916 lines
39 KiB
Python
916 lines
39 KiB
Python
"""Playwright RPA：从 SmartCampus HR 平台抓合同表 + 续聘材料包。
|
||
|
||
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 → 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 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
|
||
|
||
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 (
|
||
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
|
||
|
||
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"
|
||
|
||
|
||
# ---------- 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:
|
||
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 = GOTO_TIMEOUT_MS) -> 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 _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
|
||
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=URL_AFTER_LOGIN_TIMEOUT_MS,
|
||
)
|
||
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=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, 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(
|
||
'#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；当前 URL=%s", e, page.url)
|
||
return False
|
||
# 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
|
||
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[type="submit"]'
|
||
).first.click()
|
||
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.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,
|
||
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:
|
||
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 "
|
||
"human_wait_timeout=%d",
|
||
profile_dir, download_dir, headless, limit, human_wait_timeout,
|
||
)
|
||
|
||
contracts: list[dict] = []
|
||
fetched_rows = 0
|
||
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=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. 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)
|
||
|
||
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 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（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)
|
||
page.wait_for_timeout(SPA_HOME_RETRY_DELAY_MS)
|
||
if _fill_spa_login(page):
|
||
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(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 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$='/hr/contracts']",
|
||
timeout=SIDEBAR_LINK_TIMEOUT_MS,
|
||
state="attached",
|
||
)
|
||
except Exception as e:
|
||
logger.warning("等侧边栏 hr/contracts link 超时: %s", e)
|
||
|
||
link = page.locator("a[href$='/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=SIDEBAR_CLICK_URL_TIMEOUT_MS,
|
||
)
|
||
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(PUSHSTATE_SETTLE_MS)
|
||
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)
|
||
|
||
# 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:
|
||
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=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）
|
||
_dump_page(page, download_dir.parent / "hr_contracts_dump.html", "hr/contracts")
|
||
|
||
# 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(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=TABLE_TR_TIMEOUT_MS,
|
||
)
|
||
found_table = True
|
||
break
|
||
except Exception:
|
||
logger.info(
|
||
"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:
|
||
# 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: 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})"
|
||
)
|
||
|
||
# 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=DEFAULT_PAGE_TIMEOUT_MS,
|
||
)
|
||
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)
|
||
|
||
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
|
||
|
||
# 抓「材料包」card 区段的 DOM（用于后续解析每行 click 后的卡片文本）
|
||
# sandbox 行为：click 按钮后会在表格下方追加「续聘准备任务书」+「单位清单」卡片
|
||
|
||
for i, r in enumerate(rows):
|
||
if limit and i >= limit:
|
||
break
|
||
# 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
|
||
|
||
# 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()
|
||
period = r[5].strip()
|
||
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()
|
||
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,
|
||
"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": [],
|
||
}
|
||
|
||
# 点「续聘材料包」按钮 → 等卡片展开 → 抓卡片文本（含 checklist）
|
||
if mat_btn_count > 0:
|
||
try:
|
||
btn = page.locator("table tbody tr").nth(i).locator(
|
||
"button:has-text('续聘材料包')"
|
||
)
|
||
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(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"
|
||
).all_inner_texts()
|
||
materials_text = "\n\n".join(
|
||
t.strip() for t in cards_text if t.strip()
|
||
)
|
||
if materials_text:
|
||
# 存到 materials_content（sandbox mock 卡片文本作为材料包内容）
|
||
contract["materials"].append({
|
||
"kind": "sandbox_card",
|
||
"file_name": f"{contract_id}_materials.txt",
|
||
"text": materials_text,
|
||
})
|
||
downloaded += 1
|
||
logger.info(
|
||
"platform_collector: 抓到卡片文本 %d 字 (%s)",
|
||
len(materials_text), contract_id,
|
||
)
|
||
# dump 一次（i==0）方便调试
|
||
if i == 0:
|
||
_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)
|
||
else:
|
||
if i == 0:
|
||
logger.info(
|
||
"platform_collector: sandbox 未部署「续聘材料包」按钮，"
|
||
"跳过材料抓取（仅采集表格列）",
|
||
)
|
||
|
||
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（sandbox card 文本 + parse-materials 解析后文件路径）
|
||
from db.migrations import ensure_materials_content_schema
|
||
|
||
ensure_materials_content_schema(conn)
|
||
|
||
for m in c["materials"]:
|
||
if isinstance(m, dict) and m.get("kind") == "sandbox_card":
|
||
# sandbox mock 卡片文本，直接写入 extracted_text
|
||
conn.execute(
|
||
"""
|
||
INSERT OR REPLACE INTO materials_content
|
||
(contract_id, file_name, file_path, extracted_text,
|
||
parse_method, parsed_at)
|
||
VALUES (?, ?, ?, ?, 'sandbox_card', ?)
|
||
""",
|
||
(
|
||
c["contract_id"],
|
||
m["file_name"],
|
||
f"sandbox://hr/contracts/{c['contract_id']}",
|
||
m["text"],
|
||
datetime.now().isoformat(timespec="seconds"),
|
||
),
|
||
)
|
||
# 同步解析 → 抽 year + 等次 → 写入 performance_records
|
||
perf_n = repo.parse_sandbox_card_performance(
|
||
conn, c["contract_id"], m["text"],
|
||
)
|
||
if perf_n > 0:
|
||
logger.info(
|
||
"platform_collector: %s 解析卡片 → performance %d 条",
|
||
c["contract_id"], perf_n,
|
||
)
|
||
else:
|
||
# 本地文件路径（parse-materials 解析后写入）
|
||
fp = m if isinstance(m, str) else m.get("file_path")
|
||
fname = Path(fp).name if fp else "unknown"
|
||
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(emp_id: str, end_date: str) -> str:
|
||
"""从 (工号, 到期日) 派 contract_id，确保幂等。
|
||
|
||
sandbox v1.1.1 起改用「工号」作主键（之前用姓名）。
|
||
"""
|
||
safe_emp = re.sub(r"[^\w]", "", emp_id)[:10] or "T"
|
||
safe_end = end_date.replace("-", "")[:8]
|
||
return f"RPA-{safe_emp}-{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" |