上传文件至 'spider'

spider/requirements.txt

@@ -0,0 +1,14 @@
+requests>=2.28
+DrissionPage>=4.0
+Pillow>=10.0
+pandas>=2.0
+pymysql>=1.0
+DBUtils>=3.0
+lxml>=4.9
+oss2>=2.18
+pycryptodome>=3.19
+python-dotenv>=1.0
+schedule>=1.2
+playwright>=1.40
+curl_cffi>=0.7
+openpyxl>=3.1

spider/snapshot_jd.py

@@ -0,0 +1,123 @@
+import json
+import time
+import requests
+from commons.Logger import logger
+from commons.conn_mysql import MySQLPoolOnline, MySQLPool39
+from spiders.jd.jd_auto_crawl_snap2 import JdCrawlerV2
+from commons.scheduler import CrawlerScheduler
+from commons.feishu_webhook import send_text
+import random
+from commons.config import JD_DEVICE_ID
+platform_name = "京东"
+
+
+class JdMain:
+    def __init__(self):
+        # self.db_online = MySQLPool39()
+        self.db_online = MySQLPoolOnline()
+        self.crawl_count = ""
+        self.task_id = ""
+        self.task_dict = None
+        self.driver = None
+        self.cumulative_pages = 0
+        self.cumulative_items = 0
+        self.cumulative_stored = 0
+        self.cumulative_skipped = 0
+
+    def get_status(self, status):
+        if status not in (2, 3, 4):
+            logger.warning(f"未知状态值: {status}, 跳过状态上报")
+            return
+        if status == 2:
+            parmas = {
+                "collect_task_allocate_id": self.task_id, "status": status, "finish_status": 0,
+                "start_time": int(time.time())
+            }
+        if status == 3:
+            parmas = {
+                "collect_task_allocate_id": self.task_id, "status": status, "finish_status": 1,
+                "real_count": self.crawl_count, "end_time": int(time.time()),
+            }
+        if status == 4:
+            parmas = {
+                "collect_task_allocate_id": self.task_id, "status": status, "finish_status": 0,
+                "end_time": int(time.time())}
+
+        # url = "http://scheduletest.dfwy.tech/api/collect_equipment_execute/result_report"
+        url = "http://scheduleapi.findit.ltd/api/collect_equipment_execute/result_report"
+
+        try:
+            res = requests.get(url, params=parmas, timeout=20)
+            res.raise_for_status()
+            logger.info("状态上报: %s", res.text)
+        except Exception as e:
+            logger.warning(f"状态上报失败: {e}")
+
+    def get_task(self):
+        """获取当前设备绑定的京东待执行快照任务。"""
+        sql = """
+            SELECT t.*
+            FROM `retrieve_collect_task_allocate` t
+            INNER JOIN `retrieve_collect_equipment_account` a
+                ON t.`collect_equipment_account_id` = a.`id`
+            WHERE t.`platform` = 2
+              AND t.`status` = 1
+              AND t.`snapshot_collect_status` = 0
+            LIMIT 1
+        """
+        task_list = self.db_online.select_data(sql)
+        print(task_list)
+        if not task_list:
+            return {}
+
+        task_dict = task_list[0]
+        self.task_id = task_dict["id"]
+        print(task_dict)
+        return task_dict
+
+    def heartbeat_task(self):
+        url = "https://scheduleapi.findit.ltd/api/collect_equipment_execute/heartbeat"
+
+        params = {
+            "collect_task_allocate_id": self.task_id,
+        }
+
+        try:
+            res = requests.get(url, params=params, timeout=20)
+            logger.info("心跳任务上报成功")
+        except Exception as e:
+            logger.info("心跳任务上报失败")
+
+    def run(self):
+
+        spider_schedule = CrawlerScheduler(JD_DEVICE_ID, 2)
+        spider_schedule.start()
+        time.sleep(3)
+
+        while 1:
+            if not spider_schedule.end:
+                self.task_dict = spider_schedule.get_task()
+
+                if not self.task_dict:
+                    logger.info(f"{platform_name}暂无任务")
+                    time.sleep(35)
+                    continue
+
+                self.task_id = self.task_dict.get("id", "")
+                self.crawl_count, is_success, self.driver, self.cumulative_pages, self.cumulative_items, self.cumulative_stored, self.cumulative_skipped = JdCrawlerV2(self.task_dict, spider_schedule, self.driver, self.cumulative_pages, self.cumulative_items, self.cumulative_stored, self.cumulative_skipped).run()
+                spider_schedule.stop()
+
+            else:
+                spider_schedule.start()
+                print('休息')
+                time.sleep(35)
+
+            time.sleep(10)
+
+
+if __name__ == '__main__':
+    while True:
+        JdMain().run()
+        interval_time = random.randint(180, 300)
+        logger.info(f"程序睡眠{interval_time}秒后继续执行")
+        time.sleep(interval_time)

spider/snapshot_taobao.py

@@ -0,0 +1,125 @@
+import json
+import random
+import time
+import requests
+from commons.Logger import logger
+from commons.conn_mysql import MySQLPoolOnline, MySQLPool39
+from spiders.taobao.snapshot_taobao_crawl2 import TaobaoCrawl
+from commons.scheduler import CrawlerScheduler
+from commons.feishu_webhook import send_text
+from commons.config import TB_DEVICE_ID
+
+platform_name = "淘宝"
+
+
+class TaobaoMain:
+    def __init__(self):
+        # self.db_online = MySQLPool39()
+        self.db_online = MySQLPoolOnline()
+        self.crawl_count = ""
+        self.task_id = ""
+        self.task_dict = None
+        self.driver = None
+        self.cumulative_pages = 0
+        self.cumulative_items = 0
+        self.cumulative_stored = 0
+        self.cumulative_skipped = 0
+
+    def get_status(self, status):
+        if status not in (2, 3, 4):
+            logger.warning(f"未知状态值: {status}, 跳过状态上报")
+            return
+        if status == 2:
+            parmas = {
+                "collect_task_allocate_id": self.task_id, "status": status, "finish_status": 0,
+                "start_time": int(time.time())
+            }
+        if status == 3:
+            parmas = {
+                "collect_task_allocate_id": self.task_id, "status": status, "finish_status": 1,
+                "real_count": self.crawl_count, "end_time": int(time.time()),
+            }
+        if status == 4:
+            parmas = {
+                "collect_task_allocate_id": self.task_id, "status": status, "finish_status": 0,
+                "end_time": int(time.time())}
+        # url = "http://scheduletest.dfwy.tech/api/collect_equipment_execute/result_report"
+        url = "http://scheduleapi.findit.ltd/api/collect_equipment_execute/result_report"
+
+        try:
+            res = requests.get(url, params=parmas, timeout=20)
+            res.raise_for_status()
+            logger.info("状态上报: %s", res.text[:500])
+        except Exception as e:
+            logger.warning(f"状态上报失败: {e}")
+
+    def heartbeat_task(self):
+        url = "https://scheduleapi.findit.ltd/api/collect_equipment_execute/heartbeat"
+        params = {
+            "collect_task_allocate_id": self.task_id,
+        }
+        try:
+            res = requests.get(url, params=params, timeout=20)
+            logger.info("心跳任务上报成功")
+        except Exception as e:
+            logger.info(f"心跳任务上报失败{str(e)}")
+
+    def get_task(self):
+        """获取当前设备绑定的淘宝待执行任务（快照版）。"""
+        sql = """
+            SELECT t.*
+            FROM `retrieve_collect_task_allocate` t
+            INNER JOIN `retrieve_collect_equipment_account` a
+                ON t.`collect_equipment_account_id` = a.`id`
+            WHERE a.`device_id` = %s
+              AND t.`platform` = 1
+              AND t.`status` = 1
+              AND t.`snapshot_collect_status` = 0
+            LIMIT 1
+        """
+        task_list = self.db_online.select_data(sql, (TB_DEVICE_ID,))
+
+        if not task_list:
+            return {}
+
+        task_dict = task_list[0]
+        self.task_id = task_dict["id"]
+        return task_dict
+
+    def run(self):
+
+        spider_schedule = CrawlerScheduler(TB_DEVICE_ID, 1)
+        spider_schedule.start()
+        time.sleep(3)
+
+        while 1:
+            print(f'not spider_schedule.end:{not spider_schedule.end}')
+            if not spider_schedule.end:
+                print('进入工作')
+
+                self.task_dict = spider_schedule.get_task()
+
+                if not self.task_dict:
+                    logger.info(f"{platform_name}暂无任务")
+                    time.sleep(35)
+                    continue
+
+                print(self.task_dict)
+                self.task_dict.update({'collect_equipment_account_id': TB_DEVICE_ID})
+                self.crawl_count, is_success, self.driver, self.cumulative_pages, self.cumulative_items, self.cumulative_stored, self.cumulative_skipped = TaobaoCrawl(self.task_dict, spider_schedule, self.driver, self.cumulative_pages, self.cumulative_items, self.cumulative_stored, self.cumulative_skipped).run()
+                spider_schedule.stop()
+            else:
+                spider_schedule.start()
+                print('休息')
+                time.sleep(35)
+
+            time.sleep(30)
+
+
+if __name__ == '__main__':
+    # 每10分钟执行一次
+    while True:
+        TaobaoMain().run()
+        interval_time = random.randint(1200, 1800)
+        logger.info(f"程序睡眠{interval_time}秒后继续执行")
+        time.sleep(interval_time)

spider/start_run_jd.py

@@ -0,0 +1,165 @@
+import json
+import time
+import requests
+from commons.Logger import logger
+
+from commons.scheduler import CrawlerScheduler
+
+from commons.conn_mysql import MySQLPoolOn2, MySQLPool39
+from spiders.jd.jd_auto_crawl import JdCrawlerV2
+import schedule
+from commons.feishu_webhook import send_text
+import random
+from commons.config import JD_DEVICE_ID
+platform_name = "京东"
+
+
+class JdMain:
+    def __init__(self):
+        # self.db_online = MySQLPool39()
+        self.db_online = MySQLPoolOn2()
+        self.crawl_count = ""
+        self.task_id = ""
+        #self.task_dict = self.get_task()
+
+    def get_status(self, status):
+        if status not in (2, 3, 4):
+            logger.warning(f"未知状态值: {status}, 跳过状态上报")
+            return
+        if status == 2:
+            parmas = {
+                "collect_task_allocate_id": self.task_id, "status": status, "finish_status": 0,
+                "start_time": int(time.time())
+            }
+        if status == 3:
+            parmas = {
+                "collect_task_allocate_id": self.task_id, "status": status, "finish_status": 1,
+                "real_count": self.crawl_count, "end_time": int(time.time()),
+            }
+        if status == 4:
+            parmas = {
+                "collect_task_allocate_id": self.task_id, "status": status, "finish_status": 0,
+                "end_time": int(time.time())}
+
+        # url = "http://scheduletest.dfwy.tech/api/collect_equipment_execute/result_report"
+        url = "http://scheduleapi.findit.ltd/api/collect_equipment_execute/result_report"
+
+        try:
+            res = requests.get(url, params=parmas, timeout=20)
+            res.raise_for_status()
+            logger.info("状态上报: %s", res.text)
+        except Exception as e:
+            logger.warning(f"状态上报失败: {e}")
+
+    def get_task(self):
+        """获取当前设备绑定的京东待执行任务。"""
+        sql = """
+            SELECT t.*
+            FROM `retrieve_collect_task_allocate` t
+            INNER JOIN `retrieve_collect_equipment_account` a
+                ON t.`collect_equipment_account_id` = a.`id`
+            WHERE a.`device_id` = %s
+              AND t.`platform` = 2
+              AND t.`status` = 3
+            LIMIT 1
+        """
+        task_list = self.db_online.select_data(sql, (JD_DEVICE_ID,))
+        print(task_list)
+        if not task_list:
+            return {}
+
+        task_dict = task_list[0]
+        self.task_id = task_dict["id"]
+        print(task_dict)
+        return task_dict
+
+    def get_task(self):
+        task_api = "http://192.168.2.246:8080/api/collect_task/pull"
+
+        headers = {'X-Crawler-Token':'zhijiayun_crawler_2026'}
+        
+        params = {
+        'platform': 2,
+        'username': JD_DEVICE_ID
+        }
+        response = requests.get(task_api, params=params,headers=headers)
+        result = response.json()
+        if result.get('code') =='success':
+            return result.get('data').get('task')
+        
+        logger.info(f'拉取任务：{result}')
+        print('拉取任务返回',result)
+
+
+    def heartbeat_task(self):
+        url = "https://scheduleapi.findit.ltd/api/collect_equipment_execute/heartbeat"
+
+        params = {
+            "collect_task_allocate_id": self.task_id,
+        }
+
+        try:
+            res = requests.get(url, params=params, timeout=20)
+            logger.info("心跳任务上报成功")
+        except Exception as e:
+            logger.info("心跳任务上报失败")
+
+    def run(self):
+
+        spider_schedule =  CrawlerScheduler(JD_DEVICE_ID,2)
+        spider_schedule.start()
+        time.sleep(3)
+
+        while 1 :
+            print(f'not spider_schedule.end:{not spider_schedule.end}')
+            if(not spider_schedule.end):
+                print('进入工作')
+
+                self.task_dict = spider_schedule.get_task()
+                
+                #self.task_dict = {'id': 4, 'company_id': 0, 'product_name': '藿香正气合剂', 'product_specs': '', 'product_brand': '999', 'product_keyword': '', 'current_page': 0, 'start_offset': 0}
+
+                print(self.task_dict)
+
+
+
+                if not self.task_dict:
+                    logger.info(f"{platform_name}暂无任务")
+                    time.sleep(35)
+                    continue
+
+                
+                # self.get_status(2)
+                self.crawl_count, is_success = JdCrawlerV2(self.task_dict,spider_schedule).run()
+                spider_schedule.stop()
+            else:
+
+                spider_schedule.start()
+                print('休息')
+                time.sleep(35)
+
+            
+            time.sleep(30)
+
+        # self.heartbeat_task()
+        # # send_text(
+        # #     f"""{str(time.strftime("%Y-%m-%d %H:%M:%S"))} 通知:\n平台: {platform_name}, 药品: {self.task_dict.get("product_brand") + " " + self.task_dict.get("product_name") + " " + self.task_dict.get("product_specs")},  爬取数据: {self.crawl_count}条""")
+        # if is_success:
+        #     self.get_status(3)
+        # else:
+        #     self.get_status(4)
+
+
+if __name__ == '__main__':
+    # task_dict= {"id": 1622, 'collect_task_id': 4596, 'company_id': 8, 'product_name': '小儿氨酚烷胺颗粒',
+    # 'product_specs': '', 'product_keyword': '', 'product_brand': '可复美', 'sampling_cycle': 1,
+    # 'sampling_start_time': 1778083200, 'sampling_end_time': 1778342399, 'collect_equipment_account_id': 15,
+    # 'collect_region_id': 0, 'collect_equipment_id': 25, 'collect_round': 2,"start_page":4,"end_page":10}
+    # JdCrawlerV2(task_dict).run()
+    # 每10分钟执行一次
+    while True:
+        JdMain().run()
+        interval_time = random.randint(60, 180)
+        interval_time = 60
+        logger.info(f"程序睡眠{interval_time}秒后继续执行")
+        time.sleep(interval_time)

spider/start_run_taobao.py

@@ -0,0 +1,126 @@
+import random
+import time
+import requests
+from commons.Logger import logger
+from commons.conn_mysql import MySQLPoolOnline
+from spiders.taobao.taobao_crawl import TaobaoCrawl
+from commons.scheduler import CrawlerScheduler
+from commons.config import TB_DEVICE_ID
+
+platform_name = "淘宝"
+TB_DEVICE_ID = '17'
+
+class TaobaoMain:
+    def __init__(self):
+        # self.db_online = MySQLPool39()
+        self.db_online = MySQLPoolOnline()
+        self.crawl_count = ""
+        self.task_id = ""
+        self.task_dict = None
+
+    def get_status(self, status):
+        if status not in (2, 3, 4):
+            logger.warning(f"未知状态值: {status}, 跳过状态上报")
+            return
+        if status == 2:
+            parmas = {
+                "collect_task_allocate_id": self.task_id, "status": status, "finish_status": 0,
+                "start_time": int(time.time())
+            }
+        if status == 3:
+            parmas = {
+                "collect_task_allocate_id": self.task_id, "status": status, "finish_status": 1,
+                "real_count": self.crawl_count, "end_time": int(time.time()),
+            }
+        if status == 4:
+            parmas = {
+                "collect_task_allocate_id": self.task_id, "status": status, "finish_status": 0,
+                "end_time": int(time.time())}
+        # url = "http://scheduletest.dfwy.tech/api/collect_equipment_execute/result_report"
+        url = "http://scheduleapi.findit.ltd/api/collect_equipment_execute/result_report"
+
+        try:
+            res = requests.get(url, params=parmas, timeout=20)
+            res.raise_for_status()
+            logger.info("状态上报: %s", res.text[:500])
+        except Exception as e:
+            logger.warning(f"状态上报失败: {e}")
+
+    def heartbeat_task(self):
+        url = "https://scheduleapi.findit.ltd/api/collect_equipment_execute/heartbeat"
+        params = {
+            "collect_task_allocate_id": self.task_id,
+        }
+        try:
+            res = requests.get(url, params=params, timeout=20)
+            logger.info("心跳任务上报成功")
+        except Exception as e:
+            logger.info(f"心跳任务上报失败{str(e)}")
+
+    def get_task(self):
+        """获取当前设备绑定的京东待执行任务。"""
+        sql = """
+            SELECT t.*
+            FROM `retrieve_collect_task_allocate` t
+            INNER JOIN `retrieve_collect_equipment_account` a
+                ON t.`collect_equipment_account_id` = a.`id`
+            WHERE a.`device_id` = %s
+              AND t.`platform` = 1
+              AND t.`status` = 1
+            LIMIT 1
+        """
+        task_list = self.db_online.select_data(sql, (TB_DEVICE_ID,))
+
+        if not task_list:
+            return {}
+
+        task_dict = task_list[0]
+        self.task_id = task_dict["id"]
+        return task_dict
+
+    def run(self):
+
+        spider_schedule =  CrawlerScheduler(TB_DEVICE_ID,1)
+        spider_schedule.start()
+        time.sleep(3)
+
+        while 1 :
+            print(f'not spider_schedule.end:{not spider_schedule.end}')
+            if(not spider_schedule.end):
+                print('进入工作')
+
+                self.task_dict = spider_schedule.get_task()
+                
+                #self.task_dict = {'id': 4, 'company_id': 0, 'product_name': '藿香正气合剂', 'product_specs': '', 'product_brand': '999', 'product_keyword': '', 'current_page': 0, 'start_offset': 0}
+
+
+
+                if not self.task_dict:
+
+
+                    logger.info(f"{platform_name}暂无任务")
+                    time.sleep(35)
+                    continue
+
+                print(self.task_dict)
+                self.task_dict.update({'collect_equipment_account_id':TB_DEVICE_ID})
+                # self.get_status(2)
+                self.crawl_count, is_success = TaobaoCrawl(self.task_dict,spider_schedule).run()
+                spider_schedule.stop()
+            else:
+
+                spider_schedule.start()
+                print('休息')
+                time.sleep(35)
+
+            
+            time.sleep(30)
+
+
+if __name__ == '__main__':
+    # 每10分钟执行一次
+    while True:
+        TaobaoMain().run()
+        interval_time = random.randint(1200, 1800)
+        logger.info(f"程序睡眠{interval_time}秒后继续执行")
+        time.sleep(interval_time)