更新 'spiders/yaoex/yaoex_crawl.py'

spiders/yaoex/yaoex_crawl.py

@@ -19,6 +19,11 @@ PLATFORM_ID = 6
 YYC_DEVICE_ID = "18193030281"
 
 HEARTBEAT_INTERVAL_SECONDS = 60
+TASK_API_BASE = "http://192.168.2.246:8080/api/collect_task"
+TASK_API_TOKEN = "zhijiayun_crawler_2026"
+TASK_PULL_URL = TASK_API_BASE + "/pull"
+TASK_HEARTBEAT_URL = TASK_API_BASE + "/heartbeat"
+TASK_REPORT_URL = TASK_API_BASE + "/report"
 
 headers = {
     "Accept": "application/json, text/plain, */*",
@@ -61,6 +66,74 @@ class YaoexCrawler:
         self.is_success = True
         self.is_not_product = 0
 
+    # ---------- API report helpers ----------
+
+    def _send_report(self, params: dict, log_msg: str):
+        try:
+            resp = requests.post(
+                TASK_REPORT_URL, json=params, timeout=10,
+                headers={'X-Crawler-Token': TASK_API_TOKEN},
+            )
+            if resp.status_code == 200:
+                try:
+                    data = resp.json()
+                    if data.get("code") == "success":
+                        logger.info("回告成功：%s", log_msg)
+                        return "success"
+                    else:
+                        msg = data.get("msg", "")
+                        if "已达平台限额" in msg or "限额" in msg:
+                            logger.warning("回告接口返回限额错误：code=%s, msg=%s", data.get('code'), msg)
+                            return "limit_reached"
+                        else:
+                            logger.warning("回告接口返回错误：code=%s, msg=%s", data.get('code'), msg)
+                            return "error"
+                except ValueError:
+                    logger.warning("回告响应非 JSON：%s", resp.text[:200])
+                    return "error"
+            else:
+                logger.warning("回告 HTTP %s", resp.status_code)
+                return "error"
+        except Exception as e:
+            logger.error("回告失败：%s，错误：%s", log_msg, str(e))
+            return "error"
+
+    def _report_start(self):
+        payload = {
+            "task_id": self.task_id,
+            "platform": str(self.platform),
+            "username": YYC_DEVICE_ID,
+            "current_page": 0,
+            "total_pages": 0,
+            "is_finished": 0,
+        }
+        logger.info("上报开始 task_id=%s", self.task_id)
+        return self._send_report(payload, "开始上报（is_finished=0）")
+
+    def _report_progress(self, current_page: int, total_pages: int = 0):
+        payload = {
+            "task_id": self.task_id,
+            "platform": str(self.platform),
+            "username": YYC_DEVICE_ID,
+            "current_page": current_page,
+            "total_pages": total_pages,
+            "is_finished": 0,
+        }
+        return self._send_report(payload, f"进度上报 page={current_page}")
+
+    def _report_end(self, success: bool, real_count: int, page_no: int = 0, total_pages: int = 0):
+        payload = {
+            "task_id": self.task_id,
+            "platform": str(self.platform),
+            "username": YYC_DEVICE_ID,
+            "current_page": page_no,
+            "total_pages": total_pages if total_pages > 0 else page_no,
+            "crawled_count": real_count,
+            "is_finished": 1 if success else 0,
+        }
+        logger.info("上报结束 task_id=%s payload=%s", self.task_id, payload)
+        self._send_report(payload, "结束上报（is_finished=1）")
+
     def _post_with_retry(self, url, payload, retries=REQUEST_RETRY_COUNT, timeout=REQUEST_TIMEOUT_SEC):
         last_err = None
         for attempt in range(1, retries + 1):
@@ -98,7 +171,6 @@ class YaoexCrawler:
         self.collect_region_id = self.task_dict.get("collect_region_id", "")
         self.collect_round = self.task_dict.get("collect_round", 1)
 
-    @staticmethod
     def _timestamp_ms() -> str:
         return str(int(time.time() * 1000))