PDD/pdd1/pdd_auto_scrape.py

import requests
import base64
import cv2
import uiautomator2 as u2
import time
import subprocess
import re
import random
import datetime
import json
from apscheduler.schedulers.blocking import BlockingScheduler
from aip import AipOcr
import numpy as np
import cv2
import os
from config import Config
import logging
from logger import setup_logger
import xml.etree.ElementTree as ET
import secrets
import threading
from collections import deque
from typing import Dict, Any
import schedule

setup_logger("pdd_spider")          # 初始化日志

class SpiderMonitor(threading.Thread):
    """全局弹窗监控线程（增强版）"""
    def __init__(self, spider_instance):
        super().__init__(daemon=True)
        self.spider = spider_instance
        self.running = True
        self.pausing = threading.Event()          # 主线程同步事件
        self.last_verification_time = 0
        self.verification_count = 0
        self.MAX_VERIFICATION_RETRY = 10
        self.recent_clicks = deque(maxlen=10)  # 防重复点击
        self.logger = logging.getLogger("SpiderMonitor")

        # 可配置化弹窗规则
        self.popup_rules = {
            "simple": [
                ('//*[@text="确定"]', "点击确定"),
                ('//*[@text="允许"]', "点击允许"),
                ('//*[@text="关闭"]', "点击关闭"),
                ('//*[@resource-id="com.sankuai.meituan:id/close"]', "关闭按钮"),
                ('//*[@resource-id="com.sankuai.meituan:id/address_center_location_close"]', "关闭按钮"),
                ('//*[@resource-id="com.sankuai.meituan:id/location_close"]', "关闭按钮"),
            ],  
            "verification": [
                '//*[contains(@text, "验证")]',
                '//*[contains(@text, "滑块")]',
                '//*[contains(@text, "依次点击")]',
                '//*[contains(@text, "请点击")]',
                '//*[contains(@text, "拖动滑块刚")]',  #这个需要拖动滑块至最右边，然后再截图
                '//*[contains(@text, "请输入图片中的内容")]',
                '//*[contains(@text, "用最短线连接")]',
                '//*[contains(@text, "请按语序依次点击")]',
                '//*[contains(@text, "请向右滑动滑块")]',
                '//*[contains(@text, "请拖动下方滑块完成拼图")]',
                '//*[contains(@resource-id, "captcha")]'
            ]
        }

    def run(self):
        while self.running:
            try:
                handled = self.check_and_handle_popup()
                time.sleep(2 if handled else 1)
            except Exception as e:
                self.logger.exception("监控线程异常: %s", e)
                time.sleep(3)

    def _is_recent_click(self, xpath):
        """防止重复点击同一个弹窗"""
        key = f"{xpath}_{int(time.time())}"
        if key in self.recent_clicks:
            return True
        self.recent_clicks.append(key)
        return False

    def check_and_handle_popup(self):
        d = self.spider.d

        # 1. 处理简单弹窗
        for xpath, desc in self.popup_rules["simple"]:
            if d.xpath(xpath).exists and not self._is_recent_click(xpath):
                self.logger.info("检测到弹窗: %s", desc)
                d.xpath(xpath).click()
                return True

        # 2. 处理验证码弹窗
        for xpath in self.popup_rules["verification"]:
            if d.xpath(xpath).exists:
                now = time.time()
                if now - self.last_verification_time < 30:
                    return False  # 30秒内不重复触发

                self.last_verification_time = now
                self.verification_count += 1
                self.logger.warning("验证码弹窗触发，等待人工处理...")

                if self.verification_count > self.MAX_VERIFICATION_RETRY:
                    self.logger.error("验证码重试超限，终止任务")
                    self.spider.stop_all()
                    return True
                
                self.pausing.set()   # 通知主线程暂停
                d.toast.show("需要人工处理验证码", 120)

                # 等待人工处理
                start = time.time()
                # while time.time() - start < 120*60:
                #     if not d.xpath(xpath).exists:
                #         self.logger.info("验证码已处理")
                #         d.toast.show("验证完成", 2)
                #         self.pausing.clear()      # 放行主线程
                #         return True
                #     time.sleep(5)
                while True:
                    if not d.xpath(xpath).exists:
                        self.logger.info("验证码已处理")
                        d.toast.show("验证完成", 2)
                        self.pausing.clear()      # 放行主线程
                        return True
                    time.sleep(5)


                self.logger.warning("验证码超时，重启APP")
                self.spider.restart_app()
                return True

        # 3. 处理广告弹窗（点击右上角）
        if d.xpath('//*[contains(@text, "广告")]').exists:
            w, h = d.info['displayWidth'], d.info['displayHeight']
            d.click(w - 50, 50)
            self.logger.info("关闭广告弹窗")
            return True

        return False

    def stop(self):
        self.running = False

def get_access_token():
    AppKey = "tRK2RhyItCSh6BzyT4CNVXQa"
    AppSrcret = "TDgKiPo94i2mOM1sDqOuDnlcK1bG66jh"
    token_url = 'https://aip.baidubce.com/oauth/2.0/token'
    url = f"{token_url}?grant_type=client_credentials&client_id={AppKey}&client_secret={AppSrcret}"

    payload = ""
    headers = {
        'Content-Type': 'application/json',
        'Accept': 'application/json'
    }

    response = requests.request("POST", url, headers=headers, data=payload)

    try:
        return response.json()['access_token']
    except:
        return None
        

def get_mysql():
    """
    建立并返回一个到数据库的连接对象
    """
    import pymysql
    return pymysql.connect(
        host = Config.DB_HOST,        #"localhost",  # 修改后的主机
        port = Config.DB_PORT,        #3306,  # 添加端口号
        user = Config.DB_USER,        #'root', # 修改后的用户名
        password = Config.DB_PASSWORD,  # 修改后的密码
        db = Config.DB_NAME,     #"drug_data",  # 修改后的数据库名
        charset='utf8mb4'
    )

#获取滑块验证中滑块需要移动的距离
def slide_verify(img_path):
    with open(img_path, 'rb') as f:
        b = base64.b64encode(f.read()).decode()  ## 图片二进制流base64字符串
    url = "http://api.jfbym.com/api/YmServer/customApi"
    data = {
        ## 关于参数,一般来说有3个;不同类型id可能有不同的参数个数和参数名,找客服获取
        "token": "1nDVocTE2mJ0yLEYb2sZJ5uUY2VIEoGTkIpW44X7Kgk",
        "type": "22222",
        "image": b,
    }
    _headers = {
        "Content-Type": "application/json"
    }
    response = requests.request("POST", url, headers=_headers, json=data).json()
    print(response)
    
    if response.get("msg") == "识别成功":
        # 获取 data 中的 data 字段
        result = response.get("data", {}).get("data")
        if result:
            print(result)  # 输出结果
        else:
            print("无法获取数据")
    else:
        print("识别未成功")
    
    return result



class TaskReporter:
    """任务上报管理器（线程安全）"""
    def __init__(self):
        self.tasks_data = {}  # 存储每个任务的数据
        self.lock = threading.Lock()
        
    def start_task(self, task_id: int, start_page: int, end_page: int):
        """记录任务开始"""
        with self.lock:
            self.tasks_data[task_id] = {
                'task_id': task_id,
                'start_time': int(time.time()),
                'end_time': None,
                'start_page': start_page,
                'end_page': end_page,
                'actual_end_page': start_page,  # 实际结束页数
                'real_count': 0,  # 实际采集数量
                'status': 'running',  # running, completed, failed
                'finish_status': 0,  # 0:未完成，1:已完成
            }
            
    def update_task_progress(self, task_id: int, 
                           actual_end_page: int = None,
                           real_count: int = None):
        """更新任务进度（线程安全）"""
        with self.lock:
            if task_id in self.tasks_data:
                if actual_end_page is not None:
                    self.tasks_data[task_id]['actual_end_page'] = actual_end_page
                if real_count is not None:
                    self.tasks_data[task_id]['real_count'] = real_count
                        
    def end_task(self, task_id: int, status: str = 'completed', 
                finish_status: int = 0, force_end_page: int = None):
        """记录任务结束并上报"""
        with self.lock:
            if task_id in self.tasks_data:
                data = self.tasks_data[task_id]
                data['end_time'] = int(time.time())
                data['status'] = status
                data['finish_status'] = finish_status
                if force_end_page is not None:
                    data['actual_end_page'] = force_end_page
                    
                # 准备上报数据
                report_data = {
                    "collect_task_allocate_id": data['task_id'],
                    "status": 3 if data['status'] == 'completed' else 4,
                    "finish_status": data['finish_status'],
                    'real_count': data['real_count'],
                    'start_time': data['start_time'],
                    'end_time': data['end_time'],
                    'start_page': data['start_page'],
                    'end_page': data['actual_end_page']
                }
                
                # 调用上报接口
                self._call_report_api(report_data)
                
    def _call_report_api(self, data: Dict[str, Any]):
        """调用上报接口"""
        try:
            url =  'http://schedule.dfwy.tech/api/collect_equipment_execute/result_report'
            resp = requests.post(url, json=data, timeout=10)
            
            if resp.status_code == 200:
                print(f"任务 {data['collect_task_allocate_id']} 上报成功")
                # self.loggerPdd.info(f"任务 {data['collect_task_allocate_id']} 上报成功")
            else:
                print(f"任务 {data['collect_task_allocate_id']} 上报失败: {resp.status_code}")
                # self.loggerPdd.info(f"任务 {data['collect_task_allocate_id']} 上报失败: {resp.status_code}")
        except Exception as e:
            print(f"上报接口调用异常: {e}")

# 全局上报管理器
reporter = TaskReporter()



class PDD:
    def __init__(self, search_key, device_id):
        self.package_name = 'com.xunmeng.pinduoduo'
        self.APP_ID = '116857964'
        self.API_KEY = '1gAzACJOAr7BeILKqkqPOETh'
        self.SECRET_KEY = 'ZNArANb9GwJYgLKg4EfYhukKBfPdl1n3'
        self.client = AipOcr(self.APP_ID, self.API_KEY, self.SECRET_KEY)
        self.city2province = self.get_city_info()
        # host = "localhost"
        # user = "root"
        # password = "dfwy2025"
        # database = "drug_data"
        # port = 3306
        # self.table_name = "mt_drug"

        self.table_name = Config.DB_PDD_AUTO_TABLE #"pdd_drug"  #pdd_auto_drug_test
        self.shop_table_name = Config.DB_PDD_SHOP_TABLE #"pdd_shop_info"

        self.loggerPdd = logging.getLogger()

        self.clipboard = "" #初始化剪切板的内容为空
        self.access_token = get_access_token()

        self.search_key = search_key  # 参苓健脾胃颗粒 香砂平胃颗粒 舒肝颗粒 清肺化痰丸
        self.unrelated_data = 0  # 无关数据数量
        self.device_id = device_id

         # === 新增：采集统计 ===
        self.collected_count = 0  # 实际采集的商品数量
        self.task_id = None  # 任务ID
        self.start_time = None  # 任务开始时间
        self.current_page = 0  # 当前页码
        self.task_start_page = 0  # 任务开始页码
        self.task_end_page = 0  # 任务结束页码
        # ====================

    def update_task_status(self, status):
        """更新任务状态到数据库"""
        if not self.task_id:
            return
        
        try:
            retrieve_conn = get_retrieve_mysql()
            cursor = retrieve_conn.cursor()
            update_time = time.time()
            update_sql = """
                UPDATE retrieve_collect_task_allocate 
                SET status = %s, update_time = %s 
                WHERE id = %s
            """
            cursor.execute(update_sql, (status,update_time, self.task_id))
            retrieve_conn.commit()
            
            self.loggerPdd.info(f"任务 {self.task_id} 状态更新为 {status}")
            
        except Exception as e:
            self.loggerPdd.error(f"更新任务状态失败: {e}")
        finally:
            if 'cursor' in locals():
                cursor.close()
            if 'retrieve_conn' in locals():
                retrieve_conn.close()

    def stop_app(self):
        self.d.app_stop(self.package_name)
        time.sleep(5)

    def start_app(self):
        self.d.app_start(self.package_name)
        time.sleep(5)

    def restart_app(self):
        """
        重启app
        :return:
        """
        self.stop_app()
        self.start_app()

    @staticmethod
    def get_sleep_time():
        return random.randint(1, 3)
        # return random.randint(5, 8)

    @staticmethod
    def get_current_date():
        return datetime.datetime.now().strftime('%Y/%m/%d')

    @staticmethod
    def get_city_info():
        """
        获取所有的省市数据
        :return:
        """
        file_path = '../kailin_city.json'
        with open(file_path, 'r', encoding='utf-8') as f:
            data = json.load(f)
        province = {province_one["id"]: province_one for province_one in data['province']}
        city2province = dict()
        city = data['city']
        for city_one in city:
            name = city_one['name']
            pid = city_one['pid']
            if len(str(pid)) > 2:
                pid = int(re.match('^\d{2}', str(pid)).group())
            city2province[name] = province[pid]['name']
        return city2province

    def remove_watermark(self, img_path):
        """
        图片去水印(将水印部分变成白色背景)并将数据转化为二进制数据
        :param img_path: 图片路径
        :return: 二进制图片数据
        """
        img = cv2.imdecode(np.fromfile(img_path, dtype=np.uint8), -1)
        endswith = os.path.splitext(img_path)[1]
        new = np.clip(1.4057577998008846 * img - 38.33089999653017, 0, 255).astype(np.uint8)
        _, img_binary = cv2.imencode(endswith, new)
        return img_binary

    def human_slide(self,start_x, start_y, end_x, end_y):
        """模拟人类滑动轨迹"""
        # 生成带加速度的轨迹
        points = []
        total_steps = 50
        distance_x = end_x - start_x
        distance_y = end_y - start_y
        
        previous_x = start_x  # 用于记录上一个 x 坐标值
        for i in range(total_steps):
            # 非线性进度（慢-快-慢）
            ratio = (i / total_steps)
            if ratio < 0.3:
                progress = 0.5 * (ratio / 0.3)**2
            elif ratio < 0.7:
                progress = 0.5 + (ratio - 0.3) * 1.25
            else:
                progress = 0.9 + 0.5 * ((ratio - 0.7)/0.3)**0.5
            
            # 添加随机抖动
            # offset_x = np.random.randint(-2, 3)
            # offset_y = np.random.randint(-2, 3)
            offset_x = np.random.randint(-1, 1)  # 控制抖动范围
            offset_y = np.random.randint(-1, 1)
            
            x = start_x + distance_x * min(progress, 0.99) + offset_x
            y = start_y + distance_y * min(progress, 0.99) + offset_y
         
            # 确保 x 坐标单调递增
            if x < previous_x and x < end_x:
                x = previous_x + 1
                if x > end_x:
                    x = end_x
                
            previous_x = x
            points.append((x, y))
            
            # 变速延迟（移动越快延迟越短）
            delay = 0.002 + 0.01 * (1 - abs(0.5 - ratio))
            time.sleep(delay)
        
        print(f"points: {points}")
        self.loggerPdd.info(f"points: {points}")


        # 执行滑动轨迹
        # self.d.touch.down(points[0][0], points[0][1])
        for point in points[1:]:
            self.d.touch.move(point[0], point[1])
        self.d.touch.up(points[-1][0], points[-1][1])
        # print(f"points: {points}")
        # self.loggerPdd.info(f"points: {points}")
        # self.d.swipe_points(points, duration=0.05)

    def get_shop_name(self):
        """
        获取店铺名
        :return:
        """
        try:
            xpath = '//*[@text="进店"]/preceding-sibling::android.view.ViewGroup/android.widget.LinearLayout/android.widget.TextView'

            if self.d.xpath(xpath).exists:
                shop_name = self.d.xpath(xpath).text
                self.loggerPdd.info(f'1-获取到店铺名：{shop_name}')
            else:
            #进入店铺新页面 
                shop_btn_xpath = '//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.LinearLayout[1]/android.widget.LinearLayout[1]/android.widget.LinearLayout[1]'
                if self.d.xpath(shop_btn_xpath).exists:
                    self.d.xpath(shop_btn_xpath).click()

                    time.sleep(1)
                    # self.d.xpath('//*[@text="店铺"]').click() 
                
                    
                    xpath_shop_name = '//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.widget.LinearLayout[1]/android.widget.RelativeLayout[1]/android.widget.LinearLayout[1]/android.support.v7.widget.RecyclerView[1]/android.widget.RelativeLayout[1]/android.view.ViewGroup[1]/android.widget.LinearLayout[1]/android.widget.LinearLayout[1]/android.widget.LinearLayout[1]/android.widget.LinearLayout[1]/android.widget.TextView[1]'
                    if self.d.xpath(xpath_shop_name).exists:
                        shop_name = self.d.xpath(xpath_shop_name).text
                        self.loggerPdd.info(f'2-获取到店铺名：{shop_name}')
                    else:
                        shop_name = ''
                        self.loggerPdd.info(f'3-获取到店铺名：{shop_name}')
                    
                    self.swipe_back(1) #
                else:
                    shop_name = ''
                    self.loggerPdd.info('4-因为shop_btn_xpath不存在，获取到店铺名为空')
                    # time.sleep(10000)
            
            #进入店铺新页面 测试代码
            # self.d.xpath('//*[@text="店铺"]').click() 
            # time.sleep(1)

            # content_frame = self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]').exists
            # print(content_frame)
            # ViewGroup3 = self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]').exists
            # print(ViewGroup3)
            # LinearLayout = self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.widget.LinearLayout[1]').exists
            # print(LinearLayout)
            # RelativeLayout = self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.widget.LinearLayout[1]/android.widget.RelativeLayout[1]').exists
            # print(RelativeLayout)
            # LinearLayout2 = self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.widget.LinearLayout[1]/android.widget.RelativeLayout[1]/android.widget.LinearLayout[1]').exists
            # print(LinearLayout2)
            # RecyclerView = self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.widget.LinearLayout[1]/android.widget.RelativeLayout[1]/android.widget.LinearLayout[1]/android.support.v7.widget.RecyclerView[1]').exists
            # print(RecyclerView)

            # xpath2 = '//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.widget.LinearLayout[1]/android.widget.RelativeLayout[1]/android.widget.LinearLayout[1]/android.support.v7.widget.RecyclerView[1]/android.widget.RelativeLayout[1]/android.view.ViewGroup[1]/android.widget.LinearLayout[1]/android.widget.LinearLayout[1]/android.widget.LinearLayout[1]/android.widget.LinearLayout[1]/android.widget.TextView[1]'

            # if self.d.xpath(xpath2).exists:
            #     shop_name = self.d.xpath(xpath2).text
            #     self.loggerPdd.info(f'2-获取到店铺名：{shop_name}')
            # else:
            #     shop_name = ''
            #     self.loggerPdd.info(f'3-获取到店铺名：{shop_name}')
            
            # self.swipe_back(1) #返回
            
            return shop_name
        except Exception as e:
            print(f'获取店铺名出错:{e}')
            self.loggerPdd.error(f'获取店铺名出错:{e}')
            return None

    def get_qualification_number(self):
        """
        获取资质编号
        :return:
        """
        try:
            qualification_number_str = self.d.xpath(
                '//*[@resource-id="com.sankuai.meituan:id/mil_container"]/android.webkit.WebView[1]/android.webkit.WebView[1]/android.view.View[1]/android.view.View[1]/android.widget.TextView[2]').text

            qualification_number = qualification_number_str.strip('资质编号：').strip()
            return qualification_number
        except:
            return None

    def enter_detail(self):
        self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/recycler"]/android.widget.FrameLayout[1]').click()
        time.sleep(self.get_sleep_time())

    def save_to_database(self, data):
        print(f'保存数据到数据库:{data}')
        # 连接数据库
        conn = get_mysql()
        # 创建游标对象
        cur = conn.cursor()

        # add_sql = "insert into delete_friend_table(delete_user_name,delete_user_id,delete_content,delete_time) value(%s,%s,%s,%s)"
        add_sql = f"""
            INSERT INTO {self.table_name} 
            (product, min_price, manufacture_date, expiry_date, shop, business_license_company, province, city, manufacturer, specification, approval_number, product_link, scrape_date, scrape_province, availability, credit_code, platform, search_key, number) 
            VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
        """
        # cur.execute(add_sql, (data['product'], data['min_price'], data['manufacture_date'], data['expiry_date'], data['shop'], data['business_license_company'],data['province'], data['city'], data['manufacturer'], data['specification'], data['approval_number'], data['product_link'], self.get_current_date(), data['scrape_province'], data['availability'], data['credit_code'], data['platform']))
        cur.execute(add_sql, (data['product'], data['min_price'], data['manufacture_date'], data['expiry_date'], data['shop'], data['business_license_company'],data['province'], data['city'], data['manufacturer'], data['specification'], data['approval_number'], data['product_link'], data['scrape_date'], data['scrape_province'], data['availability'], data['credit_code'], data['platform'], data['search_key'], data['number']))
        conn.commit()  # 提交数据

        print(f"存入数据库成功")

         # === 新增：更新采集计数 ===
        self.collected_count += 1
        if self.task_id:
            # 更新上报进度
            reporter.update_task_progress(
                task_id=self.task_id,
                real_count=self.collected_count
            )

    def swipe_up(self):
        """
        上滑
        :return:
        """
        screen_width = self.d.info['displayWidth']
        screen_height = self.d.info['displayHeight']
        duration_rate = random.uniform(0, 0.3)
        self.d.swipe(screen_width // 2, screen_height - 100, screen_width // 2, 100, duration=duration_rate)
        no = random.uniform(0, 1)
        if no > 0.85:
            # 有的时候卡着 再稍微往上滑一点点
            self.d.swipe_ext("up", 0.1)
            time.sleep(self.get_sleep_time())

    def swipe_back(self, no):
        """
        返回
        :param no: 回退次数
        :return:
        """
        if not self.distinct_target():
            for idx in range(no):
                self.d.press('back')
                time.sleep(self.get_sleep_time())

    def drug_price(self):
        """
        获取药品价格
        :return:
        """
        try:
            xpath = '//*[@text="¥"]/following-sibling::android.widget.TextView[1]'
            price_str = self.d.xpath(xpath).text
            price = float(re.search('[\d\.]+', price_str).group())
            print(f'获取到价格:{price}')
            return float(price)
        except Exception as e:
            print(f'提取价格出错-->{e}')
            return None
    
    def drug_price_ex(self):

        price_str = ''  #价格初始化
        ext       = ''  #初始化已选择的信息
        price     = ''
        
        button_xpath_1 = '//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.LinearLayout[1]/android.widget.LinearLayout[2]/android.widget.LinearLayout[1]/android.widget.LinearLayout[1]/android.view.ViewGroup[last()]'

        button_xpath_2 = '//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.LinearLayout[1]/android.widget.LinearLayout[2]/android.widget.LinearLayout[1]/android.widget.LinearLayout[1]/android.widget.LinearLayout[1]/android.view.ViewGroup[last()]'

        #调试
        # test_button = self.d.xpath(button_xpath_1).exists
        # print(test_button)

        # test_button_2 = self.d.xpath(button_xpath_2).exists
        # print(test_button_2)
        # time.sleep(1000)
        # if self.d.xpath('//*[@text="发起拼单"]').exists:
        #     self.d.xpath('//*[@text="发起拼单"]').click()
        # elif self.d.xpath('//*[@text="去复诊开药"]').exists:
        #     self.d.xpath('//*[@text="去复诊开药"]').click()

        if self.d.xpath(button_xpath_1).exists:
            self.d.xpath(button_xpath_1).click()
        elif self.d.xpath(button_xpath_2).exists:
            self.d.xpath(button_xpath_2).click()
        else:
            print("button1 and button_2 all not exist")
            return price, ext

        #获取是已选择还是请选择

        # select_xpath = '//*[@resource-id="android:id/content"]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.RelativeLayout[1]/android.widget.TextView[2]'
        select_xpath_1 = '//*[@resource-id="android:id/content"]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.TextView[last()]'
        select_xpath_2 = '//*[@resource-id="android:id/content"]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.RelativeLayout[1]/android.widget.TextView[last()]'
        select_xpath_3 = '//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.view.ViewGroup[2]/android.widget.LinearLayout[1]/android.view.ViewGroup[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.view.ViewGroup[1]/android.widget.TextView[last()]'
        select_xpath_3_2 = '//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.view.ViewGroup[2]/android.widget.LinearLayout[1]/android.view.ViewGroup[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.view.ViewGroup[1]/android.widget.TextView[last()-1]'

        # select_xpath1 = self.d.xpath(select_xpath_1).exists
        # print(select_xpath1)

        # select_xpath2 = self.d.xpath(select_xpath_2).exists
        # print(select_xpath2)
        
        # select_xpath3 = self.d.xpath(select_xpath_3).exists
        # print(select_xpath3)

        # time.sleep(1000)


        price_xpath_1  = '//*[@resource-id="android:id/content"]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.TextView[1]'
        price_xpath_2 = '//*[@resource-id="android:id/content"]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.RelativeLayout[1]/android.widget.TextView[1]'
        price_xpath_3 = '//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.view.ViewGroup[2]/android.widget.LinearLayout[1]/android.view.ViewGroup[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.view.ViewGroup[1]//android.widget.TextView[1]'

        if self.d.xpath(select_xpath_1).exists:
            text1 = self.d.xpath(select_xpath_1).text

            print(f"select_xpath_1--text1={text1}")

            if '已选' in text1:
                if self.d.xpath(price_xpath_1).exists:
                    price_str = self.d.xpath(price_xpath_1).text
                    print(f"select_xpath_1--price_str-1={price_str}")
                else:
                    print("select_xpath_1--price_xpath_1-1 not exist")
                
                ext = text1
            elif '请选择' in text1:
                #需要再下面点击选择
                scroll_xpath_1 =   '//*[@resource-id="android:id/content"]//android.widget.ScrollView[1]/android.widget.LinearLayout[1]/android.support.v7.widget.RecyclerView[1]/android.widget.LinearLayout[last()]/android.view.ViewGroup[1]/android.view.ViewGroup[last()]'

                if self.d.xpath(scroll_xpath_1).exists:
                    self.d.xpath(scroll_xpath_1).click
                    time.sleep(2) #延时2秒钟，选择了之后价格会刷新
                    if self.d.xpath(select_xpath_1).exists:
                        text2 = self.d.xpath(select_xpath_1).text
                        if '已选' in text2:
                            print(f"select_xpath_1--已选择2:text2={text2}")
                            if self.d.xpath(price_xpath_1).exists:
                                price_str = self.d.xpath(price_xpath_1).text
                                print(f"select_xpath_1--price_str-2={price_str}")
                            else:
                                print("select_xpath_1--price_xpath_1-2 not exist")

                            ext = text2
                else:
                    print("select_xpath_1--scroll_xpath_1 not exist")
        elif self.d.xpath(select_xpath_2).exists:
            text1 = self.d.xpath(select_xpath_2).text
            print(f"xpath2--text1={text1}")
            if '已选' in text1:
                ext = text1
                if self.d.xpath(price_xpath_2).exists:
                    price_str = self.d.xpath(price_xpath_2).text
                    print(f"select_xpath_2--price_str-2={price_str}")
                else:
                    print("select_xpath_2--price_xpath_2-1 not exist")
            elif '请选择' in text1:
                print('come in here')
                #需要再下面点击选择
                scroll_xpath_1 = '//*[@resource-id="android:id/content"]//android.widget.ScrollView[1]/android.widget.LinearLayout[1]/android.support.v7.widget.RecyclerView[1]/android.widget.LinearLayout[last()]/android.view.ViewGroup[1]/android.view.ViewGroup[1]'

                if self.d.xpath(scroll_xpath_1).exists:
                    print("scroll_xpath_1 exists")
                    self.d.xpath(scroll_xpath_1).click()
                    time.sleep(2) #延时2秒钟，选择了之后价格可能会刷新
                    if self.d.xpath(select_xpath_2).exists:
                        text2 = self.d.xpath(select_xpath_2).text
                        if '已选' in text2:
                            ext = text2
                            print(f"select_xpath_2--已选择2:text2={text2}")
                            if self.d.xpath(price_xpath_2).exists:
                                price_str = self.d.xpath(price_xpath_2).text
                                print(f"select_xpath_2--price_str-2={price_str}")
                            else:
                                print("select_xpath_2--price_xpath_2-2 not exist")
                else:
                    print("scroll_xpath_1 not exists")
            else:
                print("not exist 请选择 or 已选")
        elif self.d.xpath(select_xpath_3).exists:
            text1 = self.d.xpath(select_xpath_3).text
            print(f"xpath3--text1-1={text1}")
            
            if ('请选择' not in text1) and ('已选' not in text1):
                text1 = self.d.xpath(select_xpath_3_2).text
                print(f"xpath3--text1-2={text1}")

            if '已选' in text1:
                ext = text1
                if self.d.xpath(price_xpath_3).exists:
                    price_str = self.d.xpath(price_xpath_3).text
                    print(f"select_xpath_3--price_str-3-3-1={price_str}")
                else:
                    print("select_xpath_3--price_xpath_3-3-1 not exist")
            elif '请选择' in text1:
                print('come in here')
                #需要再下面点击选择
                scroll_xpath_1 = '//*[@resource-id="android:id/content"]//android.widget.ScrollView[1]/android.widget.LinearLayout[1]/android.support.v7.widget.RecyclerView[1]/android.widget.LinearLayout[last()]/android.view.ViewGroup[1]/android.view.ViewGroup[1]'
                recycler_view_xpath =  '//*[@resource-id="android:id/content"]//android.support.v7.widget.RecyclerView[1]/android.widget.LinearLayout[1]/android.widget.LinearLayout[last()]/android.view.ViewGroup[1]/android.view.ViewGroup[1]'

                if self.d.xpath(scroll_xpath_1).exists:
                    print("scroll_xpath_1 exists")
                    self.d.xpath(scroll_xpath_1).click()
                    time.sleep(2) #延时2秒钟，选择了之后价格可能会刷新
                    if self.d.xpath(select_xpath_3).exists:
                        text2 = self.d.xpath(select_xpath_3).text
                        if '已选' in text2:
                            ext = text2
                            print(f"select_xpath_3--已选择2:text2={text2}")
                            if self.d.xpath(price_xpath_3).exists:
                                price_str = self.d.xpath(price_xpath_3).text
                                print(f"select_xpath_3--price_str-3-2={price_str}")
                            else:
                                print("select_xpath_3--price_xpath_3-3-2 not exist")
                elif self.d.xpath(recycler_view_xpath).exists:
                    self.d.xpath(recycler_view_xpath).click()
                    time.sleep(2) #延时2秒钟，选择了之后价格可能会刷新
                    if self.d.xpath(select_xpath_3).exists:
                        text2 = self.d.xpath(select_xpath_3).text
                        if '已选' in text2:
                            ext = text2
                            print(f"select_xpath_3--已选择2:text2={text2}")
                            if self.d.xpath(price_xpath_3).exists:
                                price_str = self.d.xpath(price_xpath_3).text
                                print(f"select_xpath_3--price_str-3-3={price_str}")
                            else:
                                print("select_xpath_3--price_xpath_3-3-3 not exist")

                else:
                    print("scroll_xpath_1 not exists")
            else :
                print(f"xpath3--text1-不包含请选择和已选择")

        else :
            print("select_xpath_1 and select_xpath_2 and select_xpath_3 all not exist")

        if price_str:
            # price = float(re.search('[\d\.]+', price_str).group())  
            match = re.search(r'¥([\d\.]+)', price_str)
            if match:
                price = float(match.group(1))
            else:
                price = ''        

            # price = float(re.search(r'¥([\d\.]+)', price_str).group(1))          
            print(f'获取到价格:{price}')
            

        
        print(f"ext={ext}")

        self.swipe_back(1) #

        # time.sleep(1000)
        return price, ext

    def restart_uiautomator_services(self, device_id):
        """
        重启atx的uiautomator 服务
        :param device_id:
        :return:
        """
        stop_uiautomator_services = f'adb -s {device_id} shell /data/local/tmp/atx-agent server -d --stop'
        start_uiautomator_services = f'adb -s {device_id} shell /data/local/tmp/atx-agent server -d'
        # result = subprocess.run(stop_uiautomator_services, capture_output=True, text=True, shell=True)
        # print(result.stdout)
        subprocess.run(stop_uiautomator_services, capture_output=True, text=True, shell=True)
        time.sleep(self.get_sleep_time())
        subprocess.run(start_uiautomator_services, capture_output=True, text=True, shell=True)
        time.sleep(self.get_sleep_time())

    

    def connect_devices(self, device_id):
        """
        连接设备
        :return:
        """
        try:
            self.d = u2.connect_usb(device_id)
            # 设置隐形等待时间
            # self.d.implicitly_wait(5)
            self.restart_uiautomator_services(device_id)
            print(f'连接到设备:{device_id}')
        except Exception as e:
            print(f'{device_id} 连接错误: {e}')
            raise Exception(e)

    def get_ocr_res(self, img):
        try:
            image = self.remove_watermark(img)
            # image_file = open(img,'wb')
            # image_file.write(image)
            # res_image = self.client.basicAccurate(image)  # 高精度
            res_image = self.client.basicGeneral(image)
            # print(f'百度api返回结果:{res_image}')
            # print(res_image.get('words_result', ''))
            # new_dic = dict()
            data = res_image.get('words_result', '')
            print(f'百度api返回结果:{data}')

            # full_text = ';'.join(item['words'] for item in data)
            # address = ''
            # for item in data:
            #     if '企业注册号' in item['words']:
            #         print('come in 111')
            #         reg_number = item['words'].split('：', 1)[1].strip()
            #     elif '企业名称' in item['words']:
            #         print('come in 222')
            #         company_name = item['words'].split('：', 1)[1].strip()
            #     elif '所：' in item['words']:
            #         print('come in 333')
            #         address = item['words'].split('：', 1)[1].strip()

            # # 输出结果
            # print("企业注册号:", reg_number)
            # print("企业名称:", company_name)
            # print("住所:", address)
            return data
        except:
            return None
        
    # def get_ocr_res(self, img):
    #     try:
    #         #img地址
    #         print(f'开始识别图片:{img}')
    #         request_url = "https://aip.baidubce.com/rest/2.0/ocr/v1/business_license"
    #         # 二进制方式打开图片文件
    #         f = open(img, 'rb')
    #         img = base64.b64encode(f.read())

    #         # img = self.remove_watermark(img)

    #         # print(f'图片转base64成功:{img}')
    #         params = {"image": img}
    #         # access_token = get_access_token()
    #         request_url = request_url + "?access_token=" + self.access_token
    #         headers = {'content-type': 'application/x-www-form-urlencoded'}
    #         response = requests.post(request_url, data=params, headers=headers)
    #         print(f'请求百度api成功{response}')
    #         if response:
    #             res = response.json()
    #             print(f'百度api返回结果{res}')
    #             new_dic = dict()
    #             for ite in res['words_result'].keys():
    #                 new_dic[ite] = res['words_result'][ite]['words']
    #             print('资质数据信息', new_dic)
    #             return new_dic
    #         else:
    #             return None
    #     except:
    #         return None

    def screenshot_the_business_license(self):
        screenshot_path = 'screenshot1.png'
        self.d.screenshot(screenshot_path)
        img = cv2.imread(screenshot_path)
        # 指定裁剪区域 (left, top, right, bottom)
        left = 0
        top = 480
        right = 720
        bottom = 1420
        cropped_img = img[top:bottom, left:right]
        cropped_screenshot_path = 'cropped_screenshot.png'
        cv2.imwrite(cropped_screenshot_path, cropped_img)
    
    def screenshot_the_shop_qualifications(self):
        screenshot_path = 'screenshot2.png'
        self.d.screenshot(screenshot_path)
        img = cv2.imread(screenshot_path)
        # 指定裁剪区域 (left, top, right, bottom)
        left = 0
        top = 480
        right = 720
        bottom = 1420
    
    
    def first_screenshot_the_verify(self):
        screenshot_verify_path = 'first_screenshot_verify.png'
        self.d.screenshot(screenshot_verify_path)
        img = cv2.imread(screenshot_verify_path)

        ocr_res = self.get_ocr_res('first_screenshot_verify.png')
        event = '' #事件类型：滑块验证、计算结果输入
        if ocr_res:
            for item in ocr_res:
                if '拖动滑块完成' in item['words']:
                    print("滑块验证")
                    event = '滑块验证'
                    break
        
         # 指定裁剪区域 (left, top, right, bottom)
        if event == '滑块验证':
            left = 118
            top = 478
            right = 602
            bottom = 722
        else:
            left = 118
            top = 478
            right = 602
            bottom = 722     
            cropped_verify_img = img[top:bottom, left:right]
            cropped_verify_creenshot_path = 'first_cropped_verify_screenshot.png'
            cv2.imwrite(cropped_verify_creenshot_path, cropped_verify_img)
        return event

    def slide_second_screenshot_the_verify(self):
        screenshot_verify_path = 'slide_second_screenshot_verify.png'
        self.d.screenshot(screenshot_verify_path)
        img = cv2.imread(screenshot_verify_path)
        left = 118
        top = 478
        right = 602
        bottom = 722
        cropped_verify_img = img[top:bottom, left:right]
        cropped_verify_creenshot_path = 'second_slide_cropped_verify_screenshot.png'
        cv2.imwrite(cropped_verify_creenshot_path, cropped_verify_img)
    
    def second_screenshot_the_verify(self):
        screenshot_verify_path = 'second_screenshot_verify.png'
        self.d.screenshot(screenshot_verify_path)
        img = cv2.imread(screenshot_verify_path)

        ocr_res = self.get_ocr_res('second_screenshot_verify.png')

        print(f'second_ocr_res:{ocr_res}')
        
        result = ''

        if ocr_res:
            result = '验证成功'
            for item in ocr_res:
                if '验证成功' in item['words']:
                    result = '验证成功'
                    break
                elif '验证不成功' in item['words']:
                    result = '验证不成功'
                    break
        return result
    
    def screenshot_business_license(self,shop_name):
        screenshot_lincense_path = 'license_screenshot.png'
        self.d.screenshot(screenshot_lincense_path)
        img = cv2.imread(screenshot_lincense_path)

        #裁剪
        left = 0
        top = 160
        right = 720
        bottom = 1000
        cropped_verify_img = img[top:bottom, left:right]

        cropped_screenshot_path = 'D:\\work\\dfwy_spider\\drug_data\\pdd\\screenshot\\' + shop_name + '.png'
        cv2.imwrite(cropped_screenshot_path, cropped_verify_img)
        return cropped_screenshot_path

    def drug_slide(self, distance):

        print(f"滑动的distance= {distance}")
        # 获取设备上所有窗口的层次结构
        dump = self.d.dump_hierarchy()
        print(f"drug_slide-111:{dump}")
        # 解析 JSON 数据
        root = ET.fromstring(dump)
        # dump_data = json.loads(dump)
        print("drug_slide-222")
        # 查找包含 meco.webkit.WebView 的元素
        
        webview_elements = root.findall(".//node[@class='meco.webkit.WebView']")

        print("drug_slide-333")
        if webview_elements:
            print("找到 WebView 元素:", webview_elements[0].attrib)
             # 获取WebView的bounds信息
            webview_bounds = webview_elements[0].attrib['bounds']
            print("WebView bounds:", webview_bounds)
             # 假设你需要操作的元素在WebView中的XPath为'//node[@class="meco.webkit.WebView"]'
            webview_element_xpath = '//node[@class="meco.webkit.WebView"]'
            # 获取WebView内部元素
            webview_inner_elements = self.d.xpath(webview_element_xpath)
            if webview_inner_elements:
                # 拖动元素300像素
                start_x = webview_inner_elements[0].info['bounds'][0]
                start_y = webview_inner_elements[0].info['bounds'][1]
                end_x = start_x + distance
                end_y = start_y
                self.d.swipe(start_x, start_y, end_x, end_y)
                print("拖动成功")
            else:
                print("未找到需要拖动的元素")
        else:
            print("未找到 WebView 元素")

    def get_title(self):
        try:
            print('开始提取标题')
            time.sleep(self.get_sleep_time())
            title_xpath = '//*[@resource-id="com.xunmeng.pinduoduo:id/tv_title"]'
            if self.d.xpath(title_xpath).exists:
                title = self.d.xpath(title_xpath).info['contentDescription'].strip()
            else:
                return None
            # title = self.d.xpath('//*[@resource-id="com.xunmeng.pinduoduo:id/tv_title"]').info['contentDescription'].strip()
            print(f'提取到标题：{title}')
            return title
        except Exception as e:
            print(f'获取标题出错：{e}')
            return None
        # 从里面匹配出药品名和规格
        # drugs_name
        # specifications
        # match = re.search(r'([^\d]+)([\d\D]+)', title)

        # match = re.search(r'(\[[^\]]+\])(.+?)(\d+.*)', title)
        # if match:
        #     drugs_name = match.group(1).strip() + match.group(2).strip()
        #     specifications = match.group(3).strip()
        #     print("药品名:", drugs_name)
        #     print("规格:", specifications)
        #     print('完整药名:', drugs_name + specifications)
        #     return drugs_name, specifications
        # else:
        #     print("没有匹配到预期格式")

    def enter_shop(self):
        """
        进店，方便提取资质环境
        :return:
        """
        # self.d.xpath('//*[@text="进店"]').click()
        self.d.xpath('//*[@text="店铺"]').click()
        time.sleep(self.get_sleep_time())

    def enter_shoper(self):
        """
        进入商家
        :return:
        """
        self.d.xpath('//*[@text="商家"]').click()
        time.sleep(self.get_sleep_time())

    def scan_shoper_license(self):
        self.d.xpath('//*[@text="查看商家资质"]').click()
        time.sleep(self.get_sleep_time())

    def data_is_exists(self, data):
        # 1. 验证必要字段
        required_keys = ['search_key', 'min_price', 'shop', 'scrape_date', 'platform']
        if not all(key in data for key in required_keys):
            missing = [key for key in required_keys if key not in data]
            # logging.error(f"缺少必要字段: {', '.join(missing)}")
            print(f"缺少必要字段: {', '.join(missing)}")
            return None
        
        try:
            # 连接数据库
            conn = get_mysql()

            # 创建游标对象
            cur = conn.cursor()

            # query_sql = f"SELECT * FROM {self.table_name} WHERE product = '{data['product']}' AND min_price = '{data['min_price']}' AND shop = '{data['shop']}' AND scrape_date = '{data['scrape_date']}' AND platform = '{data['platform']}'"

            # cur.execute(query_sql)

            query_sql = """
                SELECT * FROM {} 
                WHERE search_key = %s 
                AND min_price = %s 
                AND shop = %s 
                AND scrape_date = %s 
                AND platform = %s
            """.format(self.table_name)

            cur.execute(query_sql, (
                data['search_key'],
                data['min_price'],
                data['shop'],
                data['scrape_date'],
                data['platform']
            ))

            result = cur.fetchone()

            return bool(result)  # 如果存在返回True，否则False
        except Exception as e:
            print(f"MySQL 错误: {str(e)}")
    
        #验证店铺信息是否在数据库中已存在
    def shop_is_exists_database(self, shop):
        try:
            # 连接数据库
            conn = get_mysql()

            # 创建游标对象
            cur = conn.cursor()
            query_sql = """
                SELECT * FROM {} 
                WHERE  shop = %s 
            """.format(self.shop_table_name)

            cur.execute(query_sql, (
                shop
            ))

            result = cur.fetchone()

            return bool(result)  # 如果存在返回True，否则False
        except Exception as e:
            print(f"MySQL 错误: {str(e)}")

    def wait_if_verifying(self, monitor, timeout=120):
        """验证码处理期间阻塞主线程"""
        start = time.time()
        while monitor.pausing.is_set() and time.time() - start < timeout:
            time.sleep(1)

    # def safe_xpath(self, xpath, timeout=10):
    #     """线程安全 xpath 查找"""
    #     self.wait_if_verifying(self.monitor)
    #     return self.d.xpath(xpath).wait(timeout=timeout)
    
    def wait_for_ready(self, monitor, timeout=86400):
        """进入每一页前都先等验证码"""
        start = time.time()
        while monitor.pausing.is_set() and time.time() - start < timeout:
            time.sleep(1)

        # 额外保险：如果验证码突然在这一秒才弹，再主动扫一次
        monitor.check_and_handle_popup()

    def safe_list(self, xpath, monitor):
        """线程安全地拿商品列表"""
        self.wait_for_ready(monitor)
        return self.d.xpath(xpath).all()

    def safe_exec(self, func, *args, **kwargs):
        """
        万能安全壳：执行 func 前检查验证码，
        若监控线程已置位 pausing，则一直阻塞直到放行。
        """
        while self.monitor.pausing.is_set():
            time.sleep(1)
        # 执行真正逻辑
        return func(*args, **kwargs)

    def get_instructions_data(self):
        """
        确定有详情页之后之后，提取所有的详情页数据
        :return:
        """
        #下面的for循环已经有滑动的操作了，不要一进来就滑动。
        # self.d.swipe_ext("up", scale=0.5) 
        for i in range(8):
            # if self.d(textStartsWith="查看全部").exists:
            if self.d.xpath('//*[@text="品牌"]').exists or self.d.xpath('//*[@text="药品通用名"]').exists:
                self.d.swipe_ext("up", scale=0.1)
                print('开始采集详情数据')
                break
            # screen_width = self.d.info['displayWidth']
            # screen_height = self.d.info['displayHeight']
            # self.d.swipe(screen_width // 2, screen_height - 400, screen_width // 2, 400, duration=0.2)
            self.d.swipe_ext("up", scale=0.5)
            time.sleep(self.get_sleep_time())

        # 点击查看全部
        if self.d.xpath('//*[@text="品牌"]').exists:
            self.d.xpath('//*[@text="品牌"]').click()
        else:
            self.d.xpath('//*[@text="药品通用名"]').click()
        time.sleep(self.get_sleep_time())
        attr = dict()
        # # 获取详情页信息
        xpath = '//*[starts-with(@text,"商品参数")]/parent::*/parent::*/following-sibling::*/*/*/android.view.ViewGroup//android.widget.TextView'
        ddd = self.d.xpath(xpath).all()
        for i in range(0, len(ddd), 2):
            group = ddd[i:i + 2]
            attr[group[0].text] = group[1].text
        # 截图获取未获取到的数据
        # if not all(i in ['有效期', '生产企业', '批准文号', '药品规格', '产品规格'] for i in attr.keys()):
        if not all(i in ['有效期', '生产企业', '批准文号', '药品规格'] for i in attr.keys()):
            self.d.swipe_ext("up", 0.4)
            time.sleep(self.get_sleep_time())
            xpath = '//*[starts-with(@text,"商品参数")]/parent::*/parent::*/following-sibling::*/*/*/android.view.ViewGroup//android.widget.TextView'
            ddd = self.d.xpath(xpath).all()
            for i in range(0, len(ddd), 2):
                group = ddd[i:i + 2]
                attr[group[0].text] = group[1].text
        print(f'当前说明书规格参数:{attr}')
        res_data = {
            # "有效期": attr.get('有效期',''),
            # "生产单位": attr['生产企业'],
            # "批准文号": attr['批准文号'],
            # "产品规格": attr.get('药品规格') if attr.get('药品规格', '') else attr.get('药品规格')
            "有效期": attr.get('有效期',''),
            "生产单位": attr.get('生产企业', ''),
            "批准文号": attr.get('批准文号', ''),
            "产品规格": attr.get('药品规格', '') 
        }
        print(f'当前规格参数字典数据:{res_data}')
        return res_data

    def has_instructions(self):
        """
        是否有详情页
        :return:如果有详情页返回True，否则返回False
        """
        # 没有说明书的无法采集具体数据
        max_attempts = 12 # 最大尝试次数
        attempt = 0  # 当前尝试次数

        while attempt < max_attempts:   
            time.sleep(0.5)
            xpath = '//*[@text="商品详情"]'
            is_has_instructions = self.d.xpath(xpath).exists
            if is_has_instructions:
                return True  # 如果找到“商品详情”，则返回True
            self.d.swipe_ext("up", 0.3)
            attempt += 1

        return False  # 如果尝试次数达到最大次数，则返回False
        # time.sleep(self.get_sleep_time())
        # xpath = '//*[@text="商品详情"]'
        # is_has_instructions = self.d.xpath(xpath).exists
        # return 
    
    def has_shop_qualifications(self):
        max_attempts = 3 # 最大尝试次数
        attempt = 0  # 当前尝试次数
        while attempt < max_attempts:   
            time.sleep(0.5)
            xpath = '//*[@text="查看全部"]'
            is_has_search_all = self.d.xpath(xpath).exists
            if is_has_search_all:

                elements = self.d.xpath(xpath).all()
                count = len(elements)
                print(f"页面上共有 {count} 个 '查看全部' 元素")
                if count >= 2:
                    second_element = elements[1]
                    bounds = second_element.bounds
                else:
                    element = self.d.xpath(xpath).get()
                    bounds = element.bounds

                print(f'bounds:{bounds}')
                # time.sleep(1000000)
                # 获取元素的坐标和尺寸
                x1, y1, x2, y2 = bounds  # x1, y1 是左上角坐标，x2, y2 是右下角坐标
                element_x = (x1 + x2) / 2  # 元素的中心 x 坐标
                element_y = (y1 + y2) / 2  # 元素的中心 y 坐标

                if element_y > 500:
                    self.d.swipe(element_x, element_y, element_x, 500, 1)
                    #画完之后再去一次坐标
                    elements_ex = self.d.xpath(xpath).all()
                    count_ex = len(elements_ex)
                    print(f"第二次页面上共有 {count_ex} 个 '查看全部' 元素")
                    if count_ex >= 2:
                        second_element_ex = elements[1]
                        bounds_ex = second_element_ex.bounds
                    else:
                        element_ex = self.d.xpath(xpath).get()
                        bounds_ex = element_ex.bounds
                    print(f'bounds_ex:{bounds_ex}')
                    
                    x1, y1, x2, y2 = bounds_ex  # x1, y1 是左上角坐标，x2, y2 是右下角坐标
                    element_x = (x1 + x2) / 2  # 元素的中心 x 坐标
                    element_y = (y1 + y2) / 2  # 元素的中心 y 坐标
                
                time.sleep(self.get_sleep_time())

                target_x = element_x
                target_y = element_y + 80
                
                print(f'目标坐标：{target_x}, {target_y}')
                #点击图片
                self.d.click(target_x, target_y)
                time.sleep(self.get_sleep_time())
                #获取图片内容
                self.screenshot_the_shop_qualifications()
                ocr_res = self.get_ocr_res('screenshot2.png')
                print(f'ocr_res:{ocr_res}')
                time.sleep(100000)

                return True  # 如果找到“商品详情”，则返回True
            self.d.swipe_ext("up", 0.1)
            attempt += 1

        return False  # 如果尝试次数达到最大次数，则返回False

    def get_license_info_ex(self, shop_name):
        # print('开始获取商家资质信息')
        self.enter_shop() #点击店铺
        #点击店铺图片
        xpath_shop_image = '//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.widget.LinearLayout[1]/android.widget.RelativeLayout[1]/android.widget.LinearLayout[1]/android.support.v7.widget.RecyclerView[1]/android.widget.RelativeLayout[1]/android.view.ViewGroup[1]/android.widget.LinearLayout[1]/android.widget.LinearLayout[1]/android.widget.ImageView[1]'
        if self.d.xpath(xpath_shop_image).exists:
            self.d.xpath(xpath_shop_image).click()
            time.sleep(self.get_sleep_time())
            #从弹窗页获取店铺资质的位置
            for i in range(10):
                if self.d.xpath('//*[@text="店铺资质"]').exists:
                    print('店铺资质存在1')
                    break
                self.d.swipe_ext('up', 0.3)
                time.sleep(1)
                if self.d.xpath('//*[@text="店铺资质"]').exists:
                    print('店铺资质存在2')
                    break
            if self.d.xpath('//*[@text="已上传"]').exists:
                self.d.xpath('//*[@text="已上传"]').click()
            else:
                self.d.xpath('//*[@text="店铺资质"]').click()
            time.sleep(self.get_sleep_time())
            
            xpath_pop_window = '//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/meco.webkit.WebView[1]' 
            #等待验证弹窗出现
            for i in range(10):    
                if self.d.xpath(xpath_pop_window).exists:
                    print(f'第{i}次安全验证弹窗存在')
                    break
                else:
                    print(f'第{i}次安全验证弹窗不存在')
                    time.sleep(self.get_sleep_time())

            time.sleep(10)
            
            #第一次截屏
            event = self.first_screenshot_the_verify()

            #用ocr的方式识别当前是拖动还是点击

            # ocr_res = self.get_ocr_res('screenshot_verify.png')

            # event = '' 
            # if ocr_res:
            #     for item in ocr_res:
            #         if '拖动滑块完成' in item['words']:
            #             print("滑块验证")
            #             event = '滑块验证'
            #             break
                    

            # print("ocr_res end")    

            if event == '滑块验证':
                #需要点击》按钮不懂后截屏，获取
                self.d.touch.down(110, 780)
                time.sleep(0.5)
                #截屏
                event = self.slide_second_screenshot_the_verify()


                # result = slide_verify('first_cropped_verify_screenshot.png') second_slide_cropped_verify_screenshot
                result = slide_verify('second_slide_cropped_verify_screenshot.png') 
                result = int(result)
                print(f'滑动距离：{result}')
                print('开始滑动')
                # internel = 1000
                # self.d.touch.move_to(110 + result, 780, duration=internel)
                # self.d.touch.up(110 + result, 780)
                self.human_slide(110, 780, 110 + result, 780)
                print('滑动结束')
                time.sleep(self.get_sleep_time())
                #滑完之后怎么判断是否验证成功？
                second_resut = self.second_screenshot_the_verify()

                if second_resut == '验证成功':

                    time.sleep(8)

                    cropped_screenshot_path = self.screenshot_business_license(shop_name)

                    ocr_res = self.get_ocr_res(cropped_screenshot_path)
                    print(f'ocr_res:{ocr_res}')

                    company_name = ''
                    reg_number = ''
                    address = ''
                    if ocr_res:
                        for item in ocr_res:
                            if '企业注册号' in item['words']:
                                # print('come in 111')
                                reg_number = item['words'].split('：', 1)[1].strip()
                            elif '企业名称' in item['words']:
                                # print('come in 222')
                                company_name = item['words'].split('：', 1)[1].strip()
                            elif '所：' in item['words']:
                                # print('come in 333')
                                address = item['words'].split('：', 1)[1].strip()

                    # 输出结果
                    print("企业注册号:", reg_number)
                    print("企业名称:", company_name)
                    print("住所:", address)

                    print("yanzhenghcenggong")
                    # 截取图片保存 第三次截屏，保存到本地

                


                       



            #将图片传给第三方verify接口得到需要移动的距离
            #result = slide_verify('cropped_verify_screenshot.png')
            #print(f'滑动距离：{result}')

            # self.drug_slide(340)

            # print('开始滑动')
            # self.d.swipe(120, 760, 460, 760, 0.3)
            # print('滑动结束')



            # time.sleep(1000000)  
            #截图获取需要验证的内容
                    

            


    def get_license_info(self):
        self.enter_shop()
        self.enter_shoper()
        self.scan_shoper_license()
        # 获取资质编码
        qualification_number = self.get_qualification_number()
        if qualification_number:
            table_license_info = self.get_table_license_info(qualification_number)
            if table_license_info:
                return {
                    '单位名称': table_license_info[0],
                    '地址': table_license_info[1],
                    '社会信用代码': table_license_info[2]
                }
            else:
                # operate_no = random.randint(0, 1)
                self.d.click(0.603, 0.27)
                # if operate_no == 0:
                #     self.d.xpath('//*[@text="营业执照"]').click()
                # else:
                #     self.d.click(0.603, 0.27)
                time.sleep(self.get_sleep_time())
                self.screenshot_the_business_license()
                ocr_res = self.get_ocr_res('cropped_screenshot.png')
                return ocr_res
        # operate_no = random.randint(0, 1)
        self.d.click(0.603, 0.27)
        # if operate_no == 0:
        #     self.d.xpath('//*[@text="营业执照"]').click()
        # else:
        #     self.d.click(0.603, 0.27)
        time.sleep(self.get_sleep_time())
        self.screenshot_the_business_license()
        ocr_res = self.get_ocr_res('cropped_screenshot.png')
        return ocr_res

    def distinct_target(self):
        result = False

        is_position = self.d.xpath('//*[@content-desc="拍照搜索"]').exists
        is_position2 = self.d.xpath('//*[@text="年货节大促"]').exists

        is_position3 = self.d.xpath('//*[@text="筛选"]').exists
        is_position4 = self.d.xpath('//*[@text="回头客常拼"]').exists

        list_page_xpath = '//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[2]/android.view.ViewGroup[1]//android.widget.LinearLayout[1]/android.support.v7.widget.RecyclerView[1]'

        is_position_new = self.d.xpath(list_page_xpath).exists
        print(f'is_position_new={is_position_new}')

        if is_position or is_position2 or is_position3 or is_position4 or is_position_new:
            result = True

        return result

    def click_element_with_retry(self, xpath, max_retries=5, timeout=5):
        """
        带重试机制的点击函数
        """
        for attempt in range(max_retries):
            try:
                if self.d.xpath(xpath).exists:
                    self.d.xpath(xpath).click()
                    print(f"第{attempt+1}次尝试点击成功")
                    return True
                else:
                    print(f"第{attempt+1}次尝试：元素不存在")
            except Exception as e:
                print(f"第{attempt+1}次尝试失败: {e}")
            
            if attempt < max_retries - 1:
                time.sleep(1)  # 等待1秒后重试
        
        print(f"经过{max_retries}次尝试后点击失败")
        return False

    def enter_target_page(self):
        self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]').click()
        time.sleep(self.get_sleep_time())
        self.d(className='android.widget.EditText').click()
        time.sleep(self.get_sleep_time())
        self.d.send_keys(self.search_key, clear=True)
        time.sleep(self.get_sleep_time())
        self.d.xpath('//*[@text="搜索"]').click()
        time.sleep(self.get_sleep_time())

        #点击价格
        self.click_element_with_retry('//*[@text="价格"]')
        # self.d.xpath('//*[@text="价格"]').click()
        time.sleep(self.get_sleep_time())

    """暂不用该功能
    def get_table_license_info(self, qualification_number):
        try:
            sql = f'select business_license_company,city,credit_code from mt_drug  where credit_code = "{qualification_number}"'
            self.mysql_client.cur.execute(sql)
            res = self.mysql_client.cur.fetchone()
            return res
        except:
            return None
    """
    def get_clipboard(self):
        self.loggerPdd.info(f"Clipboard content:{self.d.clipboard}")  # 打印调试信息
        clipboard_content = self.d.clipboard
        if clipboard_content is None:
            return ''
        return clipboard_content.strip()
    
    def clear_clipboard(self):
        self.d.set_clipboard("")

    def get_product_link(self):
        product_link = ''
        print('开始获取商品链接')

        content_frame = self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]').exists
        print(content_frame)
        
        relative_layout = self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]').exists
        print(relative_layout)

        relative_layout2 = self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.RelativeLayout[1]').exists
        print(relative_layout2)

        Frame_Layout = self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[2]').exists
        print(Frame_Layout)
        ImageView = self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[2]/android.view.View[1]').exists
        print(ImageView)

        ImageView2 = self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[3]/android.view.View[1]').exists
        print(ImageView2)
        # time.sleep(10000)


        '''
        if self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[2]/android.view.View[1]').exists:
            self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[2]/android.view.View[1]').click()
            print('进入分享成功')
            time.sleep(1)
            #先清除剪切板的数据
            # self.clear_clipboard()
            #需要增加从右往左的滑动
            # self.d.swipe_ext("left", 0.5)
            print('开始滑动')
            self.d.swipe(400, 1250, 100, 1250, 0.2)
            time.sleep(0.2)
            if self.d.xpath('//*[@text="复制链接"]').exists:
               self.d.xpath('//*[@text="复制链接"]').click()
               print('点击复制链接')             
            # self.d.xpath('//*[@text="复制链接"]').click_exists()
            # self.d.xpath('//*[contains(@text="复")]').click_exists()
            # time.sleep(1)
            product_link = self.get_clipboard()
            time.sleep(0.5)
            print(f'商品链接:{product_link}')
        elif self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[3]/android.view.View[1]').exists:
            self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[3]/android.view.View[1]').click()
            print('进入分享成功111')
            time.sleep(1)
            print('开始滑动')
            self.d.swipe(400, 1250, 100, 1250, 0.2)
            time.sleep(0.2)
            if self.d.xpath('//*[@text="复制链接"]').exists:
               self.d.xpath('//*[@text="复制链接"]').click()
               print('点击复制链接')             

            product_link = self.get_clipboard()
            time.sleep(0.5)
            print(f'商品链接:{product_link}')
        else:
            print('进入分享失败')

        time.sleep(10000)
        '''

        # 多种可能的“分享”按钮
        dots_xpaths = [
            # '//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[2]/android.view.View[1]',
            '//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[last()]/android.view.View[1]',
            # '//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[2]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[2]/android.view.View[1]',
            # '//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[2]/android.widget.RelativeLayout[2]/android.widget.FrameLayout[3]/android.widget.ImageView[1]',
        ]

        max_retry = 5        # 最多尝试次数
        for idx in range(1, max_retry + 1):
            if product_link:              # 已经拿到则退出
                break

            for xp in dots_xpaths:
                if self.d.xpath(xp).exists:
                    # print(f'{idx}-进入分享点点点')
                    self.loggerPdd.info(f'{idx}-进入分享点点点')

                    self.d.xpath(xp).click()
                    time.sleep(1)
                    # self.d.xpath('//*[@text="分享商品"]').click_exists()
                    # time.sleep(0.2)
                    # print('开始滑动')
                    self.loggerPdd.info('开始滑动')
                    if (self.device_id == '2e58510' or self.device_id == 'fcb3c749' or self.device_id == 'ea4e4eb8' or self.device_id == '95b2c764' or 
                        self.device_id == '369dcf96' or self.device_id == 'ZDQWUSSWBEDI896T' or self.device_id == 'IRLZAAQCDMHYWKTS' or 
                        self.device_id == 'U47HZDRG8XJBBURW' or self.device_id == 'WWRO9LTGG6KFGQCM' or self.device_id == 'fcb3c749' or 
                        self.device_id == 'OVFETO8PCY45E6A6' or self.device_id == 'U8ONIJJJS4CELVD6'):
                        self.d.swipe(400, 1350, 100, 1350, 0.3)
                    elif (self.device_id == 'KNNNEMNVWCJZQOLZ' or self.device_id == 'CMKFUSSG99ROR489' or self.device_id == '656DTOPRZDEALZ5X' or 
                          self.device_id == 'UCQGF6CQFMU8WKHI' or self.device_id == '4TZDUGTOAIFMJVGU' or self.device_id == 'DEZXWKUC7DJBLVPJ' or
                          self.device_id == 'GQIRKB7LVOONM7VW'):
                        self.d.swipe(400, 1300, 100, 1300, 0.3)
                    elif self.device_id == 'e2899b34':
                        self.d.swipe(400, 1050, 100, 1050, 0.3)
                    else:
                        self.d.swipe(400, 1250, 100, 1250, 0.3)
                    # self.d.swipe(400, 1250, 100, 1250, 0.3)
                    # self.d.drag(300, 1280, 50, 1280, 0.3)
                    # self.d.swipe_ext('left', 0.3)

                    time.sleep(0.2)
                    self.d.xpath('//*[@text="复制链接"]').click_exists()
                    time.sleep(1)
                    product_link = self.get_clipboard()
                    time.sleep(0.5)
                    # print(f'{idx}-商品链接:{product_link}')
                    self.loggerPdd.info(f'{idx}-商品链接:{product_link}')
                    break                       # 找到并执行后跳出内层循环
                    
                    # if self.d.xpath('//*[@text="复制链接"]').exists:
                    #     self.d.xpath('//*[@text="复制链接"]').click()
                    #     # print('点击复制链接')           
                    #     self.loggerPdd.info('点击复制链接')     

                    #     product_link = self.get_clipboard()
                    #     time.sleep(0.5)
                    #     # print(f'{idx}-商品链接:{product_link}')
                    #     self.loggerPdd.info(f'{idx}-商品链接:{product_link}')
                    #     break                       # 找到并执行后跳出内层循环

        if not product_link and idx < max_retry:
            time.sleep(0.5)               # 最后一次不需要再等待 
        
        # time.sleep(100000)

        return product_link

    def integrate_data(self):
        """
        整合数据
        :return:
        """
        #测试通过点击店铺获取店铺的名称：
        # shop = self.get_shop_name()
        # print(f'店铺名称:{shop}')
        # time.sleep(100000)  

        #测试点击店铺进入获取店铺资质


        # license_info = self.get_license_info_ex('1234')#店铺名称

        # time.sleep(100000)  

        #首先判断是否存在：商品已售罄，推荐以下相似商品 的文本

        # if self.d.xpath('//*[contains(@text, "商品已售罄，推荐以下相似商品")]'):
        #     self.loggerPdd.info(f'商品已售罄：{self.search_key}')
        #     self.swipe_back(1)
        #     return
        

        #获取价格和盒数备注
        min_price, ext = self.safe_exec(self.drug_price_ex)  # 最低价格和盒数备注


       
        title_info = self.safe_exec(self.get_title)  # 药品名字
        
        if title_info:
        
            if '999' in self.search_key:
                temp_search_key = self.search_key.replace('999', '')

                if self.search_key == '999强力枇杷露225ml':
                    temp_search_key = temp_search_key.replace('225ml', '')               
                elif self.search_key == '999糠酸莫米松凝胶15':
                    temp_search_key = temp_search_key.replace('15', '')
                elif self.search_key == '999养胃舒颗粒10g*6':
                    temp_search_key = temp_search_key.replace('10g*6', '')
                elif self.search_key == '999曲安奈德益康唑乳膏30g':
                    temp_search_key = temp_search_key.replace ('30g', '')
                elif self.search_key == '999抗病毒口服液10ml*6支':
                    temp_search_key = temp_search_key.replace('10ml*6支', '')
                elif self.search_key == '999复方板蓝根颗粒15袋':
                    temp_search_key = temp_search_key.replace('15袋', '')
                elif self.search_key == '999可调式生理性海水鼻腔喷雾50':
                    temp_search_key = temp_search_key.replace('50', '')
                elif self.search_key == '999维生素E.C颗粒9袋':
                    temp_search_key = temp_search_key.replace('9袋', '')
                elif self.search_key == '999复方氨酚烷胺胶囊6粒':
                    temp_search_key = temp_search_key.replace('6粒', '')
                elif self.search_key == '999复方板蓝根颗粒15g*15袋':
                    temp_search_key = temp_search_key.replace('15g*15袋', '')
                elif self.search_key == '999止泻利颗粒15g*8':
                    temp_search_key = temp_search_key.replace('15g*8', '')
                elif self.search_key == '999三蛇胆川贝膏138':
                    temp_search_key = temp_search_key.replace('138', '')
                elif self.search_key == '999强力枇杷露16袋':
                    temp_search_key = temp_search_key.replace('16袋', '')
                elif self.search_key == '999复方苦参肠炎康片12片':
                    temp_search_key = temp_search_key.replace('12片', '')
                elif self.search_key == '999必无忧盐酸特比萘芬乳膏15':
                    temp_search_key = temp_search_key.replace('必无忧', '')
                    temp_search_key = temp_search_key.replace('15', '')
                elif self.search_key == '999速复康布洛芬缓释胶囊':
                    temp_search_key = temp_search_key.replace('速复康', '')
                elif self.search_key == '999强力枇杷露120ml':
                    temp_search_key = temp_search_key.replace('120ml', '')
                elif self.search_key == '999强力枇杷露150ml':
                    temp_search_key = temp_search_key.replace('150ml', '')
                elif self.search_key == '999抗病毒口服液10ml*10':
                    temp_search_key = temp_search_key.replace('10ml*10', '')
                elif self.search_key == '999抗病毒口服液10ml*12':
                    temp_search_key = temp_search_key.replace('10ml*12', '')
                elif self.search_key == '999感冒清热颗粒6g*10':
                    temp_search_key = temp_search_key.replace('6g*10', '')
                elif self.search_key == '999选平硝酸咪康唑乳膏20g':
                    temp_search_key = temp_search_key.replace('选平', '')
                    temp_search_key = temp_search_key.replace('20g', '')
                elif self.search_key == '999糠酸莫米松乳膏10g':
                    temp_search_key = temp_search_key.replace('10g', '')      
                elif self.search_key == '999壮骨关节丸6g*20':
                    temp_search_key = temp_search_key.replace('6g*20', '')   
                elif self.search_key == '999正天丸6g*15':
                    temp_search_key = temp_search_key.replace('6g*15', '')   
                elif self.search_key == '999藿香正气合剂10ml*6':
                    temp_search_key = temp_search_key.replace('10ml*6', '')   
                elif self.search_key == '999藿香正气合剂10ml*10':
                    temp_search_key = temp_search_key.replace('10ml*10', '')   
                elif self.search_key == '999小儿止咳糖浆120':
                    temp_search_key = temp_search_key.replace('120', '')   
                elif self.search_key == '999小儿止咳糖浆225':
                    temp_search_key = temp_search_key.replace('225', '')  
                elif self.search_key == '999小儿感冒颗粒6g*10':
                    temp_search_key = temp_search_key.replace('6g*10', '')  
                elif self.search_key == '999小儿感冒颗粒6g*24':
                    temp_search_key = temp_search_key.replace('6g*24', '')  
                elif self.search_key == '999小儿氨酚黄那敏颗粒6g*10袋':
                    temp_search_key = temp_search_key.replace('6g*10袋', '')  
                elif self.search_key == '999小儿氨酚黄那敏颗粒6g*20袋':
                    temp_search_key = temp_search_key.replace('6g*20袋', '')  
                elif self.search_key == '999感冒灵颗粒10g*9袋':
                    temp_search_key = temp_search_key.replace('10g*9袋', '') 
                elif self.search_key == '999皮炎平复方醋酸地塞米松乳膏20':
                    temp_search_key = temp_search_key.replace('皮炎平', '')
                    temp_search_key = temp_search_key.replace('20', '')
                elif self.search_key == '999糠酸莫米松凝胶10':
                    temp_search_key = temp_search_key.replace('10', '')
                elif self.search_key == '999板蓝根颗粒10g*20':
                    temp_search_key = temp_search_key.replace('10g*20', '') 
                elif self.search_key == '999咽炎片0.26g*12片':
                    temp_search_key = temp_search_key.replace('0.26g*12片', '') 
                elif self.search_key == '999小儿咽扁颗粒8g*10袋':
                    temp_search_key = temp_search_key.replace('8g*10袋', '') 
                elif self.search_key == '999感冒清热颗粒12g*18':
                    temp_search_key = temp_search_key.replace('12g*18', '') 






                
                # print (f"temp_search_key={temp_search_key}")
            
                if self.search_key == '999抗病毒口服液': #如果标题不包含 999 或 抗病毒口服液 或 (10ml*12 和 10ml*18) 则退出
                    if '999' not in title_info or temp_search_key not in title_info:
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '10ml*12' not in title_info and '10ml*10' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含10*12或10*10品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return   
                elif self.search_key == '999抗病毒口服液10ml*6支': #如果标题不包含 999 或 抗病毒口服液 或 (10ml*12 和 10ml*18) 则退出
                    if '999' not in title_info or temp_search_key not in title_info:
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '10ml*6' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含10ml*6品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                elif self.search_key == '999曲安奈德益康唑乳膏30g':
                    if '999' not in title_info or temp_search_key not in title_info:
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '30' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含30品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                elif self.search_key == '999复方感冒灵颗粒':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '14g*15' not in title_info and '14g*9' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含14g*15 和 14g*9品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                elif self.search_key == '999养胃舒颗粒10g*6':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '10g*6' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含10g*6品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                elif self.search_key == '999糠酸莫米松凝胶15':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '15' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含15品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                        
                elif self.search_key == '999强力枇杷露225ml':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '225' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含225品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999强力枇杷露120ml':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '120' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含120品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999强力枇杷露150ml':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '150' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含150品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999抗病毒口服液10ml*10':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '10ml*10' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含10ml*10品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999抗病毒口服液10ml*12':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '10ml*12' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含10ml*12品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999复方板蓝根颗粒15袋':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '15袋' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含15袋品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999可调式生理性海水鼻腔喷雾50':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999维生素E.C颗粒9袋':
                     if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999复方氨酚烷胺胶囊6粒':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '6粒' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含6粒品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999复方板蓝根颗粒15g*15袋':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '15g*15' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含15g*15品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999止泻利颗粒15g*8':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '15g*8' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含15g*8品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999三蛇胆川贝膏138':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '138' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含138品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999强力枇杷露16袋':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '16袋' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含16袋品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999复方苦参肠炎康片12片':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '12片' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含12片品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1     
                        return                               
                elif self.search_key == '999必无忧盐酸特比萘芬乳膏15':
                    if  temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif ('999' not in title_info)  and ('必无忧' not in title_info):
                        print(f"当前商品名称:{title_info} 不包含关键字:999或 必无忧")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '15' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含15品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return    
                elif self.search_key == '999速复康布洛芬缓释胶囊':
                     if  temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return   
                     elif ('999' not in title_info)  and ('速复康' not in title_info):
                        print(f"当前商品名称:{title_info} 不包含关键字:999或 速复康")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return   
                elif self.search_key == '999维生素C咀嚼片':
                    if  '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '80' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含80品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return
                elif self.search_key == '999精氨酸布洛芬颗粒':
                    if  '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '9' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含9品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return
                elif self.search_key == '999阿奇霉素片':
                    if  '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '0.25g*6' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含0.25g*6品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return
                elif self.search_key == '999感冒清热颗粒6g*10':
                    if  '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '6g*10' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含6g*10品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return
                elif self.search_key == '999选平硝酸咪康唑乳膏20g':
                    if  temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif ('999' not in title_info)  and ('选平' not in title_info):
                        print(f"当前商品名称:{title_info} 不包含关键字:999或 选平")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '20g' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含20g品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return 
                elif self.search_key == '999糠酸莫米松乳膏10g':
                    if  '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '10g' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含10g品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return   
                elif self.search_key == '999补脾益肠丸':
                    if  temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif ('999' not in title_info)  and ('三九' not in title_info):
                        print(f"当前商品名称:{title_info} 不包含关键字:999或 三九")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                elif self.search_key == '999壮骨关节丸6g*20':
                    if  '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '6g*20' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含6g*20品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return 
                elif self.search_key == '999正天丸6g*15':
                    if  '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '6g*15' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含6g*15品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return 
                elif self.search_key == '999藿香正气合剂10ml*6':
                    if  '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '10ml*6' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含10ml*6品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return 
                elif self.search_key == '999藿香正气合剂10ml*10':
                    if '999' not in title_info or  temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '10ml*10' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含10ml*10品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return 
                elif self.search_key == '999小儿止咳糖浆120':
                    if '999' not in title_info or  temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '120' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含120品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return 
                elif self.search_key == '999小儿止咳糖浆225':
                    if '999' not in title_info or  temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '225' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含225品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return 
                elif self.search_key == '999小儿感冒颗粒6g*10':
                    if '999' not in title_info or  temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '6g*10' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含6g*10品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return 
                elif self.search_key == '999小儿感冒颗粒6g*24':
                    if '999' not in title_info or  temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '6g*24' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含6g*24品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return 
                elif self.search_key == '999小儿氨酚黄那敏颗粒6g*10袋':
                    if '999' not in title_info or  temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '6g*10' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含6g*10品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return 
                elif self.search_key == '999小儿氨酚黄那敏颗粒6g*20袋':
                    if '999' not in title_info or  temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '6g*20' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含6g*20品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return 
                elif self.search_key == '999感冒灵颗粒':
                    if '999' not in title_info or  temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '10g*9' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含10g*9品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return 
                elif self.search_key == '999皮炎平复方醋酸地塞米松乳膏20':
                    if  temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{temp_search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif ('999' not in title_info)  and ('皮炎平' not in title_info):
                        print(f"当前商品名称:{title_info} 不包含关键字:999或 皮炎平")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '20g' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含20g品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1      
                        return 
                elif self.search_key == '999糠酸莫米松凝胶10':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '10' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含10品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999板蓝根颗粒10g*20':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '10g*20' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含10g*20品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999咽炎片0.26g*12片':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '0.26g*12' not in title_info and '0.26g*24' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含0.26g*12 和 0.26g*24品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999感冒清热颗粒12g*18':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '12g*18' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含12g*18品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '999小儿咽扁颗粒8g*10袋':
                    if '999' not in title_info or temp_search_key not in title_info :
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
                    elif '8g*10' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含8g*10品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return


                else:
                    if '999' not in title_info or temp_search_key not in title_info:
                        print(f"当前商品名称:{title_info} 不包含关键字:{self.search_key}")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return 
            else:
                if self.search_key == '史达功右美沙芬愈创甘油醚糖浆120':
                    temp_search_key = self.search_key.replace('史达功', '')
                    temp_search_key = temp_search_key.replace('120', '')
                    if '史达功' not in title_info or  temp_search_key not in title_info:
                        print(f'药品标题未包含药品关键字：-->{temp_search_key}')
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '120' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含120品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '三九胃泰养胃舒颗粒8袋':
                    temp_search_key = self.search_key.replace('三九胃泰', '')
                    temp_search_key = temp_search_key.replace('8袋', '')
                    if '三九胃泰' not in title_info or  temp_search_key not in title_info:
                        print(f'药品标题未包含药品关键字：-->{temp_search_key}')
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '8袋' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含8袋品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '三九复方金银花颗粒10g*8袋':
                    temp_search_key = self.search_key.replace('三九', '')
                    temp_search_key = temp_search_key.replace('10g*8袋', '')
                    if '三九' not in title_info or  temp_search_key not in title_info:
                        print(f'药品标题未包含药品关键字：-->{temp_search_key}')
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '10g*8' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含10g*8品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '必无忧盐酸特比萘芬喷雾剂30ml':
                    temp_search_key = self.search_key.replace('必无忧', '')
                    temp_search_key = temp_search_key.replace('30ml', '')
                    if '必无忧' not in title_info or  temp_search_key not in title_info:
                        print(f'药品标题未包含药品关键字：-->{temp_search_key}')
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '30' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含30品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '佳美舒阿奇霉素肠溶胶囊4':
                    temp_search_key = self.search_key.replace('佳美舒', '')
                    temp_search_key = temp_search_key.replace('4', '')
                    if '佳美舒' not in title_info or  temp_search_key not in title_info:
                        print(f'药品标题未包含药品关键字：-->{temp_search_key}')
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '4' not in title_info and '8' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含4品规或8品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '三九胃泰颗粒20g*10':
                    temp_search_key = self.search_key.replace('20g*10', '')
                    if  temp_search_key not in title_info:
                        print(f'药品标题未包含药品关键字：-->{temp_search_key}')
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '20g*10' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含20g*10品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return

                elif self.search_key == '三九胃泰颗粒2.5g*6':
                    temp_search_key = self.search_key.replace('2.5g*6', '')
                    if  temp_search_key not in title_info:
                        print(f'药品标题未包含药品关键字：-->{temp_search_key}')
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '2.5g*6' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含2.5g*6品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '三九胃泰颗粒20g*6袋':
                    temp_search_key = self.search_key.replace('20g*6袋', '')
                    if  temp_search_key not in title_info:
                        print(f'药品标题未包含药品关键字：-->{temp_search_key}')
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '20g*6' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含20g*6品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '顺峰酮康他索乳膏':
                    temp_search_key = self.search_key.replace('顺峰', '')
                    if  temp_search_key not in title_info or '顺峰' not in title_info:
                        print(f'药品标题未包含药品关键字：-->{temp_search_key}')
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                elif self.search_key == '速复康磷酸奥司他韦胶囊75mg*10':
                    temp_search_key = self.search_key.replace('速复康', '')
                    temp_search_key = temp_search_key.replace('75mg*10', '')
                    if '佳美舒' not in title_info or  temp_search_key not in title_info:
                        print(f'药品标题未包含药品关键字：-->{temp_search_key}')
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return
                    elif '75mg*10' not in title_info:
                        print(f"当前商品名称:{title_info} 不包含75mg*10品规")
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return

                    
                    
                else:
                    if self.search_key not in title_info:
                        print(f'药品标题未包含药品关键字：-->{self.search_key}')
                        self.swipe_back(1)
                        self.unrelated_data += 1
                        return



            # temp_search_key = self.search_key

            # if self.search_key == '三九胃泰颗粒':
            #     temp_search_key = '三九胃泰' #兼容三九胃泰 温胃舒颗粒
            # elif '999' in self.search_key:
            #     temp_search_key = self.search_key.replace('999', '')
            
            # if '999' in self.search_key:
            #      if ('999' not in title_info) or (temp_search_key not in title_info):
            #         print(f'药品标题未包含药品关键字：-->{temp_search_key}和未包含999')
            #         self.swipe_back(1)
            #         self.unrelated_data += 1
            #         return
            # else:
            #     if temp_search_key not in title_info:
            #         print(f'药品标题未包含药品关键字：-->{temp_search_key}')
            #         self.swipe_back(1)
            #         self.unrelated_data += 1
            #         return
        else:
            print('标题获取为空')
            self.swipe_back(1)
            return
        
        #第一次没有获取到价格
        if not min_price:
            min_price = self.drug_price()  # 最低价格 第二次获取
            if not min_price:
                print('提取价格出错，回退到列表页')
                self.swipe_back(1)
                self.unrelated_data += 1
                return
        
         # 商品链接 分享链接
        
        product_link = self.get_product_link()
        time.sleep(2)
        if self.search_key == '999小儿止咳糖浆' or self.search_key == '999小儿氨酚黄那敏颗粒' or self.search_key == '999小儿感冒颗粒':
            shop = self.get_shop_name()
        else:
            for i in range(15):
                if self.d(textStartsWith="进店").exists:
                    print('开始获取店铺名')
                    break
                screen_width = self.d.info['displayWidth']
                screen_height = self.d.info['displayHeight']
                # self.d.swipe(screen_width // 2, screen_height - 400, screen_width // 2, 400, duration=0.2)
                self.d.swipe_ext("up", scale=0.3)
                time.sleep(self.get_sleep_time())
                if self.d(textStartsWith="进店").exists:
                    print('可以开始获取店铺名')
                    
        #     shop = self.get_shop_name()
        shop = self.get_shop_name()
        if not shop:
            print('当前店铺名称为空')
            self.swipe_back(1)
            self.unrelated_data += 1
            return
        # 爬取日期
        scrape_date = self.get_current_date()
        dup_data = {'search_key': self.search_key, 'min_price': min_price, 'shop': shop, 'scrape_date': scrape_date,
                    'platform': '拼多多'}
        if self.data_is_exists(dup_data):
            print('存在相同数据不入库')
            self.swipe_back(1)
            return
        is_has_instructions = self.has_instructions()
        # print(f'是否有说明书:{is_has_instructions}')
        self.loggerPdd.info(f'是否有说明书:{is_has_instructions}')
        # 生产日期为空
        manufacture_date = ''
        # 执政信息
        # if is_has_enter_shop:
        #     license_info = self.get_license_info()
        #     business_license_company = license_info["单位名称"]
        #     credit_code = license_info['社会信用代码']
        #     city_str = license_info['地址']
        #     # 先把省份啥的替换掉
        #     city_sub_str = re.sub(r'[u4e00-\u9fa5]+省', '', city_str)
        #     try:
        #         city = re.search(r'[\u4e00-\u9fa5]+?(市|区|县)', city_sub_str).group(0)
        #     except:
        #         city = city_sub_str
        #     try:
        #         province = self.city2province[city]
        #     except:
        #         province = ''
        #     self.swipe_back(2)
        # else:
        #     business_license_company = ''
        #     credit_code = ''
        #     city = ''
        #     province = ''
        business_license_company = ''
        # credit_code = ''
        credit_code = ext
        city = ''
        province = ''
        # 说明书等信息
        if is_has_instructions:
            try:
                instructions_info = self.safe_exec(self.get_instructions_data) 
                # print('说明书相关信息:', instructions_info)
                expiry_date = instructions_info['有效期'].strip('。')
                manufacturer = instructions_info['生产单位'].strip('。')
                approval_number = instructions_info['批准文号'].strip('。')
                specifications = instructions_info['产品规格'].strip('。')
            except Exception as e:
                print(f'获取详情页规格参数出错：{e}')
                self.swipe_back(2)
                return
        else:
            expiry_date = ''
            manufacturer = ''
            approval_number = ''
            specifications = ''

        # if self.search_key == '999小柴胡颗粒':
        #     if '10g*9' in specifications or '10克x9' in specifications or '10g*15' in specifications or '10克/袋*9' in specifications:
        #         print("111")
        #     else:
        #         self.swipe_back(1)
        #         return
        # elif self.search_key == '':
        #     if '10ml*12' in specifications or '10ml*18' in specifications:
        #         print(222)
        #     else:
        #         self.swipe_back(1)
        #         return






        self.unrelated_data = 0
        # 商品链接
        # product_link = ''
        # 爬取省份
        scrape_province = '广东'  # 这里先默认广东
        # 是否有货
        availability = ''
        save_data = {
            'product': title_info,
            'min_price': min_price,
            'manufacture_date': manufacture_date,
            'expiry_date': expiry_date,
            'shop': shop,
            'business_license_company': business_license_company,
            'province': province,
            'city': city,
            'manufacturer': manufacturer,
            'specification': specifications,
            'approval_number': approval_number,
            'product_link': product_link,
            'scrape_date': scrape_date,
            'scrape_province': scrape_province,
            'availability': availability,
            'credit_code': credit_code,
            'platform': '拼多多',
            'search_key': self.search_key,
            'number'    : 1
        }
        # print(f'待插入数据:{save_data}')
        self.save_to_database(save_data)
        self.swipe_back(1)

        #获取店铺信息start 2025-07-28

        '''
        #不获取店铺信息
        #1、判断店铺名称是否已存在
        shop_is_exists = self.shop_is_exists_database(shop)
        #2、获取店铺资质 是否存在
        # is_has_shop_qualifications = self.has_shop_qualifications()

        if not shop_is_exists :
            print('开始获取店铺信息')
            #点击店铺，点击店铺标题，点击店铺资质


            # license_info = self.get_license_info_ex()

        else:
            #日志中加上店铺名称
            self.loggerPdd.info(f'店铺{shop}信息已存在数据库')

        #获取店铺信息end
        '''

        if self.distinct_target():
            print('已到达搜索列表页')
        else:
            for i in range(2):
                self.swipe_back(1)
                # 最外部有个定位按钮
                if self.distinct_target():
                    break

    def main(self, device_id, start_page, end_page, task_id, max_duration_minutes=None, retry_count=0):

        # === 新增：初始化任务信息 ===
        self.task_id = task_id
        self.task_start_page = start_page
        self.task_end_page = end_page
        # self.current_page = start_page
        self.start_time = time.time()


        # === 新增：线程启动成功后更新状态为2 ===
        if self.task_id:
            try:
                self.update_task_status(2)  # 状态2: 执行中
                self.loggerPdd.info(f"任务 {task_id} 线程启动成功，状态已更新为2")
            except Exception as e:
                self.loggerPdd.error(f"更新任务状态失败: {e}")
        # =====================================
                
        # 记录任务开始
        if task_id:
            reporter.start_task(task_id, start_page, end_page)
        # ========================
            
        task_scape_count = 0 #任务采集数量初始化为0

         # 计算超时时间（秒）
        timeout_seconds = None
        if max_duration_minutes:
            timeout_seconds = max_duration_minutes * 60


        MAX_RETRY = 3  # 最大重试次数
        spider_no = 0
        self.connect_devices(device_id)
        time.sleep(self.get_sleep_time())

        # 启动全局弹窗监控
        self.monitor = SpiderMonitor(self)
        self.monitor.start()
        # 重新开启拼多多应用
        try:
            self.restart_app()
            # 搜索关键字
            # self.enter_target_page()
            self.safe_exec(self.enter_target_page)

            # === 新增：跳过前面的页面直到start_page start===
            if start_page > 1:
                self.loggerPdd.info(f"跳过前 {start_page-1} 页，从第 {start_page} 页开始采集")
                current_page = 1

                while current_page < start_page:
                     # 检查是否需要暂停
                    if self.monitor.pausing.is_set():
                        self.wait_for_ready(self.monitor)

                     # 检查是否到达底部
                    if self.d.xpath('//*[@text="已经到底啦"]').exists:
                        self.loggerPdd.info(f"在第 {current_page} 页已到达底部，无法继续翻页")
                        self.loggerPdd.warning(f"未能到达目标页码 {start_page}，实际只到达第 {current_page} 页")

                        if task_id:
                            reporter.end_task(
                                task_id=task_id,
                                status='completed',
                                finish_status=1,
                                force_end_page=idx
                            )
                        return
                        # break
                    
                     # 滑动到下一页
                    self.d.swipe(200, 1400, 200, 300, 0.4)
                    time.sleep(self.get_sleep_time())
                    current_page += 1
                     # 可选：添加页码日志
                    self.loggerPdd.debug(f"已翻到第 {current_page} 页")
                
                # 验证是否到达目标页码
                if current_page < start_page:
                    self.loggerPdd.error(f"翻页失败！目标页码：{start_page}，实际到达：{current_page}")
                    # 这里可以根据需要决定是否继续执行或抛出异常
                    # return False 或 raise Exception
                else:
                    self.loggerPdd.info(f"成功翻到第 {start_page} 页，开始采集")
             # === 新增：跳过前面的页面直到start_page    end===


            # === 新增：跳过前面的页面直到start_page start===
            # if start_page > 1:
            #     self.loggerPdd.info(f"跳过前 {start_page-1} 页，从第 {start_page} 页开始采集")
            #     for skip_idx in range(1, start_page):
            #         # 检查是否需要暂停
            #         if self.monitor.pausing.is_set():
            #             self.wait_for_ready(self.monitor)
                    
            #         # 滑动到下一页
            #         # self.d.drag(300, 1400, 300, 400, 1)
            #         self.d.swipe(200, 1400, 200, 300, 0.4)
            #         time.sleep(self.get_sleep_time())
                    
            #         # 检查是否到达底部
            #         if self.d.xpath('//*[@text="已经到底啦"]').exists:
            #             self.loggerPdd.info(f"在第 {skip_idx} 页已到达底部，无法继续翻页")
            #             break
            # === 新增：跳过前面的页面直到start_page    end===




            # for idx in range(300):
            for idx in range(start_page, end_page + 1):

                # === 新增：检查是否超过结束页 ===
                if idx > end_page:
                    self.loggerPdd.info(f"已采集到指定结束页 {end_page}，停止采集")
                    if task_id:
                        reporter.end_task(
                            task_id=task_id,
                            status='completed',
                            finish_status=1,
                            force_end_page=end_page
                        )
                    return

                # === 新增：检查超时 ===
                if timeout_seconds and (time.time() - self.start_time) > timeout_seconds:
                    print(f"任务 {task_id} 达到时间限制 {max_duration_minutes} 分钟，停止采集")
                    self.loggerPdd.info(f"任务 {task_id} 达到时间限制 {max_duration_minutes} 分钟，停止采集")
                    # 上报未完成状态
                    if task_id:
                        reporter.end_task(
                            task_id=task_id,
                            status='completed',
                            finish_status=0,  # 0:未完成
                            force_end_page=self.current_page
                        )
                    return
                # ====================

                # print(f'第{idx + 1}页')
                print(f'第{idx}页（指定范围: {start_page}-{end_page}）')

                self.current_page = idx  # 更新当前页码

                # === 新增：更新上报进度 ===
                if task_id:
                    reporter.update_task_progress(
                        task_id=task_id,
                        actual_end_page=self.current_page
                    )
                # ========================


                # print(f'第{idx + 1}页')
                if spider_no > 30:
                    time.sleep(300)
                    spider_no = 0

                # 检查是否需要暂停（验证码过多）
                if self.monitor.verification_count >= self.monitor.MAX_VERIFICATION_RETRY:
                    print("频繁遇到验证码，暂停程序")
                    self.d.toast("请处理验证码后点击继续", 30)
                    # 等待用户点击屏幕继续
                    self.d.click(0, 0)  # 无效点击，等待用户操作
                    self.monitor.verification_count = 0

                if self.unrelated_data > 30:
                    print('连续超过30个不达标的数据则停止采集')
                    # 连续超过30个不达标的数据则停止采集
                    self.loggerPdd.info(f"连续20个数据不达标，品规：{self.search_key}")

                     # === 新增：任务正常完成 ===
                    if task_id:
                        reporter.end_task(
                            task_id=task_id,
                            status='completed',
                            finish_status=1,  # 1:已完成
                            force_end_page=end_page
                        )
                    # ========================
                    break
                # if idx == 0:
                if idx == 1:
                    drug_lis =  self.safe_exec(self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.FrameLayout[2]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout').all)
                else:
                    for i in range(1, 6):
                        drug_xpath = f'/hierarchy/android.widget.FrameLayout[{i}]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout' 
                        drug_lis = self.safe_exec(self.d.xpath(
                            f'/hierarchy/android.widget.FrameLayout[{i}]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout').all)
                        if drug_lis:
                            break
                print('数量', len(drug_lis))
                for idd, drug_one in enumerate(drug_lis):
                    print(idd+1, drug_one.info)
                    time.sleep(self.get_sleep_time())
                    # left = drug_one.info['bounds']['left']
                    top = drug_one.info['bounds']['top']
                    # right = drug_one.info['bounds']['right']
                    bottom = drug_one.info['bounds']['bottom']
                    # height = bottom - top
                    # 高度低于多少的不点击采集

                    # if bottom <= 1400 and top >= 258:
                    if bottom <= 1524 and top >= 258:
                        # print(f"这页的第{idd+1}个商品")    
                        # #商品名称的xpath

                        # if idx == 0:
                        #     product_tittle_xpath = f'//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.FrameLayout[2]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout[{idd+2}]/android.widget.LinearLayout[1]/android.widget.FrameLayout[2]/android.widget.TextView'
                        # else:
                        #     product_tittle_xpath = drug_xpath + f'[{idd+1}]/android.widget.LinearLayout[1]/android.widget.FrameLayout[2]/android.widget.TextView'
                        
                        # print(f"商品名称的xpath:{product_tittle_xpath}")      

                        # if self.d.xpath(product_tittle_xpath).exists:
                        #     # product_title = self.d.xpath(product_tittle_xpath).info['contentDescription']
                        #     print(f"列表当前info:{self.d.xpath(product_tittle_xpath).info}")   
                        #     product_title = self.d.xpath(product_tittle_xpath).text
                        #     print(f"列表当前商品名称:{product_title}")

                        #     if '999' in self.search_key:
                        #         temp_search_key = self.search_key.replace('999', '')
                        #         if '999' not in product_title or temp_search_key not in product_title:
                        #             print(f"当前商品名称:{product_title} 不包含关键字:{self.search_key}")
                        #             continue
                        #     else:
                        #         if self.search_key not in product_title.replace(' ', ''):
                        #             continue
                        # else:
                        #     print(f"列表当前商品路径不存在")

                        
                        self.safe_exec(drug_one.click)
                        time.sleep(self.get_sleep_time())
                        # 采集药品信息
                        try:
                            self.safe_exec(self.integrate_data)
                            # 检测下是否回退到列表页
                            if self.distinct_target():
                                print('回退到列表页', True)
                            else:
                                if retry_count < MAX_RETRY:
                                    # 停止当前监控线程
                                    self.monitor.stop()
                                    self.monitor.join()
                                    # 递归重启采集
                                    return self.main(device_id, start_page, end_page, task_id, max_duration_minutes, retry_count+1)
                                else:
                                    print("超过最大重试次数，终止程序")
                                    return    

                                print('回退到列表页失败，终止采集')
                                return
                            time.sleep(self.get_sleep_time())
                            spider_no += 1
                        except Exception as e:
                            print(f'采集药品详情数据出错:{e}')
                            self.loggerPdd.error(f'采集药品详情数据出错:{e}')
                            if not self.distinct_target():
                                for i in range(1):
                                    self.swipe_back(1)
                                    # 最外部有个列表按钮
                                    if self.distinct_target():
                                        break
                                    if i == 0 and not self.distinct_target():
                                        print('页面出错，退出采集')
                                        return
                            else:
                                continue
                # if self.d(textStartsWith="抱歉，没有更多商品啦~").exists:
                #     print('已经到达列表页最底部')
                #     break
                # 翻页逻辑（如果是最后一页则不再翻页）
                if idx < end_page:
                    if self.d(textStartsWith="抱歉，没有更多商品啦~").exists:
                        self.loggerPdd.info(f'在第 {idx} 页已到达列表最底部')
                        if task_id:
                            reporter.end_task(
                                task_id=task_id,
                                status='completed',
                                finish_status=1,
                                force_end_page=idx
                            )
                        return
                    
                    # 翻页
                    print('开始滑动')
                    self.d.drag(200, 1400, 200, 300, 0.4)
                    print('滑动结束')
                    time.sleep(self.get_sleep_time())
                
            # 采集完成，数据上报
            if task_id:
                reporter.end_task(
                    task_id=task_id,
                    status='completed',
                    finish_status=1,
                    force_end_page=end_page
                )


                print('开始滑入下一页')
                # search_list = self.d.xpath('//*[@resource-id="android:id/content"]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.support.v7.widget.RecyclerView[1]').info
                # bounds = search_list['bounds']
                # try:
                #     top = drug_lis[0].info['bounds']['top']
                # except Exception as e:
                #     print(f'获取滑动参数top出错:{e}')
                #     top = 250
                # search_list = self.d.xpath('//android.support.v7.widget.RecyclerView').info
                # bottom = search_list['bounds']['bottom']

                # end_y = 1400 + top - bottom + 162

                # if end_y < 150:
                #     end_y = 150

                '''
                end_y = 300

                # self.d.swipe(200, 1400, 200, 1400 + bounds['top'] - bounds['bottom'] + 162, 0.4)
                self.d.swipe(200, 1400, 200, end_y, 0.4)
                time.sleep(self.get_sleep_time())
                '''
        except Exception as e:
            print(f"采集任务异常: {e}")
            # === 新增：异常结束上报 ===
            if task_id:
                reporter.end_task(
                    task_id=task_id,
                    status='failed',
                    finish_status=0,  # 未完成
                    force_end_page=self.current_page
                )
            # ========================
            raise
        finally:
            # 确保监控线程被停止
            self.monitor.stop()
            self.monitor.join()

   

    def unitest(self):
        """
        单元测试
        :return:
        """
        # device_id = '21885f5'
        #         # self.connect_devices(device_id)
        #         # self.screenshot_the_business_license()
        #         # cropped_screenshot_path = 'cropped_screenshot.png'
        #         # self.get_ocr_res(cropped_screenshot_path)

        
        # shop_name = '我的店铺'
        
        # base_path = r'D:\work\dfwy_spider\drug_data\pdd\screenshot'
        # cropped_screenshot_path = os.path.join(base_path, shop_name + '.png')

        # os.makedirs(base_path, exist_ok=True)

        # print(cropped_screenshot_path)


        # cropped_screenshot_path = 'D:\\work\\dfwy_spider\\drug_data\\pdd\\screenshot\\' + shop_name + '.png'
        # print(cropped_screenshot_path)
        # time.sleep(10000)

        ocr_res = self.get_ocr_res('ceshi1.jpg')
        print(f'ocr_res:{ocr_res}')


        # 获取当前时间
        current_time = datetime.datetime.now()

        # 格式化为时分秒
        time_str = current_time.strftime("%H-%M-%S")

        # 生成随机的 8 位字符串
        random_str = secrets.token_hex(4)  # 生成 4 个字节的随机字符串，转换为 8 位十六进制字符串


        screenshot_path = 'instructionscreenshot1-' + time_str + '-' + random_str  + '.png'

        print(screenshot_path)
        

        # if ocr_res:
        #     for item in ocr_res:
        #         if '拖动滑块完成' in item['words']:
        #             print("滑块验证")
        #             break

        # print("ocr_res end")        

        

        
        # company_name = ''
        # reg_number = ''
        # address = ''
        # if ocr_res:
        #     for item in ocr_res:
        #         if '企业注册号' in item['words']:
        #             # print('come in 111')
        #             reg_number = item['words'].split('：', 1)[1].strip()
        #         elif '企业名称' in item['words']:
        #             # print('come in 222')
        #             company_name = item['words'].split('：', 1)[1].strip()
        #         elif '所：' in item['words']:
        #             # print('come in 333')
        #             address = item['words'].split('：', 1)[1].strip()

        # # 输出结果
        # print("企业注册号:", reg_number)
        # print("企业名称:", company_name)
        # print("住所:", address)


        # screenshot_verify_path = 'screenshot_verify.png'
        # img = cv2.imread(screenshot_verify_path)
        #  # 指定裁剪区域 (left, top, right, bottom)
        # left = 118
        # top = 478
        # right = 602
        # bottom = 722
        # cropped_verify_img = img[top:bottom, left:right]
        # cropped_verify_creenshot_path = 'cropped_verify_screenshot.png'
        # cv2.imwrite(cropped_verify_creenshot_path, cropped_verify_img)
        # print('裁剪完成')



        time.sleep(100000)

        title_info = '云南白药 参苓健脾胃颗粒10袋 补脾健胃利湿止泻 脾胃虚弱 饮食不消 或泻或吐 形瘦色萎 神疲乏力 5盒装（补脾健胃）'
        min_price = 85
        shop = '堂鹭北大药房旗舰店'
        scrape_date = '2025-03-19'
        dup_data = {'product': title_info, 'min_price': min_price, 'shop': shop, 'scrape_date': scrape_date}
        print(self.data_is_exists(dup_data))

#pdd
        
'''
def main():
    
    # search_key = '999板蓝根颗粒10g*20'  # 参苓健脾胃颗粒 香砂平胃颗粒 舒肝颗粒 清肺化痰丸


    keys_list = [
        #999感冒清热颗粒、 三九胃泰颗粒

        #暂时不需要的：
        # '999小儿止咳糖浆'
        # '999小儿氨酚黄那敏颗粒'
        # '999小儿感冒颗粒'
        # '999抗病毒口服液10ml*6支'
        # '今维多赐多康牌蛋白粉',
        # '必无忧盐酸特比萘芬喷雾剂30ml'
        # '999冰连清咽'
        # '999复方苦参肠炎康片12片'
        # '999强力枇杷露16袋'
        # '999三蛇胆川贝膏138'
        # '999维生素E.C颗粒9袋'
        # '三九胃泰养胃舒颗粒8袋'
        # '999止泻利颗粒15g*8'
        # '史达功右美沙芬愈创甘油醚糖浆120'
        # '999复方氨酚烷胺胶囊6粒'
        # '999可调式生理性海水鼻腔喷雾50'
        # '999小儿止咳糖浆120'              #不低于19.8 
        # '999小儿止咳糖浆225'              #禁止挂网
        # '999小儿感冒颗粒6g*10'            #不低于24.9
        # '999小儿感冒颗粒6g*24'            #禁止挂网
        # '999小儿氨酚黄那敏颗粒6g*10袋'     #不低于15.8
        # '999小儿氨酚黄那敏颗粒6g*20袋'     #禁止挂网
        # '999小儿咽扁颗粒8g*10袋'           #仅限999官旗店
        # '999阿奇霉素片'


        #2025-08-01最新  其中 藿香正气合剂两种规格 10支和6支 抗病毒口服液 12支和18支 蒲地蓝 24片 36片和44片 枇杷露225ml 小柴胡颗粒9袋和15袋 养胃舒 6袋 复方感冒灵颗粒15袋,
        #曲安奈德益康唑乳膏 30g 葡萄糖酸锌口服溶液 12支 18支 24支和30支,
        # 1、999止泻利颗粒15g*8 没有数据  2、三九胃泰养胃舒颗粒8袋 没有数据  3、999三蛇胆川贝膏138 没有数据 4、999强力枇杷露16袋 没有数据 5、999复方苦参肠炎康片12片 6、999冰连清咽 没有数据
        # '999藿香正气合剂'
        # '999藿香正气合剂10ml*6',
        # '999藿香正气合剂10ml*10',
        # '999糠酸莫米松凝胶15',
        # '999抗病毒口服液',
        # '999抗病毒口服液10ml*10'
        # '999抗病毒口服液10ml*12'
        # '999蒲地蓝消炎片',
        # '999强力枇杷露225ml',
        # '999小柴胡颗粒',
        # '999养胃舒颗粒10g*6',
        # '999复方感冒灵颗粒',
        # '999黄芪精',
        # '999曲安奈德益康唑乳膏30g',
        # '999葡萄糖酸锌口服溶液',    
        # '佳美舒阿奇霉素肠溶胶囊4'    
        # '三九复方金银花颗粒10g*8袋'    
        # '999必无忧盐酸特比萘芬乳膏15'    
        # '999复方板蓝根颗粒15g*15袋'    
        # '999速复康布洛芬缓释胶囊'
        # '999维生素C咀嚼片'
        # '999精氨酸布洛芬颗粒'
        # '999强力枇杷露120ml' 
        # '999强力枇杷露150ml'
        # '999强力枇杷露'   #同时支持120,150和225ml

        #OTC
    
        # '999银菊清咽颗粒'  #没有数据
        # '999感冒清热颗粒6g*10'
        # '999选平硝酸咪康唑乳膏20g'
        # '999糠酸莫米松乳膏10g'
        # '999表虚感冒颗粒' #没有数据
        # '999补脾益肠丸'
        # '999壮骨关节胶囊'
        # '999壮骨关节丸6g*20'
        # '999正天丸6g*15'
        # '999正天胶囊'
        # '三九胃泰胶囊'
        # '三九胃泰颗粒20g*10'
        # '三九胃泰颗粒2.5g*6'

        #10.31 new add

        '999感冒灵颗粒'            #不低于15.5 
        # '999皮炎平复方醋酸地塞米松乳膏20'  #不低于12.5
        # '三九胃泰颗粒20g*6袋'             #不低于13.5
        # '顺峰酮康他索乳膏' #包含10g和20g两个规格  10g 不低于7.5 20g 不低于12.5 '顺峰康王酮康他索乳膏'
        # '999糠酸莫米松凝胶10'             #不低于26.9
        # '999板蓝根颗粒10g*20'             #不低于26.9
        # '999复方氨酚烷胺胶囊12粒'          #不低于17.9 #统一成：999复方氨酚烷胺胶囊 
        # '999复方氨酚烷胺胶囊10粒'          #禁止挂网   #统一成：999复方氨酚烷胺胶囊 
        # '999复方氨酚烷胺胶囊6粒'           #禁止挂网   #统一成：999复方氨酚烷胺胶囊 
        # '999复方氨酚烷胺胶囊'
        # '999咽炎片0.26g*12片'         #不低于13.5   #999咽炎片0.26g*12片*2板改成 999咽炎片0.26g*12片
        # '999感冒灵胶囊'                   #仅限999官旗店
        # '999荆防颗粒'                     #美团没有数据 #禁止挂网 拼多多也没数据
        # '999小儿感冒宁颗粒'       #禁止挂网 999小儿感冒宁颗粒2.5g*10袋  改成 999小儿感冒宁颗粒
        # '速复康磷酸奥司他韦胶囊75mg*10'       #美团没数据 # 禁止挂网 999磷酸奥司他韦胶囊75mg*10 改成 速复康磷酸奥司他韦胶囊75mg*10 
        # '史达功右美沙芬愈创甘油醚糖浆120'   #仅限999官旗店
        # '999感冒清热颗粒12g*18'          #禁止挂网

    ]



    
    # 设备序列号
    # device_id = 'e2899b34'
    # device_id = '2e58510'
    # device_id = '369dcf96'
    # device_id = 'ea4e4eb8'    
    # device_id = 'IZTOWWDQT45D49BU'
    # device_id = 'INXCDAIR75FMMFGU'
    # device_id = 'CMKFUSSG99ROR489'
    # device_id = '95b2c764'
    # device_id = 'UCQGF6CQFMU8WKHI'    
    device_id = 'U8ONIJJJS4CELVD6'

    # device_id = 'OVFETO8PCY45E6A6'       
    # device_id = 'IRLZAAQCDMHYWKTS'
    # device_id = 'DEZXWKUC7DJBLVPJ'
    # device_id = 'U47HZDRG8XJBBURW'
    # device_id = 'WWRO9LTGG6KFGQCM'
    # device_id = 'GQIRKB7LVOONM7VW'

    # device_id = 'ZDQWUSSWBEDI896T' 
    # device_id = '656DTOPRZDEALZ5X'
    # device_id = 'N7ZXBITOSOGMYXQS'
    # device_id = '1462a51f' 
    # device_id = '4TZDUGTOAIFMJVGU'
    # device_id = 'GIOFIBRKZTUGJJAE'    
    # device_id = 'fcb3c749'

    cycle_no  = 0               # 轮次计数

    while True:
        cycle_no += 1
        logging.info(f'========== 第 {cycle_no} 轮采集开始 ==========')
        for idx, key in enumerate(keys_list, 1):
            logging.info(f'[{idx}/{len(keys_list)}] 开始采集关键字：{key}')
            try:
                # mt = MT(key)          # 用当前关键字实例化
                # mt.main(device_id)    # 执行一次完整采集
                pdd = PDD(key, device_id)
                pdd.main(device_id)
                logging.info(f'关键字 {key} 本轮采集完成')
            except Exception as e:
                # 发生异常直接跳过该关键字，继续下一轮
                logging.exception(f'关键字 {key} 采集异常：{e}')
            finally:
                # 关闭当前 MT 实例资源（如有需要）
                if hasattr(pdd, 'close'):
                    pdd.close()

        # logging.info('本轮全部关键字采集完成，等待 2 小时后下一轮...')
        # time.sleep(1 * 3600)   # 2 小时 = 7200 秒
    

    # pdd = PDD(search_key, device_id)
    # pdd.unitest()
    # pdd.main('369dcf96')
   
    # pdd.main(device_id)
'''
def get_retrieve_mysql():
    """
    建立远端连接并返回一个到数据库的连接对象
    """
    import pymysql
    return pymysql.connect(
        host='39.108.116.125',  # 修改后的主机
        port=3306,  # 添加端口号
        user='drug_retrieve',  # 修改后的用户名
        password='Pem287cwM58jNpe2',  # 修改后的密码
        db='drug_retrieve',  # 修改后的数据库名
        charset='utf8mb4'
    )

class TimeoutException(Exception):
    pass

# 如果需要并行处理（提高效率），可以使用线程池：
def process_tasks_in_parallel(max_workers=12):
    """使用线程池并行处理多个任务""" """使用线程池并行处理多个任务，每个任务最多执行30分钟"""
    from concurrent.futures import ThreadPoolExecutor, as_completed
    import concurrent.futures  # ← 新增导入
    
    retrieve_conn = get_retrieve_mysql()
    cursor = retrieve_conn.cursor()
    
    query = """
    SELECT id, collect_equipment_id, product_name, start_page, end_page, duration 
    FROM retrieve_collect_task_allocate 
    WHERE status = 1 AND platform = 3
    """
    cursor.execute(query)
    results = cursor.fetchall()

    print(f"获取到的任务结果={results}")
    
    if not results:
        print("PDD 没有要采集的品规")
        return
    
    # 准备任务列表
    tasks = []
    device_map = {}
    
    for result in results:
        task_id = result[0]
        collect_equipment_id = result[1]
        product_name = result[2]
        start_page = result[3]
        end_page = result[4]
        duration = result[5]
        
        if collect_equipment_id != 0 and product_name and product_name.strip():
            # 缓存设备查询
            if collect_equipment_id not in device_map:
                device_query = "SELECT device_id FROM retrieve_collect_equipment WHERE id = %s AND status = 0"
                cursor.execute(device_query, (collect_equipment_id,))
                device_result = cursor.fetchone()
                device_map[collect_equipment_id] = device_result[0] if device_result else None
            
            if device_map[collect_equipment_id]:
                # ↓ 使用数据库中的duration，如果没有设置则用默认值30分钟
                duration_minutes = duration if duration is not None else 30
                tasks.append({
                    'task_id': task_id,
                    'device_id': device_map[collect_equipment_id],
                    'key': product_name.strip(),
                    'start_page': start_page,
                    'end_page': end_page,
                    'duration_minutes': duration_minutes,  # 存储执行时间限制（分钟）
                })
    
    cursor.close()
    retrieve_conn.close()
    
    if not tasks:
        print("没有有效的采集任务")
        return
    
    print(f"准备并行处理 {len(tasks)} 个任务")
    
    def process_single_task(task):
        """处理单个任务的函数"""
        task_start_time = time.time()  # ← 记录开始时间

        # start_time = time.time()
        
        try:
            pdd = PDD(task['key'], task['device_id'])            
            
            # 执行采集，获取采集数量 关键数据：实际采集的数量,实际的页数
            pdd.main(
                device_id = task['device_id'], 
                start_page = task['start_page'], 
                end_page = task['end_page'], 
                task_id = task['task_id'],
                max_duration_minutes = task['duration_minutes']  # 传入时间限制
            )

            return {
                'task_id': task['task_id'],
                'success': True,
                'collected_count': pdd.collected_count,
                'final_page': pdd.current_page
            }      
        except Exception as e:
            print(f"任务 {task['task_id']} 执行异常: {e}")
            return {
                'task_id': task['task_id'],
                'success': False,
                'error': str(e)
            }
        finally:
            if 'mt' in locals() and hasattr(pdd, 'close'):
                try:
                    pdd.close()
                except:
                    pass
    
    # 使用线程池并行执行
    successful_tasks = 0
    failed_tasks = 0
    # total_execution_time = 0  # 初始化总执行时间变量
    
    with ThreadPoolExecutor(max_workers=max_workers) as executor:
        # 提交所有任务
        future_to_task = {
            executor.submit(process_single_task, task): task 
            for task in tasks
        }
        
        # 处理完成的任务
        for future in as_completed(future_to_task):
            task = future_to_task[future]
            try:
                task_timeout = (task['duration_minutes'] + 5) * 60  # 加5分钟缓冲
                result = future.result(timeout=task_timeout)  # 使用动态超时时间
                if result['success']:
                    successful_tasks += 1
                    print(f"任务 {result['task_id']}: 完成，采集 {result['collected_count']} 条数据")
                else:
                    failed_tasks += 1
                    print(f"任务 {result['task_id']}: 失败，错误: {result['error']}")
            except concurrent.futures.TimeoutError:  # ← 捕获超时异常
                failed_tasks += 1
                timeout_tasks += 1
                print(f"任务 {task['task_id']}: 超时（限制 {task['duration_minutes']} 分钟）")
                
                # ↓ 超时后上报数据
                if task['task_id']:
                    # 这里需要调用上报，但reporter可能没有这个任务的数据
                    # 更好的方式是在MT.main中已经上报了
                    pass
            except Exception as e:
                failed_tasks += 1
                print(f"任务 {task['task_id']}: 执行异常 {e}")
    
    # if (successful_tasks + failed_tasks) > 0:
    #     avg_time = total_execution_time / (successful_tasks + failed_tasks)
    #     avg_minutes = avg_time / 60
    # else:
    #     avg_minutes = 0
    
    # total_minutes = total_execution_time / 60
    
    print(f"\n并行采集完成:")
    print(f"成功: {successful_tasks} 个")
    print(f"失败: {failed_tasks} 个")


if __name__ == '__main__':

    # process_tasks_in_parallel(max_workers=10)  # 可以同时处理10个任务

    def run_collection():
        """执行采集任务"""
        try:
            print(f"【定时任务开始】时间: {datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
            process_tasks_in_parallel(max_workers=12)
            print(f"【定时任务结束】时间: {datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
        except Exception as e:
            print(f"【定时任务异常】: {e}")
    
    # 设置定时任务
    schedule.every(130).minutes.do(run_collection)

     # 立即执行一次
    run_collection()

    print("定时任务已设置，每130分钟执行一次采集")

    # 循环执行
    while True:
        schedule.run_pending()
        time.sleep(60)  # 每分钟检查一次

    # main()
    # scheduler = BlockingScheduler()
    # scheduler.add_job(main, 'cron', hour=11, minute=1, misfire_grace_time=120)
    # try:
    #     scheduler.start()
    # except (KeyboardInterrupt, SystemExit):
    #     pass