feat: add three-surface RPA locator standards and examples
All checks were successful
技能自动化发布 / release (push) Successful in 5s

This commit is contained in:
2026-07-25 10:20:45 +08:00
parent c15e23e0d4
commit 79d21c063d
27 changed files with 1448 additions and 61 deletions

View File

@@ -33,6 +33,8 @@ real_browser_rpa/
│ └── util/
│ ├── constants.py # 平台常量、selector 占位
│ └── logging.py # 结构化日志与脱敏
├── assets/
│ └── element-map.sample.yaml # 元素清单模板;真实拾取后填写
└── tests/
├── test_human_verification.py # 验证码误判防护
└── test_stop_reason.py # 停止原因文案
@@ -55,12 +57,13 @@ real_browser_rpa/
## 开发新 skill 时如何复制
1. **先阅读**本 README 及下方「Copy map」「复制边界」章节
2. 按 copy map **选择性复制**到新技能 `scripts/`(**不要**整包照搬 `examples/real_browser_rpa/`)
3. 修改 `util/constants.py` 中的 `TARGET_PLATFORM`、`DEFAULT_START_URL`、selector 常量
4. 替换 `task_rpa.py` 中的登录态 marker、搜索框/结果解析逻辑(**必须 F12 实测**)
5. 替换 `human_verification.py` 中的验证码 selector(若目标站点 DOM 不同)
6. 在 `task_service.py` 中接入真实 DB、任务日志、RpaVideoSession
7. 在新技能根目录补齐 `scripts/main.py` CLI;`SKILL.md` 与根 `README.md` 按模板主目录规则编写,**不要**复制本 README
2. **先完成元素工程**:阅读 `development/RPA_ELEMENT_LOCATING.md` 与 `development/RPA_BROWSER.md`,在真实站用 Pick Locator/F12 拾取并填写 element map
3. 按 copy map **选择性复制**到新技能 `scripts/`(**不要**整包照搬 `examples/real_browser_rpa/`)
4. 修改 `util/constants.py` 中的 `TARGET_PLATFORM`、`DEFAULT_START_URL`、selector 常量
5. 替换 `task_rpa.py` 中的登录态 marker、搜索框/结果解析逻辑(**必须 F12 实测**)
6. 替换 `human_verification.py` 中的验证码 selector(若目标站点 DOM 不同)
7. 在 `task_service.py` 中接入真实 DB、任务日志、RpaVideoSession
8. 在新技能根目录补齐 `scripts/main.py` CLI;`SKILL.md` 与根 `README.md` 按模板主目录规则编写,**不要**复制本 README
## Copy map(复制到新技能 `scripts/`)
@@ -73,6 +76,7 @@ real_browser_rpa/
| `examples/real_browser_rpa/scripts/service/task_service.py` | `scripts/service/task_service.py` | 参考并合并编排层 |
| `examples/real_browser_rpa/scripts/util/constants.py` | `scripts/util/constants.py` | 平台常量与 selector(须替换) |
| `examples/real_browser_rpa/scripts/util/logging.py` | `scripts/util/logging.py` | 可选,按需合并 |
| `examples/real_browser_rpa/assets/element-map.sample.yaml` | `assets/<platform>-element-map.yaml` | 真实 Pick Locator/F12 拾取后填写 |
| `examples/real_browser_rpa/tests/` | `tests/` | 可按需复制测试思路 |
| `examples/real_browser_rpa/README.md` | — | **只读参考**,不复制为新技能根 README |
@@ -121,6 +125,8 @@ real_browser_rpa/
- 不要照抄平台名、slug、logger 名
- 不要依赖 `D:\OpenClaw\client-commons\account-manager\scripts\main.py` 等开发机绝对路径作为生产依赖
- 不要把示例里的 result selector 当成真实站点 selector
- 不要复制“扫描所有 input 再按宽度/位置打分”的诊断式猜测作为生产主定位器
- 不要用 `.first` / `.nth` 绕过多匹配;关键动作必须先解决唯一性
- 不要把示例代码原样发布为业务 skill
- 不要把真实账号、手机号、cookie、token 写入代码或 README

View File

@@ -0,0 +1,45 @@
surface: browser
status: placeholder_requires_real_site_inspection
elements:
- logical_name: search_input
purpose: 输入搜索关键词
scope:
kind: main
business_container: 待真实拾取
primary_locator:
strategy: role_or_label
value: 待真实拾取
fallback_locators: []
expected_count: 1
ready_condition:
visible: true
enabled: true
postcondition:
description: 搜索结果容器出现
verified_target_version: 待填写
- logical_name: search_button
purpose: 提交搜索
scope:
logical_parent: search_form
primary_locator:
strategy: role
value: button,name=搜索
fallback_locators: []
expected_count: 1
postcondition:
description: 结果页或业务错误状态出现
verified_target_version: 待填写
- logical_name: result_container
purpose: 承载搜索结果
scope:
kind: main
primary_locator:
strategy: stable_business_container
value: 待真实拾取
fallback_locators: []
expected_count: 1
postcondition:
description: 列表项、空结果或结束标记可区分
verified_target_version: 待填写

View File

@@ -188,42 +188,22 @@ async def _ensure_logged_in(page, *, wait_sec: int) -> None:
async def _find_search_input(page) -> Tuple[Optional[Any], str]:
for sel in SEARCH_INPUT_SELECTORS:
try:
loc = page.locator(sel).first
if await _visible(loc):
loc = page.locator(sel)
count = await loc.count()
if count == 1 and await _visible(loc):
return loc, sel
if count > 1:
logger.warning("search_input_ambiguous selector=%s count=%s", sel, count)
except Exception:
continue
candidates: List[Tuple[int, Any, str]] = []
try:
inputs = await page.locator("input").all()
except Exception:
inputs = []
for inp in inputs:
try:
if not await inp.is_visible():
continue
box = await inp.bounding_box()
if not box or box.get("width", 0) < 120:
continue
placeholder = await inp.get_attribute("placeholder") or ""
score = box.get("width", 0)
if "搜索" in placeholder:
score += 500
if box.get("y", 9999) < 200:
score += 200
candidates.append((score, inp, f"input placeholder={placeholder!r}"))
except Exception:
continue
if candidates:
candidates.sort(key=lambda x: x[0], reverse=True)
_, inp, sel = candidates[0]
return inp, sel
try:
ph = page.get_by_placeholder(re.compile("搜索"))
if await ph.count() > 0 and await ph.first.is_visible():
return ph.first, "placeholder=搜索"
count = await ph.count()
if count == 1 and await ph.is_visible():
return ph, "placeholder=搜索"
if count > 1:
logger.warning("search_input_ambiguous selector=placeholder_search count=%s", count)
except Exception:
pass
return None, ""
@@ -232,14 +212,24 @@ async def _find_search_input(page) -> Tuple[Optional[Any], str]:
async def _find_search_button(page):
try:
btn = page.get_by_role("button", name="搜索")
if await btn.count() > 0 and await btn.first.is_visible():
return btn.first
count = await btn.count()
if count == 1 and await btn.is_visible():
return btn
if count > 1:
logger.warning("search_button_ambiguous selector=role_button_search count=%s", count)
except Exception:
pass
try:
btn = page.locator(SEARCH_BUTTON_SELECTOR).first
if await btn.count() > 0 and await btn.is_visible():
btn = page.locator(SEARCH_BUTTON_SELECTOR)
count = await btn.count()
if count == 1 and await btn.is_visible():
return btn
if count > 1:
logger.warning(
"search_button_ambiguous selector=%s count=%s",
SEARCH_BUTTON_SELECTOR,
count,
)
except Exception:
pass
return None