taojianmin
213ab5e209
修复 Playwright 自动化流程稳定性问题：
1. 提取辅助函数 _goto / _fill_root_login / _click_campus_link / _fill_spa_login，
每个失败独立处理，避免一处报错阻塞后续步骤
2. 强化导航路径：强制 goto /select → click 智慧校园 → goto sandbox SPA login →
SPA login → 强制 goto SPA_HOME → 等侧边栏 link 出现 → click hr/contracts
- 即使 sandbox 后端跳走不一致（root login demo/123456 不稳定），也能继续
3. SPA 路由 vs 整页 reload：
- click 侧边栏 link 优先（SPA pushState，避免 goto 触发整页 reload 被踢回 login）
- 兜底用 history.pushState + dispatchEvent('popstate') 触发 SPA 路由
4. 表格渲染等待：
- 增加 3s 初始等待 + 20 次重试（共 40s），给 SPA 异步填充 mock 数据时间
5. 材料下载按钮检查：
- 检查 '续聘材料包' 按钮是否存在；当前 sandbox mock 未部署此按钮，
自动跳过下载（仅采集 6 列：姓名/单位/到期日/剩余天数/预警/建议）
6. 调试 dump：
- SPA home → spa_home_dump.html
- hr/contracts → hr_contracts_dump.html
- 失败兜底 → sandbox_dump.html
实测结果（headless=True，profile cookie 复用）：
- 抓 3 行合同落库（RPA-钱实验-20260415 / 孙助理 / 王明远）
- sandbox 未部署材料包按钮，跳过下载（不阻塞采集）
- 所有 11 个 CLI exit code = 0
Co-Authored-By: Claude Code <noreply@anthropic.com>
482 lines
19 KiB
Python
482 lines
19 KiB
Python
"""Playwright RPA：从 SmartCampus HR 平台抓合同表 + 续聘材料包。
|
||
|
||
设计要点：
|
||
- 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）
|
||
- 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
|
||
|
||
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
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import os
|
||
import re
|
||
import sqlite3
|
||
from datetime import datetime
|
||
from pathlib import Path
|
||
|
||
from db import repository as repo
|
||
from util.constants import SKILL_SLUG
|
||
from util.logging_setup import get_skill_logger
|
||
from util.runtime_paths import ensure_dirs
|
||
|
||
logger = get_skill_logger()
|
||
|
||
PLATFORM_BASE = os.environ.get("SMARTCAMPUS_BASE_URL", "https://sandbox.jc2009.com")
|
||
PLATFORM_HR_PATH = os.environ.get(
|
||
"SMARTCAMPUS_HR_PATH", "/industries/campus/smartcampus/app/hr/contracts"
|
||
)
|
||
PLATFORM_URL = PLATFORM_BASE + PLATFORM_HR_PATH
|
||
|
||
ROOT_URL = PLATFORM_BASE + "/"
|
||
SELECT_URL = PLATFORM_BASE + "/select"
|
||
SPA_HOME_URL = PLATFORM_BASE + "/industries/campus/smartcampus/app/home"
|
||
SPA_LOGIN_URL = PLATFORM_BASE + "/industries/campus/smartcampus/login"
|
||
|
||
|
||
def _safe_getenv_dir(env_key: str, default_rel: str) -> Path:
|
||
raw = os.environ.get(env_key)
|
||
if raw:
|
||
return Path(raw).resolve()
|
||
from util.runtime_paths import get_data_dir
|
||
|
||
return (get_data_dir() / default_rel).resolve()
|
||
|
||
|
||
def _goto(page, url: str, timeout: int = 20_000) -> None:
|
||
"""带 networkidle / domcontentloaded 双兜底的 goto。"""
|
||
try:
|
||
page.goto(url, wait_until="networkidle", timeout=timeout)
|
||
except Exception as e:
|
||
logger.warning("goto networkidle 失败 %s: %s；尝试 domcontentloaded", url, e)
|
||
try:
|
||
page.goto(url, wait_until="domcontentloaded", timeout=timeout)
|
||
except Exception as e2:
|
||
logger.warning("goto domcontentloaded 也失败 %s: %s", url, e2)
|
||
|
||
|
||
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
|
||
if user_input.count() == 0:
|
||
return False
|
||
user_input.fill("demo")
|
||
page.locator('#jc-pass').first.fill("123456")
|
||
page.locator('button[type="submit"]:has-text("Sign in")').first.click()
|
||
logger.info("platform_collector: 根域自动登录 demo/123456...")
|
||
try:
|
||
page.wait_for_url(
|
||
lambda u: "/home" in u or "/select" in u or "/industries/" in u,
|
||
timeout=20_000,
|
||
)
|
||
except Exception as e:
|
||
logger.warning("等根域登录跳转超时: %s", e)
|
||
logger.info("platform_collector: 根域登录后 URL=%s", page.url)
|
||
return True
|
||
|
||
|
||
def _click_campus_link(page) -> bool:
|
||
"""在 /select 页面点智慧校园 tile，返回是否点中。"""
|
||
link = page.locator("a[href*='/industries/campus']").first
|
||
if link.count() == 0:
|
||
logger.warning("platform_collector: 未找到 智慧校园 link")
|
||
return False
|
||
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)
|
||
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:
|
||
return False
|
||
try:
|
||
page.wait_for_selector('input[autocomplete="username"]', timeout=10_000)
|
||
except Exception as e:
|
||
logger.warning("SPA login input 未出现: %s", e)
|
||
return False
|
||
spa_user = page.locator('input[autocomplete="username"]').first
|
||
if spa_user.count() == 0:
|
||
logger.warning("SPA login input count=0")
|
||
return False
|
||
spa_user.fill("demo")
|
||
page.locator('input[autocomplete="current-password"]').first.fill("123456")
|
||
page.locator(
|
||
'button:has-text("登录"), button[type="submit"]:has-text("Sign in")'
|
||
).first.click()
|
||
logger.info("platform_collector: sandbox SPA 自动登录...")
|
||
try:
|
||
page.wait_for_url(
|
||
lambda u: "/login" not in u and "/signin" not in u,
|
||
timeout=20_000,
|
||
)
|
||
except Exception as e:
|
||
logger.warning("SPA 登录超时: %s；当前 URL=%s", e, page.url)
|
||
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。"""
|
||
try:
|
||
from playwright.sync_api import sync_playwright
|
||
except ImportError:
|
||
logger.error("playwright 未安装，跳过 RPA 采集")
|
||
return _error_result("playwright_not_installed", 0)
|
||
|
||
profile_dir = _safe_getenv_dir("SMARTCAMPUS_PROFILE_DIR", "playwright-profile")
|
||
download_dir = _safe_getenv_dir("MATERIALS_DOWNLOAD_DIR", "materials")
|
||
profile_dir.mkdir(parents=True, exist_ok=True)
|
||
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,
|
||
)
|
||
|
||
contracts: list[dict] = []
|
||
fetched_rows = 0
|
||
downloaded = 0
|
||
|
||
with sync_playwright() as p:
|
||
ctx = p.chromium.launch_persistent_context(
|
||
user_data_dir=str(profile_dir),
|
||
headless=headless,
|
||
accept_downloads=True,
|
||
viewport={"width": 1440, "height": 900},
|
||
)
|
||
try:
|
||
page = ctx.new_page()
|
||
|
||
# 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)
|
||
|
||
# 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)
|
||
_goto(page, SPA_LOGIN_URL)
|
||
|
||
# 3. sandbox SPA 登录（demo/123456 已知可用）
|
||
page.wait_for_timeout(1500)
|
||
_fill_spa_login(page)
|
||
|
||
# 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)
|
||
_goto(page, SPA_HOME_URL)
|
||
# SPA home 也可能再次 redirect 到 /login（session 没保住）
|
||
page.wait_for_timeout(1500)
|
||
if _fill_spa_login(page):
|
||
_goto(page, SPA_HOME_URL)
|
||
|
||
# 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
|
||
|
||
# 等 SPA 真正加载完（侧边栏 link 出现，最长 15s）
|
||
try:
|
||
page.wait_for_selector(
|
||
"a[href$='/hr/contracts']", timeout=15_000, state="attached"
|
||
)
|
||
except Exception as e:
|
||
logger.warning("等侧边栏 hr/contracts link 超时: %s", e)
|
||
|
||
link = page.locator("a[href$='/hr/contracts']").first
|
||
if link.count() > 0:
|
||
link.click()
|
||
logger.info("platform_collector: click 侧边栏 hr/contracts")
|
||
try:
|
||
page.wait_for_url(
|
||
lambda u: "/hr/contracts" in u, timeout=10_000
|
||
)
|
||
except Exception as e:
|
||
logger.warning("等 /hr/contracts URL 超时: %s；当前 URL=%s",
|
||
e, page.url)
|
||
else:
|
||
logger.info(
|
||
"platform_collector: 侧边栏 link 仍未出现，"
|
||
"使用 SPA 路由（pushState）到 hr/contracts, 当前 URL=%s",
|
||
page.url,
|
||
)
|
||
# 用 SPA 内部路由而非整页 goto，避免 session 被 server 端踢回 login
|
||
try:
|
||
page.evaluate(
|
||
"u => history.pushState({}, '', u) || "
|
||
"window.dispatchEvent(new PopStateEvent('popstate')),"
|
||
" '/industries/campus/smartcampus/app/hr/contracts'"
|
||
)
|
||
page.wait_for_timeout(1500)
|
||
except Exception as e:
|
||
logger.warning("SPA pushState 失败: %s", e)
|
||
_goto(page, PLATFORM_URL)
|
||
except Exception as e:
|
||
logger.warning("click 侧边栏失败: %s；fallback goto", e)
|
||
_goto(page, PLATFORM_URL)
|
||
|
||
logger.info("platform_collector: 当前 URL=%s", page.url)
|
||
|
||
# 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
|
||
|
||
# 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
|
||
found_table = False
|
||
for attempt in range(20):
|
||
page.wait_for_timeout(2000)
|
||
cur_url = page.url
|
||
try:
|
||
page.wait_for_selector("table tbody tr", timeout=3000)
|
||
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,
|
||
)
|
||
|
||
if not found_table:
|
||
try:
|
||
html = page.content()
|
||
dump_path = download_dir.parent / "sandbox_dump.html"
|
||
dump_path.write_text(html, encoding="utf-8")
|
||
logger.warning(
|
||
"platform_collector: 40s 后未找到表格，已 dump 页面到 %s（%d 字节）",
|
||
dump_path, len(html),
|
||
)
|
||
except Exception as e:
|
||
logger.warning("dump 失败: %s", e)
|
||
return _error_result("table_not_found_after_40s", 0)
|
||
|
||
rows = page.eval_on_selector_all(
|
||
"table tbody tr",
|
||
"rs => rs.map(r => Array.from(r.querySelectorAll('td')).map(td => td.innerText))",
|
||
)
|
||
fetched_rows = len(rows)
|
||
logger.info("platform_collector: 抓到 %d 行", fetched_rows)
|
||
|
||
# 检查每行是否有「续聘材料包」按钮
|
||
try:
|
||
mat_btn_count = page.locator(
|
||
"table tbody tr button:has-text('续聘材料包')"
|
||
).count()
|
||
logger.info(
|
||
"platform_collector: 「续聘材料包」按钮数=%d", mat_btn_count,
|
||
)
|
||
except Exception:
|
||
mat_btn_count = 0
|
||
|
||
for i, r in enumerate(rows):
|
||
if limit and i >= limit:
|
||
break
|
||
if len(r) < 6:
|
||
logger.warning("行 %d 列数 < 6，跳过: %s", i, r)
|
||
continue
|
||
|
||
teacher = r[0].strip()
|
||
unit = r[1].strip()
|
||
contract_end = r[2].strip()
|
||
days_raw = r[3].strip()
|
||
alert_label = r[4].strip()
|
||
suggestion_hint = r[5].strip()
|
||
|
||
contract_id = _gen_contract_id(teacher, contract_end)
|
||
contract = {
|
||
"contract_id": contract_id,
|
||
"teacher_name": teacher,
|
||
"unit_name": unit,
|
||
"contract_end": _normalize_date(contract_end),
|
||
"days_to_expire_hint": _parse_days(days_raw),
|
||
"alert_level_hint": _parse_alert(alert_label),
|
||
"ai_suggestion_hint": suggestion_hint,
|
||
"materials": [],
|
||
}
|
||
|
||
# 只有在按钮存在时才尝试下载（sandbox mock 当前未部署此按钮）
|
||
if mat_btn_count > 0:
|
||
try:
|
||
btn = page.locator("table tbody tr").nth(i).locator(
|
||
"button:has-text('续聘材料包')"
|
||
)
|
||
with page.expect_download(timeout=10_000) as dl_info:
|
||
btn.click()
|
||
dl = dl_info.value
|
||
fname = dl.suggested_filename or "materials.zip"
|
||
dest = download_dir / f"{contract_id}_{fname}"
|
||
dl.save_as(str(dest))
|
||
contract["materials"].append(str(dest))
|
||
downloaded += 1
|
||
except Exception as e:
|
||
logger.warning("材料下载失败 %s: %s", contract_id, e)
|
||
else:
|
||
logger.info(
|
||
"platform_collector: sandbox 未部署「续聘材料包」按钮，"
|
||
"跳过材料下载（仅采集表格列）",
|
||
)
|
||
# 仅警告一次
|
||
if i == 0:
|
||
logger.warning(
|
||
"platform_collector: 提示：材料包缺失时，"
|
||
"parse-materials CLI 将标记为「无材料」"
|
||
)
|
||
|
||
contracts.append(contract)
|
||
finally:
|
||
ctx.close()
|
||
|
||
saved = _persist_contracts(contracts)
|
||
return {
|
||
"platform_url": PLATFORM_URL,
|
||
"fetched_rows": fetched_rows,
|
||
"saved_contracts": saved,
|
||
"downloaded_materials": downloaded,
|
||
"contracts": contracts,
|
||
}
|
||
|
||
|
||
def _persist_contracts(contracts: list[dict]) -> int:
|
||
"""把抓到的合同 + 材料落到 SQLite。仅插入 contracts 表的占位行，
|
||
materials_content 由 parse-materials CLI 后续解析写入。
|
||
|
||
真正的合同台账来自 HR 系统 API（生产）或样例 CSV（本地），
|
||
本采集仅作为"快照"记录抓取时间与材料路径。
|
||
"""
|
||
if not contracts:
|
||
return 0
|
||
|
||
from db.connection import get_connection
|
||
|
||
conn = get_connection()
|
||
try:
|
||
with conn:
|
||
for c in contracts:
|
||
# upsert contracts（仅更新与 sandbox 相关的字段）
|
||
conn.execute(
|
||
"""
|
||
INSERT INTO contracts
|
||
(contract_id, employee_id, teacher_name, unit_id, unit_name,
|
||
position, contract_type, contract_start, contract_end,
|
||
trial_period_end, status, last_material_id, renewed_at)
|
||
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, '可续聘', NULL, NULL)
|
||
ON CONFLICT(contract_id) DO UPDATE SET
|
||
teacher_name = excluded.teacher_name,
|
||
unit_name = excluded.unit_name,
|
||
contract_end = excluded.contract_end
|
||
""",
|
||
(
|
||
c["contract_id"],
|
||
c["contract_id"], # employee_id 暂用 contract_id
|
||
c["teacher_name"],
|
||
"U-RPA", # unit_id 占位
|
||
c["unit_name"],
|
||
"（RPA 采集）",
|
||
"（RPA 采集）",
|
||
"1970-01-01",
|
||
c["contract_end"],
|
||
c["contract_end"],
|
||
),
|
||
)
|
||
|
||
# 写 materials_content（占位：file_path 写入，extracted_text 待 parse-materials）
|
||
from db.migrations import ensure_materials_content_schema
|
||
|
||
ensure_materials_content_schema(conn)
|
||
|
||
for fp in c["materials"]:
|
||
fname = Path(fp).name
|
||
conn.execute(
|
||
"""
|
||
INSERT OR REPLACE INTO materials_content
|
||
(contract_id, file_name, file_path, extracted_text,
|
||
parse_method, parsed_at)
|
||
VALUES (?, ?, ?, NULL, 'pending', ?)
|
||
""",
|
||
(
|
||
c["contract_id"],
|
||
fname,
|
||
fp,
|
||
datetime.now().isoformat(timespec="seconds"),
|
||
),
|
||
)
|
||
return len(contracts)
|
||
finally:
|
||
conn.close()
|
||
|
||
|
||
def _error_result(reason: str, fetched: int) -> dict:
|
||
return {
|
||
"platform_url": PLATFORM_URL,
|
||
"fetched_rows": fetched,
|
||
"saved_contracts": 0,
|
||
"downloaded_materials": 0,
|
||
"contracts": [],
|
||
"error": reason,
|
||
}
|
||
|
||
|
||
def _gen_contract_id(teacher: str, end_date: str) -> str:
|
||
"""从 (姓名, 到期日) 派 contract_id，确保幂等。"""
|
||
safe_teacher = re.sub(r"[^\w]", "", teacher)[:8] or "T"
|
||
safe_end = end_date.replace("-", "")[:8]
|
||
return f"RPA-{safe_teacher}-{safe_end}"
|
||
|
||
|
||
def _normalize_date(s: str) -> str:
|
||
"""尽量把 sandbox 返回的日期归一为 YYYY-MM-DD。"""
|
||
s = s.strip()
|
||
if re.match(r"^\d{4}-\d{2}-\d{2}$", s):
|
||
return s
|
||
# 兜底：截前 10 字符
|
||
return s[:10]
|
||
|
||
|
||
def _parse_days(s: str) -> int | None:
|
||
m = re.search(r"-?\d+", s)
|
||
return int(m.group(0)) if m else None
|
||
|
||
|
||
def _parse_alert(s: str) -> str:
|
||
s = s.strip()
|
||
if "红" in s:
|
||
return "red"
|
||
if "橙" in s:
|
||
return "orange"
|
||
if "黄" in s:
|
||
return "yellow"
|
||
return "unknown" |