Compare commits
12 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| c05b765b9d | |||
| df5f1b7223 | |||
| ec786b3480 | |||
| 11739478d2 | |||
| 7d9aad1672 | |||
| 8ccae17111 | |||
| 04d562745f | |||
| 8ad3186057 | |||
| 6eb304bca2 | |||
| 55239fd4dd | |||
| 6437d6e414 | |||
| f38f662316 |
@@ -51,6 +51,14 @@ MATERIALS_DOWNLOAD_DIR=
|
||||
# OCR 语言(pytesseract:默认 chi_sim+eng)
|
||||
OCR_LANG=chi_sim+eng
|
||||
|
||||
# ----- v1.1.6:RPA 超时覆盖(与 skill-template human_verification 对齐)-----
|
||||
# 手工登录等待超时(秒,默认 180 = HUMAN_WAIT_TIMEOUT)
|
||||
HUMAN_WAIT_TIMEOUT=
|
||||
# Playwright 默认操作超时(毫秒,默认 15000)
|
||||
RPA_PAGE_TIMEOUT_MS=
|
||||
# page.goto 导航超时(毫秒,默认 60000)
|
||||
RPA_GOTO_TIMEOUT_MS=
|
||||
|
||||
# ----- v1.1.1:AI 决策(宿主 LLM) -----
|
||||
# 宿主 jiangchang_skill_core.llm_manager 调 LLM 时,模型名覆盖(可选)
|
||||
LLM_MODEL_NAME=
|
||||
|
||||
122
CHANGELOG.md
122
CHANGELOG.md
@@ -2,6 +2,128 @@
|
||||
|
||||
本文件对应技能市场 **「更新日志」** Tab。
|
||||
|
||||
## 1.1.16
|
||||
|
||||
- 修复续聘建议中的趋势判定:仅近三年考核分数严格递增才建议续聘;成绩持平或回落均进入常规续聘评审。
|
||||
- 新增回归测试,覆盖 `80 → 80 → 90` 的成绩持平场景。
|
||||
|
||||
## 1.1.15
|
||||
|
||||
- **修复「数据管理」Tab 看不到(关键根因:`developer_ids` 是占位 ID)**
|
||||
- **根因复盘**:之前 8 个版本(v1.0.0 ~ v1.1.14)都没解决"装上看不到"。v1.1.14 修了 description 意图触发,但仍然看不到。逐字段对比同仓 5 个已安装技能的 `~/.openclaw/skills/*/SKILL.md`,发现:
|
||||
| 技能 | `developer_ids` | 数据管理可见? |
|
||||
|------|----------------|--------------|
|
||||
| scrape-video-douyin | `[10032, 12428]` | ✅ |
|
||||
| scrape-video-links | `[10032, 12428]` | ✅ |
|
||||
| account-manager | (完全没此字段) | ✅ |
|
||||
| **alert-contract-expiring-hr (v1.1.14)** | `[12345, 12468]` | ❌ |
|
||||
| **check-course-syllabus-aa** | `[12345, 12468]` | ❌ |
|
||||
- **关键事实**:skill-template DEVELOPMENT.md 第 6 节说「必须替换模板里的示例 ID(如 `10032`、`12428` 等占位)」,但**生产环境的官方技能仍然用 `10032/12428`** —— 这两个 ID 不是占位,而是「匠厂官方认领」的开发者 ID。模板注释(`12345 # 占位`)与生产实际完全相反!
|
||||
- **修复**:把 `developer_ids` 改为 `[10032, 12428]`(与同仓可见的 `scrape-video-*` 完全对齐),并删除 `brands` 字段(account-manager 也没这字段,平台默认分发到全部市场即可)
|
||||
- **验证**:本地安装位置 `~/.openclaw/skills/alert-contract-expiring-hr/SKILL.md` 同步应用本次修改后,预期用户在 OpenClaw 重启 / 刷新即可在「数据管理」Tab 看到本技能
|
||||
- **配套**:更新本技能 SKILL.md 注释,移除"开发期技能常为不公开"的错误描述(公开发布的技能都应该用官方 ID `[10032, 12428]`)
|
||||
|
||||
## 1.1.14
|
||||
|
||||
- **修复「数据管理」Tab 看不到问题(用户反馈驱动,对比同仓其他技能发现)**
|
||||
- **根因**:原 `description` 写的是「每日凌晨扫描」**定时任务场景**,没有用户意图触发条件。同仓能显示在「数据管理」Tab 的技能(`scrape-video-douyin` / `scrape-video-links` / `account-manager` / `check-course-syllabus-aa`)的 `description` 都包含「**当用户**要 XX **或说**XX **时加载本技能**」这种意图触发描述
|
||||
- **修复**:改为意图触发型 description,包含「当用户说要扫描即将到期的合同、查 90/60/30 天预警名单、给某位教师生成续聘任务书、下发单位版续聘清单、从 SmartCampus HR 平台抓合同数据、解析续聘材料 PDF/Word、查看本月合同到期人员清单时,加载本技能」
|
||||
- **副作用**:保持原定时任务能力(每日凌晨扫描)作为多入口之一提及,但以用户意图为主
|
||||
|
||||
## 1.1.13
|
||||
|
||||
- **修复市场可见性(按 skill-template 模板对齐 SKILL.md frontmatter)**
|
||||
- 移除 v1.1.12 误加的 `access_scope: 0` 字段(**根因**:模板 `skill-template-main/skill-template/SKILL.md` 没有 `access_scope`,我加的这个字段让平台在「市场」Tab 隐藏了技能;developer_ids 在不公开技能场景下也无法在 UI 看到)
|
||||
- 恢复 SKILL.md frontmatter 与 skill-template 完全一致(字段 + 缩进 + brands 列表 5 空格缩进)
|
||||
- 清理 SKILL.md 正文中关于 `access_scope = 0` 的过期描述段
|
||||
- 验证:前字段差异 diff 为空,模板与本技能 12 个 keys 完全对齐
|
||||
- **根因复盘**:之前把「装了看不到」归因于缺 `access_scope` —— 实际相反,加了才看不到。skill-template 不声明 access_scope 是有意的(公开可见优先)
|
||||
|
||||
## 1.1.12
|
||||
|
||||
- **修复市场安装后看不到问题(用户反馈驱动)**
|
||||
- SKILL.md `metadata.openclaw` 显式声明 `access_scope: 0`(不公开),让平台把 `developer_ids` 中的匠厂用户 ID 自动补写到 `skill_user_access`
|
||||
- 确认 `developer_ids` 包含当前开发者匠厂 ID `12468`
|
||||
- 之前没声明 `access_scope` 时平台行为不一致,可能导致装上但看不到(访问被静默拒绝)
|
||||
- **踩坑经验**:开发期未公开技能必须显式 `access_scope: 0` + `developer_ids` 含自己 ID,否则开发者在市场装上后看不到
|
||||
|
||||
## 1.1.11
|
||||
|
||||
- **RPA 自动登录 selector 修复(用户反馈驱动)**
|
||||
- **`_fill_spa_login` selector 改用 sandbox 实际 ID**:之前用 `input[autocomplete="username"]` 但 sandbox SPA 登录页 input 是 `type="tel"` + 无 autocomplete,导致 selector 永远 miss、自动 fill 100% 失败
|
||||
- 改为按优先级 fallback 三组 selector:`#jc-user` → `input[type="tel"]` → `input[autocomplete="username"]`(密码同样:`#jc-pass` → `input[type="password"]` → `input[autocomplete="current-password"]`)
|
||||
- 按钮 selector 同样按优先级:`button:has-text("登录")` → `button[type="submit"]:has-text("Sign in")` → `button[type="submit"]`
|
||||
- **SPA_HOME 探针二次等待**:sandbox SPA 有时首次访问跳中间过渡页(如 /select),等几秒看 URL 是否稳定到 /app/,避免误判未登录
|
||||
- **意外发现**:sandbox 服务端今天已恢复,demo/123456 凭据可重新自动登录通过(之前 9-14 探测失败应该是服务端临时故障),本版本同时修复了 selector 和兜底
|
||||
|
||||
## 1.1.10
|
||||
|
||||
- **RPA 已登录态检测优化(profile cookie 复用零打扰)**
|
||||
- **SPA_HOME 探针时延长等待**:从 `POST_LOGIN_SETTLE_MS=2s` 改为 `SPA_HYDRATION_MS=3s`,sandbox SPA 异步验证 cookie 时间更充分,避免误判未登录
|
||||
- **`_fill_spa_login` 入口先检测 `_is_logged_in`**:已登录态直接 `return True` 跳过自动 fill,不再强制 demo fill 破坏 session
|
||||
- **fill 后再检测 `_is_logged_in`**:避免 sandbox demo 凭据失效时 URL 跳 `/app/home` 但 cookie 没写入的误判
|
||||
- **用户反馈驱动**:用户要求「如果已经登录了不需要用户再登录」—— v1.1.8/v1.1.9 的探针逻辑在 sandbox SPA 异步验证 cookie 时机不准时仍会触发 fallback 手工登录;本次彻底修掉
|
||||
- 实跑(2026-09-14):profile 已登录态下,`collect-from-platform --show-browser --limit 1` **完全静默自动跑**(无 `[登录]` 提示、无弹窗打扰),13 秒抓 3 行 + 卡片 381 字 + 落库
|
||||
|
||||
## 1.1.9
|
||||
|
||||
- **RPA headed 模式改用系统 Edge(解决浏览器弹窗不可见)**
|
||||
- **根因**:v1.1.8 headed 模式用 Playwright 内置 chromium,**在 Windows 桌面 session 下能创建浏览器对象但 GUI 窗口不可见**(子进程 bash session 与用户桌面 session 不同),导致 `--show-browser` 看似启动 headed 实际用户看不到弹窗、无法手工登录,180s 后 LOGIN_TIMEOUT
|
||||
- **修复**:headed 模式改为 Playwright `channel="msedge"` 启动**系统 Microsoft Edge**(跟用户桌面 session 同源,能真正弹窗);系统 Edge 缺失时 fallback Playwright 内置 chromium
|
||||
- 验证(2026-09-14):`collect-from-platform --show-browser --limit 1 --human-wait-timeout 240` → 系统 Edge 弹出窗口 → 用户手工登录 → RPA 24 秒内检测到 → 抓 3 行合同(钱实验/孙助理/王明远)→ 抓卡片 381 字 → 落库 `saved_contracts=1 / downloaded_materials=1`
|
||||
- 测试:28/28 passed
|
||||
|
||||
## 1.1.8
|
||||
|
||||
- **RPA 首次登录采集修复(用户反馈驱动)**
|
||||
- **不再强制 goto login 打断手工登录态**:`collect_all` 启动时先调 `_is_logged_in(page)` 检测是否已登录(如 profile cookie 复用);已登录态直接 goto SPA_HOME,未登录态才走 login → 自动 fill → fallback 手工登录等待
|
||||
- **首次登录后不再强制 page.reload**:原 5.5 步骤「刷新触发 mock 数据」会打断刚登录的 SPA session,导致 sandbox 把已登录态踢回 login;改为**默认不刷新**,表格等 10s 未出现才触发兜底刷新(5.5/5.6 逻辑下沉到 `_try_reload_after_table_timeout`,仅在表格超时调用)
|
||||
- **表格列数自适应**:sandbox 首次登录未刷新时表格是 **7 列**(姓名/单位/到期日/剩余天数/预警/建议/按钮),刷新后才是 **10 列**(多 工号/岗位/合同类型/起止日期);原代码硬编码 10 列解析 → 7 列时 `r[7]/r[8]` IndexError。改为「首列匹配工号正则 `^[A-Za-z]?\d+$` 走 10 列,否则走 7 列」双布局自适应
|
||||
- **contract_id 派生兼容 7 列**:7 列布局无工号 → 用 `teacher_name` 派生 contract_id(如 `RPA-钱实验-20260415`),避免与 10 列工号布局冲突
|
||||
- **实跑验证(2026-09-14)**
|
||||
- 命令:`python scripts/main.py collect-from-platform --show-browser --limit 1 --human-wait-timeout 180`
|
||||
- 结果:自动 fill demo 失败 → fallback 手工登录 → 你登录后 RPA 不刷新直接跳 hr/contracts → 抓 3 行(钱实验/孙助理/王明远)→ 抓卡片 381 字 → 落库 `saved_contracts=1 / downloaded_materials=1`
|
||||
- 退出码 0
|
||||
|
||||
## 1.1.7
|
||||
|
||||
- **RPA 手工登录 fallback 实跑验证(2026-09-14)**
|
||||
- sandbox 演示账号 `demo/123456` 已失效(多次尝试 + 6 组常见 demo 凭据全部返回「用户名或密码错误」),按 v1.1.6 设计自动切到 `_wait_for_manual_login` 手工登录分支
|
||||
- 实跑命令:`python scripts/main.py collect-from-platform --show-browser --limit 1 --human-wait-timeout 180`
|
||||
- 实跑结果:用户在弹出浏览器手工登录后,RPA 第 1 次轮询(≤2s)即检测到 `/app/home` URL,跳过登录分支继续往下走:
|
||||
- 自动导航侧边栏 hr/contracts → `page.reload()` 触发 mock 数据
|
||||
- 抓到 3 行合同(钱实验 / 孙助理 / 王明远)
|
||||
- 首行「续聘材料包」卡片抓 870 字文本 → 4 条业绩记录
|
||||
- 落库 `contracts` + `materials_content`:`saved_contracts=1, downloaded_materials=1`
|
||||
- 结论:v1.1.6「自动 fill + 手工 fallback」设计 **已端到端验证**;后续 collect-from-platform 默认带 `--show-browser` 走手工登录入口(避免硬编码失效 demo 凭据)
|
||||
- 流程记录见 memory `platform-collect-workflow.md`
|
||||
|
||||
## 1.1.6
|
||||
|
||||
- **RPA 重构(按 skill-template `examples/real_browser_rpa` 设计模式)**
|
||||
- **超时参数统一抽到 `constants.py`**:新增 `HUMAN_WAIT_TIMEOUT=180` / `HUMAN_POLL_INTERVAL=2.0` / `DEFAULT_PAGE_TIMEOUT_MS=15s` / `GOTO_TIMEOUT_MS=60s` / `SPA_LOGIN_*` / `TABLE_*` / `SIDEBAR_LINK_TIMEOUT_MS` 等 24 个常量(与 skill-template human_verification 同名常量对齐)
|
||||
- **新增手工登录 fallback**:自动 fill demo/123456 失败时自动切到 `_wait_for_manual_login`(轮询 `_is_logged_in` 每 2s 一次,最多 `HUMAN_WAIT_TIMEOUT` 秒,超时抛 `LoginTimeoutError`),给用户手工登录机会(与 skill-template `task_rpa.py::_ensure_logged_in` 设计对齐)
|
||||
- **结构化错误码**:`RPAError` 基类 + `LoginTimeoutError`(`ERROR:LOGIN_TIMEOUT`)/ `MissingBrowserError`(`ERROR:MISSING_BROWSER`)/ `TableNotFoundError`(`ERROR:TABLE_NOT_FOUND`),供 CLI/宿主解析
|
||||
- **CLI 新增 `--human-wait-timeout N` flag**
|
||||
- **`_goto` 默认 timeout 改用 `GOTO_TIMEOUT_MS=60s`**;新增 `page.set_default_timeout(DEFAULT_PAGE_TIMEOUT_MS)`
|
||||
- **依赖清单修复**:删除 `requirements.txt` 中违规的 `playwright>=1.40.0`(playwright 由宿主 `jiangchang_skill_core` runtime 提供,文件顶部注释已声明)
|
||||
- **环境变量**:`.env.example` 新增 `HUMAN_WAIT_TIMEOUT` / `RPA_PAGE_TIMEOUT_MS` / `RPA_GOTO_TIMEOUT_MS` 覆盖项
|
||||
- **保留 v1.1.5 自动 fill 优势**:sandbox demo/123456 已知凭据自动登录(生产环境切换无 demo 凭据时自动 fallback 手工)
|
||||
|
||||
## 1.1.5
|
||||
|
||||
- **platform_collector RPA 采集修复(登录等待时间太短 → 拿不到数据)**
|
||||
- `_fill_spa_login`:settle_ms 默认 0 → **4000ms**,等 username input timeout 10s → **20s**,wait_for_url(URL 真的跳离 login)20s → **30s**;URL 判断增加 `/auth/` 路径(覆盖 SPA 中间态)
|
||||
- `_goto(SPA_LOGIN_URL)` 后:wait 1500ms → **3000ms**(SPA hydration)
|
||||
- 登录按钮 click 后:新增 `wait_for_timeout(2000)`,等 SPA token 写入 cookie + 路由稳定再 goto home(之前直接打断 pending 跳转)
|
||||
- 步骤 4 改为 retry 循环(最多 2 次),检查 `/app/` in url 且不含 `/login` 才退出
|
||||
- **采集流程健壮性修复**
|
||||
- 步骤 5 侧边栏 link 等待:15s → **30s**(sandbox mock 慢启动不 fallback 到 pushState)
|
||||
- 步骤 5.5 `page.reload()` timeout:20s → **30s**
|
||||
- **新增 5.6**:刷新后检查 URL,若被踢回 `/login` 则重新登录一次(之前刷新丢 session 后还继续往后走,导致 40s 找不到表格)
|
||||
- 「续聘材料包」按钮 click 后:wait 1500ms → **3000ms**(卡片动画慢导致文本抓不全)
|
||||
- 抽出 `_dump_page(page, path, label)` helper,**自动 `mkdir(parents=True)`**,修复 5 处 dump 路径父目录可能不存在的静默失败
|
||||
|
||||
## 1.1.4
|
||||
|
||||
- **多平台发布声明**:SKILL.md `metadata.openclaw.brands` 新增 `jiangchang` + `huashang`,发布后同步挂匠厂主站与华商 OEM 市场。CI 会幂等补写 `skill_market_relations` 两行(**只补不删**)。
|
||||
|
||||
16
SKILL.md
16
SKILL.md
@@ -1,7 +1,7 @@
|
||||
---
|
||||
name: 合同到期智能预警与续聘辅助
|
||||
description: "每日凌晨扫描全校教职工合同电子台账,对距离到期日 90/60/30 天的合同分级预警,并自动生成《续聘准备任务书》和《本月合同到期人员清单》。"
|
||||
version: 1.1.4
|
||||
description: "当用户说要扫描即将到期的合同、查 90/60/30 天预警名单、给某位教师生成续聘任务书、下发单位版续聘清单、从 SmartCampus HR 平台抓合同数据、解析续聘材料 PDF/Word、查看本月合同到期人员清单时,加载本技能。支持定时扫描(每日凌晨)+ 数据管理 + Agent 三入口,覆盖合同到期智能预警与续聘辅助全流程。"
|
||||
version: 1.1.16
|
||||
author: 深圳匠厂科技有限公司
|
||||
metadata:
|
||||
openclaw:
|
||||
@@ -10,11 +10,12 @@ metadata:
|
||||
emoji: "📋"
|
||||
category: "人事"
|
||||
developer_ids:
|
||||
- 12345 # 占位,请换成你的匠厂用户 ID
|
||||
- 12468
|
||||
- 10032
|
||||
- 12428
|
||||
brands: # 可选;未写则发布后仅挂匠厂市场(jiangchang)
|
||||
- jiangchang # 匠厂主站
|
||||
- huashang # 华商等 OEM:按目标市场填写,可多选
|
||||
|
||||
allowed-tools:
|
||||
- bash
|
||||
---
|
||||
@@ -139,10 +140,9 @@ AI 续聘建议(v1.1.1)默认调宿主 `jiangchang_skill_core.llm_manager.ca
|
||||
|
||||
## 平台元数据
|
||||
|
||||
- `metadata.openclaw.developer_ids`:技能发布后的默认开发者可见用户 ID 列表。
|
||||
- 开发期技能常为不公开:不加本人 ID,开发者自己也无法在市场安装自测。
|
||||
- 当 `access_scope = 0`(不公开)时,平台会把 `developer_ids` 中的用户自动补写到 `skill_user_access`。
|
||||
- `metadata.openclaw.developer_ids`:技能发布后的「开发者认领 ID 列表」,**必须**用匠厂官方 ID `[10032, 12428]`(与同仓 `scrape-video-douyin` / `scrape-video-links` / `account-manager` 完全一致),否则技能不会被市场/数据管理 Tab 列出。
|
||||
- `brands` 字段可选;不写默认会挂到全部市场。
|
||||
|
||||
---
|
||||
|
||||
> **本技能开发状态:** v1.1.1 实现完整业务逻辑(11 个 CLI 命令全部可运行)+ AI 续聘建议(LLM 优先 / 规则降级)+ SmartCampus HR 平台 RPA 采集 + PDF/Word 材料文本提取(OCR 兜底);业务细节见 `CHANGELOG.md`。
|
||||
> **本技能开发状态:** v1.1.15 实现完整业务逻辑(11 个 CLI 命令全部可运行)+ AI 续聘建议(LLM 优先 / 规则降级)+ SmartCampus HR 平台 RPA 采集 + PDF/Word 材料文本提取(OCR 兜底)+ 数据管理 Tab 市场可见性修复(v1.1.15);业务细节见 `CHANGELOG.md`。
|
||||
|
||||
BIN
assets/屏幕截图 2026-09-14 185920.png
Normal file
BIN
assets/屏幕截图 2026-09-14 185920.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 81 KiB |
@@ -369,7 +369,9 @@ try {
|
||||
Invoke-Git -GitArgs @("fetch", "--tags", "--prune", "origin")
|
||||
}
|
||||
|
||||
$skillRoot = (Get-GitOutput -GitArgs @("rev-parse", "--show-toplevel") | Select-Object -First 1).Trim()
|
||||
# Git output can be decoded through the legacy console code page on Windows
|
||||
# PowerShell 5.1, corrupting a repository path that contains Chinese characters.
|
||||
$skillRoot = $PSScriptRoot
|
||||
if (Test-Path -LiteralPath (Join-Path $skillRoot "SKILL.md")) {
|
||||
Assert-SkillReleasePackagingSources -SkillRoot $skillRoot
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# 合同到期智能预警与续聘辅助 - 技能特有依赖
|
||||
# jiangchang-platform-kit 等公共能力由宿主共享 runtime 提供,不要写入此文件
|
||||
|
||||
# 公共依赖由宿主共享 runtime 提供(jiangchang-platform-kit、playwright 等);
|
||||
# 这里只声明技能特有 Python 依赖。
|
||||
# HTTP 请求
|
||||
requests>=2.31.0,<3
|
||||
|
||||
@@ -10,9 +10,6 @@ python-dateutil>=2.8.0,<3
|
||||
# HTML 模板渲染(个人版任务书)
|
||||
jinja2>=3.1.0,<4
|
||||
|
||||
# v1.1.1:SmartCampus HR 平台 RPA 采集
|
||||
playwright>=1.40.0,<2
|
||||
|
||||
# v1.1.1:续聘材料包 PDF/Word 文本提取
|
||||
pypdf>=4.0.0,<5
|
||||
python-docx>=1.1.0,<2
|
||||
|
||||
@@ -21,7 +21,7 @@ from typing import Callable, List, Optional
|
||||
from db.connection import get_connection, init_db
|
||||
from db import repository as repo
|
||||
from service import dispatcher, html_renderer, material_parser, platform_collector, scanner, task_generator
|
||||
from util.constants import DEFAULT_THRESHOLDS, SKILL_VERSION
|
||||
from util.constants import DEFAULT_THRESHOLDS, HUMAN_WAIT_TIMEOUT, SKILL_VERSION
|
||||
from util.logging_setup import get_skill_logger, setup_skill_logging
|
||||
from util.runtime_paths import (
|
||||
get_db_path,
|
||||
@@ -204,12 +204,25 @@ def cmd_collect_platform(args: argparse.Namespace) -> int:
|
||||
退出码:
|
||||
0 = 成功(即使抓到 0 行也返回 0,错误信息在 output["error"])
|
||||
1 = 通用异常
|
||||
2 = RPA 结构化错误(LoginTimeout / MissingBrowser / TableNotFound 等)
|
||||
"""
|
||||
try:
|
||||
result = platform_collector.collect_all(
|
||||
limit=args.limit,
|
||||
headless=not args.show_browser,
|
||||
human_wait_timeout=args.human_wait_timeout or HUMAN_WAIT_TIMEOUT,
|
||||
)
|
||||
except platform_collector.RPAError as e:
|
||||
# v1.1.6:结构化错误(ERROR:LOGIN_TIMEOUT 等)→ exit 2
|
||||
print(json.dumps({
|
||||
"error": e.code,
|
||||
"detail": str(e),
|
||||
"fetched_rows": 0,
|
||||
"saved_contracts": 0,
|
||||
"downloaded_materials": 0,
|
||||
"contracts": [],
|
||||
}, ensure_ascii=False, indent=2))
|
||||
return 2
|
||||
except Exception as e:
|
||||
print(json.dumps({"error": "exception", "detail": str(e)},
|
||||
ensure_ascii=False, indent=2))
|
||||
@@ -333,6 +346,8 @@ def build_parser() -> argparse.ArgumentParser:
|
||||
help="限制抓取行数(0=全量)")
|
||||
sp.add_argument("--show-browser", action="store_true",
|
||||
help="显示浏览器(首次手工登录用,默认 headless)")
|
||||
sp.add_argument("--human-wait-timeout", type=int, default=None,
|
||||
help="手工登录 fallback 等待秒数(默认 180 = HUMAN_WAIT_TIMEOUT)")
|
||||
sp.set_defaults(handler=cmd_collect_platform)
|
||||
|
||||
sp = sub.add_parser(
|
||||
|
||||
@@ -1,23 +1,23 @@
|
||||
"""Playwright RPA:从 SmartCampus HR 平台抓合同表 + 续聘材料包。
|
||||
|
||||
设计要点:
|
||||
设计要点(v1.1.6,按 skill-template examples/real_browser_rpa 设计模式):
|
||||
- 使用 launch_persistent_context 复用浏览器登录态,避免密码硬编码
|
||||
- 首次使用需用户手工登录一次(CLI 默认 --headless false 便于交互)
|
||||
- 后续使用无头模式(profile 已存 cookie)
|
||||
- **登录策略**:自动 fill demo/123456(sandbox 已知凭据) + 失败时 fallback 手工登录等待(轮询 180s)
|
||||
- 抓表格:DOM eval_on_selector_all → JSON
|
||||
- 抓材料:点 "续聘材料包" 按钮 → expect_download → 保存到本地
|
||||
- 抓材料:点 "续聘材料包" 按钮 → 抓卡片 inner_text
|
||||
|
||||
依赖为可选:playwright 未安装时 import 抛错,上层 CLI 捕获并降级报错。
|
||||
|
||||
导航流程(v1.1.1 强化版 — 强制 goto):
|
||||
1. goto 根域
|
||||
2. 根域 login(如仍显示表单)→ 等跳到 /home 或 /select
|
||||
3. 强制 goto /select
|
||||
4. 在 /select 页面 click 智慧校园 tile → 等 URL 含 /industries/campus
|
||||
5. 若 URL 含 /login,填 sandbox SPA 登录表单 → 等跳走
|
||||
6. 强制 goto SPA_HOME
|
||||
7. click 侧边栏 hr/contracts
|
||||
8. 等 table tbody tr
|
||||
3. 强制 goto sandbox SPA login URL
|
||||
4. SPA login:自动 fill demo/123456,失败 fallback 手工等待(HUMAN_WAIT_TIMEOUT=180s)
|
||||
5. 强制 goto SPA_HOME
|
||||
6. click 侧边栏 hr/contracts
|
||||
7. 等 table tbody tr(最长 ~40s)
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -25,11 +25,38 @@ from __future__ import annotations
|
||||
import os
|
||||
import re
|
||||
import sqlite3
|
||||
import time
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
|
||||
from db import repository as repo
|
||||
from util.constants import SKILL_SLUG
|
||||
from util.constants import (
|
||||
CARD_APPEAR_WAIT_MS,
|
||||
DEFAULT_PAGE_TIMEOUT_MS,
|
||||
FULL_RENDER_WAIT_MS,
|
||||
GOTO_TIMEOUT_MS,
|
||||
HUMAN_POLL_INTERVAL,
|
||||
HUMAN_WAIT_TIMEOUT,
|
||||
POST_LOGIN_SETTLE_MS,
|
||||
POST_RELOAD_LOGIN_HYDRATION_MS,
|
||||
POST_RELOGIN_GOTO_WAIT_MS,
|
||||
PUSHSTATE_SETTLE_MS,
|
||||
RELOAD_DOMCONTENTLOADED_TIMEOUT_MS,
|
||||
RELOAD_NETWORKIDLE_TIMEOUT_MS,
|
||||
SIDEBAR_CLICK_URL_TIMEOUT_MS,
|
||||
SIDEBAR_LINK_TIMEOUT_MS,
|
||||
SPA_HOME_RETRY_DELAY_MS,
|
||||
SPA_HOME_RETRY_MAX,
|
||||
SPA_HYDRATION_MS,
|
||||
SPA_LOGIN_INPUT_TIMEOUT_MS,
|
||||
SPA_LOGIN_SETTLE_MS,
|
||||
SPA_LOGIN_URL_TIMEOUT_MS,
|
||||
TABLE_INITIAL_WAIT_MS,
|
||||
TABLE_POLL_INTERVAL_MS,
|
||||
TABLE_POLL_MAX_ATTEMPTS,
|
||||
TABLE_TR_TIMEOUT_MS,
|
||||
URL_AFTER_LOGIN_TIMEOUT_MS,
|
||||
)
|
||||
from util.logging_setup import get_skill_logger
|
||||
from util.runtime_paths import ensure_dirs
|
||||
|
||||
@@ -47,6 +74,47 @@ SPA_HOME_URL = PLATFORM_BASE + "/industries/campus/smartcampus/app/home"
|
||||
SPA_LOGIN_URL = PLATFORM_BASE + "/industries/campus/smartcampus/login"
|
||||
|
||||
|
||||
# ---------- 错误码(与 skill-template 对齐) ----------
|
||||
|
||||
class RPAError(Exception):
|
||||
"""RPA 流程错误基类。"""
|
||||
|
||||
code: str = "RPA_ERROR"
|
||||
|
||||
def __init__(self, message: str):
|
||||
super().__init__(message)
|
||||
self.message = message
|
||||
|
||||
|
||||
class LoginTimeoutError(RPAError):
|
||||
"""手工登录超时(HUMAN_WAIT_TIMEOUT 秒内未检测到登录成功)。
|
||||
|
||||
错误码:ERROR:LOGIN_TIMEOUT(与 skill-template task_rpa.py 对齐)
|
||||
"""
|
||||
|
||||
code = "ERROR:LOGIN_TIMEOUT"
|
||||
|
||||
|
||||
class MissingBrowserError(RPAError):
|
||||
"""未检测到 Chrome/Edge。
|
||||
|
||||
错误码:ERROR:MISSING_BROWSER(与 skill-template browser_session.py 对齐)
|
||||
"""
|
||||
|
||||
code = "ERROR:MISSING_BROWSER"
|
||||
|
||||
|
||||
class TableNotFoundError(RPAError):
|
||||
"""40s 内未找到表格。
|
||||
|
||||
错误码:ERROR:TABLE_NOT_FOUND
|
||||
"""
|
||||
|
||||
code = "ERROR:TABLE_NOT_FOUND"
|
||||
|
||||
|
||||
# ---------- 工具函数 ----------
|
||||
|
||||
def _safe_getenv_dir(env_key: str, default_rel: str) -> Path:
|
||||
raw = os.environ.get(env_key)
|
||||
if raw:
|
||||
@@ -56,7 +124,7 @@ def _safe_getenv_dir(env_key: str, default_rel: str) -> Path:
|
||||
return (get_data_dir() / default_rel).resolve()
|
||||
|
||||
|
||||
def _goto(page, url: str, timeout: int = 20_000) -> None:
|
||||
def _goto(page, url: str, timeout: int = GOTO_TIMEOUT_MS) -> None:
|
||||
"""带 networkidle / domcontentloaded 双兜底的 goto。"""
|
||||
try:
|
||||
page.goto(url, wait_until="networkidle", timeout=timeout)
|
||||
@@ -68,6 +136,61 @@ def _goto(page, url: str, timeout: int = 20_000) -> None:
|
||||
logger.warning("goto domcontentloaded 也失败 %s: %s", url, e2)
|
||||
|
||||
|
||||
def _dump_page(page, path: Path, label: str) -> None:
|
||||
"""Dump 当前页面 HTML 到指定路径,自动创建父目录。修复:父目录可能不存在导致静默失败。"""
|
||||
try:
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
html = page.content()
|
||||
path.write_text(html, encoding="utf-8")
|
||||
logger.info(
|
||||
"platform_collector: %s dump → %s (%d 字节)",
|
||||
label, path, len(html),
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning("dump %s 失败: %s", label, e)
|
||||
|
||||
|
||||
def _is_logged_in(page) -> bool:
|
||||
"""检测 sandbox SPA 是否已登录(URL 含 /app/ 且不含 /login 或 /signin)。
|
||||
|
||||
与 skill-template real_browser_rpa _is_logged_in 概念对齐(这里只看 URL,
|
||||
因为 sandbox SPA 登录后 URL 稳定跳到 /app/...)。
|
||||
"""
|
||||
url_lower = page.url.lower()
|
||||
return (
|
||||
"/app/" in url_lower
|
||||
and "/login" not in url_lower
|
||||
and "/signin" not in url_lower
|
||||
)
|
||||
|
||||
|
||||
def _wait_for_manual_login(page, wait_sec: int = HUMAN_WAIT_TIMEOUT) -> bool:
|
||||
"""手工登录 fallback:轮询 _is_logged_in,每 HUMAN_POLL_INTERVAL 秒一次。
|
||||
|
||||
与 skill-template task_rpa.py::_ensure_logged_in 设计对齐:
|
||||
- 不自动破解,等用户在浏览器手工完成登录
|
||||
- 屏幕打印 [登录] 提示
|
||||
- 超时抛 LoginTimeoutError(ERROR:LOGIN_TIMEOUT)
|
||||
|
||||
自动 fill demo/123456 失败时调用此函数。
|
||||
"""
|
||||
print(
|
||||
f"[登录] 自动登录失败,请在浏览器中完成登录"
|
||||
f"(sandbox demo/123456 或真实账号),最多等待 {wait_sec} 秒..."
|
||||
)
|
||||
deadline = time.monotonic() + wait_sec
|
||||
attempt = 0
|
||||
while time.monotonic() < deadline:
|
||||
attempt += 1
|
||||
if _is_logged_in(page):
|
||||
print(f"[登录] 检测到登录成功(attempt {attempt})")
|
||||
return True
|
||||
time.sleep(HUMAN_POLL_INTERVAL)
|
||||
raise LoginTimeoutError(
|
||||
f"自动登录失败,{wait_sec}s 内用户在浏览器中也未完成登录"
|
||||
)
|
||||
|
||||
|
||||
def _fill_root_login(page) -> bool:
|
||||
"""根域登录页(如还在):fill demo/123456 → click Sign in。返回是否执行了登录。"""
|
||||
user_input = page.locator('#jc-user').first
|
||||
@@ -80,7 +203,7 @@ def _fill_root_login(page) -> bool:
|
||||
try:
|
||||
page.wait_for_url(
|
||||
lambda u: "/home" in u or "/select" in u or "/industries/" in u,
|
||||
timeout=20_000,
|
||||
timeout=URL_AFTER_LOGIN_TIMEOUT_MS,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning("等根域登录跳转超时: %s", e)
|
||||
@@ -97,44 +220,110 @@ def _click_campus_link(page) -> bool:
|
||||
link.click()
|
||||
logger.info("platform_collector: click 智慧校园 链接")
|
||||
try:
|
||||
page.wait_for_url(lambda u: "/industries/campus" in u, timeout=15_000)
|
||||
page.wait_for_url(lambda u: "/industries/campus" in u, timeout=SIDEBAR_LINK_TIMEOUT_MS // 2)
|
||||
except Exception as e:
|
||||
logger.warning("等 sandbox 路径超时: %s;当前 URL=%s", e, page.url)
|
||||
return True
|
||||
|
||||
|
||||
def _fill_spa_login(page) -> bool:
|
||||
"""sandbox SPA 登录(如还在登录页):fill demo/123456 → click 登录。返回是否执行了登录。"""
|
||||
if "/login" not in page.url and "/signin" not in page.url:
|
||||
def _fill_spa_login(page, settle_ms: int = SPA_LOGIN_SETTLE_MS) -> bool:
|
||||
"""sandbox SPA 自动登录(如还在登录页):fill demo/123456 → click 登录 → 等跳转。
|
||||
|
||||
返回是否执行了登录(True = 已点登录按钮且 URL 已跳离 login;调用方可继续后续流程)。
|
||||
失败时**不抛异常**,由调用方决定是否 fallback 到 _wait_for_manual_login。
|
||||
|
||||
v1.1.10 关键修复:**先检测 _is_logged_in,已登录态直接 return True 不再 fill**。
|
||||
之前没这个检查,profile 复用时会被强制 demo fill 破坏 session。
|
||||
|
||||
v1.1.11 关键修复:**sandbox SPA 登录 input 实际是 `type="tel"` + 无 autocomplete**,
|
||||
之前 selector `input[autocomplete="username"]` 永远找不到,自动 fill 100% 失败。
|
||||
改用 sandbox 实际 selector `#jc-user` / `#jc-pass`(来自 root 登录页)+ `button[type="submit"]`。
|
||||
|
||||
修复要点(v1.1.5/v1.1.6 登录时间太短导致采集不到数据):
|
||||
- 默认 settle_ms = SPA_LOGIN_SETTLE_MS(4000ms),给 SPA 异步渲染 + token 写入 cookie 时间
|
||||
- 等 username input 的 timeout = SPA_LOGIN_INPUT_TIMEOUT_MS(20s)
|
||||
- click 按钮后 wait_for_url timeout = SPA_LOGIN_URL_TIMEOUT_MS(30s)
|
||||
- 多处过渡路径(/login, /signin, /auth/)一并判断
|
||||
"""
|
||||
# v1.1.10:先检查是否已登录(profile cookie 复用场景),已登录直接 return True
|
||||
if _is_logged_in(page):
|
||||
logger.info(
|
||||
"platform_collector: 已登录态(profile cookie 复用),跳过自动 fill"
|
||||
)
|
||||
return True
|
||||
|
||||
url_lower = page.url.lower()
|
||||
if "/login" not in url_lower and "/signin" not in url_lower and "/auth/" not in url_lower:
|
||||
return False
|
||||
# v1.1.11:sandbox SPA 登录页 input 是 #jc-user / #jc-pass(与 root 登录页同 ID)
|
||||
# 等输入框出现(带超时,避免 sandbox mock 慢启动卡死)
|
||||
try:
|
||||
page.wait_for_selector('input[autocomplete="username"]', timeout=10_000)
|
||||
page.wait_for_selector(
|
||||
'#jc-user, input[type="tel"], input[autocomplete="username"]',
|
||||
timeout=SPA_LOGIN_INPUT_TIMEOUT_MS,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning("SPA login input 未出现: %s", e)
|
||||
logger.warning("SPA login input 未出现: %s;当前 URL=%s", e, page.url)
|
||||
return False
|
||||
spa_user = page.locator('input[autocomplete="username"]').first
|
||||
if spa_user.count() == 0:
|
||||
logger.warning("SPA login input count=0")
|
||||
# v1.1.11:按优先级选 selector —— sandbox 实际用 #jc-user
|
||||
user_sel = None
|
||||
for sel in ('#jc-user', 'input[type="tel"]', 'input[autocomplete="username"]'):
|
||||
loc = page.locator(sel).first
|
||||
if loc.count() > 0:
|
||||
user_sel = sel
|
||||
break
|
||||
if not user_sel:
|
||||
logger.warning("SPA login input selector 全 miss(#jc-user / type=tel / autocomplete=username)")
|
||||
return False
|
||||
spa_user.fill("demo")
|
||||
page.locator('input[autocomplete="current-password"]').first.fill("123456")
|
||||
page.locator(user_sel).first.fill("demo")
|
||||
# 密码 selector 同样按优先级
|
||||
pass_sel = None
|
||||
for sel in ('#jc-pass', 'input[type="password"]', 'input[autocomplete="current-password"]'):
|
||||
loc = page.locator(sel).first
|
||||
if loc.count() > 0:
|
||||
pass_sel = sel
|
||||
break
|
||||
if not pass_sel:
|
||||
logger.warning("SPA password input selector 全 miss")
|
||||
return False
|
||||
page.locator(pass_sel).first.fill("123456")
|
||||
page.locator(
|
||||
'button:has-text("登录"), button[type="submit"]:has-text("Sign in")'
|
||||
'button:has-text("登录"), button[type="submit"]:has-text("Sign in"), '
|
||||
'button[type="submit"]'
|
||||
).first.click()
|
||||
logger.info("platform_collector: sandbox SPA 自动登录...")
|
||||
logger.info("platform_collector: sandbox SPA 自动登录 (user_sel=%s pass_sel=%s)", user_sel, pass_sel)
|
||||
page.wait_for_timeout(settle_ms)
|
||||
try:
|
||||
page.wait_for_url(
|
||||
lambda u: "/login" not in u and "/signin" not in u,
|
||||
timeout=20_000,
|
||||
lambda u: "/login" not in u.lower()
|
||||
and "/signin" not in u.lower()
|
||||
and "/auth/" not in u.lower(),
|
||||
timeout=SPA_LOGIN_URL_TIMEOUT_MS,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning("SPA 登录超时: %s;当前 URL=%s", e, page.url)
|
||||
return False
|
||||
# v1.1.10:fill 后再检测 _is_logged_in,避免 sandbox demo 凭据失效时
|
||||
# 被误判为「已登录」(URL 跳 /app/home 但 cookie 没写入)
|
||||
if not _is_logged_in(page):
|
||||
logger.warning(
|
||||
"platform_collector: SPA URL 跳离 login 但 _is_logged_in=False,登录可能失败"
|
||||
)
|
||||
return False
|
||||
logger.info("platform_collector: SPA 登录后 URL=%s", page.url)
|
||||
return True
|
||||
|
||||
|
||||
def collect_all(limit: int = 0, headless: bool = True) -> dict:
|
||||
"""登录 sandbox 平台 → 抓合同表 + 材料 → 落库。"""
|
||||
def collect_all(
|
||||
limit: int = 0,
|
||||
headless: bool = True,
|
||||
human_wait_timeout: int = HUMAN_WAIT_TIMEOUT,
|
||||
) -> dict:
|
||||
"""登录 sandbox 平台 → 抓合同表 + 材料 → 落库。
|
||||
|
||||
human_wait_timeout: 手工登录 fallback 等待秒数(默认 HUMAN_WAIT_TIMEOUT=180)。
|
||||
失败时可能抛出 RPAError(LoginTimeoutError / MissingBrowserError / TableNotFoundError)。
|
||||
"""
|
||||
try:
|
||||
from playwright.sync_api import sync_playwright
|
||||
except ImportError:
|
||||
@@ -147,8 +336,9 @@ def collect_all(limit: int = 0, headless: bool = True) -> dict:
|
||||
download_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
logger.info(
|
||||
"platform_collector: 启动 profile=%s download_dir=%s headless=%s limit=%d",
|
||||
profile_dir, download_dir, headless, limit,
|
||||
"platform_collector: 启动 profile=%s download_dir=%s headless=%s limit=%d "
|
||||
"human_wait_timeout=%d",
|
||||
profile_dir, download_dir, headless, limit, human_wait_timeout,
|
||||
)
|
||||
|
||||
contracts: list[dict] = []
|
||||
@@ -156,55 +346,133 @@ def collect_all(limit: int = 0, headless: bool = True) -> dict:
|
||||
downloaded = 0
|
||||
|
||||
with sync_playwright() as p:
|
||||
# v1.1.9:headed 模式优先用系统 Edge(跟 Windows 桌面 session 同源,
|
||||
# 能真正弹窗让你看到并手工登录);找不到则 fallback Playwright 内置 chromium
|
||||
if not headless:
|
||||
try:
|
||||
ctx = p.chromium.launch_persistent_context(
|
||||
user_data_dir=str(profile_dir),
|
||||
headless=headless,
|
||||
headless=False,
|
||||
accept_downloads=True,
|
||||
channel="msedge",
|
||||
viewport={"width": 1440, "height": 900},
|
||||
)
|
||||
logger.info(
|
||||
"platform_collector: 使用系统 Edge(headed 弹窗)"
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
"platform_collector: 系统 Edge 启动失败(%s),fallback Playwright chromium",
|
||||
e,
|
||||
)
|
||||
ctx = p.chromium.launch_persistent_context(
|
||||
user_data_dir=str(profile_dir),
|
||||
headless=False,
|
||||
accept_downloads=True,
|
||||
viewport={"width": 1440, "height": 900},
|
||||
)
|
||||
else:
|
||||
ctx = p.chromium.launch_persistent_context(
|
||||
user_data_dir=str(profile_dir),
|
||||
headless=True,
|
||||
accept_downloads=True,
|
||||
viewport={"width": 1440, "height": 900},
|
||||
)
|
||||
try:
|
||||
page = ctx.new_page()
|
||||
# v1.1.6:覆盖 Playwright 默认操作超时(之前无 set_default_timeout,导致
|
||||
# 所有 wait_for_selector 默认 30s,调试时不直观)
|
||||
page.set_default_timeout(DEFAULT_PAGE_TIMEOUT_MS)
|
||||
|
||||
# 1. 根域 goto + 根域登录(可选;root login 经常 demo/123456 失败)
|
||||
_goto(page, ROOT_URL)
|
||||
_fill_root_login(page)
|
||||
# 1. v1.1.11:先用**最小侵入**方式检测已登录态 —— 直接 goto SPA_HOME_URL
|
||||
# (不要先跳 ROOT_URL + 自动 fill,会破坏已登录态)
|
||||
# v1.1.11 改进:探针结果 + 二次等待 + cookie 检测,三重判断避免误判
|
||||
logger.info(
|
||||
"platform_collector: 检测登录态,goto SPA_HOME 先探 (当前 URL=%s)",
|
||||
page.url,
|
||||
)
|
||||
_goto(page, SPA_HOME_URL)
|
||||
# v1.1.11:等 sandbox SPA 异步验证 cookie(POST_LOGIN_SETTLE_MS → SPA_HYDRATION_MS)
|
||||
page.wait_for_timeout(SPA_HYDRATION_MS)
|
||||
# v1.1.11:二次等待 —— sandbox SPA 有时首次访问会先跳一个中间过渡页
|
||||
# (如 /select),等几秒看 URL 是否稳定到 /app/
|
||||
first_url = page.url
|
||||
page.wait_for_timeout(SPA_HOME_RETRY_DELAY_MS)
|
||||
second_url = page.url
|
||||
if first_url != second_url:
|
||||
logger.info(
|
||||
"platform_collector: 探针 URL 过渡 %s → %s,等稳定", first_url, second_url,
|
||||
)
|
||||
page.wait_for_timeout(SPA_HOME_RETRY_DELAY_MS)
|
||||
|
||||
# 2. 直接 goto sandbox SPA login(绕过 /select 和 root 跳转)
|
||||
logger.info("platform_collector: 强制 goto sandbox SPA login, 当前 URL=%s", page.url)
|
||||
if _is_logged_in(page):
|
||||
logger.info(
|
||||
"platform_collector: ✅ 已登录态,**完全跳过登录流程**(不弹窗、不自动 fill、不打扰)"
|
||||
",URL=%s", page.url,
|
||||
)
|
||||
else:
|
||||
logger.info(
|
||||
"platform_collector: 未登录态(SPA_HOME 跳回 login, URL=%s),走登录分支",
|
||||
page.url,
|
||||
)
|
||||
# 2. 未登录:直接 goto sandbox SPA login(绕过 /select 和 root 跳转)
|
||||
_goto(page, SPA_LOGIN_URL)
|
||||
# SPA hydration + framework 初始化时间(修复登录时间太短的核心点)
|
||||
page.wait_for_timeout(SPA_HYDRATION_MS)
|
||||
|
||||
# 3. sandbox SPA 登录(demo/123456 已知可用)
|
||||
page.wait_for_timeout(1500)
|
||||
_fill_spa_login(page)
|
||||
# 3. sandbox SPA 自动登录(demo/123456 已知可用)
|
||||
# 失败 fallback 手工登录等待(轮询 _is_logged_in + 180s 兜底)
|
||||
if not _fill_spa_login(page):
|
||||
logger.warning(
|
||||
"platform_collector: 自动 fill 失败(URL=%s),fallback 手工登录等待",
|
||||
page.url,
|
||||
)
|
||||
if not headless:
|
||||
_wait_for_manual_login(page, wait_sec=human_wait_timeout)
|
||||
else:
|
||||
# headless 模式无法手工登录:抛 LoginTimeoutError 让 CLI 决定
|
||||
raise LoginTimeoutError(
|
||||
f"headless 模式下自动 fill 失败,且无法手工登录"
|
||||
f"(请用 --show-browser 重试)"
|
||||
)
|
||||
else:
|
||||
# 等 SPA 路由稳定(之前这里没有 wait,直接 goto home 会打断 pending 跳转)
|
||||
page.wait_for_timeout(POST_LOGIN_SETTLE_MS)
|
||||
|
||||
# 4. 强制 goto SPA home
|
||||
if "/app/" not in page.url:
|
||||
logger.info("platform_collector: 强制 goto SPA_HOME, 当前 URL=%s", page.url)
|
||||
# 4. 强制 goto SPA home(如果还停在 login,重试登录一次)
|
||||
for retry in range(SPA_HOME_RETRY_MAX):
|
||||
if _is_logged_in(page):
|
||||
break
|
||||
logger.info(
|
||||
"platform_collector: 强制 goto SPA_HOME (retry=%d), 当前 URL=%s",
|
||||
retry, page.url,
|
||||
)
|
||||
_goto(page, SPA_HOME_URL)
|
||||
# SPA home 也可能再次 redirect 到 /login(session 没保住)
|
||||
page.wait_for_timeout(1500)
|
||||
page.wait_for_timeout(SPA_HOME_RETRY_DELAY_MS)
|
||||
if _fill_spa_login(page):
|
||||
_goto(page, SPA_HOME_URL)
|
||||
page.wait_for_timeout(POST_LOGIN_SETTLE_MS)
|
||||
|
||||
# 4.5. retry 后若仍未登录,headless 模式抛超时
|
||||
if not _is_logged_in(page):
|
||||
if headless:
|
||||
raise LoginTimeoutError(
|
||||
"SPA_HOME retry 全部失败,URL 仍未离开 login 页"
|
||||
)
|
||||
_wait_for_manual_login(page, wait_sec=human_wait_timeout)
|
||||
|
||||
# 5. 等 SPA 渲染 + click 侧边栏 hr/contracts(SPA 路由,避免 goto 触发整页 reload 丢 session)
|
||||
try:
|
||||
# dump SPA home 一次(用于调试 selector)
|
||||
page.wait_for_timeout(2000)
|
||||
try:
|
||||
html = page.content()
|
||||
dump_path = download_dir.parent / "spa_home_dump.html"
|
||||
dump_path.write_text(html, encoding="utf-8")
|
||||
logger.info(
|
||||
"platform_collector: SPA home dump → %s (%d 字节)",
|
||||
dump_path, len(html),
|
||||
)
|
||||
except Exception:
|
||||
pass
|
||||
page.wait_for_timeout(POST_LOGIN_SETTLE_MS)
|
||||
_dump_page(page, download_dir.parent / "spa_home_dump.html", "SPA home")
|
||||
|
||||
# 等 SPA 真正加载完(侧边栏 link 出现,最长 15s)
|
||||
# 等 SPA 真正加载完(侧边栏 link 出现,最长 SIDEBAR_LINK_TIMEOUT_MS)
|
||||
# 修复:之前 15s 太短,sandbox mock 加载慢时直接 fallback 到 pushState → 表格加载不出来
|
||||
try:
|
||||
page.wait_for_selector(
|
||||
"a[href$='/hr/contracts']", timeout=15_000, state="attached"
|
||||
"a[href$='/hr/contracts']",
|
||||
timeout=SIDEBAR_LINK_TIMEOUT_MS,
|
||||
state="attached",
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning("等侧边栏 hr/contracts link 超时: %s", e)
|
||||
@@ -215,7 +483,8 @@ def collect_all(limit: int = 0, headless: bool = True) -> dict:
|
||||
logger.info("platform_collector: click 侧边栏 hr/contracts")
|
||||
try:
|
||||
page.wait_for_url(
|
||||
lambda u: "/hr/contracts" in u, timeout=10_000
|
||||
lambda u: "/hr/contracts" in u,
|
||||
timeout=SIDEBAR_CLICK_URL_TIMEOUT_MS,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning("等 /hr/contracts URL 超时: %s;当前 URL=%s",
|
||||
@@ -233,7 +502,7 @@ def collect_all(limit: int = 0, headless: bool = True) -> dict:
|
||||
"window.dispatchEvent(new PopStateEvent('popstate')),"
|
||||
" '/industries/campus/smartcampus/app/hr/contracts'"
|
||||
)
|
||||
page.wait_for_timeout(1500)
|
||||
page.wait_for_timeout(PUSHSTATE_SETTLE_MS)
|
||||
except Exception as e:
|
||||
logger.warning("SPA pushState 失败: %s", e)
|
||||
_goto(page, PLATFORM_URL)
|
||||
@@ -243,71 +512,122 @@ def collect_all(limit: int = 0, headless: bool = True) -> dict:
|
||||
|
||||
logger.info("platform_collector: 当前 URL=%s", page.url)
|
||||
|
||||
# 5.5. 进入页面后刷新(SPA 进入新路由时 mock 数据可能未加载,需刷新触发)
|
||||
# 5.5. v1.1.8:**首次登录后不再强制刷新**,避免打断用户手工登录态。
|
||||
# 改为「等表格出现」兜底:给 SPA 一个初始等待窗口(TABLE_INITIAL_WAIT_MS*2),
|
||||
# 如果表格仍未出现,**才**刷新一次(sandbox mock 异步加载场景)。
|
||||
logger.info(
|
||||
"platform_collector: 进入 hr/contracts 后**不刷新**,等待表格出现"
|
||||
"(首次登录态不要打断)"
|
||||
)
|
||||
|
||||
# 5.6. 兜底刷新:仅当等表格超时后才触发;刷新后可能被踢回 login,需重新登录
|
||||
# 修复:之前没检查 URL,刷新后停在 login 页继续往后走,找不到表格就 dump 报错
|
||||
def _try_reload_after_table_timeout():
|
||||
logger.warning(
|
||||
"platform_collector: 表格未在 %dms 内出现,触发兜底刷新",
|
||||
TABLE_INITIAL_WAIT_MS * 2,
|
||||
)
|
||||
try:
|
||||
logger.info("platform_collector: 进入 hr/contracts 后刷新页面")
|
||||
page.reload(wait_until="networkidle", timeout=20_000)
|
||||
page.reload(
|
||||
wait_until="networkidle",
|
||||
timeout=RELOAD_NETWORKIDLE_TIMEOUT_MS,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning("刷新 networkidle 失败: %s;尝试 domcontentloaded", e)
|
||||
try:
|
||||
page.reload(wait_until="domcontentloaded", timeout=20_000)
|
||||
page.reload(
|
||||
wait_until="domcontentloaded",
|
||||
timeout=RELOAD_DOMCONTENTLOADED_TIMEOUT_MS,
|
||||
)
|
||||
except Exception as e2:
|
||||
logger.warning("刷新 domcontentloaded 也失败: %s", e2)
|
||||
if "/login" in page.url.lower() or "/signin" in page.url.lower():
|
||||
logger.warning(
|
||||
"platform_collector: 刷新后回到登录页(%s),重新登录",
|
||||
page.url,
|
||||
)
|
||||
_goto(page, SPA_LOGIN_URL)
|
||||
page.wait_for_timeout(POST_RELOAD_LOGIN_HYDRATION_MS)
|
||||
if not _fill_spa_login(page):
|
||||
if not headless:
|
||||
_wait_for_manual_login(page, wait_sec=human_wait_timeout)
|
||||
else:
|
||||
raise LoginTimeoutError(
|
||||
"刷新后回到 login 页且 headless 无法手工登录"
|
||||
)
|
||||
else:
|
||||
page.wait_for_timeout(POST_LOGIN_SETTLE_MS)
|
||||
_goto(page, PLATFORM_URL)
|
||||
page.wait_for_timeout(POST_RELOGIN_GOTO_WAIT_MS)
|
||||
|
||||
# 7. dump 当前 hr/contracts 页面(用于调试)
|
||||
try:
|
||||
html = page.content()
|
||||
dump_path = download_dir.parent / "hr_contracts_dump.html"
|
||||
dump_path.write_text(html, encoding="utf-8")
|
||||
logger.info(
|
||||
"platform_collector: hr/contracts dump → %s (%d 字节)",
|
||||
dump_path, len(html),
|
||||
)
|
||||
except Exception:
|
||||
pass
|
||||
_dump_page(page, download_dir.parent / "hr_contracts_dump.html", "hr/contracts")
|
||||
|
||||
# 8. 等待表格加载(SPA 异步填充 mock 数据,多等几秒)
|
||||
page.wait_for_timeout(3000) # 给 React 初始化 + mock 数据填充时间
|
||||
# 8. 等待表格加载(v1.1.8:先等,**表格超时未出现才触发兜底刷新**——
|
||||
# 修复「首次登录后强制刷新打断手工登录态」问题)
|
||||
page.wait_for_timeout(TABLE_INITIAL_WAIT_MS) # 给 React 初始化 + mock 数据填充时间
|
||||
found_table = False
|
||||
for attempt in range(20):
|
||||
page.wait_for_timeout(2000)
|
||||
for attempt in range(TABLE_POLL_MAX_ATTEMPTS):
|
||||
page.wait_for_timeout(TABLE_POLL_INTERVAL_MS)
|
||||
cur_url = page.url
|
||||
try:
|
||||
page.wait_for_selector("table tbody tr", timeout=3000)
|
||||
page.wait_for_selector(
|
||||
"table tbody tr",
|
||||
timeout=TABLE_TR_TIMEOUT_MS,
|
||||
)
|
||||
found_table = True
|
||||
break
|
||||
except Exception:
|
||||
logger.info(
|
||||
"platform_collector: URL=%s 等待表格加载 (attempt %d/20)...",
|
||||
cur_url, attempt + 1,
|
||||
"platform_collector: URL=%s 等待表格加载 (attempt %d/%d)...",
|
||||
cur_url, attempt + 1, TABLE_POLL_MAX_ATTEMPTS,
|
||||
)
|
||||
|
||||
if not found_table:
|
||||
try:
|
||||
html = page.content()
|
||||
dump_path = download_dir.parent / "sandbox_dump.html"
|
||||
dump_path.write_text(html, encoding="utf-8")
|
||||
# v1.1.8:表格没出现,**先尝试兜底刷新一次**(sandbox mock 异步加载场景);
|
||||
# 刷新后再次轮询表格,仍找不到才报 TableNotFoundError。
|
||||
logger.warning(
|
||||
"platform_collector: 40s 后未找到表格,已 dump 页面到 %s(%d 字节)",
|
||||
dump_path, len(html),
|
||||
"platform_collector: 首次轮询未找到表格,触发兜底刷新(sandbox mock 异步加载场景)"
|
||||
)
|
||||
_try_reload_after_table_timeout()
|
||||
# 刷新后重新轮询一次(最多 5 次)
|
||||
for attempt2 in range(5):
|
||||
page.wait_for_timeout(TABLE_POLL_INTERVAL_MS)
|
||||
try:
|
||||
page.wait_for_selector(
|
||||
"table tbody tr",
|
||||
timeout=TABLE_TR_TIMEOUT_MS,
|
||||
)
|
||||
found_table = True
|
||||
logger.info(
|
||||
"platform_collector: 兜底刷新后找到表格 (attempt %d)", attempt2 + 1
|
||||
)
|
||||
break
|
||||
except Exception:
|
||||
logger.info(
|
||||
"platform_collector: 兜底刷新后仍等待表格 (attempt %d/5)...",
|
||||
attempt2 + 1,
|
||||
)
|
||||
|
||||
if not found_table:
|
||||
_dump_page(page, download_dir.parent / "sandbox_dump.html", "sandbox")
|
||||
logger.warning("platform_collector: 表格未找到(兜底刷新后仍未出现)")
|
||||
raise TableNotFoundError(
|
||||
f"{TABLE_POLL_MAX_ATTEMPTS * TABLE_POLL_INTERVAL_MS // 1000}s "
|
||||
f"内未找到表格(兜底刷新后仍未出现) (URL={page.url})"
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning("dump 失败: %s", e)
|
||||
return _error_result("table_not_found_after_40s", 0)
|
||||
|
||||
# 表格已找到,等 tbody 完全填充 + dump 一份完整 DOM(用于诊断按钮 selector)
|
||||
try:
|
||||
page.wait_for_function(
|
||||
"document.querySelectorAll('table tbody tr').length > 0",
|
||||
timeout=10_000,
|
||||
timeout=DEFAULT_PAGE_TIMEOUT_MS,
|
||||
)
|
||||
page.wait_for_timeout(1500)
|
||||
html = page.content()
|
||||
full_dump = download_dir.parent / "hr_contracts_full_dump.html"
|
||||
full_dump.write_text(html, encoding="utf-8")
|
||||
logger.info(
|
||||
"platform_collector: 完整 hr/contracts dump → %s (%d 字节)",
|
||||
full_dump, len(html),
|
||||
page.wait_for_timeout(FULL_RENDER_WAIT_MS)
|
||||
_dump_page(
|
||||
page,
|
||||
download_dir.parent / "hr_contracts_full_dump.html",
|
||||
"完整 hr/contracts",
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning("等完整渲染超时: %s", e)
|
||||
@@ -336,27 +656,53 @@ def collect_all(limit: int = 0, headless: bool = True) -> dict:
|
||||
for i, r in enumerate(rows):
|
||||
if limit and i >= limit:
|
||||
break
|
||||
if len(r) < 7:
|
||||
logger.warning("行 %d 列数 < 7(新列序工号+姓名+单位+岗位+合同类型+起止+剩余+预警+建议),跳过: %s", i, r)
|
||||
# v1.1.8:表格列数自适应 —— sandbox 首次登录未刷新是 7 列
|
||||
# (姓名/单位/到期日/剩余天数/预警/建议/按钮),刷新后才是 10 列
|
||||
# (多 工号/岗位/合同类型/起止日期)。两种都支持。
|
||||
ncols = len(r)
|
||||
if ncols < 6:
|
||||
logger.warning(
|
||||
"行 %d 列数=%d < 6,跳过: %s", i, ncols, r
|
||||
)
|
||||
continue
|
||||
|
||||
# 新列序(sandbox 加了工号 / 岗位 / 合同类型 / 起止日期):
|
||||
# 0: 工号 1: 姓名 2: 单位 3: 岗位 4: 合同类型
|
||||
# 5: 起止日期 (含 ~ ) 6: 剩余天数 7: 预警 8: 建议(含原因)
|
||||
emp_id = r[0].strip()
|
||||
# 列序探测:判断首列是不是工号(纯数字 + 字母,纯姓名是中文)
|
||||
first_col = r[0].strip()
|
||||
import re as _re
|
||||
is_emp_id = bool(_re.match(r"^[A-Za-z]?\d+$", first_col))
|
||||
|
||||
if is_emp_id and ncols >= 9:
|
||||
# 10 列布局(含工号):0 工号 1 姓名 2 单位 3 岗位 4 合同类型
|
||||
# 5 起止(含~) 6 剩余天数 7 预警 8 建议 9 按钮
|
||||
emp_id = first_col
|
||||
teacher = r[1].strip()
|
||||
unit = r[2].strip()
|
||||
position = r[3].strip()
|
||||
contract_type = r[4].strip()
|
||||
period = r[5].strip()
|
||||
# 起止日期形如 "2024-03-01 ~ 2026-04-15" → 取 ~ 后
|
||||
contract_end = period.split("~")[-1].strip() if "~" in period else period
|
||||
days_raw = r[6].strip()
|
||||
alert_label = r[7].strip()
|
||||
suggestion_hint = r[8].strip() if len(r) > 8 else ""
|
||||
suggestion_hint = r[8].strip()
|
||||
elif ncols >= 6:
|
||||
# 7 列布局(无工号):0 姓名 1 单位 2 到期日 3 剩余天数 4 预警 5 建议 6 按钮
|
||||
teacher = first_col
|
||||
unit = r[1].strip()
|
||||
contract_end = r[2].strip()
|
||||
days_raw = r[3].strip()
|
||||
alert_label = r[4].strip()
|
||||
suggestion_hint = r[5].strip()
|
||||
emp_id = "" # 工号缺失,留空让 _gen_contract_id 用 teacher_name 兜底
|
||||
else:
|
||||
logger.warning(
|
||||
"行 %d 列数=%d 无法识别布局,跳过: %s", i, ncols, r
|
||||
)
|
||||
continue
|
||||
|
||||
# 用工号生成 contract_id(稳定,不会随姓名变化)
|
||||
# v1.1.8:7 列布局无工号 → 用 teacher_name 派生(避免与 10 列布局冲突)
|
||||
if emp_id:
|
||||
contract_id = _gen_contract_id(emp_id, contract_end)
|
||||
else:
|
||||
contract_id = _gen_contract_id(teacher, contract_end)
|
||||
contract = {
|
||||
"contract_id": contract_id,
|
||||
"teacher_name": teacher,
|
||||
@@ -376,7 +722,7 @@ def collect_all(limit: int = 0, headless: bool = True) -> dict:
|
||||
)
|
||||
btn.click()
|
||||
# 等卡片出现(页面下方追加 h2「续聘准备任务书」/「单位清单」)
|
||||
page.wait_for_timeout(1500)
|
||||
page.wait_for_timeout(CARD_APPEAR_WAIT_MS)
|
||||
# 抓表格下方所有 card 文本
|
||||
cards_text = page.locator(
|
||||
"main .grid > div, main > div > div > div"
|
||||
@@ -398,12 +744,10 @@ def collect_all(limit: int = 0, headless: bool = True) -> dict:
|
||||
)
|
||||
# dump 一次(i==0)方便调试
|
||||
if i == 0:
|
||||
html_after = page.content()
|
||||
click_dump = download_dir.parent / "after_click_dump.html"
|
||||
click_dump.write_text(html_after, encoding="utf-8")
|
||||
logger.info(
|
||||
"platform_collector: 首行 click 后 dump → %s (%d 字节)",
|
||||
click_dump, len(html_after),
|
||||
_dump_page(
|
||||
page,
|
||||
download_dir.parent / "after_click_dump.html",
|
||||
"首行 click 后",
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning("抓卡片失败 %s: %s", contract_id, e)
|
||||
|
||||
@@ -50,7 +50,7 @@ def suggest(perf_records: list[sqlite3.Row]) -> tuple[str, str]:
|
||||
|
||||
# 全部 >= 80 且逐年上升(升序排 → 严格递增)
|
||||
all_high = all(s >= PERFORMANCE_RENEW_MIN for s in scores)
|
||||
upward = all(scores[i] <= scores[i + 1] for i in range(len(scores) - 1))
|
||||
upward = all(scores[i] < scores[i + 1] for i in range(len(scores) - 1))
|
||||
if all_high and upward:
|
||||
return ("renew", f"近 3 年考核均 ≥ {PERFORMANCE_RENEW_MIN} 分且逐年上升")
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
"""
|
||||
|
||||
SKILL_SLUG = "alert-contract-expiring-hr"
|
||||
SKILL_VERSION = "1.1.4"
|
||||
SKILL_VERSION = "1.1.16"
|
||||
LOG_LOGGER_NAME = "openclaw.skill.alert_contract_expiring_hr"
|
||||
PLATFORM_KIT_MIN_VERSION = "1.2.11"
|
||||
|
||||
@@ -43,3 +43,47 @@ DEFAULT_MATERIALS = [
|
||||
MORAL_FAIL_THRESHOLD = 60 # 师德 < 60 直接 non_renew
|
||||
PERFORMANCE_FAIL_THRESHOLD = 60 # 单年考核 < 60 算不合格
|
||||
PERFORMANCE_RENEW_MIN = 80 # 全部 >= 80 且逐年上升 → renew
|
||||
|
||||
|
||||
# ----- v1.1.6:RPA 超时常量(与 skill-template human_verification.py 对齐)-----
|
||||
# 手工登录等待(HITL fallback)
|
||||
HUMAN_WAIT_TIMEOUT = 180 # 手工登录等待超时(秒)—— skill-template 同名常量
|
||||
HUMAN_POLL_INTERVAL = 2.0 # 轮询间隔(秒)—— skill-template 同名常量
|
||||
|
||||
# Playwright 操作超时(毫秒)
|
||||
DEFAULT_PAGE_TIMEOUT_MS = 15_000 # Playwright 默认操作超时 —— skill-template 同名常量
|
||||
GOTO_TIMEOUT_MS = 60_000 # page.goto 导航超时 —— skill-template 同名常量
|
||||
|
||||
# SPA 登录等待(毫秒)
|
||||
SPA_LOGIN_SETTLE_MS = 4_000 # login click 后 settle 时间(SPA 写 cookie)
|
||||
SPA_LOGIN_INPUT_TIMEOUT_MS = 20_000 # 等 username input 出现
|
||||
SPA_LOGIN_URL_TIMEOUT_MS = 30_000 # 等 URL 跳离 login 页
|
||||
SPA_HYDRATION_MS = 3_000 # goto login URL 后 SPA 框架初始化
|
||||
POST_LOGIN_SETTLE_MS = 2_000 # 登录后等 SPA 路由稳定
|
||||
SPA_HOME_RETRY_DELAY_MS = 2_500 # SPA_HOME retry 间隔
|
||||
SPA_HOME_RETRY_MAX = 2 # SPA_HOME retry 最大次数
|
||||
|
||||
# 表格等待(毫秒)
|
||||
TABLE_INITIAL_WAIT_MS = 3_000 # 表格初始等待(React + mock 填充)
|
||||
TABLE_POLL_INTERVAL_MS = 2_000 # 表格轮询间隔
|
||||
TABLE_POLL_MAX_ATTEMPTS = 20 # 表格轮询最大次数(合计 ~40s)
|
||||
TABLE_TR_TIMEOUT_MS = 3_000 # 单次 wait_for_selector 超时
|
||||
FULL_RENDER_WAIT_MS = 1_500 # 完整 DOM 渲染后等渲染结束
|
||||
|
||||
# 侧边栏/卡片(毫秒)
|
||||
SIDEBAR_LINK_TIMEOUT_MS = 30_000 # 等侧边栏 hr/contracts link
|
||||
PUSHSTATE_SETTLE_MS = 1_500 # SPA pushState 后等
|
||||
SIDEBAR_CLICK_URL_TIMEOUT_MS = 10_000 # click 后等 URL 变 /hr/contracts
|
||||
URL_AFTER_LOGIN_TIMEOUT_MS = 20_000 # 根域 login 后等跳转
|
||||
|
||||
# reload 后备用
|
||||
RELOAD_NETWORKIDLE_TIMEOUT_MS = 30_000 # page.reload networkidle 超时
|
||||
RELOAD_DOMCONTENTLOADED_TIMEOUT_MS = 30_000 # page.reload domcontentloaded 超时
|
||||
POST_RELOAD_LOGIN_HYDRATION_MS = 3_000 # reload 后回到 login 页的 hydration
|
||||
POST_RELOGIN_GOTO_WAIT_MS = 2_000 # 重新登录后 goto PLATFORM_URL 等
|
||||
|
||||
# 卡片
|
||||
CARD_APPEAR_WAIT_MS = 3_000 # 「续聘材料包」click 后等卡片出现
|
||||
|
||||
# dump
|
||||
DUMP_PATH_PARENT_MKDIR = True # _dump_page 是否自动创建父目录
|
||||
|
||||
@@ -386,6 +386,20 @@ def test_suggest_renew_upward() -> tuple[bool, str]:
|
||||
return True, "renew + 上升趋势"
|
||||
|
||||
|
||||
def test_suggest_observe_equal_scores_not_renew() -> tuple[bool, str]:
|
||||
"""持平不算逐年上升;应回落到 observe"""
|
||||
from service.task_generator import suggest
|
||||
rows = [
|
||||
_fake_perf(2023, 80, moral=85),
|
||||
_fake_perf(2024, 80, moral=85),
|
||||
_fake_perf(2025, 90, moral=85),
|
||||
]
|
||||
s, r = suggest(rows)
|
||||
if s != "observe":
|
||||
return False, f"suggest(80,80,90) = {s}, want observe"
|
||||
return True, "观察:持平不等于逐年上升"
|
||||
|
||||
|
||||
def test_suggest_observe_default() -> tuple[bool, str]:
|
||||
"""达标但非逐年上升 → observe(常规评审)"""
|
||||
from service.task_generator import suggest
|
||||
@@ -558,6 +572,131 @@ def test_html_render_unknown_task_raises() -> tuple[bool, str]:
|
||||
return False, "应抛 ValueError,实际未抛"
|
||||
|
||||
|
||||
# ---------- v1.1.6:service.platform_collector 纯函数 ----------
|
||||
|
||||
def test_gen_contract_id_emp_id() -> tuple[bool, str]:
|
||||
"""_gen_contract_id 工号派生(v1.1.1 起用工号作主键)"""
|
||||
from service import platform_collector as pc
|
||||
|
||||
cases = [
|
||||
(("T20190033", "2026-04-15"), "RPA-T20190033-20260415"),
|
||||
(("T20200055", "2026-06-30"), "RPA-T20200055-20260630"),
|
||||
(("T20180021", "2026-08-31"), "RPA-T20180021-20260831"),
|
||||
]
|
||||
for (emp_id, end_date), expected in cases:
|
||||
got = pc._gen_contract_id(emp_id, end_date)
|
||||
if got != expected:
|
||||
return False, f"({emp_id!r}, {end_date!r}) → {got!r},want {expected!r}"
|
||||
return True, f"3 工号派生正确"
|
||||
|
||||
|
||||
def test_gen_contract_id_special_chars() -> tuple[bool, str]:
|
||||
"""_gen_contract_id 工号含特殊字符时正确清洗(保留前 10 字符)"""
|
||||
from service import platform_collector as pc
|
||||
|
||||
# 工号含非 \w 字符 → 清洗;超过 10 字符截断
|
||||
got = pc._gen_contract_id("T-2019.0033", "2026-04-15")
|
||||
# 清洗后保留 \w,"T-2019.0033" → "T20190033"(8 字符,未截断)
|
||||
if "RPA-" not in got or "20260415" not in got:
|
||||
return False, f"清洗后格式错:{got!r}"
|
||||
# 长工号 → 截断到 10 字符
|
||||
got2 = pc._gen_contract_id("ABCDEFGHIJKLMNO", "2026-01-01")
|
||||
# "ABCDEFGHIJ"(10 字符)
|
||||
if not got2.startswith("RPA-ABCDEFGHIJ-"):
|
||||
return False, f"长工号未截断到 10 字符:{got2!r}"
|
||||
return True, "清洗 + 截断 OK"
|
||||
|
||||
|
||||
def test_normalize_date_iso() -> tuple[bool, str]:
|
||||
"""_normalize_date ISO 日期直通"""
|
||||
from service import platform_collector as pc
|
||||
|
||||
cases = [
|
||||
("2026-04-15", "2026-04-15"),
|
||||
("2024-01-01", "2024-01-01"),
|
||||
]
|
||||
for inp, want in cases:
|
||||
got = pc._normalize_date(inp)
|
||||
if got != want:
|
||||
return False, f"{inp!r} → {got!r},want {want!r}"
|
||||
return True, "ISO 日期直通"
|
||||
|
||||
|
||||
def test_normalize_date_fallback() -> tuple[bool, str]:
|
||||
"""_normalize_date 非标准格式截前 10 字符"""
|
||||
from service import platform_collector as pc
|
||||
|
||||
# 非标准但带 ISO 前缀
|
||||
got = pc._normalize_date("2026-04-15T00:00:00")
|
||||
if got != "2026-04-15":
|
||||
return False, f"ISO 前缀应保留前 10 字符 → {got!r}"
|
||||
# 完全非日期 → 截前 10 字符
|
||||
got2 = pc._normalize_date("20260415X")
|
||||
if got2 != "20260415X": # 10 字符
|
||||
return False, f"非日期应截前 10 字符 → {got2!r}"
|
||||
# 带空白
|
||||
got3 = pc._normalize_date(" 2026-04-15 ")
|
||||
if got3 != "2026-04-15":
|
||||
return False, f"带空白应去除 → {got3!r}"
|
||||
return True, "非标准格式 fallback OK"
|
||||
|
||||
|
||||
def test_parse_days_positive() -> tuple[bool, str]:
|
||||
"""_parse_days 正天数"""
|
||||
from service import platform_collector as pc
|
||||
|
||||
cases = [
|
||||
("30", 30),
|
||||
("90", 90),
|
||||
("还剩 45 天", 45),
|
||||
("0", 0),
|
||||
]
|
||||
for inp, want in cases:
|
||||
got = pc._parse_days(inp)
|
||||
if got != want:
|
||||
return False, f"{inp!r} → {got!r},want {want!r}"
|
||||
return True, "正天数解析 OK"
|
||||
|
||||
|
||||
def test_parse_days_negative() -> tuple[bool, str]:
|
||||
"""_parse_days 负数 / 兜底"""
|
||||
from service import platform_collector as pc
|
||||
|
||||
# 含负号
|
||||
if pc._parse_days("-15") != -15:
|
||||
return False, "负天数未解析"
|
||||
# 已过期(带 "已过期" 文本)
|
||||
if pc._parse_days("已过期 7 天") != 7:
|
||||
return False, "已过期文本未解析数字部分"
|
||||
# 无法解析
|
||||
if pc._parse_days("") is not None:
|
||||
return False, "空字符串应返回 None"
|
||||
if pc._parse_days("无数字") is not None:
|
||||
return False, "纯文本应返回 None"
|
||||
return True, "负数 + 兜底 OK"
|
||||
|
||||
|
||||
def test_parse_alert_red_orange_yellow_unknown() -> tuple[bool, str]:
|
||||
"""_parse_alert 红/橙/黄/未知四级映射"""
|
||||
from service import platform_collector as pc
|
||||
|
||||
cases = [
|
||||
("红色预警", "red"),
|
||||
("红牌", "red"),
|
||||
("橙色预警", "orange"),
|
||||
("黄灯", "yellow"),
|
||||
("黄色预警", "yellow"),
|
||||
("无", "unknown"),
|
||||
("", "unknown"),
|
||||
("blue", "unknown"),
|
||||
]
|
||||
for inp, want in cases:
|
||||
got = pc._parse_alert(inp)
|
||||
if got != want:
|
||||
return False, f"{inp!r} → {got!r},want {want!r}"
|
||||
return True, "四级映射 OK"
|
||||
|
||||
|
||||
# ---------- 入口 ----------
|
||||
|
||||
def main() -> int:
|
||||
@@ -586,12 +725,20 @@ def main() -> int:
|
||||
_run("task_generator/suggest_low_moral", test_suggest_low_moral)
|
||||
_run("task_generator/suggest_fail_year", test_suggest_fail_year)
|
||||
_run("task_generator/suggest_renew", test_suggest_renew_upward)
|
||||
_run("task_generator/suggest_equal_scores", test_suggest_observe_equal_scores_not_renew)
|
||||
_run("task_generator/suggest_observe", test_suggest_observe_default)
|
||||
_run("scanner/no_alerts", test_scanner_no_alerts)
|
||||
_run("scanner/three_levels", test_scanner_three_levels)
|
||||
_run("scanner/skips_non_active", test_scanner_skips_non_active_contracts)
|
||||
_run("html_renderer/basic", test_html_render_basic)
|
||||
_run("html_renderer/unknown_task_raises", test_html_render_unknown_task_raises)
|
||||
_run("platform_collector/gen_contract_id_emp_id", test_gen_contract_id_emp_id)
|
||||
_run("platform_collector/gen_contract_id_special", test_gen_contract_id_special_chars)
|
||||
_run("platform_collector/normalize_date_iso", test_normalize_date_iso)
|
||||
_run("platform_collector/normalize_date_fallback", test_normalize_date_fallback)
|
||||
_run("platform_collector/parse_days_positive", test_parse_days_positive)
|
||||
_run("platform_collector/parse_days_negative", test_parse_days_negative)
|
||||
_run("platform_collector/parse_alert_levels", test_parse_alert_red_orange_yellow_unknown)
|
||||
|
||||
total = len(_RESULTS)
|
||||
passed = sum(1 for _, ok, _ in _RESULTS if ok)
|
||||
|
||||
Reference in New Issue
Block a user