- task_process_undelivered_data now accepts site_name (default 顺心)
and reads/writes {site}-{应到/实到/应到未到}货物数据.xlsx
- Menu option 5 prompts for site name before running reconciliation
- Update 顺心 site outputs to 顺心-应到/实到货物数据.xlsx naming
- Remove redundant inline comments in site_shunxin.py
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
178 lines
7.6 KiB
Python
178 lines
7.6 KiB
Python
# main_router.py
|
||
|
||
import os
|
||
import pandas as pd
|
||
from playwright.sync_api import sync_playwright
|
||
|
||
# 导入抽离出去的各个网点模块
|
||
import site_shunxin
|
||
import site_baishi
|
||
|
||
# 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",
|
||
}
|
||
|
||
|
||
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 = os.path.join(os.getcwd(), "downloads")
|
||
# 动态拼接带网点前缀的文件路径
|
||
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...")
|
||
df_expected = pd.read_excel(expected_path)
|
||
df_actual = pd.read_excel(actual_path)
|
||
|
||
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...")
|
||
|
||
# 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(df_actual["运单号"])]
|
||
|
||
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"""
|
||
with sync_playwright() as p:
|
||
browser = p.chromium.launch(headless=False)
|
||
# 取消禁用视口大小限制,防止有些系统自适应出问题
|
||
context = browser.new_context(viewport={"width": 1920, "height": 1080})
|
||
|
||
# 用于存储网点名称与 Page 对象的映射字典
|
||
pages_map = {}
|
||
|
||
print("\n====================================================")
|
||
print("【初始化阶段】正在构建多网点运行环境...")
|
||
print("====================================================")
|
||
|
||
# 遍历配置,依次创建独立的标签页
|
||
for site_name, url in SITES_CONFIG.items():
|
||
print(f">> 正在打开【{site_name}】页面: {url}")
|
||
page = context.new_page()
|
||
page.goto(url)
|
||
pages_map[site_name] = page
|
||
page.wait_for_timeout(1000)
|
||
|
||
print("\n====================================================")
|
||
print("⚠️ 【等待人工介入】")
|
||
print("请在弹出的浏览器中,依次切换标签页,人工完成所有网点的登录!")
|
||
print("====================================================")
|
||
|
||
# 阻塞程序,等待用户登录完毕
|
||
input(">> 登录全部完成后,请在此处按下【回车键】正式接管中控台...")
|
||
|
||
print("\n====================================================")
|
||
print("【系统接管】正在执行各网点就绪前初始化动作...")
|
||
print("====================================================")
|
||
|
||
# 处理【顺心】网点的登录后就绪判定与弹窗清理
|
||
try:
|
||
sx_page = pages_map["顺心"]
|
||
sx_page.bring_to_front()
|
||
print(">> 正在处理【顺心】网点初始状态...")
|
||
|
||
# 使用较长超时时间确认登录状态(避免回车按得太早没加载完)
|
||
sx_page.wait_for_selector('h1:has-text("盟商门户网")', timeout=30000)
|
||
print(" 🎉 登录成功!系统已接管顺心浏览器。")
|
||
sx_page.wait_for_timeout(1000)
|
||
|
||
# 跳过初始一些弹窗干扰
|
||
sx_page.locator("a").nth(4).click()
|
||
sx_page.wait_for_timeout(1000)
|
||
sx_page.get_by_role("button", name="Close").click()
|
||
sx_page.wait_for_timeout(1000)
|
||
sx_page.get_by_role("button", name="不再询问").click()
|
||
sx_page.wait_for_timeout(1000)
|
||
print(" ✅ 【顺心】弹窗清理完毕,状态就绪!")
|
||
|
||
except Exception as e:
|
||
print(f" ⚠️ 【顺心】初始化或弹窗清理异常 (如无弹窗可忽略): {e}")
|
||
|
||
# 未来如果要加【百世】的弹窗清理,可以直接在这里依葫芦画瓢加上
|
||
# try:
|
||
# bs_page = pages_map["百世"]
|
||
# bs_page.bring_to_front()
|
||
# ...
|
||
|
||
while True:
|
||
print("\n==============================")
|
||
print(" 物流数据多端提取总枢纽 ")
|
||
print("==============================")
|
||
print("1. [顺心] - 执行【应到货物数据下载】")
|
||
print("2. [顺心] - 执行【实到货物数据下载】")
|
||
print("3. [百世] - 执行【应到货物数据下载】")
|
||
print("4. [百世] - 执行【实到货物数据下载】")
|
||
print("5. [全局] - 执行【应到未到数据清洗比对】")
|
||
print("0. 退出系统")
|
||
print("==============================")
|
||
|
||
choice = input("请输入任务编号并回车: ")
|
||
|
||
try:
|
||
if choice == "1":
|
||
pages_map["顺心"].bring_to_front()
|
||
site_shunxin.shunxin_expected_download(pages_map["顺心"])
|
||
elif choice == "2":
|
||
pages_map["顺心"].bring_to_front()
|
||
site_shunxin.shunxin_actual_download(pages_map["顺心"])
|
||
elif choice == "3":
|
||
pages_map["百世"].bring_to_front()
|
||
site_baishi.baishi_expected_download(pages_map["百世"])
|
||
elif choice == "4":
|
||
pages_map["百世"].bring_to_front()
|
||
site_baishi.baishi_actual_download(pages_map["百世"])
|
||
elif choice == "5":
|
||
site_name = input("请输入要比对的网点名称 (默认: 顺心): ").strip()
|
||
if not site_name:
|
||
site_name = "顺心"
|
||
task_process_undelivered_data(site_name)
|
||
elif choice == "0":
|
||
print("\n准备退出程序,释放浏览器资源...")
|
||
break
|
||
else:
|
||
print("\n⚠️ 无效输入,请重新选一下。")
|
||
except Exception as e:
|
||
print(f"❌ 调度执行异常: {e}")
|
||
|
||
# 退出循环后关闭浏览器
|
||
browser.close()
|
||
print("系统已安全关闭。")
|
||
|
||
|
||
if __name__ == "__main__":
|
||
run_multi_site_daemon()
|