抓取生产工单，赚取发料异常

2026-06-11 15:58:56 +08:00
parent 66eecd0daa
commit 5b19790037
40 changed files with 4942 additions and 54 deletions
--- a/browser_login/fetch_work_orders.py
+++ b/browser_login/fetch_work_orders.py
@@ -0,0 +1,107 @@
+"""
+生产工单查询 - 数据提取
+"""
+
+import os
+import sys
+import json
+import time
+import datetime
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent))
+from login import get_page, login, login_manual, log, dump_page_state
+from config import OUTPUT_DIR
+
+PAGE_URL = "https://yunmes.tftykj.cn/WorkOrdersQuery"
+API_PATH = "WorkOrdersDetailed_SearchListAll_Proxy"  # 精确匹配生产工单列表 API
+
+# ── 导航到目标页面 ───────────────────────────────────────────────────────────
+def navigate_to_page(page):
+    log("INFO", f"导航到生产工单查询页面...")
+    page.get(PAGE_URL)
+    # 等待数据表格区域出现
+    table = page.ele("xpath://table | .el-table__body", timeout=15)
+    if table:
+        log("OK", "页面已加载")
+    else:
+        log("WARN", "表格元素未找到，继续执行")
+
+# ── 拦截并获取第 1 页数据 ───────────────────────────────────────────────
+def fetch_page1(page) -> dict:
+    log("INFO", "开启网络监听...")
+    page.listen.start(API_PATH)
+
+    # 刷新页面触发自动加载请求
+    page.refresh()
+
+    log("INFO", "等待 API 响应...")
+    packet = page.listen.wait(timeout=30)
+    page.listen.stop()
+
+    if not packet:
+        log("ERR", "超时未收到响应")
+        dump_page_state(page, "监听超时")
+        return None
+
+    log("OK", f"拦截成功 → HTTP {packet.response.status} (URL: {packet.request.url})")
+
+    try:
+        body = packet.response.body
+        data = body if isinstance(body, (dict, list)) else json.loads(body)
+        
+        if isinstance(data, dict):
+            result = data.get("result", {})
+            if isinstance(result, dict) and "totalCount" in result:
+                items  = result.get("items", [])
+                total  = result.get("totalCount", "?")
+                log("INFO", f"本页记录: {len(items)} 条 | 总计: {total} 条")
+                return data
+    except Exception as e:
+        log("WARN", f"解析 {packet.request.url} 失败: {e}")
+                 
+    log("ERR", "未解析到有效的数据结构")
+    return None
+
+# ── 保存为 JSON ───────────────────────────────────────────────────────────────
+def save_json(data, prefix: str = "work_orders") -> Path:
+    ts   = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
+    path = OUTPUT_DIR / f"{prefix}_{ts}.json"
+    with open(path, "w", encoding="utf-8") as f:
+        json.dump(data, f, ensure_ascii=False, indent=2)
+    log("OK", f"已保存: {path}")
+    return path
+
+# ── 主流程 ────────────────────────────────────────────────────────────────────
+def run(manual: bool = False):
+    mode = "复用保活浏览器"
+    log("INFO", f"生产工单查询提取启动 [{mode}]")
+
+    # 使用已经登录的保活浏览器端口 9222
+    page = get_page(port=9222)
+    try:
+        # Step 1: 进入页面
+        navigate_to_page(page)
+
+        # Step 2: 获取第 1 页数据
+        data = fetch_page1(page)
+        if data is None:
+            log("ERR", "数据获取失败")
+            return
+
+        # Step 3: 保存 JSON
+        save_json(data, prefix="work_orders_page1")
+        log("OK", "完成！文件保存在 output/")
+
+    except KeyboardInterrupt:
+        log("INFO", "用户中断 (Ctrl+C)")
+    except Exception as e:
+        log("ERR", f"异常: {e}")
+        import traceback
+        traceback.print_exc()
+    finally:
+        # 复用浏览器的情况下不关闭浏览器
+        pass
+
+if __name__ == "__main__":
+    run(manual="--manual" in sys.argv)