ab3f25a10e
- Add paths.py: BASE_DIR/DOWNLOAD_DIR/CONFIG_PATH anchored on __file__ so paths resolve regardless of the launch cwd - Route main_router and all site modules through DOWNLOAD_DIR/CONFIG_PATH, replacing os.getcwd()-based download dirs and the "config.yaml" literal - main_router compare engine: read Excel as str with keep_default_na, strip/normalize 运单号, drop blanks, and isin against a set so int/float-vs-str mismatches no longer produce false "undelivered" - Shunxin: give downloaded files unique microsecond temp names and read Excel as str to preserve long-waybill precision - Normalize bare except: to except Exception: across affected files Co-Authored-By: Claude <noreply@anthropic.com>
307 lines
14 KiB
Python
307 lines
14 KiB
Python
# main_router.py
|
||
|
||
import os
|
||
import yaml
|
||
import pandas as pd
|
||
from playwright.sync_api import sync_playwright
|
||
|
||
from paths import DOWNLOAD_DIR, CONFIG_PATH
|
||
|
||
# 导入抽离出去的各个网点模块
|
||
import site_shunxin
|
||
import site_baishi
|
||
import site_zto
|
||
import site_yunda
|
||
|
||
# 定义网点及对应的初始登录 URL
|
||
SITES_CONFIG = {
|
||
"顺心": "https://sxne.sxjdfreight.com",
|
||
"百世": "https://v5.800best.com",
|
||
"中通": "https://ws.zto56.com/",
|
||
"韵达": "https://ky-sso.yunda56.com",
|
||
}
|
||
|
||
# ====================================================================
|
||
# 🛡️ 网点特征注册表：定义每个网点登录成功、成功进入工作台的标志性控件
|
||
# ====================================================================
|
||
READY_SELECTORS = {
|
||
"顺心": 'h1:has-text("盟商门户网")',
|
||
"百世": 'h1[title="百世快运"]',
|
||
"中通": '.logo:has-text("网点版")',
|
||
"韵达": '.el-menu-item:has-text("首页")',
|
||
}
|
||
|
||
|
||
def task_process_undelivered_data(site_name="顺心"):
|
||
"""全局模块：应到未到异常件比对引擎 (支持动态网点前缀)"""
|
||
print(f"\n▶ 开始执行【{site_name} - 应到未到数据处理】任务...")
|
||
|
||
download_dir = DOWNLOAD_DIR
|
||
expected_path = os.path.join(download_dir, f"{site_name}-应到货物数据.xlsx")
|
||
actual_path = os.path.join(download_dir, f"{site_name}-实到货物数据.xlsx")
|
||
output_path = os.path.join(download_dir, f"{site_name}-应到未到货物数据.xlsx")
|
||
|
||
if not os.path.exists(expected_path):
|
||
print(f"❌ 错误：找不到【{site_name}-应到货物数据】主文档：{expected_path}")
|
||
return
|
||
|
||
if not os.path.exists(actual_path):
|
||
print(f"❌ 错误：找不到【{site_name}-实到货物数据】主文档：{actual_path}")
|
||
return
|
||
|
||
try:
|
||
print(">> 正在载入本地 Excel 文档...")
|
||
# 全部按字符串读取并保留空串：避免 18 位运单号被当成浮点数丢精度，也避免空单元格变成 NaN。
|
||
df_expected = pd.read_excel(expected_path, dtype=str, keep_default_na=False)
|
||
df_actual = pd.read_excel(actual_path, dtype=str, keep_default_na=False)
|
||
|
||
if "运单号" not in df_expected.columns or "运单号" not in df_actual.columns:
|
||
print("❌ 核心资产校验失败：数据源中缺失【运单号】字段，请检查导出配置。")
|
||
return
|
||
|
||
print(">> 正在启动多维数据集比对引擎...")
|
||
|
||
# 统一运单号为去空白字符串，消除 int/float 与 str 混读导致 isin 永不命中的隐患
|
||
df_expected["运单号"] = df_expected["运单号"].astype(str).str.strip()
|
||
df_actual["运单号"] = df_actual["运单号"].astype(str).str.strip()
|
||
|
||
# 剔除空白运单号，避免空值被误判为“应到未到”
|
||
df_expected = df_expected[df_expected["运单号"] != ""]
|
||
actual_set = set(df_actual["运单号"]) - {""}
|
||
|
||
# Left Anti-Join：在应到中找出不存在于实到里的运单号
|
||
df_undelivered = df_expected[~df_expected["运单号"].isin(actual_set)]
|
||
|
||
target_columns = ["班次号", "交接单号", "运单号"]
|
||
available_columns = [
|
||
col for col in target_columns if col in df_undelivered.columns
|
||
]
|
||
df_output = df_undelivered[available_columns]
|
||
|
||
print(f">> 筛选完毕！共捕获到异常【应到未到】货物数据: {len(df_output)} 条。")
|
||
|
||
df_output.to_excel(output_path, index=False)
|
||
print(f"====================================================")
|
||
print(f" 🎉 异常比对流完成！独立数据已安全输出。")
|
||
print(f" 📁 成果归档路径: {output_path}")
|
||
print(f"====================================================")
|
||
|
||
except Exception as e:
|
||
print(f"❌ 数据处理引擎在执行连接和输出时发生致命异常: {e}")
|
||
|
||
|
||
def run_multi_site_daemon():
|
||
"""多网点自动化主控引擎 (状态机卫语句驱动版)"""
|
||
|
||
# 1. 读取配置文件
|
||
debug_mode = False
|
||
debug_target = ""
|
||
try:
|
||
if os.path.exists(CONFIG_PATH):
|
||
with open(CONFIG_PATH, "r", encoding="utf-8") as f:
|
||
config = yaml.safe_load(f)
|
||
debug_mode = config.get("debug", {}).get("enabled", False)
|
||
debug_target = config.get("debug", {}).get("target_site", "")
|
||
except Exception as e:
|
||
print(f"⚠️ 读取 config.yaml 异常，将使用全量模式启动: {e}")
|
||
|
||
# 动态确定需要挂载启动的网页
|
||
active_sites = {}
|
||
if debug_mode and debug_target in SITES_CONFIG:
|
||
print(f"\n🛠️ 【调试模式激活】当前中控台仅挂载并开启目标站点: [{debug_target}]")
|
||
active_sites = {debug_target: SITES_CONFIG[debug_target]}
|
||
else:
|
||
active_sites = SITES_CONFIG
|
||
|
||
with sync_playwright() as p:
|
||
browser = p.chromium.launch(headless=False)
|
||
context = browser.new_context(viewport={"width": 1920, "height": 1080})
|
||
|
||
pages_map = {}
|
||
|
||
print("\n====================================================")
|
||
print("【唤醒阶段】正在构建多网点并行运行环境...")
|
||
print("====================================================")
|
||
|
||
for site_name, url in active_sites.items():
|
||
print(f">> 正在启动【{site_name}】页面: {url}")
|
||
page = context.new_page()
|
||
page.goto(url)
|
||
pages_map[site_name] = page
|
||
|
||
print("\n====================================================")
|
||
print("【状态自检】启动前置智能接管机制...")
|
||
print("====================================================")
|
||
|
||
# 针对支持纯代码自动登录的站点，在此处前置注入登录事件
|
||
if "韵达" in pages_map:
|
||
try:
|
||
pages_map["韵达"].bring_to_front()
|
||
site_yunda.yunda_login(pages_map["韵达"])
|
||
except Exception as e:
|
||
print(f" ⚠️ 韵达前置自动登录模块发生波动: {e}")
|
||
|
||
# ====================================================================
|
||
# 🛡️ 就绪卫语句轮询器 (Ready Guard Polling)
|
||
# 无需死板的输入回车，全自动识别状态并无缝放行
|
||
# ====================================================================
|
||
ready_status = {site: False for site in active_sites.keys()}
|
||
|
||
print("\n>> 正在静默轮询全网点就绪状态 (自动免密/手工登录均可激活)...")
|
||
while not all(ready_status.values()):
|
||
for site_name, page in pages_map.items():
|
||
if not ready_status[site_name]:
|
||
try:
|
||
# 0.5秒轻量级探针，避免阻塞主循环
|
||
if page.locator(READY_SELECTORS[site_name]).is_visible(
|
||
timeout=500
|
||
):
|
||
ready_status[site_name] = True
|
||
print(f" 🎉 【{site_name}】探测到主页特征，状态已就绪！")
|
||
except Exception:
|
||
pass
|
||
|
||
pending_sites = [s for s, ready in ready_status.items() if not ready]
|
||
if pending_sites:
|
||
print(
|
||
f" ⏳ 等待以下网点登录验证: [{', '.join(pending_sites)}] ... (请在浏览器中操作)"
|
||
)
|
||
page.wait_for_timeout(3000) # 挂起 3 秒后执行下一轮盘点
|
||
|
||
print("\n====================================================")
|
||
print("【接管阶段】所有活跃网点均已就绪，正在执行环境净化...")
|
||
print("====================================================")
|
||
|
||
# 顺心环境净化
|
||
if "顺心" in pages_map:
|
||
try:
|
||
sx_page = pages_map["顺心"]
|
||
sx_page.bring_to_front()
|
||
print(">> 正在处理【顺心】弹窗与遮罩...")
|
||
sx_page.locator("a").nth(4).click(timeout=2000)
|
||
sx_page.wait_for_timeout(500)
|
||
sx_page.get_by_role("button", name="Close").click(timeout=2000)
|
||
sx_page.wait_for_timeout(500)
|
||
sx_page.get_by_role("button", name="不再询问").click(timeout=2000)
|
||
print(" ✅ 【顺心】环境准备就绪！")
|
||
except Exception:
|
||
pass # 环境可能很干净没有弹窗，无视报错
|
||
|
||
# 百世环境打地鼠
|
||
if "百世" in pages_map:
|
||
try:
|
||
bs_page = pages_map["百世"]
|
||
bs_page.bring_to_front()
|
||
print(">> 正在处理【百世】阅读完毕与关闭按钮...")
|
||
for round_idx in range(4):
|
||
handled_any = False
|
||
try:
|
||
read_btns = bs_page.locator("button:has-text('阅读完毕')")
|
||
if read_btns.count() > 0:
|
||
for i in range(read_btns.count()):
|
||
if read_btns.nth(i).is_visible(timeout=500):
|
||
read_btns.nth(i).click()
|
||
handled_any = True
|
||
except Exception:
|
||
pass
|
||
try:
|
||
if bs_page.locator("button:has-text('关 闭')").is_visible(
|
||
timeout=500
|
||
):
|
||
bs_page.locator("button:has-text('关 闭')").click()
|
||
handled_any = True
|
||
except Exception:
|
||
pass
|
||
if not handled_any:
|
||
break
|
||
bs_page.wait_for_timeout(800)
|
||
print(" ✅ 【百世】界面净化完毕！")
|
||
except Exception:
|
||
pass
|
||
|
||
if "中通" in pages_map:
|
||
print(" ✅ 【中通】状态就绪！")
|
||
|
||
if "韵达" in pages_map:
|
||
print(" ✅ 【韵达】工作区状态就绪！")
|
||
|
||
def is_site_ready(site_name):
|
||
if site_name not in pages_map:
|
||
print(f"\n🚫 【安全拦截】当前处于局部调试，[{site_name}] 未挂载加载！")
|
||
return False
|
||
return True
|
||
|
||
while True:
|
||
print("\n====================================================")
|
||
print(" 物流数据多端提取总枢纽 ")
|
||
if debug_mode:
|
||
print(f" [ 🛠️ 调试模式独立聚焦 : {debug_target} ]")
|
||
print("====================================================")
|
||
print(" 模块一：【顺心】数据处理流")
|
||
print(" [1] 执行 - 应到货物数据下载")
|
||
print(" [2] 执行 - 实到货物数据下载")
|
||
print("-" * 52)
|
||
print(" 模块二：【百世】数据处理流")
|
||
print(" [3] 执行 - 一键提取应到未到异常数据")
|
||
print("-" * 52)
|
||
print(" 模块三：【中通】数据处理流")
|
||
print(" [4] 执行 - 应到货物数据下载")
|
||
print(" [5] 执行 - 实到货物数据下载")
|
||
print("-" * 52)
|
||
print(" 模块四：【韵达】数据处理流")
|
||
print(" [6] 执行 - 应到货物数据下载")
|
||
print(" [7] 执行 - 实到货物数据下载")
|
||
print("-" * 52)
|
||
print(" 全局离线数据引擎")
|
||
print(" [9] 执行 - 异常数据清洗比对 (Left Anti-Join)")
|
||
print("-" * 52)
|
||
print(" [0] 退出系统")
|
||
print("====================================================")
|
||
|
||
choice = input("请输入任务编号并回车: ")
|
||
|
||
try:
|
||
if choice == "1" and is_site_ready("顺心"):
|
||
pages_map["顺心"].bring_to_front()
|
||
site_shunxin.shunxin_expected_download(pages_map["顺心"])
|
||
elif choice == "2" and is_site_ready("顺心"):
|
||
pages_map["顺心"].bring_to_front()
|
||
site_shunxin.shunxin_actual_download(pages_map["顺心"])
|
||
elif choice == "3" and is_site_ready("百世"):
|
||
pages_map["百世"].bring_to_front()
|
||
site_baishi.baishi_download_undelivered_data(pages_map["百世"])
|
||
elif choice == "4" and is_site_ready("中通"):
|
||
pages_map["中通"].bring_to_front()
|
||
site_zto.zto_expected_download(pages_map["中通"])
|
||
elif choice == "5" and is_site_ready("中通"):
|
||
pages_map["中通"].bring_to_front()
|
||
site_zto.zto_actual_download(pages_map["中通"])
|
||
elif choice == "6" and is_site_ready("韵达"):
|
||
pages_map["韵达"].bring_to_front()
|
||
site_yunda.yunda_expected_download(pages_map["韵达"])
|
||
elif choice == "7" and is_site_ready("韵达"):
|
||
pages_map["韵达"].bring_to_front()
|
||
site_yunda.yunda_actual_download(pages_map["韵达"])
|
||
elif choice == "9":
|
||
site_name = input(
|
||
"请输入要比对的网点名称 (如 顺心/中通/韵达): "
|
||
).strip()
|
||
if not site_name:
|
||
site_name = "顺心"
|
||
task_process_undelivered_data(site_name)
|
||
elif choice == "0":
|
||
print("\n正在释放浏览器并安全登出系统...")
|
||
break
|
||
else:
|
||
if choice not in ["1", "2", "3", "4", "5", "6", "7", "9", "0"]:
|
||
print("\n⚠️ 无效输入，请查证后回车。")
|
||
except Exception as e:
|
||
print(f"❌ 调度枢纽异常: {e}")
|
||
|
||
browser.close()
|
||
print("中控守护进程安全退出。")
|
||
|
||
|
||
if __name__ == "__main__":
|
||
run_multi_site_daemon()
|