import requests import base64 import cv2 import uiautomator2 as u2 import time import subprocess import re import random import datetime import json from aip import AipOcr from apscheduler.schedulers.blocking import BlockingScheduler # from db_mysql import mysqlClient import threading from collections import deque import numpy as np import secrets import os # import pyperclip from config import Config from logger import setup_logger import logging # from database import MySQLClient # 配置日志 # logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s') setup_logger("mt_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' ) class MT: def __init__(self, key): # self.package_name = 'com.sankuai.meituan' self.package_name = Config.PACKAGE_NAME self.access_token = get_access_token() self.city2province = self.get_city_info() self.APP_ID = '116857964' self.API_KEY = '1gAzACJOAr7BeILKqkqPOETh' self.SECRET_KEY = 'ZNArANb9GwJYgLKg4EfYhukKBfPdl1n3' self.client = AipOcr(self.APP_ID, self.API_KEY, self.SECRET_KEY) # host = Config.DB_HOST #"localhost" # user = Config.DB_USER #"root" # password = Config.DB_PASSWORD #"dfwy2025" # database = Config.DB_NAME #"drug_data" # port = Config.DB_PORT#3306 # print(f'数据库配置:host:{host},user:{user},password:{password},database:{database},port:{port}') self.table_name = Config.DB_RH_TABLE #"mt_drug_middle" self.shop_table_name = Config.DB_RH_SHOP_TABLE # print(f'数据库表名:table_name:{self.table_name},shop_table_name:{self.shop_table_name}') # self.mysql_client = mysqlClient(host, user, password, database, port) self.loggerMT = logging.getLogger() self.search_key = key # 参苓健脾胃颗粒 舒肝颗粒 清肺化痰丸 香砂平胃颗粒 self.unrelated_data = 0 # 无关数据数量 self.shop_data_num = 0 # 店铺数据数量 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(5, 8) return random.randint(1, 3) @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 get_shop_name(self): """ 获取店铺名 :return: """ try: shop_name = self.d.xpath( '//android.widget.ScrollView/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[last()]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[3]/android.widget.FrameLayout[1]/android.widget.TextView').text print(f'获取到店铺名:{shop_name}') return shop_name except: try: shop_name = self.d.xpath( '//android.widget.ScrollView/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[last()-1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[3]/android.widget.FrameLayout[1]/android.widget.TextView').text print(f'获取到店铺名2:{shop_name}') return shop_name except Exception as e: #点击店铺曲获取店铺名称 print("点击店铺进入后获取店铺名称") self.enter_shop() shop_xpath = '//*[@resource-id="com.sankuai.meituan:id/layout_header_view"]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]//android.widget.FrameLayout[2]/android.widget.FrameLayout[1]/android.widget.TextView' if self.d.xpath(shop_xpath).exists: shop_name = self.d.xpath(shop_xpath).text self.swipe_back(1) return shop_name else: print(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 get_shop_address(self): try: xpath = '//*[@resource-id="com.sankuai.meituan:id/wm_sc_drug_shop_content_mrn_container_id_2"]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.TextView' if self.d.xpath(xpath).exists: shop_address = self.d.xpath(xpath).text print(f'111-获取到店铺地址:{shop_address}') if '发货时间' in shop_address: print(f'店铺地址包含发货时间，再次获取店铺地址') xpath2 = '//*[@resource-id="com.sankuai.meituan:id/wm_sc_drug_shop_content_mrn_container_id_2"]/android.widget.FrameLayout[1]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.TextView' if self.d.xpath(xpath2).exists: shop_address = self.d.xpath(xpath2).text print(f'222-获取到店铺地址:{shop_address}') else: print(f'222-xpath2获取店铺地址失败') else: shop_address = '' print(f'333-获取到店铺地址:{shop_address}') return shop_address except: print(f'获取店铺地址出错-get_shop_address') 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) VALUES (%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'])) conn.commit() # 提交数据 #self.mysql_client.insert(self.table_name, data) print(f"存入数据库成功") def save_shop_info_to_database(self, data): print(f'保存店铺数据到数据库:{data}') # 连接数据库 conn = get_mysql() # 创建游标对象 cur = conn.cursor() add_sql = f""" INSERT INTO {self.shop_table_name} (shop, contact_address, qualification_number, business_license_company, business_license_address, scrape_date, platform) VALUES (%s, %s, %s, %s, %s, %s, %s) """ cur.execute(add_sql, (data['shop'], data['contact_address'], data['qualification_number'], data['business_license_company'], data['business_license_address'], data['scrape_date'], data['platform'])) conn.commit() # 提交数据 #self.mysql_client.insert(self.shop_table_name, data) print(f'存入店铺信息到数据库成功') 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: """ 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: price_str = self.d.xpath('//*[starts-with(@text,"¥")]').text price = float(re.search('[\d\.]+', price_str).group()) print(f'获取到价格:{price}') return price except Exception as e: print(f'提取价格出错-->{e}') return None 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: #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()) 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) if response: res = response.json() 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 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 get_ocr_res_image(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 screenshot_the_business_license(self, qualification_number): 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] if qualification_number: cropped_screenshot_path = 'D:\\work\\dfwy_spider\\drug_data\\mt\\screenshot\\' + qualification_number + '.png' else: cropped_screenshot_path = 'cropped_screenshot.png' cv2.imwrite(cropped_screenshot_path, cropped_img) return cropped_screenshot_path def screenshot_instruction(self): # 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 print(time_str) screenshot_path = 'instructionscreenshot1-' + time_str + '-' + random_str + '.png' self.d.screenshot(screenshot_path) return screenshot_path #获取商品title def get_title(self): # try: # title = self.d.xpath( # '//android.widget.ScrollView/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.FrameLayout[1]/android.widget.TextView').text # except: # title = self.d.xpath( # '//android.widget.ScrollView/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.TextView').text # title = self.d.xpath('//*[contains(@text, "舒肝颗粒")]').text def _inner(): temp_search_key = self.search_key if '仁和' in self.search_key: if self.search_key == '仁和可立克复方氨酚烷胺胶囊12粒': temp_search_key = self.search_key.replace("仁和可立克", "") temp_search_key = temp_search_key.replace("12粒", "") elif self.search_key == '仁和咽炎片(薄膜衣片)': temp_search_key = self.search_key.replace("仁和", "") temp_search_key = temp_search_key.replace("(薄膜衣片)", "") elif self.search_key == '仁和中方消炎镇痛膏': temp_search_key = self.search_key.replace("仁和中方", "") elif self.search_key == '仁和藿香正气合剂10ml*6': temp_search_key = self.search_key.replace("仁和", "") temp_search_key = temp_search_key.replace("10ml*6", "") elif self.search_key == '仁和可立克磷酸奥司他韦胶囊': temp_search_key = self.search_key.replace("仁和可立克", "") elif self.search_key == '仁和可立克感冒软胶囊': temp_search_key = self.search_key.replace("仁和可立克", "") else: temp_search_key = self.search_key.replace("仁和", "") else: if self.search_key == '伊康美宝甲硝唑氯己定洗剂': temp_search_key = self.search_key.replace("伊康美宝", "") elif self.search_key == '闪亮萘敏维滴眼液': temp_search_key = self.search_key.replace("闪亮", "") elif self.search_key == '闪亮复方门冬维甘滴眼液': temp_search_key = self.search_key.replace("闪亮", "") elif self.search_key == '米阿卡小儿止咳糖浆': temp_search_key = self.search_key.replace("米阿卡", "") elif self.search_key == '达舒克硝酸益康唑喷雾剂': temp_search_key = self.search_key.replace("达舒克", "") elif self.search_key == '闪亮盐酸奥洛他定滴眼液': temp_search_key = self.search_key.replace("闪亮", "") elif self.search_key == '闪亮左氧氟沙星滴眼液': temp_search_key = self.search_key.replace("闪亮", "") elif self.search_key == '妇炎洁植物本草抑菌洗液380ml': temp_search_key = self.search_key.replace("妇炎洁", "") temp_search_key = temp_search_key.replace("380ml", "") elif self.search_key == '妇炎洁洁阴康洗液': temp_search_key = self.search_key.replace("妇炎洁", "") elif self.search_key == '妇炎洁医用护理垫245*70': temp_search_key = self.search_key.replace("妇炎洁", "") temp_search_key = temp_search_key.replace("245*70", "") elif self.search_key == '妇炎洁克霉唑阴道片': temp_search_key = self.search_key.replace("妇炎洁", "") elif self.search_key == '优卡丹葡萄糖酸钙锌口服溶液': temp_search_key = self.search_key.replace("优卡丹", "") elif self.search_key == '优卡丹小儿氨酚烷胺颗粒': temp_search_key = self.search_key.replace("优卡丹", "") elif self.search_key == '克快好强力枇杷露': temp_search_key = self.search_key.replace("克快好", "") elif self.search_key == '君扬他达拉非片': temp_search_key = self.search_key.replace("君扬", "") elif self.search_key == '米阿卡头孢克肟颗粒': temp_search_key = self.search_key.replace("米阿卡", "") elif self.search_key == '克快好治咳枇杷合剂': temp_search_key = self.search_key.replace("克快好", "") elif self.search_key == '优卡丹三合钙咀嚼片': temp_search_key = self.search_key.replace("优卡丹", "") elif self.search_key == '必艾得吲哚美辛巴布膏': temp_search_key = self.search_key.replace("必艾得", "") elif self.search_key == '宁新宝葡萄糖酸钙片': temp_search_key = self.search_key.replace("宁新宝", "") elif self.search_key == '闪亮玻璃酸钠滴眼液': temp_search_key = self.search_key.replace("闪亮", "") elif self.search_key == '闪亮地夸磷索钠滴眼液': temp_search_key = self.search_key.replace("闪亮", "") elif self.search_key == '闪亮复方尿维氨滴眼液': temp_search_key = self.search_key.replace("闪亮", "") elif self.search_key == '闪亮盐酸莫西沙星滴眼液': temp_search_key = self.search_key.replace("闪亮", "") print(f'获取商品title时的搜索关键字:{temp_search_key}') # title = self.d.xpath(f'//*[contains(@text, "{self.search_key}")]').text #初始化 drugs_name = '' specifications = '' title = '' #循环的获取title为了有时间来处理人机验证 for m in range(1, 6000) : if self.d.xpath(f'//*[contains(@text, "{temp_search_key}")]').exists: title = self.safe_exec( lambda: self.d.xpath(f'//*[contains(@text, "{temp_search_key}")]').text ) print(f"第{m}次获取title成功") break else: time.sleep(3) # return drugs_name, specifications # drugs_name = '' # specifications = '' # try: # title_xpath = '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.FrameLayout[1]/android.widget.TextView' # title_xpath_2 = '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.FrameLayout[1]/android.widget.TextView' # if self.d.xpath(title_xpath).exists: # title = self.d.xpath(title_xpath).text # print(f"title_xpath获取的title={title}") # if temp_search_key not in title: # return drugs_name, specifications # elif self.d.xpath(title_xpath_2).exists: # title = self.d.xpath(title_xpath_2).text # print(f"title_xpath_2获取的title={title}") # if temp_search_key not in title: # return drugs_name, specifications # else: # print('title_xpath不存在,请确认') # return drugs_name, specifications # # title = self.d.xpath(f'//*[contains(@text, "{temp_search_key}")]').text # except Exception as e: # print(f"发生异常: {e}") # return drugs_name, specifications #奇怪：有的时候title取出来的记过第一位会多一个0 # title = self.safe_exec(self.d.xpath(f'//*[contains(@text, "{self.search_key}")]').text) # title = self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.FrameLayout[1]/android.widget.TextView').text title = title[1:] if title.startswith('0') else title print(f'获取到药品标题:{title}') # 从里面匹配出药品名和规格 # drugs_name # specifications # match = re.search(r'([^\d]+)([\d\D]+)', title) if self.search_key == '999赐多康大豆': return title, '1罐' if self.search_key == "999感冒清热颗粒" : match = re.search(r'(\[[^\]]+\])(.+?)(\d+.*)', title) else: match = re.match(r'(\[[^\]]+\])(.*?)\s*((?:\d+\S*|\(.+))$', title) if match: #drugs_name = match.group(1).strip() + match.group(2).strip() drugs_name = title 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: if title == '999抗病毒口服液10ml*12' or title == '999抗病毒口服液': drugs_name = title specifications = '10ml*12支/盒' return drugs_name, specifications elif title == '999抗病毒口服液10ml*10': drugs_name = title specifications = '10ml*10支/盒' return drugs_name, specifications elif title == '999小柴胡颗粒': drugs_name = title specifications = '10g*9袋/盒' return drugs_name, specifications elif title == '999养胃舒颗粒': drugs_name = title specifications = '10g*6袋/盒' return drugs_name, specifications elif title == '三九胃泰胶囊': drugs_name = title specifications = '0.5g*24粒/盒' return drugs_name, specifications elif title == '999补脾益肠丸': drugs_name = title specifications = '6g*15袋/盒' return drugs_name, specifications elif title == '999复方感冒灵颗粒': drugs_name = title specifications = '14g*9袋/盒' return drugs_name, specifications else: print("没有匹配到预期格式") drugs_name = title specifications = '' return drugs_name, specifications # 用 safe_exec 包装内部逻辑，确保验证码阻塞 return self.safe_exec(_inner) 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: """ is_shoper_exists = 0 for i in range(10): if self.d.xpath('//*[@text="商家"]').exists: print(f'第{i}次商家存在') is_shoper_exists = 1 break else: print(f'第{i}次商家不存在') time.sleep(self.get_sleep_time()) if is_shoper_exists == 1: self.d.xpath('//*[@text="商家"]').click() time.sleep(self.get_sleep_time()) return True else: return False #点击查看商家资质 def scan_shoper_license(self): exist_shoper = 0 for i in range(10): if self.d.xpath('//*[@text="查看商家资质"]').exists: print(f'第{i}次查看商家资质存在') exist_shoper = 1 break else: print(f'第{i}次查看商家资质不存在') time.sleep(self.get_sleep_time()) if exist_shoper == 1: self.d.xpath('//*[@text="查看商家资质"]').click() time.sleep(self.get_sleep_time()) else: self.swipe_back(1) #验证商品的信息是否在数据库中已存在 def data_is_exists(self, data): """ 检查指定数据是否已存在于数据库表中（仅检查存在性） 参数: data: 包含查询条件的字典，键为列名，值为条件值 返回: True: 数据存在 False: 数据不存在 None: 检查过程中出错 """ # dup_data = {'product': product, 'min_price': min_price, 'shop': shop, 'scrape_date': scrape_date, # 'platform': '美团'} # 1. 验证必要字段 required_keys = ['product', '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)}") 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 product = %s AND min_price = %s AND shop = %s AND scrape_date = %s AND platform = %s """.format(self.table_name) cur.execute(query_sql, ( data['product'], 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_next_data(self, data, target): for i, item in enumerate(data): if item['words'] == target: if i + 1 < len(data): return data[i + 1]['words'] return None def delete_instruction_screenshot(self, screenshot_path): # 删除截图文件 try: os.remove(screenshot_path) print(f"截图文件已删除：{screenshot_path}") except FileNotFoundError: print(f"文件未找到，无法删除：{screenshot_path}") except Exception as e: print(f"删除文件时出错：{e}") ''' def get_instructions_data(self): """ 确定有说明书之后，提取所有的说明书数据 :return: """ self.d.xpath('//*[@text="说明"]').click() # time.sleep(random.randint(3, 5)) time.sleep(0.5) self.d.xpath('//*[@text="查看详细说明"]').click() # time.sleep(random.randint(3, 5)) time.sleep(0.5) self.d.xpath('//*[@text="加载更多"]').click_exists() loop_page = 5 # new_list = list() new_list = [] for i in range(loop_page): self.d.xpath('//*[@text="加载更多"]').click_exists() time.sleep(0.2) if i == 0: self.d.swipe(200, 1000, 200, 300, 0.4) else: self.d.swipe(200, 1000, 200, 62) time.sleep(0.2) if self.d.xpath('//*[@text="加载更多"]').exists: self.d.xpath('//*[@text="加载更多"]').click() time.sleep(0.2) all_tt = self.d.xpath( '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[3]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup').all() for idx in range(1, len(all_tt) + 1): all_tt1 = self.d.xpath( f'//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[3]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[{idx}]//android.widget.TextView').all() # print(f'当前说明书列表数据:{all_tt1}') for tt in all_tt1: if tt.text and tt.text != '展开全文': new_list.append(tt.text) if i == 0: height = 938 else: drug_box = self.d.xpath( '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[3]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]').info bounds = drug_box['bounds'] height = bounds['bottom'] - bounds['top'] if height < 938: # print('说明书翻页到底部') break # 展开全文 new_list = [item for item in new_list if item != '展开全文'] print(f'当前说明书列表数据:{new_list}') # expiry_date_index = next(idx for idx, i in enumerate(new_list) if i == '有效期') # manufacturer_index = next(idx for idx, i in enumerate(new_list) if i == '生产单位') # approval_number_index = next(idx for idx, i in enumerate(new_list) if i == '批准文号') # res_data = { # "有效期": new_list[expiry_date_index + 1], # "生产单位": new_list[manufacturer_index + 1], # "批准文号": new_list[approval_number_index + 1] # } res_data = { "有效期": (new_list[new_list.index("有效期") + 1]) if "有效期" in new_list and new_list.index("有效期") + 1 < len(new_list) else "", "生产单位": (new_list[new_list.index("生产单位") + 1]) if "生产单位" in new_list and new_list.index("生产单位") + 1 < len(new_list) else "", "批准文号": (new_list[new_list.index("批准文号") + 1]) if "批准文号" in new_list and new_list.index("批准文号") + 1 < len(new_list) else "" } print(f'当前说明书字典数据:{res_data}') return res_data ''' ''' def get_instructions_data(self): """ 确定有说明书之后，提取所有的说明书数据 :return: """ self.d.xpath('//*[@text="说明"]').click() # time.sleep(random.randint(3, 5)) time.sleep(0.5) self.d.xpath('//*[@text="查看详细说明"]').click() # time.sleep(random.randint(3, 5)) time.sleep(0.5) # 1) 先向上滑动一次，触发“加载更多”出现 self.d.swipe(200, 1000, 200, 300, 0.4) time.sleep(0.3) # 2) 再进入“出现就点”的循环 while self.d.xpath('//*[@text="加载更多"]').click_exists(timeout=1): time.sleep(0.2) self.d.swipe(200, 1000, 200, 300, 0.4) # self.d.swipe(200, 1000, 200, 62) time.sleep(0.2) # 一次性获取所有文本 texts = [ node.text.strip() # for node in self.d.xpath('//android.widget.TextView').all() for node in self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]//android.widget.TextView').all() if node.text and node.text.strip() and node.text != '加载更多' ] print(f'当前说明书列表数据:{texts}') # 提取关键字段 def safe_get(key): # try: # idx = texts.index(key) # return texts[idx + 1] if idx + 1 < len(texts) else "" # except ValueError: # return "" try: idx = next(i for i, text in enumerate(texts) if text == key) return texts[idx + 1] if idx + 1 < len(texts) else "" except StopIteration: return "" res_data = { "有效期": safe_get("有效期"), "生产单位": safe_get("生产单位"), "批准文号": safe_get("批准文号") } print(f'当前说明书字典数据:{res_data}') return res_data ''' ''' def get_instructions_data(self): """ 说明书键值对采集：连续两个 TextView 为一对，精确提取 """ # 1. 进入说明书 self.d(text="说明").click() time.sleep(0.5) self.d(text="查看详细说明").click() time.sleep(0.5) # self.d(text="加载更多").click_exists(timeout=0.5) # 2. 找到说明书最外层 ScrollView（页面主体） scroll_view = self.d(resourceId="com.sankuai.meituan:id/container") .child(className="android.widget.ScrollView") count = scroll_view.count print(f"找到的 ScrollView 数量: {count}") if not scroll_view.exists: return {"有效期": "", "生产单位": "", "批准文号": ""} # 3. 在 ScrollView 内再定位真正包含键值对的容器 # 绝大多数美团说明书页面对应的是 ScrollView > ViewGroup > 若干 TextView kv_container = scroll_view.child(className="android.view.ViewGroup") if not kv_container.exists: kv_container = scroll_view # 降级：直接对 ScrollView 取子孙 TextView # 4. 滑动到底并收集所有 TextView（保留顺序） all_texts = [] max_swipe = 5 last_length = 0 for _ in range(max_swipe): texts = kv_container.child(className="android.widget.TextView") #获取texts中的文本 print(f'当前说明书列表数据:{texts}') current_texts = [] self.loggerMT.info(f'说明书111') for tv in texts: try: txt = tv.get_text().strip() # txt = tv.info['text'].strip() except Exception: continue if txt and txt != "展开全文": current_texts.append(txt) self.loggerMT.info(f'说明书222') print(f'当前说明书列表数据:{current_texts}') # 去重 if current_texts: current_texts = [t for t in current_texts if t not in all_texts] all_texts.extend(current_texts) # 判断是否到底 # if not scroll_view.info.get("scrollable"): # break # 判断是否到底 if len(all_texts) == last_length: break last_length = len(all_texts) # self.d.swipe_ext("up", scale=0.7) #向上滑动一次 self.d.swipe(200, 1000, 200, 300, 0.2) time.sleep(0.2) if self.d.xpath('//*[@text="加载更多"]').exists: self.d.xpath('//*[@text="加载更多"]').click() # 5. 成对解析 res_data = {"有效期": "", "生产单位": "", "批准文号": ""} for i in range(len(all_texts) - 1): key = all_texts[i] val = all_texts[i + 1] if key in res_data: res_data[key] = val print(f'说明书文本共 {len(all_texts)} 条，提取结果: {res_data}') # time.sleep(1000000) return res_data ''' def get_instructions_data(self): """ 确定有说明书之后，提取所有的说明书数据 :return: """ self.d.xpath('//*[@text="说明"]').click() # time.sleep(random.randint(3, 5)) time.sleep(0.5) if self.d.xpath('//*[@text="查看详细说明"]').exists: self.d.xpath('//*[@text="查看详细说明"]').click() else: for i in range(8): if self.d.xpath('//*[@text="查看全部"]').exists: print('开始点击查看全部') break self.d.swipe_ext('down', 0.3) time.sleep(1) if self.d.xpath('//*[@text="查看全部"]').exists: print('开始点击查看全部2') break if self.d.xpath('//*[@text="查看全部"]').exists: self.d.xpath('//*[@text="查看全部"]').click() else: res_data = { "有效期": '', "生产单位": '', "批准文号": '' } self.loggerMT.info('获取到的说明书信息为空。') return res_data # time.sleep(random.randint(3, 5)) time.sleep(0.5) # self.d.xpath('//*[@text="加载更多"]').click_exists() # loop_page = 5 # new_list = list() # new_list = [] for ii in range(8): if self.d.xpath('//*[@text="加载更多"]').exists: self.d.xpath('//*[@text="加载更多"]').click() time.sleep(0.2) break else: self.d.swipe(200, 1000, 200, 300, 0.3) # self.d.swipe_ext("up", scale=0.3) for iii in range(10): if self.d.xpath('//*[@text="生产单位"]').exists and self.d.xpath('//*[@text="批准文号"]').exists: break else: self.d.swipe(200, 1300, 200, 300, 0.3) # self.d.swipe_ext("up", scale=0.3) instruction_path = self.screenshot_instruction() print(f"instruction_path= {instruction_path}") time.sleep(2) ocr_res = self.get_ocr_res_image(instruction_path) # print(f'ocr_res:{ocr_res}') if ocr_res: # 获取有效期的下一个数据 validity = self.get_next_data(ocr_res, '有效期') # 获取批准文号的下一个数据 approval_number = self.get_next_data(ocr_res, '批准文号') # 获取生产单位的下一个数据 manufacturer = self.get_next_data(ocr_res, '生产单位') else: validity = '' approval_number = '' manufacturer = '' # print("有效期:", validity) # print("批准文号:", approval_number) # print("生产单位:", manufacturer) res_data = { "有效期": validity, "生产单位": manufacturer, "批准文号": approval_number } print(f"res_data={res_data}") time.sleep(1) self.delete_instruction_screenshot(instruction_path) return res_data def has_instructions(self): """ 是否有说明书 :return: """ # 没有说明书的无法采集具体数据 time.sleep(self.get_sleep_time()) is_has_instructions = False for i in range(8): if self.d.xpath('//*[@text="说明"]').exists: print(f"第{i}次有说明书1") is_has_instructions = True break self.d.swipe_ext('down', 0.3) time.sleep(1) # detail_info = self.d.xpath( # '//android.widget.ScrollView/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[6]').info # bounds = detail_info['bounds'] # height = bounds['bottom'] - bounds['top'] # if self.d.xpath('//*[@text="进店"]').exists and height > 100: if self.d.xpath('//*[@text="说明"]').exists: is_has_instructions = True print(f"第{i}次有说明书2") break # is_has_instructions = self.d.xpath('//*[@text="说明"]').exists return is_has_instructions def has_shop(self): """ 是否有进店按钮 :return: """ # self.d.swipe_ext('up', 0.1) time.sleep(self.get_sleep_time()) is_has_enter_shop = self.d.xpath('//*[@text="进店"]').exists return is_has_enter_shop #获取商品对应的店铺信息 def get_license_info_ex(self): # self.enter_shop() self.safe_exec(self.enter_shop) # self.enter_shoper() result = self.safe_exec(self.enter_shoper) if result == False: license_info_data = {'contact_address': '', 'qualification_number': '', 'business_license_company': '', 'business_license_address': ''} return license_info_data for i in range(10): if self.d.xpath('//*[@text="查看商家资质"]').exists: print(f"第{i}次有商家资质") break else: print(f"第{i}次没有商家资质") time.sleep(self.get_sleep_time()) #获取地址 # contact_address = self.get_shop_address() contact_address = self.safe_exec(self.get_shop_address) # time.sleep(50000) ### # self.scan_shoper_license() self.safe_exec(self.scan_shoper_license) # 获取资质编码 # qualification_number = self.get_qualification_number() qualification_number = self.safe_exec(self.get_qualification_number) #qualification_number 不为None继续下一步 if qualification_number: #营业执照公司名称 business_license_company = '' #营业执照地址 business_license_address = '' self.d.click(0.603, 0.27) time.sleep(self.get_sleep_time()) cropped_screenshot_path = self.screenshot_the_business_license(qualification_number) print(f'cropped_screenshot_path:{cropped_screenshot_path}') # if qualification_number: # cropped_screenshot_path = 'D:\\work\\dfwy_spider\\drug_data\\mt\\screenshot\\' + qualification_number + '.png' # else: # cropped_screenshot_path = 'cropped_screenshot.png' # ocr_res = self.get_ocr_res('cropped_screenshot.png') ocr_res = self.get_ocr_res(cropped_screenshot_path) print(f'ocr_res:{ocr_res}') #获取ocr_res 中的地址、单位名称 if ocr_res: if '单位名称' in ocr_res.keys(): business_license_company = ocr_res['单位名称'] if '地址' in ocr_res.keys(): business_license_address = ocr_res['地址'] license_info_data = {'contact_address': contact_address, 'qualification_number': qualification_number, 'business_license_company': business_license_company, 'business_license_address': business_license_address} else: license_info_data = {'contact_address': contact_address, 'qualification_number': '', 'business_license_company': '', 'business_license_address': ''} return license_info_data """暂不用该功能 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 position_xpath = '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[3]' position_xpath2 = '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[2]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[3]' is_position = self.d.xpath(position_xpath).exists is_position2 = self.d.xpath(position_xpath2).exists xpath = '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.HorizontalScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[last()]' xpath2 = '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.HorizontalScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[last()]' xpath3 = '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[2]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.HorizontalScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[last()]' xpath4 = '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[2]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.HorizontalScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[last()]' is_position5 = self.d.xpath(xpath).exists is_position6 = self.d.xpath(xpath2).exists is_position7 = self.d.xpath(xpath3).exists is_position8 = self.d.xpath(xpath4).exists # print(f"is_position = {is_position}") # print(f"is_position2 = {is_position2}") if result == False: print("---检测没有回到列表页---") else: print("---检测回到了列表页---") if is_position or is_position2 or is_position5 or is_position6 or is_position7 or is_position8: result = True return result # return is_position def enter_target_page(self): self.d.xpath('//*[@content-desc="看病买药"]').click() time.sleep(self.get_sleep_time()) self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/vf_search_carousel_text"]').click() time.sleep(self.get_sleep_time()) self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]').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()) # content_frame = self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[2]').exists # print(content_frame) # position_xpath1 = '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[3]' # position_xpath2 = '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[2]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[3]' # if self.d.xpath(position_xpath1).exists: # print("position_xpath1 exist") # elif self.d.xpath(position_xpath2).exists: # print("position_xpath2 exist") # else: # print("position_xpath not exist") # time.sleep(10000) #增加点击快递送 self.click_express_send() time.sleep(self.get_sleep_time()) def click_express_send(self): # xpath= '//*[@resource-id="com.sankuai.meituan:id/container"]//android.widget.HorizontalScrollView[last()]' slide_xpath = '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.HorizontalScrollView[1]' slide_xpath2= '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.HorizontalScrollView[1]' slide_xpath3= '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[2]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.HorizontalScrollView[1]' slide_xpath4= '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[2]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.HorizontalScrollView[1]' ''' for i in range (1,3): if self.d.xpath(slide_xpath).exists: bounds = self.d.xpath(slide_xpath).info['bounds'] top = bounds['top'] bottom = bounds['bottom'] print(f'top={top}') print(f'bottom={bottom}') y = (top + bottom) // 2 print(f'y={y}') self.loggerMT.info('开始滑动1') self.d.swipe(500, y, 100, y, 0.5) time.sleep(self.get_sleep_time()) break elif self.d.xpath(slide_xpath2).exists: bounds = self.d.xpath(slide_xpath2).info['bounds'] top = bounds['top'] bottom = bounds['bottom'] print(f'top={top}') print(f'bottom={bottom}') y = (top + bottom) // 2 print(f'y={y}') self.loggerMT.info('开始滑动2') self.d.swipe(500, y, 100, y, 0.5) time.sleep(self.get_sleep_time()) break elif self.d.xpath(slide_xpath3).exists: bounds = self.d.xpath(slide_xpath3).info['bounds'] top = bounds['top'] bottom = bounds['bottom'] print(f'top={top}') print(f'bottom={bottom}') y = (top + bottom) // 2 print(f'y={y}') self.loggerMT.info('开始滑动3') self.d.swipe(500, y, 100, y, 0.5) time.sleep(self.get_sleep_time()) break elif self.d.xpath(slide_xpath4).exists: bounds = self.d.xpath(slide_xpath4).info['bounds'] top = bounds['top'] bottom = bounds['bottom'] print(f'top={top}') print(f'bottom={bottom}') y = (top + bottom) // 2 print(f'y={y}') self.loggerMT.info('开始滑动4') self.d.swipe(500, y, 100, y, 0.5) time.sleep(self.get_sleep_time()) break ''' max_retry = 5 # 最多尝试次数 for idx in range(1, max_retry + 1): # xpath= '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.HorizontalScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[last()-1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]' xpath= '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.HorizontalScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]' xpath2= '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.HorizontalScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]' xpath3= '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[2]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.HorizontalScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]' xpath4 = '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[2]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.HorizontalScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]' # print(f"xpath:{xpath}") # scroll_view = self.d(resourceId="com.sankuai.meituan:id/container") .child(className="android.widget.HorizontalScrollView") if self.d.xpath(xpath).exists: self.d.xpath(xpath).click() # time.sleep(self.get_sleep_time()) print(f"第{idx}次点击xpath快递送成功") time.sleep(self.get_sleep_time()) break elif self.d.xpath(xpath2).exists: self.d.xpath(xpath2).click() # time.sleep(self.get_sleep_time()) print(f"第{idx}次点击xpath2快递送成功") time.sleep(self.get_sleep_time()) break elif self.d.xpath(xpath3).exists: self.d.xpath(xpath3).click() # time.sleep(self.get_sleep_time()) print(f"第{idx}次点击xpath3快递送成功") time.sleep(self.get_sleep_time()) break elif self.d.xpath(xpath4).exists: self.d.xpath(xpath4).click() # time.sleep(self.get_sleep_time()) print(f"第{idx}次点击xpath4快递送成功") time.sleep(self.get_sleep_time()) break else: print(f"第{idx}次点击xpath或xpath2或xpath3快递送都失败") time.sleep(self.get_sleep_time()) # xpath2= '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.HorizontalScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[last()]' # if self.d.xpath(xpath2).exists: # self.d.xpath(xpath2).click() # print(f"第{idx}次点击xpath2快递送成功") # time.sleep(self.get_sleep_time()) # break """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): # """通过ADB获取Android手机剪贴板内容""" # try: # result = subprocess.run( # ["adb", "shell", "am", "broadcast", "-a", "clipper.get"], # capture_output=True, # text=True, # timeout=5 # ) # print(f"获取剪贴板结果: {result.stdout}") # # 解析返回信息中的剪贴板内容 # for line in result.stdout.splitlines(): # if "data=" in line: # return line.split("data=")[1].strip() # return "" # except Exception as e: # print("获取剪贴板失败:", e) # return "" # def get_clipboard(self): # """读取 Android 剪贴板（系统自带命令）""" # try: # text = subprocess.check_output( # ["adb", "shell", "cmd", "clipboard", "get"], # text=True, timeout=5, stderr=subprocess.STDOUT # ).strip() # print(f"获取剪贴板结果: {text}") # return text if text else "" # except Exception as e: # print("获取剪贴板失败:", e) # return "" def get_clipboard(self): time.sleep(1) self.loggerMT.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() # return self.d.clipboard.strip() def clear_clipboard(self): self.d.set_clipboard("", "text/plain") # def clear_clipboard(self): # """清空手机剪贴板：写入空字符串（subprocess 版）""" # try: # subprocess.run( # ["adb", "shell", "am", "broadcast", "-a", "clipper.set", "-e", "text", " "], # check=True, # capture_output=True, # text=True, # timeout=5 # ) # except subprocess.CalledProcessError as e: # print("ADB 清空失败:", e.stderr) # def clear_clipboard(): # """清空手机剪贴板：写入空字符串""" # try: # adb_shell(["shell", "am", "broadcast", "-a", "clipper.set", "-e", "text", ""]) # except subprocess.CalledProcessError as e: # print("ADB 清空失败:", e.output) #获取一个商品的数据、商品对应的店铺的数据 def get_product_link(self): product_link = '' # 两种可能的“···”按钮 dots_xpaths = [ '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]', '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[3]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]', '//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/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.loggerMT.info(f'{idx}-进入分享点点点') # #先清空剪贴板的内容 # self.clear_clipboard() # print("清空剪贴板内容成功。") self.d.xpath(xp).click() time.sleep(0.2) self.d.xpath('//*[@text="分享商品"]').click_exists() time.sleep(0.2) link_xpath = '//*[@text="复制链接"]' if self.d.xpath(link_xpath).exists: self.d.xpath(link_xpath).click() time.sleep(1) product_link = self.get_clipboard() time.sleep(0.5) print(f'{idx}-商品链接:{product_link}') self.loggerMT.info(f'{idx}-商品链接:{product_link}') break # 找到并执行后跳出内层循环 else: print(f'{idx}-商品链接:{product_link}') self.loggerMT.info(f'{idx}-商品链接:{product_link}') product_link = '' # 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.loggerMT.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 return product_link def integrate_data(self): #测试说明书详情： # instructions_info = self.safe_exec(self.get_instructions_data) # time.sleep(1000000) #测试店铺信息 # license_info = self.safe_exec(self.get_license_info_ex) # time.sleep(1000000) #测试定位地址 #获取链接开始 #self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ScrollView[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.FrameLayout[1]/android.widget.TextView').text #1、点击页面的... 先判断元素是否存在 ''' if self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]').exists: print('1-进入分享点点点111') self.loggerMT.info('1-进入分享点点点111') self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]').click() #点击分享商品 # if self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]').exists: time.sleep(0.2) self.d.xpath('//*[@text="分享商品"]').click_exists() time.sleep(0.2) self.d.xpath('//*[@text="复制链接"]').click_exists() time.sleep(1) #获取剪切板的数据 product_link = self.get_clipboard() time.sleep(0.5) print(f'1-商品链接:{product_link}') self.loggerMT.info(f'1-商品链接:{product_link}') #清空剪切板 # self.clear_clipboard() # if self.d.xpath('//*[@text="加载更多"]').click_exists(): # self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]').click() # if self.d.xpath('//android.support.v7.widget.RecyclerView/android.view.ViewGroup[3]/android.widget.ImageView[1]').exists: # self.d.xpath('//android.support.v7.widget.RecyclerView/android.view.ViewGroup[3]/android.widget.ImageView[1]').click() # #获取剪切板的数据 # product_link = self.get_clipboard() # time.sleep(0.5) # print(f'商品链接:{product_link}') # #清空剪切板 # self.clear_clipboard() # else: # print('未找到分享按钮111') elif self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[3]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]').exists: print('1-进入分享点点点222') self.loggerMT.info('1-进入分享点点点222') self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[3]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]').click() time.sleep(0.2) self.d.xpath('//*[@text="分享商品"]').click_exists() time.sleep(0.2) self.d.xpath('//*[@text="复制链接"]').click_exists() time.sleep(1) #获取剪切板的数据 product_link = self.get_clipboard() time.sleep(0.5) print(f'1-商品链接:{product_link}') self.loggerMT.info(f'1-商品链接:{product_link}') #如果为获取到product_link 则等待0.5秒再获取 if not product_link: time.sleep(0.5) if self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]').exists: print('2-进入分享点点点111') self.loggerMT.info('2-进入分享点点点111') self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]').click() #点击分享商品 # if self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]').exists: time.sleep(0.2) self.d.xpath('//*[@text="分享商品"]').click_exists() time.sleep(0.2) self.d.xpath('//*[@text="复制链接"]').click_exists() time.sleep(1) #获取剪切板的数据 product_link = self.get_clipboard() time.sleep(0.5) print(f'2-商品链接:{product_link}') self.loggerMT.info(f'2-商品链接:{product_link}') elif self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[3]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]').exists: print('2-进入分享点点点222') self.loggerMT.info('2-进入分享点点点222') self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[3]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]').click() time.sleep(0.2) self.d.xpath('//*[@text="分享商品"]').click_exists() time.sleep(0.2) self.d.xpath('//*[@text="复制链接"]').click_exists() time.sleep(1) #获取剪切板的数据 product_link = self.get_clipboard() time.sleep(0.5) print(f'2-商品链接:{product_link}') self.loggerMT.info(f'2-商品链接:{product_link}') #如果为获取到product_link 则等待0.5秒再获取 if not product_link: time.sleep(0.5) if self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]').exists: print('3-进入分享点点点111') self.loggerMT.info('3-进入分享点点点111') self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]').click() #点击分享商品 # if self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[3]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]').exists: time.sleep(0.2) self.d.xpath('//*[@text="分享商品"]').click_exists() time.sleep(0.2) self.d.xpath('//*[@text="复制链接"]').click_exists() time.sleep(1) #获取剪切板的数据 product_link = self.get_clipboard() time.sleep(0.5) print(f'3-商品链接:{product_link}') self.loggerMT.info(f'3-商品链接:{product_link}') elif self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[3]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]').exists: print('3-进入分享点点点222') self.loggerMT.info('3-进入分享点点点222') self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/container"]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.FrameLayout[3]/android.widget.FrameLayout[1]/android.view.ViewGroup[3]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.ImageView[1]').click() time.sleep(0.2) self.d.xpath('//*[@text="分享商品"]').click_exists() time.sleep(0.2) self.d.xpath('//*[@text="复制链接"]').click_exists() time.sleep(1) #获取剪切板的数据 product_link = self.get_clipboard() time.sleep(0.5) print(f'3-商品链接:{product_link}') self.loggerMT.info(f'3-商品链接:{product_link}') ''' #获取链接结束 """ 整合数据 :return: """ # title_info = self.get_title() # 药品，规格 # title_info = self.safe_exec(self.get_title) # 药品，规格 product, specifications = self.safe_exec(self.get_title) # 药品，规格 if product: # product, specifications = title_info if '仁和' in self.search_key: if self.search_key == '仁和可立克复方氨酚烷胺胶囊12粒': temp_search_key = self.search_key.replace("仁和可立克", "") temp_search_key = temp_search_key.replace("12粒", "") elif self.search_key == '仁和咽炎片(薄膜衣片)': temp_search_key = self.search_key.replace("仁和", "") temp_search_key = temp_search_key.replace("(薄膜衣片)", "") elif self.search_key == '仁和中方消炎镇痛膏': temp_search_key = self.search_key.replace("仁和中方", "") elif self.search_key == '仁和藿香正气合剂10ml*6': temp_search_key = self.search_key.replace("仁和", "") temp_search_key = temp_search_key.replace("10ml*6", "") elif self.search_key == '仁和可立克磷酸奥司他韦胶囊': temp_search_key = self.search_key.replace("仁和可立克", "") elif self.search_key == '仁和可立克感冒软胶囊': temp_search_key = self.search_key.replace("仁和可立克", "") else: temp_search_key = self.search_key.replace("仁和", "") if '仁和' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return else: if self.search_key == '伊康美宝甲硝唑氯己定洗剂': temp_search_key = self.search_key.replace("伊康美宝", "") if '伊康美宝' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '闪亮萘敏维滴眼液': temp_search_key = self.search_key.replace("闪亮", "") if '闪亮' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '闪亮复方门冬维甘滴眼液': temp_search_key = self.search_key.replace("闪亮", "") if '闪亮' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '米阿卡小儿止咳糖浆': temp_search_key = self.search_key.replace("米阿卡", "") if '米阿卡' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '达舒克硝酸益康唑喷雾剂': temp_search_key = self.search_key.replace("达舒克", "") if '达舒克' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '闪亮盐酸奥洛他定滴眼液': temp_search_key = self.search_key.replace("闪亮", "") if '闪亮' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '闪亮左氧氟沙星滴眼液': temp_search_key = self.search_key.replace("闪亮", "") if '闪亮' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '妇炎洁植物本草抑菌洗液380ml': temp_search_key = self.search_key.replace("妇炎洁", "") temp_search_key = temp_search_key.replace("380ml", "") if '妇炎洁' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif '380ml' not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '妇炎洁洁阴康洗液': temp_search_key = self.search_key.replace("妇炎洁", "") if '妇炎洁' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '妇炎洁医用护理垫245*70': temp_search_key = self.search_key.replace("妇炎洁", "") temp_search_key = temp_search_key.replace("245*70", "") if '妇炎洁' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif '245*70' not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '妇炎洁克霉唑阴道片': temp_search_key = self.search_key.replace("妇炎洁", "") if '妇炎洁' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '优卡丹葡萄糖酸钙锌口服溶液': temp_search_key = self.search_key.replace("优卡丹", "") if '优卡丹' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '优卡丹小儿氨酚烷胺颗粒': temp_search_key = self.search_key.replace("优卡丹", "") if '优卡丹' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '克快好强力枇杷露': temp_search_key = self.search_key.replace("克快好", "") if '克快好' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '君扬他达拉非片': temp_search_key = self.search_key.replace("君扬", "") if '君扬' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '米阿卡头孢克肟颗粒': temp_search_key = self.search_key.replace("米阿卡", "") if '米阿卡' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '克快好治咳枇杷合剂': temp_search_key = self.search_key.replace("克快好", "") if '克快好' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '优卡丹三合钙咀嚼片': temp_search_key = self.search_key.replace("优卡丹", "") if '优卡丹' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '必艾得吲哚美辛巴布膏': temp_search_key = self.search_key.replace("必艾得", "") if '必艾得' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '宁新宝葡萄糖酸钙片': temp_search_key = self.search_key.replace("宁新宝", "") if '宁新宝' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '闪亮玻璃酸钠滴眼液': temp_search_key = self.search_key.replace("闪亮", "") if '闪亮' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '闪亮地夸磷索钠滴眼液': temp_search_key = self.search_key.replace("闪亮", "") if '闪亮' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '闪亮复方尿维氨滴眼液': temp_search_key = self.search_key.replace("闪亮", "") if '闪亮' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return elif self.search_key == '闪亮盐酸莫西沙星滴眼液': temp_search_key = self.search_key.replace("闪亮", "") if '闪亮' not in product or temp_search_key not in product: self.swipe_back(1) self.unrelated_data += 1 return else: if self.search_key not in product.replace(' ', ''): self.swipe_back(1) self.unrelated_data += 1 return else: self.swipe_back(1) return min_price = self.drug_price() # 最低价格 # 商品链接 # product_link = self.get_product_link() product_link = '' #判断是否有自营的文本，有的话不需要获取店铺的信息 if self.d.xpath('//*[@text="自营"]').exists: shop = "美团自营大药房（快递电商）" # 爬取日期 scrape_date = self.get_current_date() # scrape_date = "2025-07-18" dup_data = {'product': product, 'min_price': min_price, 'shop': shop, 'scrape_date': scrape_date, 'platform': '美团'} print(f'当前数据:{dup_data}') if self.data_is_exists(dup_data): print('存在相同数据不入库') self.swipe_back(1) return else: for i in range(8): if self.d.xpath('//*[@text="进店"]').exists: print('开始获取店铺名1') break self.d.swipe_ext('up', 0.3) time.sleep(1) # detail_info = self.d.xpath( # '//android.widget.ScrollView/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[6]').info # bounds = detail_info['bounds'] # height = bounds['bottom'] - bounds['top'] # if self.d.xpath('//*[@text="进店"]').exists and height > 100: if self.d.xpath('//*[@text="进店"]').exists: print('开始获取店铺名2') break shop = self.get_shop_name() # 爬取日期 scrape_date = self.get_current_date() # scrape_date = "2025-07-18" dup_data = {'product': product, 'min_price': min_price, 'shop': shop, 'scrape_date': scrape_date, 'platform': '美团'} print(f'当前数据:{dup_data}') #获取店铺信息开始 #暂时不获取店铺信息 start ''' is_has_enter_shop = self.has_shop() #需要判断shop是否已经在数据库中存在，如果存在，则不再进入店铺，直接进入下一个商品 shop_is_exists = self.shop_is_exists_database(shop) #存在进店 并且店铺的名称不包含美团官方的字样 print(f"已采集{self.shop_data_num}家店铺数据") if is_has_enter_shop and '美团官方' not in shop and '美团自营' not in shop and not shop_is_exists and self.shop_data_num < 500: # license_info = self.get_license_info_ex() license_info = self.safe_exec(self.get_license_info_ex) contact_address = license_info['contact_address'] qualification_number = license_info['qualification_number'] business_license_company = license_info['business_license_company'] business_license_address = license_info['business_license_address'] save_shop_data = { 'shop': shop, 'contact_address': contact_address, 'qualification_number': qualification_number, 'scrape_date': scrape_date, 'business_license_company':business_license_company, 'business_license_address':business_license_address, 'platform': '美团' } self.save_shop_info_to_database(save_shop_data) self.shop_data_num += 1 # 店铺数据数量+1 self.swipe_back(2) else: print('不采集店铺信息') #获取店铺信息结束 ''' #暂时不获取店铺信息 end if self.data_is_exists(dup_data): print('存在相同数据不入库') self.swipe_back(1) return if not shop: print('未获取到店铺名：开始回退') self.swipe_back(1) return if not shop or '自营' in shop: self.swipe_back(1) return time.sleep(self.get_sleep_time()) # 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 = '' city = '' province = '' expiry_date = '' manufacturer = '' approval_number = '' #暂时不获取说明书信息 start medicine_info = { '仁和盐酸氨溴索口服溶液': { 'expiry_date': '24个月', 'manufacturer': '山东益康药业股份有限公司', 'approval_number': '国药准字H20065840' }, '仁和蒲公英颗粒': { 'expiry_date': '24个月', 'manufacturer': '江西心诚药业有限公司', 'approval_number': '国药准字Z200055430' }, '仁和红霉素软膏': { 'expiry_date': '24个月', 'manufacturer': '江西德成制药有限公司', 'approval_number': '国药准字H36020018' }, '仁和可立克复方氨酚烷胺胶囊12粒': { 'expiry_date': '30个月', 'manufacturer': '江西铜鼓仁和制药有限公司', 'approval_number': '国药准字H20068169' }, '仁和盐酸羟甲唑啉喷雾剂': { 'expiry_date': '24个月', 'manufacturer': '南京海鲸药业有限公司', 'approval_number': '国药准字H20057401' }, '仁和咽炎片(薄膜衣片)': { 'expiry_date': '24个月', 'manufacturer': '石家庄东方药业股份有限公司', 'approval_number': '国药准字Z20093479' }, '仁和曲安奈德益康唑乳膏': { 'expiry_date': '36个月', 'manufacturer': '福建太平洋制药有限公司', 'approval_number': '国药准字H20064180' }, '仁和头孢克洛干混悬剂': { 'expiry_date': '24个月', 'manufacturer': '山东益康药业股份有限公司', 'approval_number': '国药准字H20084417' }, '伊康美宝甲硝唑氯己定洗剂': { 'expiry_date': '24个月', 'manufacturer': '江西药都仁和制药有限公司', 'approval_number': '国药准字H20043498' }, '仁和布洛芬缓释胶囊': { 'expiry_date': '36个月', 'manufacturer': '福建太平洋制药有限公司', 'approval_number': '国药准字H20093691' }, '闪亮萘敏维滴眼液': { 'expiry_date': '24个月', 'manufacturer': '江西闪亮制药有限公司', 'approval_number': '国药准字H20064223' }, '闪亮复方门冬维甘滴眼液': { 'expiry_date': '24个月', 'manufacturer': '江西闪亮制药有限公司', 'approval_number': '国药准字H20083254‌' }, '米阿卡小儿止咳糖浆': { 'expiry_date': '24个月', 'manufacturer': '江西远东药业股份有限公司', 'approval_number': '国药准字Z36020251' }, '仁和人工牛黄甲硝唑胶囊': { 'expiry_date': '24个月', 'manufacturer': '江西药都仁和制药有限公司', 'approval_number': '国药准字H36022263' }, '仁和盐酸左氧氟沙星胶囊': { 'expiry_date': '24个月', 'manufacturer': '海南海神同洲制药有限公司', 'approval_number': '国药准字H20103012' }, '仁和苯磺酸氨氯地平片': { 'expiry_date': '36个月', 'manufacturer': '江西制药有限责任公司', 'approval_number': '国药准字H20083949' }, '仁和阿昔洛韦乳膏': { 'expiry_date': '24个月', 'manufacturer': '江西吉安三力制药有限公司', 'approval_number': '国药准字H20063386' }, '仁和阿莫西林胶囊': { 'expiry_date': '36个月', 'manufacturer': '安徽安科恒益药业有限公司‌', 'approval_number': '国药准字H34023532‌' }, '仁和小柴胡颗粒': { 'expiry_date': '24个月', 'manufacturer': '江西铜鼓仁和制药有限公司', 'approval_number': '国药准字Z20054063' }, '仁和中方消炎镇痛膏': { 'expiry_date': '24个月', 'manufacturer': '江西吉安三力制药有限公司', 'approval_number': '国药准字Z36021368' }, '仁和头孢克肟片': { 'expiry_date': '24个月', 'manufacturer': '湖南方盛制药股份有限公司', 'approval_number': '国药准字H20093161' }, '仁和头孢克洛分散片': { 'expiry_date': '24个月', 'manufacturer': '安徽安科恒益药业有限公司', 'approval_number': '国药准字H20041126' }, '仁和诺氟沙星胶囊': { 'expiry_date': '12月', 'manufacturer': '江西药都仁和制药有限公司', 'approval_number': '国药准字H36021062' }, '仁和川贝清肺糖浆': { 'expiry_date': '24个月', 'manufacturer': '江西铜鼓仁和制药有限公司', 'approval_number': '国药准字Z36021507' }, '达舒克硝酸益康唑喷雾剂': { 'expiry_date': '36个月', 'manufacturer': '广东同德药业有限公司', 'approval_number': '国药准字H44025251' }, '仁和清火胶囊': { 'expiry_date': '24个月', 'manufacturer': '江西药都仁和制药有限公司', 'approval_number': '国药准字Z20080476' }, '仁和双氯芬酸钠缓释片': { 'expiry_date': '36个月', 'manufacturer': '湖南华纳大药厂股份有限公司', 'approval_number': '国药准字H20067776' }, '仁和氨咖黄敏胶囊': { 'expiry_date': '24个月', 'manufacturer': '安徽安科恒益药业有限公司', 'approval_number': '国药准字H34023208' }, '仁和四季感冒胶囊': { 'expiry_date': '24个月', 'manufacturer': '广东佳泰药业股份有限公司', 'approval_number': '国药准字Z‌20168001' }, '仁和肺宁颗粒': { 'expiry_date': '24个月', 'manufacturer': '吉林益民堂制药有限公司', 'approval_number': '国药准字Z22023003' }, '仁和银黄颗粒': { 'expiry_date': '36个月', 'manufacturer': '河南诺美药业有限公司', 'approval_number': '国药准字Z20044588' }, '仁和蒲地蓝消炎片': { 'expiry_date': '24个月', 'manufacturer': '湖南方盛制药股份有限公司', 'approval_number': '国药准字Z20043422' }, '仁和复方鲜竹沥液': { 'expiry_date': '24个月', 'manufacturer': '江西远东药业股份有限公司', 'approval_number': '国药准字Z20153065' }, '仁和益气养血口服液': { 'expiry_date': '36个月', 'manufacturer': '通化汇金堂药业股份有限公司', 'approval_number': '国药准字Z20055044' }, '仁和氧氟沙星滴耳液': { 'expiry_date': '24个月', 'manufacturer': '武汉诺安药业有限公司', 'approval_number': '国药准字H20083321' }, '仁和蒙脱石散': { 'expiry_date': '24个月', 'manufacturer': '湖南方盛制药股份有限公司', 'approval_number': '国药准字H20094210' }, '仁和奥美拉唑肠溶胶囊': { 'expiry_date': '30个月', 'manufacturer': '河北山姆士药业有限公司', 'approval_number': '国药准字H20093291' }, '仁和氯雷他定片': { 'expiry_date': '30个月', 'manufacturer': '海南海神同洲制药有限公司', 'approval_number': '国药准字H20040797' }, '闪亮盐酸奥洛他定滴眼液': { 'expiry_date': '24个月', 'manufacturer': '江苏广承药业有限公司', 'approval_number': '国药准字H20183349' }, '闪亮左氧氟沙星滴眼液': { 'expiry_date': '24个月', 'manufacturer': '中山万汉制药有限公司', 'approval_number': '国药准字H20203122‌' }, '妇炎洁植物本草抑菌洗液380ml': { 'expiry_date': '24个月', 'manufacturer': '江西康美医药保健品有限公司', 'approval_number': '赣卫消证字(2010)第0003号‌' }, '妇炎洁洁阴康洗液': { 'expiry_date': '24个月', 'manufacturer': '江西药都仁和制药有限公司', 'approval_number': '国药准字Z20103066' }, '妇炎洁医用护理垫245*70': { 'expiry_date': '36个月', 'manufacturer': '美丽岛(福建)生活用品有限公司', 'approval_number': '闽泉械备20180016号' }, '妇炎洁克霉唑阴道片': { 'expiry_date': '36个月', 'manufacturer': '湖南华纳大药厂股份有限公司', 'approval_number': '国药准字H20043250' }, '仁和益母草颗粒': { 'expiry_date': '24个月', 'manufacturer': '广西圣特药业有限公司', 'approval_number': '国药准字Z45020484' }, '仁和红霉素眼膏': { 'expiry_date': '24个月', 'manufacturer': '福建省三明天泰制药有限公司', 'approval_number': '国药准字H20003077' }, '仁和炉甘石洗剂': { 'expiry_date': '24个月', 'manufacturer': '江苏华神药业有限公司', 'approval_number': '国药准字H20053895' }, '优卡丹葡萄糖酸钙锌口服溶液': { 'expiry_date': '24个月', 'manufacturer': '石家庄科仁医药科技有限公司', 'approval_number': '国药准字H20193310' }, '优卡丹小儿氨酚烷胺颗粒': { 'expiry_date': '2024-12-31', 'manufacturer': '江西铜鼓仁和制药有限公司', 'approval_number': '国药准字H20068170' }, '仁和湿毒清片': { 'expiry_date': '24个月', 'manufacturer': '江西药都仁和制药有限公司', 'approval_number': '国药准字Z20050472' }, '仁和阿达帕林凝胶': { 'expiry_date': '24个月', 'manufacturer': '江苏福邦药业有限公司', 'approval_number': '国药准字H20113373' }, '仁和盐酸二甲双胍缓释片': { 'expiry_date': '24个月', 'manufacturer': '河北山姆士药业有限公司', 'approval_number': '国药准字H20123024' }, '仁和替米沙坦胶囊': { 'expiry_date': '24个月', 'manufacturer': '江西杏林白马药业股份有限公司', 'approval_number': '国药准字H20070134' }, '仁和格列齐特缓释片': { 'expiry_date': '12个月', 'manufacturer': '江西制药有限责任公司', 'approval_number': '国药准字H20065489‌' }, '仁和双氯芬酸钠气雾剂': { 'expiry_date': '24个月', 'manufacturer': '广东同德药业有限公司', 'approval_number': '国药准字H20056346' }, '仁和硝苯地平缓释片': { 'expiry_date': '24个月', 'manufacturer': '烟台鲁银药业有限公司', 'approval_number': '国药准字H20073908' }, '仁和痔速宁片': { 'expiry_date': '24个月', 'manufacturer': '江西药都仁和制药有限公司', 'approval_number': '国药准字Z20073162' }, '仁和氧氟沙星滴眼液': { 'expiry_date': '24个月', 'manufacturer': '江西闪亮制药有限公司', 'approval_number': '国药准字H20067760' }, '克快好强力枇杷露': { 'expiry_date': '24个月', 'manufacturer': '江西药都樟树制药有限公司', 'approval_number': '国药准字Z36021750' }, '仁和盐酸左西替利嗪胶囊': { 'expiry_date': '18个月', 'manufacturer': '湖南九典制药股份有限公司', 'approval_number': '国药准字H20060183' }, '仁和甲钴胺胶囊': { 'expiry_date': '24个月', 'manufacturer': '山东鲁抗医药集团赛特有限责任公司', 'approval_number': '国药准字H20051424' }, '仁和多潘立酮片': { 'expiry_date': '36个月', 'manufacturer': '山西宝泰药业有限责任公司', 'approval_number': '国药准字H20010245' }, '仁和兰索拉唑肠溶片': { 'expiry_date': '24个月', 'manufacturer': '湖南华纳大药厂股份有限公司', 'approval_number': '国药准字H20084414' }, '仁和复方银翘氨敏胶囊': { 'expiry_date': '24个月', 'manufacturer': '江西新赣江药业股份有限公司', 'approval_number': '国药准字H36022108' }, '君扬他达拉非片': { 'expiry_date': '24个月', 'manufacturer': '江西药都仁和制药有限公司', 'approval_number': '国药准字H20233233‌' }, '仁和盐酸达泊西汀片': { 'expiry_date': '24个月', 'manufacturer': '厦门力卓药业有限公司', 'approval_number': '国药准字H20213156' }, '仁和藿香正气合剂10ml*6': { 'expiry_date': '24个月', 'manufacturer': '广西邦琪药业集团有限公司', 'approval_number': '国药准字Z45022009' }, '仁和阿昔洛韦片': { 'expiry_date': '24个月', 'manufacturer': '康普药业股份有限公司', 'approval_number': '国药准字H43020286' }, '仁和糠酸莫米松乳膏': { 'expiry_date': '24个月', 'manufacturer': '武汉诺安药业有限公司', 'approval_number': '国药准字H20173401' }, '米阿卡头孢克肟颗粒': { 'expiry_date': '24个月', 'manufacturer': '康普药业股份有限公司', 'approval_number': '国药准字H20068130‌' }, '克快好治咳枇杷合剂': { 'expiry_date': '24个月', 'manufacturer': '江西省芙蓉堂药业股份有限公司', 'approval_number': '国药准字Z20027452' }, '仁和雪梨膏': { 'expiry_date': '24个月', 'manufacturer': '武汉太福制药有限公司', 'approval_number': '国药准字Z42021449' }, '仁和西青果颗粒': { 'expiry_date': '18个月', 'manufacturer': '广西壮族自治区药物研究所有限公司', 'approval_number': '国药准字Z45022149' }, '仁和氨酚烷胺那敏胶囊': { 'expiry_date': '24个月', 'manufacturer': '大同市利群药业有限责任公司', 'approval_number': '国药准字H14022808' }, '仁和美洛昔康片': { 'expiry_date': '24个月', 'manufacturer': '宁波大红鹰药业股份有限公司', 'approval_number': '国药准字H20031131' } } if self.search_key in medicine_info: info = medicine_info[self.search_key] expiry_date = info['expiry_date'] manufacturer = info['manufacturer'] approval_number = info['approval_number'] else: # 如果药品不在字典中，使用默认值 expiry_date = '' manufacturer = '' approval_number = '' #是否存在说明书 # is_has_instructions = self.has_instructions() # '仁和盐酸氨溴索口服溶液', # '仁和蒲公英颗粒', # '仁和红霉素软膏', # '仁和可立克复方氨酚烷胺胶囊12粒', # '仁和盐酸羟甲唑啉喷雾剂', # '仁和咽炎片', # '仁和曲安奈德益康唑乳膏', # '仁和头孢克洛干混悬剂', # '伊康美宝甲硝唑氯己定洗剂', # '仁和布洛芬缓释胶囊' #有的药品没有说明书，直接默认 # if self.search_key == '仁和盐酸氨溴索口服溶液': # expiry_date = '24个月' # manufacturer = '山东益康药业股份有限公司' # approval_number = '国药准字H20065840' # elif self.search_key == '仁和蒲公英颗粒': # expiry_date = '24个月' # manufacturer = '江西心诚药业有限公司' # approval_number = '国药准字Z200055430' # elif self.search_key == '仁和红霉素软膏': # expiry_date = '24个月' # manufacturer = '江西德成制药有限公司' # approval_number = '国药准字H36020018' # elif self.search_key == '仁和可立克复方氨酚烷胺胶囊12粒': # expiry_date = '30个月' # manufacturer = '江西铜鼓仁和制药有限公司' # approval_number = '国药准字H20068169' # elif self.search_key == '仁和盐酸羟甲唑啉喷雾剂': # expiry_date = '24个月' # manufacturer = '南京海鲸药业有限公司' # approval_number = '国药准字H20057401' # elif self.search_key == '仁和咽炎片(薄膜衣片)': # expiry_date = '24个月' # manufacturer = '石家庄东方药业股份有限公司' # approval_number = '国药准字Z20093479' # elif self.search_key == '仁和曲安奈德益康唑乳膏': # expiry_date = '36个月' # manufacturer = '福建太平洋制药有限公司' # approval_number = '国药准字H20064180' # elif self.search_key == '仁和头孢克洛干混悬剂': # expiry_date = '24个月' # manufacturer = '山东益康药业股份有限公司' # approval_number = '国药准字H20084417' # elif self.search_key == '伊康美宝甲硝唑氯己定洗剂': # expiry_date = '24个月' # manufacturer = '江西药都仁和制药有限公司' # approval_number = '国药准字H20043498' # elif self.search_key == '仁和布洛芬缓释胶囊': # expiry_date = '36个月' # manufacturer = '福建太平洋制药有限公司' # approval_number = '国药准字H20093691' # elif self.search_key == '闪亮萘敏维滴眼液': # expiry_date = '24个月' # manufacturer = '江西闪亮制药有限公司' # approval_number = '国药准字H20064223' # elif self.search_key == '闪亮复方门冬维甘滴眼液': # expiry_date = '24个月' # manufacturer = '江西闪亮制药有限公司' # approval_number = '国药准字H20083254‌' # elif self.search_key == '米阿卡小儿止咳糖浆': # expiry_date = '24个月' # manufacturer = '江西远东药业股份有限公司' # approval_number = '国药准字Z36020251' # elif self.search_key == '仁和人工牛黄甲硝唑胶囊': # expiry_date = '24个月' # manufacturer = '江西药都仁和制药有限公司' # approval_number = '国药准字H36022263' # elif self.search_key == '仁和盐酸左氧氟沙星胶囊': # expiry_date = '24个月' # manufacturer = '海南海神同洲制药有限公司' # approval_number = '国药准字H20103012' # elif self.search_key == '仁和苯磺酸氨氯地平片': # expiry_date = '36个月' # manufacturer = '江西制药有限责任公司' # approval_number = '国药准字H20083949' # elif self.search_key == '仁和阿昔洛韦乳膏': # expiry_date = '24个月' # manufacturer = '江西吉安三力制药有限公司' # approval_number = '国药准字H20063386' # else: # is_has_instructions = self.safe_exec(self.has_instructions) # # 说明书等信息 # if is_has_instructions: # print('开始获取说明书信息') # # instructions_info = self.get_instructions_data() # instructions_info = self.safe_exec(self.get_instructions_data) # if instructions_info['有效期'] is not None: # expiry_date = instructions_info['有效期'].strip('。') # if instructions_info['生产单位'] is not None: # manufacturer = instructions_info['生产单位'].strip('。') # if instructions_info['批准文号'] is not None: # approval_number = instructions_info['批准文号'].strip('。') # else: # # 没有说明书不入库 # print('没有获取到说明书信息') # self.swipe_back(1) # return #暂时不获取说明书信息 end self.unrelated_data = 0 # 爬取省份 scrape_province = '广东' # 这里先默认广东 # 是否有货 availability = '' save_data = { 'product': product, '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': '美团', 'search_key': self.search_key, } self.save_to_database(save_data) # time.sleep(100000) time.sleep(self.get_sleep_time()) if self.distinct_target(): print('已到达搜索列表页') else: for i in range(1): print('在详情页') self.swipe_back(1) time.sleep(self.get_sleep_time()) # 最外部有个定位按钮 if self.distinct_target(): break #主函数 def main(self, device_id, retry_count=0): MAX_RETRY = 3 # 最大重试次数 spider_no = 0 self.connect_devices(device_id) time.sleep(self.get_sleep_time()) # self.d.toast.show("测试toast", 20) # 启动全局弹窗监控 self.monitor = SpiderMonitor(self) self.monitor.start() try: # 重新开启美团应用 self.restart_app() # 搜索关键字 # self.enter_target_page() self.safe_exec(self.enter_target_page) # print('开始滑动') # self.d.drag(300, 1400, 300, 400, 1) # time.sleep(100000) for idx in range(300): print(f'第{idx + 1}页') if spider_no > 30: time.sleep(60) spider_no = 0 print('目前无关数据量: ', self.unrelated_data) # 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 > 10: # # 连续超过5个不达标的数据则停止采集 self.loggerMT.info('连续10个不达标的数据则停止该品规数据的采集') return # 线程安全获取商品列表 # drug_lis = self.d.xpath('//android.support.v7.widget.RecyclerView/android.widget.FrameLayout').all() # drug_lis = self.safe_list('//android.support.v7.widget.RecyclerView/android.widget.FrameLayout', self.monitor) while True: if self.d.xpath('//android.support.v7.widget.RecyclerView/android.widget.FrameLayout').exists: break time.sleep(1) drug_lis = self.safe_exec(self.d.xpath('//android.support.v7.widget.RecyclerView/android.widget.FrameLayout').all) lis_len = len(drug_lis) print(f'当前页面共有{lis_len}个商品') for idxx,drug_one in enumerate(drug_lis,start = 1): bounds = drug_one.info['bounds'] top = bounds['top'] bottom = bounds['bottom'] # height = bottom - top print(f'当前商品bottom:{bottom}') print(f'当前商品top:{top}') # if 304 <= top and bottom <= 1475: # 默认高度241的才行 if 304 <= top and bottom <= 1475: # 默认高度241的才行 1559 # print('目标-->', drug_one.info) # drug_one.click() #获取当前元素中的属性来判断是否要点击进入采集 print(f"这页的第几个商品:{idxx}") product_title = '' price = '' shop_name = '' #商品名称的xpath product_tittle_xpath = f'//android.support.v7.widget.RecyclerView/android.widget.FrameLayout[{idxx}]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.FrameLayout[1]/android.widget.TextView' product_tittle_xpath2 = f'//android.support.v7.widget.RecyclerView/android.widget.FrameLayout[{idxx}]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.FrameLayout[1]/android.widget.TextView' if self.d.xpath(product_tittle_xpath).exists: product_title = self.d.xpath(product_tittle_xpath).text product_title = product_title[1:] if product_title.startswith('0') else product_title print(f"product_tittle_xpath列表当前商品名称:{product_title}") elif self.d.xpath(product_tittle_xpath2).exists: product_title = self.d.xpath(product_tittle_xpath2).text product_title = product_title[1:] if product_title.startswith('0') else product_title print(f"product_tittle_xpath2列表当前商品名称:{product_title}") else: print(f"列表当前商品名称不存在") #优化流程，只有product_title 不为空的时候才判断当前名称是否符合标准 if product_title: if '仁和' in self.search_key: if self.search_key == '仁和可立克复方氨酚烷胺胶囊12粒': temp_search_key = self.search_key.replace("仁和可立克", "") temp_search_key = temp_search_key.replace("12粒", "") elif self.search_key == '仁和咽炎片(薄膜衣片)': temp_search_key = self.search_key.replace("仁和", "") temp_search_key = temp_search_key.replace("(薄膜衣片)", "") elif self.search_key == '仁和中方消炎镇痛膏': temp_search_key = self.search_key.replace("仁和中方", "") elif self.search_key == '仁和藿香正气合剂10ml*6': temp_search_key = self.search_key.replace("仁和", "") temp_search_key = temp_search_key.replace("10ml*6", "") elif self.search_key == '仁和可立克磷酸奥司他韦胶囊': temp_search_key = self.search_key.replace("仁和可立克", "") elif self.search_key == '仁和可立克感冒软胶囊': temp_search_key = self.search_key.replace("仁和可立克", "") else: temp_search_key = self.search_key.replace("仁和", "") else: if self.search_key == '伊康美宝甲硝唑氯己定洗剂': temp_search_key = self.search_key.replace("伊康美宝", "") elif self.search_key == '闪亮萘敏维滴眼液': temp_search_key = self.search_key.replace("闪亮", "") elif self.search_key == '闪亮复方门冬维甘滴眼液': temp_search_key = self.search_key.replace("闪亮", "") elif self.search_key == '米阿卡小儿止咳糖浆': temp_search_key = self.search_key.replace("米阿卡", "") elif self.search_key == '达舒克硝酸益康唑喷雾剂': temp_search_key = self.search_key.replace("达舒克", "") elif self.search_key == '闪亮盐酸奥洛他定滴眼液': temp_search_key = self.search_key.replace("闪亮", "") elif self.search_key == '闪亮左氧氟沙星滴眼液': temp_search_key = self.search_key.replace("闪亮", "") elif self.search_key == '妇炎洁植物本草抑菌洗液380ml': temp_search_key = self.search_key.replace("妇炎洁", "") temp_search_key = temp_search_key.replace("380ml", "") elif self.search_key == '妇炎洁洁阴康洗液': temp_search_key = self.search_key.replace("妇炎洁", "") elif self.search_key == '妇炎洁医用护理垫245*70': temp_search_key = self.search_key.replace("妇炎洁", "") temp_search_key = temp_search_key.replace("245*70", "") elif self.search_key == '妇炎洁克霉唑阴道片': temp_search_key = self.search_key.replace("妇炎洁", "") elif self.search_key == '优卡丹葡萄糖酸钙锌口服溶液': temp_search_key = self.search_key.replace("优卡丹", "") elif self.search_key == '优卡丹小儿氨酚烷胺颗粒': temp_search_key = self.search_key.replace("优卡丹", "") elif self.search_key == '克快好强力枇杷露': temp_search_key = self.search_key.replace("克快好", "") elif self.search_key == '君扬他达拉非片': temp_search_key = self.search_key.replace("君扬", "") elif self.search_key == '米阿卡头孢克肟颗粒': temp_search_key = self.search_key.replace("米阿卡", "") elif self.search_key == '克快好治咳枇杷合剂': temp_search_key = self.search_key.replace("克快好", "") elif self.search_key == '优卡丹三合钙咀嚼片': temp_search_key = self.search_key.replace("优卡丹", "") elif self.search_key == '必艾得吲哚美辛巴布膏': temp_search_key = self.search_key.replace("必艾得", "") elif self.search_key == '宁新宝葡萄糖酸钙片': temp_search_key = self.search_key.replace("宁新宝", "") elif self.search_key == '闪亮玻璃酸钠滴眼液': temp_search_key = self.search_key.replace("闪亮", "") elif self.search_key == '闪亮地夸磷索钠滴眼液': temp_search_key = self.search_key.replace("闪亮", "") elif self.search_key == '闪亮复方尿维氨滴眼液': temp_search_key = self.search_key.replace("闪亮", "") elif self.search_key == '闪亮盐酸莫西沙星滴眼液': temp_search_key = self.search_key.replace("闪亮", "") if self.search_key == '伊康美宝甲硝唑氯己定洗剂': if '伊康美宝' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '仁和可立克复方氨酚烷胺胶囊12粒': if '仁和' 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:{temp_search_key}") self.unrelated_data += 1 continue elif '12' not in product_title: print(f"当前商品名称:{product_title} 不包含12品规") self.unrelated_data += 1 continue elif self.search_key == '仁和咽炎片(薄膜衣片)': if '仁和' 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:{temp_search_key}") self.unrelated_data += 1 continue elif '0.25g*15片*3板' not in product_title: print(f"当前商品名称:{product_title} 不包含0.25g*15片*3板品规") self.unrelated_data += 1 continue elif self.search_key == '闪亮萘敏维滴眼液': if '闪亮' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '闪亮复方门冬维甘滴眼液': if '闪亮' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '米阿卡小儿止咳糖浆': if '米阿卡' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '仁和中方消炎镇痛膏': if '仁和中方' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '达舒克硝酸益康唑喷雾剂': if '达舒克' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '闪亮盐酸奥洛他定滴眼液': if '闪亮' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '闪亮左氧氟沙星滴眼液': if '闪亮' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '妇炎洁植物本草抑菌洗液380ml': if '妇炎洁' 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:{temp_search_key}") self.unrelated_data += 1 continue elif '380ml' not in product_title: print(f"当前商品名称:{product_title} 不包含380ml品规") self.unrelated_data += 1 continue elif self.search_key == '妇炎洁洁阴康洗液': if '妇炎洁' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '妇炎洁医用护理垫245*70': if '妇炎洁' 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:{temp_search_key}") self.unrelated_data += 1 continue elif '245*70' not in product_title: print(f"当前商品名称:{product_title} 不包含245*70品规") self.unrelated_data += 1 continue elif self.search_key == '妇炎洁克霉唑阴道片': if '妇炎洁' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '优卡丹葡萄糖酸钙锌口服溶液': if '优卡丹' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '优卡丹小儿氨酚烷胺颗粒': if '优卡丹' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '克快好强力枇杷露': if '克快好' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '君扬他达拉非片': if '君扬' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '仁和藿香正气合剂10ml*6': if '仁和' 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:{temp_search_key}") self.unrelated_data += 1 continue elif '10ml*6' not in product_title: print(f"当前商品名称:{product_title} 不包含10ml*6品规") self.unrelated_data += 1 continue elif self.search_key == '米阿卡头孢克肟颗粒': if '米阿卡' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '克快好治咳枇杷合剂': if '克快好' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '仁和可立克磷酸奥司他韦胶囊': if '仁和可立克' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '仁和可立克感冒软胶囊': if '仁和可立克' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '优卡丹三合钙咀嚼片': if '优卡丹' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '必艾得吲哚美辛巴布膏': if '必艾得' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '宁新宝葡萄糖酸钙片': if '宁新宝' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '闪亮玻璃酸钠滴眼液': if '闪亮' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '闪亮地夸磷索钠滴眼液': if '闪亮' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '闪亮复方尿维氨滴眼液': if '闪亮' 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:{temp_search_key}") self.unrelated_data += 1 continue elif self.search_key == '闪亮盐酸莫西沙星滴眼液': if '闪亮' 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:{temp_search_key}") self.unrelated_data += 1 continue else: if '仁和' 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:{temp_search_key}") self.unrelated_data += 1 continue #价格 price_xpath = f'//android.support.v7.widget.RecyclerView/android.widget.FrameLayout[{idxx}]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.FrameLayout[1]/android.widget.TextView' price_xpath3 = f'//android.support.v7.widget.RecyclerView/android.widget.FrameLayout[{idxx}]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.FrameLayout[1]/android.widget.TextView' price_xpath1 = f'//android.support.v7.widget.RecyclerView/android.widget.FrameLayout[{idxx}]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.FrameLayout[1]/android.widget.TextView' if self.d.xpath(price_xpath).exists: price_str = self.d.xpath(price_xpath).text print(f"price_xpath列表当前商品价格:{price_str}") if price_str: price = float(re.search('[\d\.]+', price_str).group()) elif self.d.xpath(price_xpath3).exists: price_str = self.d.xpath(price_xpath3).text print(f"price_xpath3列表当前商品价格:{price_str}") if price_str: price = float(re.search('[\d\.]+', price_str).group()) elif self.d.xpath(price_xpath1).exists: price_str = self.d.xpath(price_xpath1).text print(f"price_xpath1列表当前商品价格:{price_str}") if price_str: price = float(re.search('[\d\.]+', price_str).group()) else: price_xpath2 = f'//android.support.v7.widget.RecyclerView/android.widget.FrameLayout[{idxx}]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.widget.FrameLayout[1]/android.widget.TextView' if self.d.xpath(price_xpath2).exists: price_str = self.d.xpath(price_xpath2).text print(f"price_xpath2列表当前商品价格:{price_str}") if price_str: price = float(re.search('[\d\.]+', price_str).group()) else: print(f"列表当前商品价格不存在") # price_str = self.d.xpath(f'//android.support.v7.widget.RecyclerView/android.widget.FrameLayout[{idxx}]//*[starts-with(@text,"¥")]').text print(f'列表获取到价格:{price}') #店铺名称的xpath shop_name_xpath = f'//android.support.v7.widget.RecyclerView/android.widget.FrameLayout[{idxx}]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.FrameLayout[last()]/android.widget.TextView[1]' shop_name_xpath2 = f'//android.support.v7.widget.RecyclerView/android.widget.FrameLayout[{idxx}]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[1]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[2]/android.view.ViewGroup[1]/android.widget.FrameLayout[last()]/android.widget.TextView[1]' if self.d.xpath(shop_name_xpath).exists: shop_name = self.d.xpath(shop_name_xpath).text print(f"shop_name_xpath列表当前商品店铺名称:{shop_name}") elif self.d.xpath(shop_name_xpath2).exists: shop_name = self.d.xpath(shop_name_xpath2).text print(f"shop_name_xpath2列表当前商品店铺名称:{shop_name}") else: print(f"列表当前商品店铺名称不存在") #如果商品的名称、价格和生产厂家都不存在则直接下一条数据。 跳过一些不是商品的数据。 if product_title == '' and price == '' and shop_name == '': continue scrape_date = self.get_current_date() if product_title and price and shop_name: #判断数据表中是否存在 dup_data = {'product': product_title, 'min_price': price, 'shop': shop_name, 'scrape_date': scrape_date,'platform': '美团'} if self.data_is_exists(dup_data): print('列表存在相同数据不入库') continue # match = re.match(r'(\[[^\]]+\])(.*?)\s*((?:\d+\S*|\(.+))$', product_title) # if match: # specifications = match.group(3).strip() # else: # specifications = '' # save_data = { # 'product': product_title, # 'min_price': price, # 'manufacture_date': '', # 'expiry_date': '', # 'shop': shop_name, # 'business_license_company': '', # 'province': '', # 'city': '', # 'manufacturer': '', # 'specification': specifications, # 'approval_number': '', # 'product_link': '', # 'scrape_date': scrape_date, # 'scrape_province': scrape_province, # 'availability': '', # 'credit_code': '', # 'platform': '美团', # 'search_key': self.search_key, # } # self.save_to_database(save_data) # time.sleep(self.get_sleep_time()) self.safe_exec(drug_one.click) print('点击目标药品完毕') time.sleep(2) # 采集药品信息 try: # self.integrate_data() 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 self.d.xpath('//*[@text="搜索"]').exists: print("检测到搜索按钮，重新开始采集流程") 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, retry_count+1) else: print("超过最大重试次数，终止程序") return else: print("无法恢复页面，终止采集") 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}') #增加阻塞的方法： if not self.distinct_target(): for i in range(1): self.swipe_back(1) # 最外部有个定位按钮 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.xpath('//*[@text="已经到底啦"]').exists: print('已经到达列表页最底部') return search_list = self.d.xpath('//android.support.v7.widget.RecyclerView').info bounds = search_list['bounds'] #print('搜索列表高度', 1400 + bounds['top'] - bounds['bottom']) # self.d.swipe(200, 1400, 200, 1400 + bounds['top'] - bounds['bottom']) # 计算滑动距离 scroll_distance = bounds['bottom'] - bounds['top'] # 正数 start_y = 1600 end_y = start_y - scroll_distance # 向上滑动，y 坐标减小 # 确保 end_y 不小于 0 end_y = max(end_y, 304) # 留出一点边距，避免滑出屏幕 # print('滑动起点 y:', start_y, '终点 y:', end_y) # self.d.swipe(200, start_y, 200, end_y, 0.4) print('开始滑动') self.d.drag(300, 1400, 300, 400, 1) # self.safe_exec(self.d.drag, 300, 1400, 300, 400, 1) print('滑动结束') #print('搜索列表高度', 1400 + bounds['top'] - bounds['bottom']) # self.d.swipe(200, 1400, 200, 1400 + bounds['top'] - bounds['bottom']) # self.d.swipe(200, 1400, 200, 1400 + bounds['top'] - bounds['bottom'], 0.4) time.sleep(self.get_sleep_time()) finally: # 确保监控线程被停止 self.monitor.stop() self.monitor.join() def unitest(self): """ 单元测试 :return: """ save_data = { 'product':"[昆中药]舒肝颗粒(低糖型)", 'min_price': 14.0, 'manufacture_date': '', 'expiry_date': '36个月', 'shop': '美团自营大药房（快递电商）', 'business_license_company': '', 'province': '', 'city': '', 'manufacturer': '昆明中药厂有限公司', 'specification': '3g*16袋/盒', 'approval_number': '国药准字Z53021161', 'product_link': '', 'scrape_date': '2025/07/09', 'scrape_province': '广东', 'availability': '', 'credit_code': '', 'platform': '美团' } self.save_to_database(save_data) time.sleep(100000) pass def main(): keys_list = [ # '三九胃泰颗粒', # '999小柴胡颗粒', # '999强力枇杷露', # '[999]感冒清热颗粒', # '999抗病毒口服液', # '999皮炎平', # '999盐酸特比萘芬乳膏', # '999盐酸特比萘芬', # '999藿香正气合剂', # '999必无忧盐酸特比萘芬乳膏', # '999复方感冒灵颗粒', # '999糠酸莫米松凝胶', # '999铝碳酸镁咀嚼片', # '999阿奇霉素片', # '999选平硝酸咪康唑乳膏', # 按需继续添加, #暂时不需要 # '999必无忧盐酸特比萘芬喷雾剂30' # '999冰连清咽' # '999复方金银花颗粒10g' # '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ec颗粒' # '三九胃泰养胃舒颗粒8袋' # '999止泻利颗粒15g*8' # '999阿奇霉素片' # '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 #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、999维生素ec颗粒 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冰连清咽 没有数据 # '999藿香正气合剂', # '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', # '999复方感冒灵颗粒', # '999黄芪精', # '999皮炎平曲安奈德益康唑乳膏30', # '999葡萄糖酸锌口服溶液', # '今维多赐多康牌蛋白粉', # '佳美舒阿奇霉素肠溶胶囊4' # '999必无忧盐酸特比萘芬乳膏15g' # '999复方板蓝根颗粒15g*15袋/盒' # '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' #OTC # '999强力枇杷露150ml' # '999糠酸莫米松乳膏10g支' # '999选平硝酸咪康唑乳膏20g' # '999感冒清热颗粒(无糖)6g' # '999银菊清咽颗粒' #只有一条数据 # '999补脾益肠丸' # '999壮骨关节丸6g*20' # '999壮骨关节胶囊' # '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(无糖)2.5g*6' # 没有数据 #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 # '顺峰康王酮康他索乳膏' #包含10g和20g两个规格 10g 不低于7.5 20g 不低于12.5 # '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 # '999复方氨酚烷胺胶囊10粒' #禁止挂网 # '999复方氨酚烷胺胶囊6粒' #禁止挂网 # '999复方氨酚烷胺胶囊' # '999咽炎片0.26g*12片*2板' #不低于13.5 # '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 # '999小儿感冒宁颗粒2.5g*10袋' #禁止挂网 # '999磷酸奥司他韦胶囊75mg*10' #仅限999官旗店 # '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' # 仁和 O2O # '仁和盐酸氨溴索口服溶液', # '仁和蒲公英颗粒', # '仁和红霉素软膏', # '仁和可立克复方氨酚烷胺胶囊12粒', # '仁和盐酸羟甲唑啉喷雾剂', # '仁和咽炎片(薄膜衣片)', # '仁和曲安奈德益康唑乳膏', # '仁和头孢克洛干混悬剂', # '伊康美宝甲硝唑氯己定洗剂', # '仁和布洛芬缓释胶囊', # '闪亮萘敏维滴眼液', # '闪亮复方门冬维甘滴眼液', # '米阿卡小儿止咳糖浆', # '仁和人工牛黄甲硝唑胶囊', # '仁和盐酸左氧氟沙星胶囊', # '仁和苯磺酸氨氯地平片', # '仁和阿昔洛韦乳膏', # '仁和阿莫西林胶囊', # '仁和小柴胡颗粒', # '仁和中方消炎镇痛膏', ##特殊处理 # '仁和头孢克肟片', # '仁和头孢克洛分散片', # '仁和诺氟沙星胶囊', # '仁和川贝清肺糖浆', # '达舒克硝酸益康唑喷雾剂', # '仁和清火胶囊', # '仁和双氯芬酸钠缓释片', # '仁和氨咖黄敏胶囊', # '仁和四季感冒胶囊', # '仁和肺宁颗粒', # '仁和银黄颗粒', # '仁和蒲地蓝消炎片', # '仁和复方鲜竹沥液', # '仁和益气养血口服液', # '仁和氧氟沙星滴耳液', # '仁和蒙脱石散', # '仁和奥美拉唑肠溶胶囊', # '仁和氯雷他定片', # '闪亮盐酸奥洛他定滴眼液', # '闪亮左氧氟沙星滴眼液', # '妇炎洁植物本草抑菌洗液380ml', # '妇炎洁洁阴康洗液', # '妇炎洁医用护理垫245*70', # '妇炎洁克霉唑阴道片', # '仁和益母草颗粒', # '仁和红霉素眼膏', # '仁和炉甘石洗剂', # '优卡丹葡萄糖酸钙锌口服溶液', # '优卡丹小儿氨酚烷胺颗粒', # '仁和湿毒清片', # '仁和阿达帕林凝胶', # '仁和盐酸二甲双胍缓释片', # '仁和替米沙坦胶囊', # '仁和格列齐特缓释片', # '仁和双氯芬酸钠气雾剂', # '仁和硝苯地平缓释片', # '仁和痔速宁片', # '仁和氧氟沙星滴眼液', # '仁和盐酸左西替利嗪胶囊', # '克快好强力枇杷露', # '仁和甲钴胺胶囊', # '仁和多潘立酮片', # '仁和兰索拉唑肠溶片', # '仁和复方银翘氨敏胶囊', # '君扬他达拉非片', # '仁和盐酸达泊西汀片', # '仁和藿香正气合剂10ml*6', # '仁和阿昔洛韦片', # '仁和糠酸莫米松乳膏', # '米阿卡头孢克肟颗粒', # '克快好治咳枇杷合剂', # '仁和雪梨膏', # '仁和西青果颗粒', # '仁和氨酚烷胺那敏胶囊', # '仁和美洛昔康片', #20260126 #20260126 # '仁和可立克磷酸奥司他韦胶囊', # '仁和二至丸', # '仁和杞菊地黄口服液', # '仁和可立克感冒软胶囊', # # '优卡丹三合钙咀嚼片', # '仁和三合钙咀嚼片', # '仁和愈风宁心片', # '仁和碳酸钙D3咀嚼片', # '仁和罗红霉素分散片', # # '必艾得吲哚美辛巴布膏', # '仁和血塞通分散片', # '仁和胶体果胶铋胶囊', # '仁和足光散', # '仁和阿莫西林克拉维酸钾颗粒', # # '宁新宝葡萄糖酸钙片', # '仁和脑心舒口服液', # '仁和前列安通胶囊', # '仁和小儿七星茶颗粒', # '仁和至灵胶囊', # '仁和肾骨片', # '仁和盐酸班布特罗胶囊', # '仁和妇炎康分散片', # '仁和益心酮分散片', # '仁和莲芝消炎片', # '仁和生发丸', # '仁和胆舒软胶囊', # '仁和咳喘舒片', # '仁和苹果酸氯波必利片', # '仁和六味补血胶囊', # '仁和复方黄连素片', # '仁和复方桔梗止咳片', # '仁和孟鲁司特钠颗粒', # '仁和吲达帕胺缓释片', # '仁和依托红霉素颗粒', # '仁和硝酸咪康唑阴道软胶囊', # '仁和尼美舒利片', # '仁和骨刺消痛胶囊', # '仁和复方罗汉果止咳颗粒', # '仁和复方熊胆薄荷含片', # '仁和灵芝胶囊', # '仁和盐酸氨基葡萄糖片', # '仁和一清软胶囊', # '仁和复方北豆根氨酚那敏片', # '仁和止咳枇杷颗粒', # '仁和润肠丸', # '仁和肌苷口服溶液', # '仁和溃疡胶囊', # '仁和磷酸苯丙哌林片', # '仁和双梅喉片', # '仁和尼美舒利胶囊', # '仁和安康胶囊', # '仁和补气口服液', # '仁和大活络丸', # '仁和龟甲胶', # '仁和蚝贝钙咀嚼片', # '仁和健心胶囊', # '仁和金参润喉合剂）', # '仁和赖氨酸维B12颗粒', # '仁和肾宝胶囊', # '仁和肾脾双补口服液', # '仁和维生素EC片', # '仁和医用透明质酸钠敷料', # '仁和龟鹿二仙膏', # '仁和硫酸氢氯吡格雷片', # '仁和复方石韦胶囊', # '仁和参芪咀嚼片', # '仁和阿胶粉', # '仁和妇炎净片', # '仁和西洋参胶囊', # '仁和强力枇杷膏（蜜炼）', # '仁和藤黄健骨片', # '仁和依折麦布片', # '仁和阿归养血颗粒', # '仁和阿胶', # '仁和阿胶益寿口服液', # '仁和阿莫西林分散片', # '仁和阿莫西林颗粒', # '仁和阿奇霉素干混悬剂', # '仁和阿奇霉素胶囊', # '仁和阿托伐他汀钙分散片', # '仁和艾司奥美拉唑镁肠溶胶囊', # '仁和安宫牛黄丸', # '仁和氨酚咖黄烷胺片', # '仁和氨糖美辛肠溶片', # '仁和氨溴特罗口服溶液', # '仁和奥美拉唑肠溶片', # '仁和奥硝唑分散片', # '仁和板蓝根颗粒', # '仁和保和颗粒', # '仁和苯磺酸左氨氯地平片', # '仁和鼻炎宁颗粒', # '仁和冰硼含片', # '闪亮玻璃酸钠滴眼液', # '仁和补肾益寿片', # '仁和不老莓叶黄素酯DHA软糖', # '仁和布洛芬混悬液', # '仁和布洛芬颗粒', # '仁和参苓白术胶囊', # '仁和参苓口服液', # '仁和参术儿康糖浆', # '仁和藏青果喉片', # '仁和川贝止咳露', # '闪亮地夸磷索钠滴眼液', # '仁和跌打损伤丸', # '仁和跌打万花油', # '仁和独一味软胶囊', # '仁和对乙酰氨基酚颗粒', # '仁和多维元素胶囊', # '仁和多维元素片', # '仁和厄贝沙坦氢氯噻嗪片', # '仁和儿宝颗粒', # '仁和二丁颗粒', # '仁和二甲双胍格列本脲片', # '仁和非布司他片', # '仁和非那雄胺片', # '仁和肺宁胶囊', # '仁和肺宁片', # '仁和风油精', # '仁和参花消渴茶', # '仁和佛手苦瓜茶', # '仁和氟康唑胶囊', # '仁和妇炎康复咀嚼片', # '仁和附桂风湿膏', # '仁和复方川芎吲哚美辛胶囊', # '仁和复方罗汉果含片', # '仁和复方氯己定含漱液', # '闪亮复方尿维氨滴眼液', # '仁和复方酮康唑软膏', # '仁和复方土槿皮酊', # '仁和复方乌鸡口服液', # '仁和复方锌铁钙口服溶液', # '仁和感冒清胶囊', # '仁和感冒清热颗粒', # '仁和感冒止咳颗粒', # '仁和格列吡嗪片', # '仁和格列美脲胶囊', # '仁和根痛平胶囊', # '仁和枸橼酸铋钾胶囊', # '仁和枸橼酸氢钾钠颗粒', # '仁和枸橼酸西地那非口崩片', # '仁和骨友灵贴膏', # '仁和关节止痛膏', # '仁和桂龙咳喘宁片', # '仁和琥珀酸亚铁片', # '仁和琥乙红霉素颗粒', # '仁和护肝片', # '仁和护花天使牌妇泰欣抑菌洗液', # '仁和活血止痛片', # '仁和藿香正气胶囊', # '仁和藿香正气口服液', # '仁和健儿消食口服液', # '仁和健心胶囊（', # '仁和降脂宁颗粒', # '仁和金参润喉合剂', # '仁和颈康胶囊', # '仁和橘红颗粒', # '仁和橘红枇杷片', # '仁和橘红痰咳颗粒', # '仁和抗病毒口服液', # '仁和抗宫炎胶囊', # '仁和抗骨质增生丸', # '仁和咳特灵胶囊', # '仁和口服补液盐散(Ⅲ)', # '仁和口服五维赖氨酸葡萄糖', # '仁和辣椒风湿膏', '仁和蓝莓叶黄素酯压片糖果', # '仁和了哥王胶囊', '仁和了哥王颗粒', # '仁和雷贝拉唑钠肠溶片', # '仁和利多卡因氯己定气雾剂', # '仁和磷酸奥司他韦胶囊', # '仁和硫酸氨基葡萄糖片', '闪亮硫酸锌尿囊素滴眼液', # '仁和六味地黄胶囊', '仁和六味地黄丸（浓缩丸）', # '仁和罗汉果止咳糖浆', # '仁和罗红霉素胶囊', '仁和罗红霉素颗粒', # '仁和洛索洛芬钠片', # '仁和孟鲁司特钠咀嚼片', '仁和尼可地尔片', # '仁和尿素维E乳膏', # '仁和排毒养颜片', # '仁和排石利胆颗粒', '仁和葡萄糖酸锌颗粒', # '仁和葡萄糖酸锌口服溶液', # '仁和杞菊地黄丸(浓缩丸)', # '仁和前列金丹胶囊', # '仁和强力枇杷露', # '仁和氢溴酸右美沙芬糖浆', # '仁和清淋颗粒', # '仁和清淋片', # '仁和清热明目茶', # '仁和祛浊茶', # '仁和瑞舒伐他汀钙片', # '仁和润肠胶囊', # '仁和润肺止咳胶囊', # '仁和三维葡磷钙咀嚼片', # '仁和伤湿解痛膏', # '仁和麝香关节止痛膏', # '仁和麝香壮骨膏', # '仁和十二乌鸡白凤丸', # '仁和舒筋活血片', # '仁和四季感冒片', # '仁和他达拉非片', # '仁和天麻首乌片', # '仁和通脉颗粒', # '仁和通宣理肺片', # '仁和酮洛芬贴片', # '仁和头孢克肟颗粒', # '仁和维生素C咀嚼片', # '仁和维生素E软胶囊', # '仁和胃康灵胶囊', # '仁和胃痛宁片', # '仁和午时茶颗粒', # '仁和消渴降糖胶囊', # '仁和消栓通络片', # '仁和消炎镇痛膏', # '仁和硝酸益康唑喷雾剂', # '仁和硝酸益康唑乳膏', # '仁和小儿氨酚黄那敏颗粒', # '仁和小儿感冒颗粒', # '仁和小儿化痰止咳颗粒', # '仁和小儿咳喘灵颗粒', # '仁和小儿咽扁颗粒', # '仁和小儿止咳糖浆', # '仁和缬沙坦氨氯地平片（Ⅰ）', # '仁和缬沙坦胶囊', # '仁和心脑康胶囊', # '仁和辛伐他汀胶囊', # '仁和新肤螨灵软膏', # '仁和新清宁片', # '仁和新血宝胶囊', # '仁和杏苏止咳颗粒', # '仁和雪山胃宝胶囊', # '仁和牙齿脱敏膏', # '仁和牙痛药水', # '仁和炎可宁胶囊', # '仁和盐酸氨溴索分散片', # '仁和盐酸氟桂利嗪胶囊', # # '闪亮盐酸莫西沙星滴眼液', # '仁和盐酸左西替利嗪口服溶液', # '仁和盐酸左氧氟沙星片', # '仁和腰痛片', # '仁和腰息痛胶囊', # '仁和叶酸片', # '仁和医用Ⅲ型胶原蛋白修复贴', # '仁和医用护眼贴', # '仁和医用面部护理敷料', # '仁和医用透明质酸钠敷料贴', # '仁和医用透明质酸钠皮肤修护液', # '仁和医用退热贴（儿童型）', # '仁和医用重组人源Ⅲ型胶原蛋白皮肤修复护理膜', # '仁和乙酰半胱氨酸颗粒', # '仁和银黄滴丸', # '仁和银杏叶分散片', # '仁和银杏叶软胶囊', # '仁和玉屏风口服液', # '仁和玉叶清火胶囊', # '仁和元七骨痛酊', # '仁和远红外活血止痛贴', # '仁和远红外止痛贴', # '仁和障眼明胶囊', # '仁和珍黄胶囊', # '仁和知柏地黄丸(浓缩丸)', # '仁和治咳枇杷合剂', # '仁和壮腰健肾片', # '仁和左氧氟沙星片', # '仁和磷酸西格列汀片', ] #美团手机号： #美团手机号： # device_id = '21885f5' # 设备序列号 # device_id = '2e58510' # 设备序列号 # device_id = 'KNNNEMNVWCJZQOLZ' # device_id = 'B6JVE6AYSWU4LRLZ' # device_id = '656DTOPRZDEALZ5X' # device_id = 'GIOFIBRKZTUGJJAE' # device_id = 'fcb3c749' # device_id = 'UCQGF6CQFMU8WKHI' # device_id = '4TZDUGTOAIFMJVGU' # device_id = '95b2c764' # device_id = 'ZDQWUSSWBEDI896T' # device_id = 'R4SKMJPNBQAENRAM' # device_id = '1462a51f' # device_id = '97ae80e0' # 设备序列号 # device_id = 'IZTOWWDQT45D49BU' # device_id = 'N7ZXBITOSOGMYXQS' # device_id = '369dcf96' # device_id = 'GQIRKB7LVOONM7VW' device_id = 'T4UCEQGQEEYP65ZL' # device_id = '49L7GMPRVS85LJHE' # device_id = 'WWRO9LTGG6KFGQCM' # device_id = 'DYF67TM7KJ4POJLF' # device_id = 'ea4e4eb8' # device_id = 'U8ONIJJJS4CELVD6' # device_id = 'LJ9PN7A6K7HQ9DPF' 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 logging.info(f'关键字 {key} 本轮采集完成') # if self.unrelated_data > 5: # # # 连续超过5个不达标的数据则停止采集 # break 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(mt, 'close'): mt.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 # keys = '小柴胡颗粒' # 参苓健脾胃颗粒 舒肝颗粒 清肺化痰丸 香砂平胃颗粒 小柴胡颗粒 # mt = MT(keys) # 参苓健脾胃颗粒 舒肝颗粒 清肺化痰丸 香砂平胃颗粒 # # mt.main('95b2c764') # mt.main('fcb3c749') if __name__ == '__main__': main() # scheduler = BlockingScheduler() # scheduler.add_job(main, 'cron', hour=21, minute=30, misfire_grace_time=120) # try: # scheduler.start() # except (KeyboardInterrupt, SystemExit): # pass