, r_vals, s_vals, t_vals,
x_vals, y_vals, z_vals]:
arr.append([""]) arr.append([""])
v_vals.append([now_str]) # U: 更新时间
u_vals.append([now_str])
cols = [ cols = [
("D", d_vals), ("H", h_vals), ("I", i_vals), ("J", j_vals), ("D", d_vals), ("H", h_vals), ("I", i_vals), ("J", j_vals),
("K", k_vals), ("L", l_vals), ("M", m_vals), ("N", n_vals), ("K", k_vals), ("L", l_vals), ("M", m_vals), ("N", n_vals),
("O", o_vals), ("P", p_vals), ("Q", q_vals), ("R", r_vals), ("O", o_vals), ("P", p_vals), ("Q", q_vals), ("R", r_vals),
("S", s_vals), ("T", t_vals), ("U", u_vals), ("V", v_vals), ("S", s_vals), ("T", t_vals), ("U", u_vals),
("X", x_vals), ("Y", y_vals), ("Z", z_vals),
] ]
for col_letter, vals in cols: for col_letter, vals in cols:
put_values(token, sid, f"{col_letter}{sr}:{col_letter}{er}", vals) put_values(token, sid, f"{col_letter}{sr}:{col_letter}{er}", vals)

217
scripts/fill_leads_sheet.py
View File

@ -3,13 +3,13 @@
端内析出leads数据 — 自动回填 + 统计汇总脚本 端内析出leads数据 — 自动回填 + 统计汇总脚本
流程： 流程：
1. 读取曲慧萌/吴迪 sheet 中 A 列的手机号 1. 读取吴迪 sheet 中 B 列的手机号
2. XXTEA 加密 → 匹配 bi_vala_app_account.tel_encrypt → 获取 account_id 2. XXTEA 加密 → 匹配 bi_vala_app_account.tel_encrypt → 获取 account_id
3. 查询注册日期、转化、退费、U0体验课完成日期 → 回写 3. 查询注册日期、转化（全部key_from，购课时间≥析出时间）、转化keyfrom、退费、U0体验课完成日期 → 回写
4. 按析出月份汇总统计 → 写入"统计" sheet 4. 按析出月份汇总统计 → 写入"统计" sheet
统计口径： 统计口径：
- 转化率 = 已转化leads / 有效析出leads（剔除端外购课用户） - 转化率 = 已转化leads / 总leads
- 退费率 = 退费leads / 已转化leads - 退费率 = 退费leads / 已转化leads
- 完成率 = 完成该课的leads / 总leads - 完成率 = 完成该课的leads / 总leads
@ -26,17 +26,9 @@ from collections import defaultdict
# ── 配置 ────────────────────────────────────────────── # ── 配置 ──────────────────────────────────────────────
SPREADSHEET_TOKEN = "FA3xsw3kph4pdatKlUrcyPgInAc" SPREADSHEET_TOKEN = "FA3xsw3kph4pdatKlUrcyPgInAc"
SHEET_QHM = "7f0e35" # 曲慧萌
SHEET_WD = "1K3O6s" # 吴迪 SHEET_WD = "1K3O6s" # 吴迪
SHEET_STAT = "scyF3H" # 统计 SHEET_STAT = "scyF3H" # 统计
# 端内渠道
INNER_CHANNELS = [
"app-active-h5-0-0",
"app-sales-bj-qhm-0",
"app-sales-bj-wd-0",
]
# U0 体验课 chapter_id # U0 体验课 chapter_id
U0_CHAPTERS = { U0_CHAPTERS = {
"L1-U0-L01": 343, "L1-U0-L01": 343,
@ -67,9 +59,11 @@ COL_EXTRACT_DATE = 4 # E: 析出日期（手动填）
COL_REG_DATE = 5 # F: 注册日期 COL_REG_DATE = 5 # F: 注册日期
COL_CONVERTED = 6 # G: 是否转化 COL_CONVERTED = 6 # G: 是否转化
COL_CONVERT_DATE = 7 # H: 转化日期 COL_CONVERT_DATE = 7 # H: 转化日期
COL_REFUND = 8 # I: 是否退费 COL_CONVERT_KEYFROM = 8 # I: 转化keyfrom
COL_REFUND_DATE = 9 # J: 退费日期 COL_CONVERT_GSV = 9 # J: 转化金额(GSV)（新增）
COL_U0_START = 10 # K-T: L1-U0-L01 ~ L2-U0-L05 COL_REFUND = 10 # K: 是否退费
COL_REFUND_DATE = 11 # L: 退费日期
COL_U0_START = 12 # M-W: L1-U0-L01 ~ L2-U0-L05
# ── 数据库 ───────────────────────────────────────────── # ── 数据库 ─────────────────────────────────────────────
PG_HOST = "bj-postgres-16pob4sg.sql.tencentcdb.com" PG_HOST = "bj-postgres-16pob4sg.sql.tencentcdb.com"
@ -180,64 +174,47 @@ def match_phones(phones: list[str]) -> dict[str, dict]:
return results return results
def query_conversion(account_ids: list[str]) -> dict[str, dict]: def query_orders_and_refunds(account_ids: list[str]) -> dict[str, dict]:
"""
查询全部渠道订单及退费信息（不限 key_from）。
返回: {account_id: {"orders": [(pay_date, key_from, is_refunded), ...], "total_gmv_cents": int, "total_gsv_cents": int}}
orders 按 pay_success_date 升序排列。
"""
if not account_ids: if not account_ids:
return {} return {}
BATCH_SIZE = 100 BATCH_SIZE = 100
results = {} results = {}
channels_str = ",".join(f"'{c}'" for c in INNER_CHANNELS)
for i in range(0, len(account_ids), BATCH_SIZE): for i in range(0, len(account_ids), BATCH_SIZE):
batch = account_ids[i:i + BATCH_SIZE] batch = account_ids[i:i + BATCH_SIZE]
ids_str = ",".join(batch) ids_str = ",".join(batch)
# 查询每笔订单及退费状态
sql = f""" sql = f"""
SELECT o.account_id::text, SELECT o.account_id::text,
MIN(o.pay_success_date::date::text) AS first_pay_date, o.pay_success_date::date::text,
BOOL_OR(r.id IS NOT NULL AND r.status = 3 AND o2.order_status = 4) AS has_refund, o.key_from,
MIN(CASE WHEN r.id IS NOT NULL AND r.status = 3 AND o2.order_status = 4 o.pay_amount_int,
THEN r.created_at::date::text END) AS first_refund_date COALESCE(SUM(CASE WHEN r.status = 3 AND o2.order_status = 4 THEN r.refund_amount::numeric * 100 ELSE 0 END), 0)::bigint AS total_refund_fen,
BOOL_OR(r.id IS NOT NULL AND r.status = 3 AND o2.order_status = 4) AS is_refunded
FROM bi_vala_order o FROM bi_vala_order o
LEFT JOIN bi_refund_order r ON o.trade_no = r.trade_no AND r.status = 3 LEFT JOIN bi_refund_order r ON o.trade_no = r.trade_no
LEFT JOIN bi_vala_order o2 ON o.trade_no = o2.trade_no AND o2.order_status = 4 LEFT JOIN bi_vala_order o2 ON o.trade_no = o2.trade_no AND o2.order_status = 4
WHERE o.account_id IN ({ids_str}) WHERE o.account_id IN ({ids_str})
AND o.key_from IN ({channels_str})
AND o.pay_success_date IS NOT NULL AND o.pay_success_date IS NOT NULL
AND o.order_status IN (3, 4) AND o.order_status IN (3, 4)
GROUP BY o.account_id GROUP BY o.account_id, o.pay_success_date, o.key_from, o.pay_amount_int
ORDER BY o.account_id, o.pay_success_date
""" """
for row in pg_query(sql): for row in pg_query(sql):
if len(row) >= 3: if len(row) >= 6:
acc_id, first_pay, has_refund = row[0], row[1], row[2] acc_id, pay_date, key_from, pay_amount, total_refund_fen, is_refunded = row[0], row[1], row[2], row[3], row[4], row[5]
first_refund = row[3] if len(row) >= 4 else "" if acc_id not in results:
results[acc_id] = { results[acc_id] = {"orders": [], "total_gmv_cents": 0, "total_gsv_cents": 0}
"converted": "是" if first_pay else "否", refunded = is_refunded in ("t", "true")
"convert_date": first_pay or "", results[acc_id]["orders"].append((pay_date, key_from, refunded))
"refunded": "是" if has_refund in ("t", "true") else "否", # 累加用户总 GMV（分）和 GSV（分）
"refund_date": first_refund or "", results[acc_id]["total_gmv_cents"] += int(pay_amount)
} gsv_fen = int(pay_amount) - int(total_refund_fen)
return results results[acc_id]["total_gsv_cents"] += gsv_fen
def query_outside_conversion(account_ids: list[str]) -> set[str]:
"""查询哪些账号有端外购课（key_from 不在端内渠道中）"""
if not account_ids:
return set()
BATCH_SIZE = 100
results = set()
channels_str = ",".join(f"'{c}'" for c in INNER_CHANNELS)
for i in range(0, len(account_ids), BATCH_SIZE):
batch = account_ids[i:i + BATCH_SIZE]
ids_str = ",".join(batch)
sql = f"""
SELECT DISTINCT o.account_id::text
FROM bi_vala_order o
WHERE o.account_id IN ({ids_str})
AND o.key_from NOT IN ({channels_str})
AND o.pay_success_date IS NOT NULL
AND o.order_status IN (3, 4)
"""
for row in pg_query(sql):
if len(row) >= 1:
results.add(row[0])
return results return results
@ -305,7 +282,7 @@ def process_sheet(sheet_id: str, sheet_name: str, dry_run: bool = False) -> list
print(f"处理 Sheet: {sheet_name} ({sheet_id})") print(f"处理 Sheet: {sheet_name} ({sheet_id})")
print(f"{'='*60}") print(f"{'='*60}")
range_str = f"{sheet_id}!A2:T" range_str = f"{sheet_id}!A2:W"
try: try:
rows = lark_read(sheet_id, range_str) rows = lark_read(sheet_id, range_str)
except Exception as e: except Exception as e:
@ -339,11 +316,8 @@ def process_sheet(sheet_id: str, sheet_name: str, dry_run: bool = False) -> list
matched_accounts = [info["id"] for info in acc_info.values()] matched_accounts = [info["id"] for info in acc_info.values()]
matched_phones = set(acc_info.keys()) matched_phones = set(acc_info.keys())
print("→ 查询转化信息...") print("→ 查询订单及退费信息（全部渠道）...")
conv_info = query_conversion(matched_accounts) order_info = query_orders_and_refunds(matched_accounts)
print("→ 查询端外购课...")
outside_accounts = query_outside_conversion(matched_accounts)
print("→ 查询 U0 学习进度...") print("→ 查询 U0 学习进度...")
learn_info = query_learning(matched_accounts) learn_info = query_learning(matched_accounts)
@ -357,7 +331,6 @@ def process_sheet(sheet_id: str, sheet_name: str, dry_run: bool = False) -> list
if not info: if not info:
continue continue
acc_id = info["id"] acc_id = info["id"]
conv = conv_info.get(acc_id, {})
learn = learn_info.get(acc_id, {}) learn = learn_info.get(acc_id, {})
for row_idx in row_indices: for row_idx in row_indices:
@ -366,32 +339,59 @@ def process_sheet(sheet_id: str, sheet_name: str, dry_run: bool = False) -> list
if len(rows[row_idx]) > COL_EXTRACT_DATE and rows[row_idx][COL_EXTRACT_DATE]: if len(rows[row_idx]) > COL_EXTRACT_DATE and rows[row_idx][COL_EXTRACT_DATE]:
extract_date = str(rows[row_idx][COL_EXTRACT_DATE]).strip() extract_date = str(rows[row_idx][COL_EXTRACT_DATE]).strip()
# F 列逻辑：端内购课 > 端外购课 > 否 # 转化判断：全部渠道，购课时间 ≥ 析出时间
is_inner = conv.get("converted", "否") == "是" # 退费判断：只要存在一笔 ≥ 析出日期且未退费的订单，就算未退费
is_outside = acc_id in outside_accounts # 转化金额：用户全部订单 GSV（全部 pay_amount - 全部 refund_amount）
if is_inner: orders = order_info.get(acc_id, {})
f_value = "是" conv_date = ""
convert_date = conv.get("convert_date", "") conv_keyfrom = ""
elif is_outside: conv_gsv = ""
f_value = "端外购课" is_refunded = "否"
convert_date = ""
# 析出日期可能是 Excel 序列数字，统一转为 YYYY-MM-DD
extract_date_ymd = ""
if extract_date:
if extract_date.isdigit():
extract_date_ymd = excel_serial_to_date(int(extract_date))
else: else:
f_value = "否" extract_date_ymd = extract_date
convert_date = ""
if extract_date_ymd:
first_match = None
has_valid_order = False
for pay_date, kf, refunded in orders.get("orders", []):
if pay_date >= extract_date_ymd:
if first_match is None:
first_match = (pay_date, kf)
if not refunded:
has_valid_order = True
if first_match:
conv_date = first_match[0]
conv_keyfrom = first_match[1]
# 转化金额 = 用户总 GSV（元）
total_gsv = orders.get("total_gsv_cents", 0)
conv_gsv = str(round(total_gsv / 100, 2))
is_refunded = "否" if has_valid_order else "是"
f_value = "是" if conv_date else "否"
updates.append((row_idx, COL_USER_ID, acc_id)) updates.append((row_idx, COL_USER_ID, acc_id))
updates.append((row_idx, COL_REG_DATE, info.get("created_at", ""))) updates.append((row_idx, COL_REG_DATE, info.get("created_at", "")))
updates.append((row_idx, COL_CONVERTED, f_value)) updates.append((row_idx, COL_CONVERTED, f_value))
updates.append((row_idx, COL_CONVERT_DATE, convert_date)) updates.append((row_idx, COL_CONVERT_DATE, conv_date))
updates.append((row_idx, COL_REFUND, conv.get("refunded", "否"))) updates.append((row_idx, COL_CONVERT_KEYFROM, conv_keyfrom))
updates.append((row_idx, COL_REFUND_DATE, conv.get("refund_date", ""))) updates.append((row_idx, COL_CONVERT_GSV, conv_gsv))
updates.append((row_idx, COL_REFUND, is_refunded))
updates.append((row_idx, COL_REFUND_DATE, ""))
for col_offset, lesson_name in enumerate(U0_COL_ORDER): for col_offset, lesson_name in enumerate(U0_COL_ORDER):
updates.append((row_idx, COL_U0_START + col_offset, learn.get(lesson_name, ""))) updates.append((row_idx, COL_U0_START + col_offset, learn.get(lesson_name, "")))
lead_data.append({ lead_data.append({
"extract_date": extract_date, "extract_date": extract_date,
"converted": f_value, "converted": f_value,
"refunded": conv.get("refunded", "否"), "refunded": is_refunded,
"gmv_cents": orders.get("total_gmv_cents", 0),
"gsv_cents": orders.get("total_gsv_cents", 0),
"lessons": {k: learn.get(k, "") for k in U0_COL_ORDER}, "lessons": {k: learn.get(k, "") for k in U0_COL_ORDER},
"has_phone": True, "has_phone": True,
}) })
@ -411,6 +411,8 @@ def process_sheet(sheet_id: str, sheet_name: str, dry_run: bool = False) -> list
"extract_date": extract_date, "extract_date": extract_date,
"converted": existing_converted, "converted": existing_converted,
"refunded": "否", "refunded": "否",
"gmv_cents": 0,
"gsv_cents": 0,
"lessons": {k: "" for k in U0_COL_ORDER}, "lessons": {k: "" for k in U0_COL_ORDER},
"has_phone": False, "has_phone": False,
}) })
@ -431,16 +433,16 @@ def process_sheet(sheet_id: str, sheet_name: str, dry_run: bool = False) -> list
lark_write(sheet_id, f"{sheet_id}!D{actual_row}:D{actual_row}", lark_write(sheet_id, f"{sheet_id}!D{actual_row}:D{actual_row}",
[[str(col_vals[COL_USER_ID])]]) [[str(col_vals[COL_USER_ID])]])
# F-T: 注册日期 ~ L2-U0-L5 # F-V: 注册日期 ~ L2-U0-L5（含 I 列转化keyfrom）
f_to_t = [] f_to_w = []
for col in range(COL_REG_DATE, COL_U0_START + len(U0_COL_ORDER)): for col in range(COL_REG_DATE, COL_U0_START + len(U0_COL_ORDER)):
val = col_vals.get(col, "") val = col_vals.get(col, "")
f_to_t.append(str(val) if val else "") f_to_w.append(str(val) if val else "")
if dry_run: if dry_run:
print(f" [DRY-RUN] {sheet_id}!D{actual_row} + F{actual_row}:T{actual_row} ← ...") print(f" [DRY-RUN] {sheet_id}!D{actual_row} + F{actual_row}:W{actual_row} ← ...")
else: else:
lark_write(sheet_id, f"{sheet_id}!F{actual_row}:T{actual_row}", [f_to_t]) lark_write(sheet_id, f"{sheet_id}!F{actual_row}:W{actual_row}", [f_to_w])
print(f" ✓ 行 {actual_row} 回写成功") print(f" ✓ 行 {actual_row} 回写成功")
unmatched = set(phones) - matched_phones unmatched = set(phones) - matched_phones
@ -458,8 +460,7 @@ def compute_stats(lead_data: list[dict]) -> dict[str, dict]:
""" """
按析出月份汇总统计 按析出月份汇总统计
口径： 口径：
- 有效析出用户数 = 总leads - 端外购课leads - 转化率 = 已转化leads / 总leads
- 转化率 = 已转化leads / 有效析出用户数
- 退费率 = 退费leads / 已转化leads - 退费率 = 退费leads / 已转化leads
- 完成率 = 完成该课的leads / 总leads - 完成率 = 完成该课的leads / 总leads
""" """
@ -494,30 +495,32 @@ def compute_stats(lead_data: list[dict]) -> dict[str, dict]:
for month, leads in sorted(month_groups.items()): for month, leads in sorted(month_groups.items()):
total = len(leads) total = len(leads)
matched = sum(1 for l in leads if l.get("has_phone", False)) matched = sum(1 for l in leads if l.get("has_phone", False))
outside_only = sum(1 for l in leads if l["converted"] == "端外购课")
converted_all = sum(1 for l in leads if l["converted"] == "是") converted_all = sum(1 for l in leads if l["converted"] == "是")
refunded = sum(1 for l in leads if l["refunded"] == "是") refunded = sum(1 for l in leads if l["refunded"] == "是")
converted_unrefunded = sum(1 for l in leads if l["converted"] == "是" and l["refunded"] != "是") converted_unrefunded = sum(1 for l in leads if l["converted"] == "是" and l["refunded"] != "是")
# 转化率分母剔除端外购课用户 conv_rate = converted_all / total * 100 if total > 0 else 0
effective_total = total - outside_only
conv_rate = converted_all / effective_total * 100 if effective_total > 0 else 0
refund_rate = refunded / converted_all * 100 if converted_all > 0 else 0 refund_rate = refunded / converted_all * 100 if converted_all > 0 else 0
# GMV / GSV 汇总（元）
total_gmv = sum(l.get("gmv_cents", 0) for l in leads) / 100
total_gsv = sum(l.get("gsv_cents", 0) for l in leads) / 100
lesson_rates = {} lesson_rates = {}
for lesson_name in U0_COL_ORDER: for lesson_name in U0_COL_ORDER:
completed = sum(1 for l in leads if l["lessons"].get(lesson_name, "")) completed = sum(1 for l in leads if l["lessons"].get(lesson_name, ""))
lesson_rates[lesson_name] = completed / total * 100 if total > 0 else 0 lesson_rates[lesson_name] = completed / total * 100 if total > 0 else 0
result[month] = { result[month] = {
"total": effective_total, "total": total,
"matched": matched, "matched": matched,
"outside_only": outside_only,
"converted_all": converted_all, "converted_all": converted_all,
"converted_unrefunded": converted_unrefunded, "converted_unrefunded": converted_unrefunded,
"refunded": refunded, "refunded": refunded,
"conv_rate": conv_rate, "conv_rate": conv_rate,
"refund_rate": refund_rate, "refund_rate": refund_rate,
"gmv": total_gmv,
"gsv": total_gsv,
"lesson_rates": lesson_rates, "lesson_rates": lesson_rates,
} }
@ -532,21 +535,21 @@ def write_all_stats(all_stats: dict[str, dict[str, dict]], dry_run: bool = False
按 销售+月份 逐行写入，从第2行开始 按 销售+月份 逐行写入，从第2行开始
""" """
# 先写表头 # 先写表头
header = ["销售", "月份", "有效析出用户数", "匹配用户数", "转化用户数", "转化率", "退费率"] + \ header = ["销售", "月份", "总析出用户数", "匹配用户数", "转化用户数", "转化率", "退费率", "GMV", "GSV"] + \
[f"{name}完成率" for name in U0_COL_ORDER] [f"{name}完成率" for name in U0_COL_ORDER]
if not dry_run: if not dry_run:
lark_write(SHEET_STAT, f"{SHEET_STAT}!A1:Q1", [header]) lark_write(SHEET_STAT, f"{SHEET_STAT}!A1:S1", [header])
# 构建有序行列表: [(sales_name, month, stats), ...] # 构建有序行列表: [(sales_name, month, stats), ...]
rows_data = [] rows_data = []
for sales_name in ["曲慧萌", "吴迪"]: for sales_name in ["吴迪"]:
stats = all_stats.get(sales_name, {}) stats = all_stats.get(sales_name, {})
for month in sorted(stats.keys()): for month in sorted(stats.keys()):
rows_data.append((sales_name, month, stats[month])) rows_data.append((sales_name, month, stats[month]))
# 先清除统计 sheet 旧数据（A2:Q50），避免残留旧行 # 先清除统计 sheet 旧数据（A2:S50），避免残留旧行
print(" → 清除统计 sheet 旧数据...") print(" → 清除统计 sheet 旧数据...")
lark_write(SHEET_STAT, f"{SHEET_STAT}!A2:Q50", [[""] * 17] * 49) lark_write(SHEET_STAT, f"{SHEET_STAT}!A2:S50", [[""] * 19] * 49)
if not rows_data: if not rows_data:
print(" 无统计数据") print(" 无统计数据")
@ -559,7 +562,7 @@ def write_all_stats(all_stats: dict[str, dict[str, dict]], dry_run: bool = False
lark_write(SHEET_STAT, f"{SHEET_STAT}!A{row_num}:A{row_num}", [[sales_name]]) lark_write(SHEET_STAT, f"{SHEET_STAT}!A{row_num}:A{row_num}", [[sales_name]])
# B: 月份 # B: 月份
lark_write(SHEET_STAT, f"{SHEET_STAT}!B{row_num}:B{row_num}", [[month]]) lark_write(SHEET_STAT, f"{SHEET_STAT}!B{row_num}:B{row_num}", [[month]])
# C: 有效析出用户数（剔除端外购课） # C: 总析出用户数
lark_write(SHEET_STAT, f"{SHEET_STAT}!C{row_num}:C{row_num}", [[s["total"]]]) lark_write(SHEET_STAT, f"{SHEET_STAT}!C{row_num}:C{row_num}", [[s["total"]]])
# D: 匹配用户数 # D: 匹配用户数
lark_write(SHEET_STAT, f"{SHEET_STAT}!D{row_num}:D{row_num}", [[s["matched"]]]) lark_write(SHEET_STAT, f"{SHEET_STAT}!D{row_num}:D{row_num}", [[s["matched"]]])
@ -569,12 +572,16 @@ def write_all_stats(all_stats: dict[str, dict[str, dict]], dry_run: bool = False
lark_write(SHEET_STAT, f"{SHEET_STAT}!F{row_num}:F{row_num}", [[round(s["conv_rate"] / 100, 3)]]) lark_write(SHEET_STAT, f"{SHEET_STAT}!F{row_num}:F{row_num}", [[round(s["conv_rate"] / 100, 3)]])
# G: 退费率 # G: 退费率
lark_write(SHEET_STAT, f"{SHEET_STAT}!G{row_num}:G{row_num}", [[round(s["refund_rate"] / 100, 3)]]) lark_write(SHEET_STAT, f"{SHEET_STAT}!G{row_num}:G{row_num}", [[round(s["refund_rate"] / 100, 3)]])
# H-Q: 完成率 # H: GMV（元）
lark_write(SHEET_STAT, f"{SHEET_STAT}!H{row_num}:H{row_num}", [[round(s["gmv"], 2)]])
# I: GSV（元）
lark_write(SHEET_STAT, f"{SHEET_STAT}!I{row_num}:I{row_num}", [[round(s["gsv"], 2)]])
# J-S: 完成率
lesson_vals = [round(s["lesson_rates"][name] / 100, 3) for name in U0_COL_ORDER] lesson_vals = [round(s["lesson_rates"][name] / 100, 3) for name in U0_COL_ORDER]
lark_write(SHEET_STAT, f"{SHEET_STAT}!H{row_num}:Q{row_num}", [lesson_vals]) lark_write(SHEET_STAT, f"{SHEET_STAT}!J{row_num}:S{row_num}", [lesson_vals])
print(f" ✓ {sales_name} {month}: 有效析出={s['total']} 匹配={s['matched']} 转化={s['converted_all']} " print(f" ✓ {sales_name} {month}: 总析出={s['total']} 匹配={s['matched']} 转化={s['converted_all']} "
f"转化率={s['conv_rate']:.1f}% 退费率={s['refund_rate']:.1f}%") f"转化率={s['conv_rate']:.1f}% 退费率={s['refund_rate']:.1f}% GMV={s['gmv']:.2f} GSV={s['gsv']:.2f}")
# ── 主流程 ────────────────────────────────────────────── # ── 主流程 ──────────────────────────────────────────────
@ -584,8 +591,7 @@ def main():
if dry_run: if dry_run:
print("⚠️ DRY-RUN 模式，不会实际写入\n") print("⚠️ DRY-RUN 模式，不会实际写入\n")
# 处理两个销售 sheet # 处理吴迪 sheet
qhm_data = process_sheet(SHEET_QHM, "曲慧萌", dry_run)
wd_data = process_sheet(SHEET_WD, "吴迪", dry_run) wd_data = process_sheet(SHEET_WD, "吴迪", dry_run)
# 汇总统计 # 汇总统计
@ -593,15 +599,14 @@ def main():
print("汇总统计 → 统计 sheet") print("汇总统计 → 统计 sheet")
print(f"{'='*60}") print(f"{'='*60}")
qhm_stats = compute_stats(qhm_data)
wd_stats = compute_stats(wd_data) wd_stats = compute_stats(wd_data)
all_stats = {"曲慧萌": qhm_stats, "吴迪": wd_stats} all_stats = {"吴迪": wd_stats}
if dry_run: if dry_run:
for sales_name, stats in all_stats.items(): for sales_name, stats in all_stats.items():
for month, s in stats.items(): for month, s in stats.items():
print(f" [DRY-RUN] {sales_name} {month}: 有效析出={s['total']} 匹配={s['matched']} 转化={s['converted_all']} 转化率={s['conv_rate']:.1f}% 退费率={s['refund_rate']:.1f}%") print(f" [DRY-RUN] {sales_name} {month}: 总析出={s['total']} 匹配={s['matched']} 转化={s['converted_all']} 转化率={s['conv_rate']:.1f}% 退费率={s['refund_rate']:.1f}% GMV={s['gmv']:.2f} GSV={s['gsv']:.2f}")
else: else:
write_all_stats(all_stats, dry_run) write_all_stats(all_stats, dry_run)

21
scripts/refresh_order_summary.py
View File

@ -19,7 +19,6 @@ APP_ID = "cli_a929ae22e0b8dcc8"
APP_SECRET = "OtFjMy7p3qE3VvLbMdcWidwgHOnGD4FJ" APP_SECRET = "OtFjMy7p3qE3VvLbMdcWidwgHOnGD4FJ"
SPREADSHEET_TOKEN = "NoZqsFi47hIOHEt9j8WcfRtbnug" SPREADSHEET_TOKEN = "NoZqsFi47hIOHEt9j8WcfRtbnug"
SALES_SHEETS = {"f975f0": "吴迪", "qJF4I": "小龙", "qJF4J": "成都"} SALES_SHEETS = {"f975f0": "吴迪", "qJF4I": "小龙", "qJF4J": "成都"}
DIRECT_SHEET = "1sosYE" # 直购表（小红书店铺+stream-xhs，不依赖手机号匹配）
SUMMARY_SHEET = "2smjwA" SUMMARY_SHEET = "2smjwA"
def _get_pg_password(): def _get_pg_password():
@ -188,24 +187,6 @@ def main():
print(f"Total rows: {len(all_rows)}") print(f"Total rows: {len(all_rows)}")
# ── Step 1.5: 读取直购表 ──
print(f"Reading 直购...")
direct_vals = read_sheet(token, DIRECT_SHEET, "A2:V10000")
direct_rows = []
for i, row in enumerate(direct_vals):
while len(row) < 22:
row.append("")
b = str(row[1]).strip() if row[1] else ""
h = str(row[7]).strip() if row[7] else ""
if b or h:
direct_rows.append({
"sid": DIRECT_SHEET, "name": "直购", "row": i + 2,
"raw": row[:22],
})
print(f" {len(direct_rows)} non-empty rows")
all_rows.extend(direct_rows)
print(f"Total rows (with 直购): {len(all_rows)}")
# ── Step 2: 筛选进订单汇总的行 ── # ── Step 2: 筛选进订单汇总的行 ──
# 条件：K=是 · O>0 · 非全额退(P空或P<O) · L≥C # 条件：K=是 · O>0 · 非全额退(P空或P<O) · L≥C
order_rows = [] order_rows = []
@ -245,7 +226,7 @@ def main():
print(f"Order rows after filter: {len(order_rows)}") print(f"Order rows after filter: {len(order_rows)}")
# ── Step 2.5: 去重（同一人可能在三表+直购中出现多次）── # ── Step 2.5: 去重（同一人可能在三表中出现多次）──
# 按 (A销售归属, B微信昵称, O下单金额, P退款金额, L下单日期) 去重 # 按 (A销售归属, B微信昵称, O下单金额, P退款金额, L下单日期) 去重
seen = set() seen = set()
deduped = [] deduped = []

194
scripts/sales_leads_full_refresh.py
View File

@ -6,15 +6,15 @@
1. 读取「小龙」「吴迪」「成都」三个 sheet 的 E 列手机号 1. 读取「小龙」「吴迪」「成都」三个 sheet 的 E 列手机号
2. XXTEA 加密 → bi_vala_app_account.tel_encrypt 精确匹配 → 获取 account_id 2. XXTEA 加密 → bi_vala_app_account.tel_encrypt 精确匹配 → 获取 account_id
3. 查询 PostgreSQL 获取用户订单/学习数据 3. 查询 PostgreSQL 获取用户订单/学习数据
4. 填写 H~V 列（自动列），V 列为操作更新时间 4. 填写 D/H/I/J/K~U/X/Y/Z 列（自动列），U 列为操作更新时间
5. 将三个 sheet 中 K=是（已下单）的用户汇总到「订单汇总」sheet 5. 将三个 sheet 中 Y=1（有效订单）的用户汇总到「订单汇总」sheet
规则（沿用 S2 规则）: 规则（沿用 S2 规则）:
① E→H: XXTEA 精确匹配, 查不到留空 ① E→H: XXTEA 精确匹配, 查不到留空
② H→D/I/J: 只补空, 不覆盖已有值 ② H→D/I/J: 只补空, 不覆盖已有值
③ K=是: 仅当 L(下单日) >= C(线索日期) ③ Y=1: 仅当 K(下单日) >= C(线索日期)
④ 全额退清: 所有订单都退费 → K/O/P/Q 全部清空 ④ 全额退清: 所有订单都退费 → N/O/P 全部清空
⑤ O/P/Q 0 留空, P 整元 ⑤ N/O/P 0 留空, O 整元
⑥ G 列不动 ⑥ G 列不动
用法: 用法:
@ -36,9 +36,9 @@ from phone_encrypt import encrypt_phone
SPREADSHEET_TOKEN = "NoZqsFi47hIOHEt9j8WcfRtbnug" SPREADSHEET_TOKEN = "NoZqsFi47hIOHEt9j8WcfRtbnug"
SALES_SHEETS = [ SALES_SHEETS = [
("qJF4I", "小龙", "A3:V2607"), ("qJF4I", "小龙", "A3:Z2607"),
("f975f0", "吴迪", "A3:V8149"), ("f975f0", "吴迪", "A3:Z8149"),
("qJF4J", "成都", "A3:V2500"), ("qJF4J", "成都", "A3:Z2500"),
] ]
SUMMARY_SHEET_ID = "2smjwA" SUMMARY_SHEET_ID = "2smjwA"
@ -60,6 +60,26 @@ CHANNEL_MAP = {
"官网": "官网", "官网": "官网",
} }
def classify_channel(keyfrom):
"""将 keyfrom 归类为 销转/直购/端内/达人/其他"""
if not keyfrom:
return ""
kf = keyfrom.lower()
if any(kw in kf for kw in ["newmedia-daren", "jingxuan", "stream-daren"]):
return "达人"
if any(kw in kf for kw in ["sales-adp", "stream-wxxd"]):
return "销转"
if "微信小店" in keyfrom:
return "销转"
if any(kw in kf for kw in ["app-active", "app-sales", "partner-active"]):
return "端内"
if any(kw in kf for kw in ["dianpu-", "stream-xhs"]):
return "直购"
if any(kw in keyfrom for kw in ["抖音", "直购", "小红书"]):
return "直购"
return "其他"
LOG_FILE = "/var/log/xiaoxi_full_refresh.log" LOG_FILE = "/var/log/xiaoxi_full_refresh.log"
@ -204,7 +224,9 @@ def parse_sales_sheets(token):
"S": safe_cell(row, 18), "S": safe_cell(row, 18),
"T": safe_cell(row, 19), "T": safe_cell(row, 19),
"U": safe_cell(row, 20), "U": safe_cell(row, 20),
"V": safe_cell(row, 21), "X": safe_cell(row, 23),
"Y": safe_cell(row, 24),
"Z": safe_cell(row, 25),
}, },
}) })
@ -299,6 +321,7 @@ def query_all_pg(all_entries, phone_map):
"has_order": False, "order_date": "", "order_channel": "", "product": "", "has_order": False, "order_date": "", "order_channel": "", "product": "",
"gmv": 0, "refund": 0, "gsv": 0, "gmv": 0, "refund": 0, "gsv": 0,
"activation": "", "lesson_progress": "", "lesson_time": "", "lesson_minutes": 0, "activation": "", "lesson_progress": "", "lesson_time": "", "lesson_minutes": 0,
"trade_no": "",
} for uid in uid_set} } for uid in uid_set}
# 3a. 注册信息 # 3a. 注册信息
@ -354,9 +377,17 @@ def query_all_pg(all_entries, phone_map):
continue continue
info[aid]["has_order"] = True info[aid]["has_order"] = True
latest = olist[0] latest = olist[0]
info[aid]["order_date"] = latest[2].strftime("%Y-%m-%d") if latest[2] else "" # K列格式: M月D日 HH:MM:SS, 同时保留 raw 用于日期比较
if latest[2]:
dt = latest[2]
info[aid]["order_date"] = f"{dt.month}月{dt.day}日 {dt.strftime('%H:%M:%S')}"
info[aid]["order_date_raw"] = dt.strftime("%Y-%m-%d %H:%M:%S")
else:
info[aid]["order_date"] = ""
info[aid]["order_date_raw"] = ""
info[aid]["order_channel"] = latest[3] or "" info[aid]["order_channel"] = latest[3] or ""
info[aid]["product"] = GOODS_NAMES.get(latest[4], f"商品{latest[4]}") info[aid]["product"] = GOODS_NAMES.get(latest[4], f"商品{latest[4]}")
info[aid]["trade_no"] = latest[1] or ""
total_gmv = sum(o[5] for o in olist) / 100.0 total_gmv = sum(o[5] for o in olist) / 100.0
total_refund = sum(refund_map.get(o[1], 0) for o in olist) / 100.0 total_refund = sum(refund_map.get(o[1], 0) for o in olist) / 100.0
info[aid]["gmv"] = total_gmv info[aid]["gmv"] = total_gmv
@ -469,7 +500,7 @@ def query_all_pg(all_entries, phone_map):
return info return info
# ═══ Step 4: 写入销售三表 H~V 列 ═══ # ═══ Step 4: 写入销售三表 D/H/I/J/K~U/X/Y/Z 列 ═══
def write_sales_sheets(token, all_entries, phone_map, db_info): def write_sales_sheets(token, all_entries, phone_map, db_info):
now_str = datetime.now().strftime("%Y-%m-%d %H:%M:%S") now_str = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
@ -496,7 +527,8 @@ def write_sales_sheets(token, all_entries, phone_map, db_info):
d_vals, h_vals, i_vals, j_vals = [], [], [], [] d_vals, h_vals, i_vals, j_vals = [], [], [], []
k_vals, l_vals, m_vals, n_vals = [], [], [], [] k_vals, l_vals, m_vals, n_vals = [], [], [], []
o_vals, p_vals, q_vals, r_vals = [], [], [], [] o_vals, p_vals, q_vals, r_vals = [], [], [], []
s_vals, t_vals, u_vals, v_vals = [], [], [], [] s_vals, t_vals, u_vals = [], [], []
x_vals, y_vals, z_vals = [], [], []
for e in g: for e in g:
phone = e["phone"] phone = e["phone"]
@ -551,52 +583,70 @@ def write_sales_sheets(token, all_entries, phone_map, db_info):
gsv_int = int(di["gsv"]) gsv_int = int(di["gsv"])
is_full_refund = (gmv_int > 0 and gmv_int == refund_int) is_full_refund = (gmv_int > 0 and gmv_int == refund_int)
# K=是: 有订单 且 非全额退清 且 L(下单日) >= C(线索日期) # 有效订单判定: 有订单 且 非全额退清 且 K(下单日) >= C(线索日期)
order_date = di["order_date"] order_date = di["order_date"]
should_k_yes = di["has_order"] and not is_full_refund should_y_yes = di["has_order"] and not is_full_refund
# 日期比较: L >= C # 日期比较: K >= C (用 raw 格式比较)
if should_k_yes and clue_date and order_date: order_date_raw = di.get("order_date_raw", "")
if order_date < clue_date: if should_y_yes and clue_date and order_date_raw:
should_k_yes = False if order_date_raw[:10] < clue_date:
should_y_yes = False
if is_full_refund: if is_full_refund:
k_vals.append([""]) n_vals.append([""])
o_vals.append([""]) o_vals.append([""])
p_vals.append([""]) p_vals.append([""])
q_vals.append([""])
else: else:
k_vals.append(["是" if should_k_yes else ""]) n_vals.append([gmv_int if gmv_int > 0 else ""])
o_vals.append([gmv_int if gmv_int > 0 else ""]) o_vals.append([refund_int if refund_int > 0 else ""])
p_vals.append([refund_int if refund_int > 0 else ""]) p_vals.append([gsv_int if gsv_int > 0 else ""])
q_vals.append([gsv_int if gsv_int > 0 else ""])
l_vals.append([order_date]) # K: 下单日期, L: 成交渠道, M: 产品
m_vals.append([di["order_channel"]]) k_vals.append([order_date])
n_vals.append([di["product"] if di["has_order"] else ""]) l_vals.append([di["order_channel"]])
m_vals.append([di["product"] if di["has_order"] else ""])
# Q: 激活课程
act = di["activation"] act = di["activation"]
if act: if act:
r_vals.append([f"{act}体验课" if act in ("A1", "A2") else act]) q_vals.append([f"{act}体验课" if act in ("A1", "A2") else act])
else: else:
r_vals.append([""]) q_vals.append([""])
s_vals.append([di["lesson_progress"] if di["lesson_progress"] else ""]) # R: 行课进度, S: 最近行课时间, T: 学习时长
t_vals.append([di["lesson_time"]]) r_vals.append([di["lesson_progress"] if di["lesson_progress"] else ""])
s_vals.append([di["lesson_time"]])
lm = di["lesson_minutes"] lm = di["lesson_minutes"]
u_vals.append([lm if lm > 0 else ""]) t_vals.append([lm if lm > 0 else ""])
# X: 订单号 — 保留已有
if existing["X"]:
x_vals.append([existing["X"]])
else:
x_vals.append([di.get("trade_no", "")])
# Y: 有效订单 — 保留已有
if existing["Y"]:
y_vals.append([existing["Y"]])
else:
y_vals.append([1 if should_y_yes else ""])
# Z: 渠道归属（销转/直购/端内/达人）
z_vals.append([classify_channel(di["order_channel"])])
else: else:
for arr in [d_vals, i_vals, j_vals, k_vals, l_vals, m_vals, n_vals, for arr in [d_vals, i_vals, j_vals, k_vals, l_vals, m_vals, n_vals,
o_vals, p_vals, q_vals, r_vals, s_vals, t_vals, u_vals]: o_vals, p_vals, q_vals, r_vals, s_vals, t_vals,
x_vals, y_vals, z_vals]:
arr.append([""]) arr.append([""])
v_vals.append([now_str]) # U: 更新时间
u_vals.append([now_str])
cols = [ cols = [
("D", d_vals), ("H", h_vals), ("I", i_vals), ("J", j_vals), ("D", d_vals), ("H", h_vals), ("I", i_vals), ("J", j_vals),
("K", k_vals), ("L", l_vals), ("M", m_vals), ("N", n_vals), ("K", k_vals), ("L", l_vals), ("M", m_vals), ("N", n_vals),
("O", o_vals), ("P", p_vals), ("Q", q_vals), ("R", r_vals), ("O", o_vals), ("P", p_vals), ("Q", q_vals), ("R", r_vals),
("S", s_vals), ("T", t_vals), ("U", u_vals), ("V", v_vals), ("S", s_vals), ("T", t_vals), ("U", u_vals),
("X", x_vals), ("Y", y_vals), ("Z", z_vals),
] ]
for col_letter, vals in cols: for col_letter, vals in cols:
put_values(token, sid, f"{col_letter}{sr}:{col_letter}{er}", vals) put_values(token, sid, f"{col_letter}{sr}:{col_letter}{er}", vals)
@ -608,7 +658,7 @@ def write_sales_sheets(token, all_entries, phone_map, db_info):
# ═══ Step 5: 汇总到「订单汇总」sheet ═══ # ═══ Step 5: 汇总到「订单汇总」sheet ═══
def clear_summary_sheet(token): def clear_summary_sheet(token):
"""先清空订单汇总 sheet 的旧数据（A~V列，从第3行开始），再写入新数据。""" """先清空订单汇总 sheet 的旧数据（A~X列，从第3行开始），再写入新数据。"""
log(" 检查订单汇总 sheet 现有数据...") log(" 检查订单汇总 sheet 现有数据...")
try: try:
rows = read_sheet(token, SUMMARY_SHEET_ID, "A3:A5000") rows = read_sheet(token, SUMMARY_SHEET_ID, "A3:A5000")
@ -621,9 +671,9 @@ def clear_summary_sheet(token):
log(" 订单汇总 sheet 无旧数据，跳过清空") log(" 订单汇总 sheet 无旧数据，跳过清空")
return return
log(f" 清空 A3:V{last_data_row}（{last_data_row - 2} 行旧数据）...") log(f" 清空 A3:X{last_data_row}（{last_data_row - 2} 行旧数据）...")
writer = FeishuSheetWriter(SPREADSHEET_TOKEN, token) writer = FeishuSheetWriter(SPREADSHEET_TOKEN, token)
writer.clear(SUMMARY_SHEET_ID, start_row=3, end_row=last_data_row, cols=22) writer.clear(SUMMARY_SHEET_ID, start_row=3, end_row=last_data_row, cols=24)
log(" 清空完成") log(" 清空完成")
except Exception as e: except Exception as e:
log(f" 清空异常: {e}") log(f" 清空异常: {e}")
@ -631,22 +681,22 @@ def clear_summary_sheet(token):
def write_summary_sheet(token, all_entries, phone_map, db_info): def write_summary_sheet(token, all_entries, phone_map, db_info):
""" """
将三个销售 sheet 中 K=是（已下单）的行汇总到「订单汇总」sheet。 将三个销售 sheet 中 Y=1（有效订单）的行汇总到「订单汇总」sheet。
先清空旧数据，再全量写入。 先清空旧数据，再全量写入。
订单汇总 sheet 的列结构（A~X）: 订单汇总 sheet 的列结构（A~X）:
A: 销售归属, B: 微信昵称, C: 进线日期, D: 体验节数, E: 手机号, A: 销售归属, B: 微信昵称, C: 进线日期, D: 体验节数, E: 手机号,
F: 用户年级, G: 课史/跟进, H: 用户ID, I: 注册日期, J: 下载渠道, F: 用户年级, G: 课史/跟进, H: 用户ID, I: 注册日期, J: 下载渠道,
K: 是否下单, L: 下单日期, M: 成交渠道, N: 产品, K: 下单日期, L: 成交渠道, M: 产品,
O: 下单金额(GMV), P: 退款金额, Q: 实际收入(GSV), R: 激活课程, N: 下单金额(GMV), O: 退款金额, P: 实际收入(GSV), Q: 激活课程,
S: 当前行课进度, T: 最近行课时间, U: 累计学习时长(min), V: 更新时间, R: 当前行课进度, S: 最近行课时间, T: 累计学习时长(min), U: 更新时间,
W: 渠道归属(公式), X: 有效成单(公式) V: 渠道归属, W: 有效成单, X: 订单号
""" """
# 先清空旧数据 # 先清空旧数据
clear_summary_sheet(token) clear_summary_sheet(token)
log(" 汇总订单数据...") log(" 汇总订单数据...")
# 收集所有 K=是 的行 # 收集所有有效订单的行
summary_rows = [] summary_rows = []
for sid, sname, _ in SALES_SHEETS: for sid, sname, _ in SALES_SHEETS:
entries = all_entries[sid] entries = all_entries[sid]
@ -663,24 +713,24 @@ def write_summary_sheet(token, all_entries, phone_map, db_info):
di = db_info.get(aid, {}) if aid > 0 else {} di = db_info.get(aid, {}) if aid > 0 else {}
# 判断是否下单 # 判断是否有效订单
gmv_int = int(di.get("gmv", 0)) gmv_int = int(di.get("gmv", 0))
refund_int = int(di.get("refund", 0)) refund_int = int(di.get("refund", 0))
gsv_int = int(di.get("gsv", 0)) gsv_int = int(di.get("gsv", 0))
is_full_refund = (gmv_int > 0 and gmv_int == refund_int) is_full_refund = (gmv_int > 0 and gmv_int == refund_int)
has_order = di.get("has_order", False) and not is_full_refund has_order = di.get("has_order", False) and not is_full_refund
# 日期比较 # 日期比较: K(下单日) >= C(进线日期) (用 raw 格式比较)
order_date = di.get("order_date", "") order_date_raw = di.get("order_date_raw", "")
clue_date = e["clue_date_parsed"] clue_date = e["clue_date_parsed"]
if has_order and clue_date and order_date: if has_order and clue_date and order_date_raw:
if order_date < clue_date: if order_date_raw[:10] < clue_date:
has_order = False has_order = False
if not has_order: if not has_order:
continue continue
# 构建汇总行 # 构建汇总行 (A~X, 24列)
row_data = [ row_data = [
e["sales"], # A: 销售归属 e["sales"], # A: 销售归属
e["nickname"], # B: 微信昵称 e["nickname"], # B: 微信昵称
@ -692,43 +742,41 @@ def write_summary_sheet(token, all_entries, phone_map, db_info):
str(aid) if aid > 0 else "", # H: 用户ID str(aid) if aid > 0 else "", # H: 用户ID
di.get("reg_date", ""), # I: 注册日期 di.get("reg_date", ""), # I: 注册日期
di.get("download_channel", ""), # J: 下载渠道 di.get("download_channel", ""), # J: 下载渠道
"是", # K: 是否下单 di.get("order_date", ""), # K: 下单日期
order_date, # L: 下单日期 di.get("order_channel", ""), # L: 成交渠道
di.get("order_channel", ""), # M: 成交渠道 di.get("product", ""), # M: 产品
di.get("product", ""), # N: 产品 gmv_int if gmv_int > 0 else "", # N: GMV
gmv_int if gmv_int > 0 else "", # O: GMV refund_int if refund_int > 0 else "", # O: 退款金额
refund_int if refund_int > 0 else "", # P: 退款金额 gsv_int if gsv_int > 0 else "", # P: GSV
gsv_int if gsv_int > 0 else "", # Q: GSV (f"{di['activation']}体验课" if di.get("activation") in ("A1", "A2") else di.get("activation", "")), # Q: 激活课程
(f"{di['activation']}体验课" if di.get("activation") in ("A1", "A2") else di.get("activation", "")), # R: 激活课程 di.get("lesson_progress", ""), # R: 行课进度
di.get("lesson_progress", ""), # S: 行课进度 di.get("lesson_time", ""), # S: 最近行课时间
di.get("lesson_time", ""), # T: 最近行课时间 di.get("lesson_minutes", 0) or "", # T: 学习时长
di.get("lesson_minutes", 0) or "", # U: 学习时长 datetime.now().strftime("%Y-%m-%d %H:%M:%S"), # U: 更新时间
datetime.now().strftime("%Y-%m-%d %H:%M:%S"), # V: 更新时间 classify_channel(di.get("order_channel", "")), # V: 渠道归属
# W: 渠道归属 — 公式 1, # W: 有效成单
# X: 有效成单 — 公式 di.get("trade_no", ""), # X: 订单号
] ]
summary_rows.append(row_data) summary_rows.append(row_data)
log(f" 共 {len(summary_rows)} 条下单记录待汇总") log(f" 共 {len(summary_rows)} 条有效订单待汇总")
if not summary_rows: if not summary_rows:
log(" 无下单记录，跳过汇总") log(" 无有效订单，跳过汇总")
return return
# 写入订单汇总 sheet（从第3行开始，覆盖 A~V 列，W/X 列保留公式） # 写入订单汇总 sheet（从第3行开始，A~X 共24列）
# 使用安全写入工具，自动分批遵守 5000 格上限
# 22 列 → 单批最大 200 行（200×22=4400 格 ≤ 5000）
writer = FeishuSheetWriter(SPREADSHEET_TOKEN, token) writer = FeishuSheetWriter(SPREADSHEET_TOKEN, token)
# 构建 A~V 的值数组（22列），确保每行长度一致 # 构建 A~X 的值数组（24列），确保每行长度一致
values = [] values = []
for row_data in summary_rows: for row_data in summary_rows:
padded = row_data[:22] padded = row_data[:24]
while len(padded) < 22: while len(padded) < 24:
padded.append("") padded.append("")
values.append(padded) values.append(padded)
writer.write(SUMMARY_SHEET_ID, start_row=3, rows=values, cols=22) writer.write(SUMMARY_SHEET_ID, start_row=3, rows=values, cols=24)
log(f" 订单汇总写入完成, 共 {len(summary_rows)} 行") log(f" 订单汇总写入完成, 共 {len(summary_rows)} 行")