| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550 |
- 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 = 3
- 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"),
- ],
- "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")]',
- '//*[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_TABLE #"mt_drug"
- self.shop_table_name = Config.DB_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:
- 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)
- VALUES (%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']))
- 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 "999" in self.search_key:
- if self.search_key == '999皮炎平曲安奈德益康唑乳膏30':
- temp_search_key = self.search_key.replace("999皮炎平", "")
- elif self.search_key == '999必无忧盐酸特比萘芬乳膏15g/支':
- temp_search_key = self.search_key.replace("999必无忧", "")
- elif self.search_key == '999必无忧盐酸特比萘芬喷雾剂30':
- temp_search_key = self.search_key.replace("999必无忧", "")
- elif self.search_key == '999速复康布洛芬缓释胶囊':
- temp_search_key = self.search_key.replace("999速复康", "")
- else:
- temp_search_key = self.search_key.replace("999", "")
- else:
- if self.search_key == '史达功右美沙芬愈创甘油醚糖浆120':
- temp_search_key = self.search_key.replace("史达功", "")
- temp_search_key = temp_search_key.replace("120", "")
- elif self.search_key == '三九胃泰养胃舒颗粒8袋':
- temp_search_key = self.search_key.replace("三九胃泰", "")
- temp_search_key = temp_search_key.replace("8袋", "")
- elif self.search_key == '今维多赐多康牌蛋白粉':
- temp_search_key = self.search_key.replace("今维多", "")
- elif self.search_key == '佳美舒阿奇霉素肠溶胶囊4':
- temp_search_key = self.search_key.replace("佳美舒", "")
- temp_search_key = temp_search_key.replace("8", "")
-
- if self.search_key == '999糠酸莫米松凝胶15':
- temp_search_key = temp_search_key.replace("15", "")
- elif self.search_key == '999皮炎平曲安奈德益康唑乳膏30':
- temp_search_key = temp_search_key.replace("30", "")
- elif self.search_key == '999复方感冒灵颗粒15':
- temp_search_key = temp_search_key.replace("15", "")
- elif self.search_key == '999必无忧盐酸特比萘芬喷雾剂30':
- temp_search_key = temp_search_key.replace("30", "")
- elif self.search_key == '999复方金银花颗粒10g':
- temp_search_key = temp_search_key.replace("10g", "")
- elif self.search_key == '999复方苦参肠炎康片12片':
- temp_search_key = temp_search_key.replace("12片", "")
- elif self.search_key == '999强力枇杷露16袋':
- temp_search_key = temp_search_key.replace("16袋", "")
- elif self.search_key == '999三蛇胆川贝膏138':
- temp_search_key = temp_search_key.replace("138", "")
- elif self.search_key == '999必无忧盐酸特比萘芬乳膏15g/支':
- temp_search_key = temp_search_key.replace("15g/支", "")
- elif self.search_key == '999止泻利颗粒15g*8':
- temp_search_key = temp_search_key.replace("15g*8", "")
- elif self.search_key == '999复方板蓝根颗粒15g*15袋/盒':
- temp_search_key = temp_search_key.replace("15g*15袋/盒", "")
- elif self.search_key == '999复方氨酚烷胺胶囊6粒':
- temp_search_key = temp_search_key.replace("6粒", "")
- elif self.search_key == '999可调式生理性海水鼻腔喷雾50':
- temp_search_key = temp_search_key.replace("50", "")
-
- 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
-
- # title_xpath = f'//*[contains(@text, "{temp_search_key}")]'
- # if self.d.xpath(title_xpath).exists:
- # title = self.safe_exec(
- # lambda: self.d.xpath(f'//*[contains(@text, "{temp_search_key}")]').text
- # )
- # else:
- # print("标题不包含关键字")
- # return None, None
-
- # if self.d.xpath(f'//*[contains(@text, "{temp_search_key}")]').exists:
-
- # else:
- # print("标题不包含关键字")
- # return None, None
- time.sleep(3)
- # container_view = self.d(resourceId="com.sankuai.meituan:id/container")
- # count = container_view.count
- # print(f"找到的 container 数量: {count}")
- # content_view = self.d(resourceId="com.sankuai.meituan:id/content")
- # count = content_view.count
- # print(f"找到的 content 数量: {count}")
- # time.sleep(1000)
- 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:
- print (f"搜索关键字:{temp_search_key}, 不存在title={title}中")
- 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:
- print (f"搜索关键字{temp_search_key} 不存在title={title}中")
- 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:
- print("没有匹配到预期格式")
- 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:
- """
- for i in range(10):
- if self.d.xpath('//*[@text="商家"]').exists:
- print(f'第{i}次商家存在')
- break
- else:
- print(f'第{i}次商家不存在')
- time.sleep(self.get_sleep_time())
- self.d.xpath('//*[@text="商家"]').click()
- time.sleep(self.get_sleep_time())
- #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)
- 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 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)
-
- 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, 1000, 200, 300, 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()
- self.safe_exec(self.enter_shoper)
- 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
- #收获地址:
- # self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/filter_container"]').click()
- position_xpath = '//*[@resource-id="com.sankuai.meituan:id/filter_container"]'
- # 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
-
- # print(f"is_position = {is_position}")
- # print(f"is_position2 = {is_position2}")
- if is_position:
- result = True
- return result
- # return is_position
-
- def enter_target_page_ex(self):
- self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/search_edit_flipper"]').click()
- time.sleep(self.get_sleep_time())
- self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/search_edit_linear_layout"]/android.widget.EditText[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())
- #点击选择收获地址
- self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/filter_container"]').click()
- time.sleep(self.get_sleep_time())
- #点击选择按钮:
- self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/selected_icon"]').click()
- #点击确认按钮
- self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/bottom_confirm"]').click()
- time.sleep(self.get_sleep_time())
- #增加点击快递送
- # self.click_express_send_ex()
- # self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/tab_item_title"]').click()
- #页面有可能需要滑动才能出现快递
- if (self.search_key == '今维多赐多康牌蛋白粉' or self.search_key == '999可调式生理性海水鼻腔喷雾50' or self.search_key == '999复方氨酚烷胺胶囊6粒' or
- self.search_key == '999复方板蓝根颗粒15g*15袋/盒' or self.search_key == '999必无忧盐酸特比萘芬乳膏15g/支' or self.search_key == '三九胃泰养胃舒颗粒8袋' or
- self.search_key == '999三蛇胆川贝膏138' or self.search_key == '999强力枇杷露16袋' or self.search_key == '999复方苦参肠炎康片12片' or
- self.search_key == '999复方金银花颗粒10g' or self.search_key == '999冰连清咽' or self.search_key == '999必无忧盐酸特比萘芬喷雾剂30' or
- self.search_key == '佳美舒阿奇霉素肠溶胶囊4' or self.search_key == '999速复康布洛芬缓释胶囊'):
- #固定的位置移动性
- self.d.swipe(400, 190, 100, 190, 0.3)
- time.sleep(0.5)
- self.d.xpath('//*[@text="快递"]').click()
- else:
- self.d.xpath('//*[@text="快递"]').click()
- time.sleep(self.get_sleep_time())
- 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):
- 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[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()]'
- # 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]'
- ]
- 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
- print(f"title_info={title_info}")
- if title_info:
- product, specifications = title_info
- #如果关键字包含999 则 product必须包含999 和 999后面的那段字符串 ps 999感冒灵颗粒必须包含:"999"和"感冒灵颗粒"
- if '999' in self.search_key:
- if self.search_key == '999皮炎平曲安奈德益康唑乳膏30':
- temp_search_key = self.search_key.replace('999皮炎平', '')
- elif self.search_key == '999必无忧盐酸特比萘芬乳膏15g/支':
- temp_search_key = self.search_key.replace("999必无忧", "")
- elif self.search_key == '999必无忧盐酸特比萘芬喷雾剂30':
- temp_search_key = self.search_key.replace("999必无忧", "")
- elif self.search_key == '999速复康布洛芬缓释胶囊':
- temp_search_key = self.search_key.replace("999速复康", "")
- else:
- temp_search_key = self.search_key.replace('999', '')
- if self.search_key == '999糠酸莫米松凝胶15':
- temp_search_key = temp_search_key.replace('15', '')
- if '999' not in product or temp_search_key not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif '15' not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif self.search_key == '999皮炎平曲安奈德益康唑乳膏30':
- temp_search_key = temp_search_key.replace('30', '')
- if '999' not in product or temp_search_key not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif '30' not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif self.search_key == '999复方感冒灵颗粒15':
- temp_search_key = temp_search_key.replace('15', '')
- if '999' not in product or temp_search_key not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif '15' not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif self.search_key == '999抗病毒口服液10ml*6支/盒':
- temp_search_key = temp_search_key.replace("10ml*6支/盒", "")
- if '999' not in product or temp_search_key not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif '10ml*6' not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif self.search_key == '999复方金银花颗粒10g':
- temp_search_key = temp_search_key.replace("10g", "")
- if temp_search_key not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif ('999' not in product) and ('三九' not in product):
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif '10g*8' not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif self.search_key == '999必无忧盐酸特比萘芬喷雾剂30':
- temp_search_key = temp_search_key.replace("30", "")
- if '999' not in product or temp_search_key not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif '30' not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif self.search_key == '999复方苦参肠炎康片12片':
- temp_search_key = temp_search_key.replace("12片", "")
- if '999' not in product or temp_search_key not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif '12' not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif self.search_key == '999强力枇杷露16袋':
- temp_search_key = temp_search_key.replace("16袋", "")
- if '999' not in product or temp_search_key not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif '16' not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif self.search_key == '999三蛇胆川贝膏138':
- temp_search_key = temp_search_key.replace("138", "")
- if '999' not in product or temp_search_key not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif '138' not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif self.search_key == '999必无忧盐酸特比萘芬乳膏15g/支':
- temp_search_key = temp_search_key.replace("15g/支", "")
- if '999' not in product or temp_search_key not in product:
- print(f"关键字temp_search_key={temp_search_key}不存在于product={product}中")
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif '15g' not in product:
- print(f"15g不存在于product={product}中")
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif self.search_key == '999止泻利颗粒15g*8':
- temp_search_key = temp_search_key.replace("15g*8", "")
- if '999' not in product or temp_search_key not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif '15g*8' not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif self.search_key == '999复方板蓝根颗粒15g*15袋/盒':
- temp_search_key = temp_search_key.replace("15g*15袋/盒", "")
- if '999' not in product or temp_search_key not in product:
- print(f"关键字temp_search_key={temp_search_key}不存在于product={product}中")
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif '15g*15' not in product:
- print(f"15g*15不存在于product={product}中")
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif self.search_key == '999复方氨酚烷胺胶囊6粒':
- temp_search_key = temp_search_key.replace("6粒", "")
- if '999' not in product or temp_search_key not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif '6' not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif self.search_key == '999可调式生理性海水鼻腔喷雾50':
- temp_search_key = temp_search_key.replace("50", "")
- if '999' not in product or temp_search_key not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif '50' not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif self.search_key == '999速复康布洛芬缓释胶囊':
- if temp_search_key not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- elif ('999' not in product) and ('三九' not in product):
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- else:
- if '999' not in product or temp_search_key not in product:
- self.swipe_back(2) #需要回退2步
- self.unrelated_data += 1
- return
- else:
- if self.search_key == '史达功右美沙芬愈创甘油醚糖浆120':
- temp_search_key = self.search_key.replace('史达功', '')
- temp_search_key = temp_search_key.replace('120', '')
- if '史达功' not in product or temp_search_key not in product:
- self.swipe_back(2) #需要回退2步到列表
- self.unrelated_data += 1
- return
- elif self.search_key == '三九胃泰养胃舒颗粒8袋':
- temp_search_key = self.search_key.replace('三九胃泰', '')
- temp_search_key = temp_search_key.replace('8袋', '')
- if '三九胃泰' not in product or temp_search_key not in product:
- self.swipe_back(2) #需要回退2步到列表
- self.unrelated_data += 1
- return
- elif self.search_key == '今维多赐多康牌蛋白粉':
- temp_search_key = self.search_key.replace('今维多', '')
- if '今维多' not in product or temp_search_key not in product:
- self.swipe_back(2) #需要回退2步到列表
- self.unrelated_data += 1
- return
- elif self.search_key == '佳美舒阿奇霉素肠溶胶囊4':
- temp_search_key = self.search_key.replace('佳美舒', '')
- temp_search_key = temp_search_key.replace('8', '')
- if '佳美舒' not in product or temp_search_key not in product:
- self.swipe_back(2) #需要回退2步到列表
- self.unrelated_data += 1
- return
- elif ('8' not in title_info ) and ('4' not in title_info):
- print(f"当前商品名称:{title_info} 不包含8或4品规")
- self.swipe_back(2)
- self.unrelated_data += 1
- return
- else:
- if self.search_key not in product.replace(' ', ''):
- self.swipe_back(2) #需要回退2步到列表
- self.unrelated_data += 1
- return
-
-
- # if self.search_key not in product.replace(' ', ''):
- # self.swipe_back(1)
- # self.unrelated_data += 1
- # return
- else:
- self.swipe_back(2) # 需要回退2步
- return
- min_price = self.drug_price() # 最低价格
- # 商品链接
- product_link = self.get_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(2) # 需要回退2步
- 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 not shop_is_exists and self.shop_data_num < 50:
- # 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) #这里执行完后会推到药品主页面
- 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)
- self.swipe_back(2) #需要回退2步到列表页
- return
-
- if not shop:
- print('未获取到店铺名:开始回退')
- #self.swipe_back(1)
- self.swipe_back(2) #需要回退2步到列表页
- return
- if not shop or '自营' in shop:
- #self.swipe_back(1)
- self.swipe_back(2) #需要回退2步到列表页
- 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
-
- #是否存在说明书
- # is_has_instructions = self.has_instructions()
- #有的药品没有说明书,直接默认
- if self.search_key == '今维多赐多康牌蛋白粉':
- expiry_date = '18个月'
- manufacturer = '华润圣海健康科技有限公司'
- approval_number = '食健备G202437001992'
- elif self.search_key == '佳美舒阿奇霉素肠溶胶囊4':
- expiry_date = '24个月'
- manufacturer = '浙江华润三九众益制药有限公司'
- approval_number = '国药准字H20090152'
- elif self.search_key == '999可调式生理性海水鼻腔喷雾50':
- expiry_date = '3年'
- manufacturer = '江苏萨瑞斯医疗科技有限公司'
- approval_number = '苏械注准20212140025'
- elif self.search_key == '999蒲地蓝消炎片':
- expiry_date = '24个月'
- manufacturer = '特一药业集团股份有限公司'
- approval_number = '国药准字Z20063596'
- elif self.search_key == '999养胃舒颗粒':
- expiry_date = '36个月'
- manufacturer = '合肥华润神鹿药业有限公司'
- approval_number = '国药准字Z34020289'
- elif self.search_key == '999糠酸莫米松凝胶15':
- expiry_date = '36个月'
- manufacturer = '华润三九(南昌)药业有限公司'
- approval_number = '国药准字H20080010'
- elif self.search_key == '999黄芪精':
- expiry_date = '36个月'
- manufacturer = '台州南峰药业有限公司'
- approval_number = '国药准字Z33020783'
- elif self.search_key == '999复方感冒灵颗粒15':
- expiry_date = '24个月'
- manufacturer = '华润三九(郴州)制药有限公司'
- approval_number = '国药准字Z43020334'
- elif self.search_key == '999皮炎平曲安奈德益康唑乳膏30':
- expiry_date = '36个月'
- manufacturer = '华润三九(南昌)药业有限公司'
- approval_number = '国药准字H20074155'
- elif self.search_key == '史达功右美沙芬愈创甘油醚糖浆120':
- expiry_date = '暂定24个月,具体有效期以实物说明书为准'
- manufacturer = '史达德药业(北京)有限公司'
- approval_number = '国药准字H11021837'
- elif self.search_key == '999速复康布洛芬缓释胶囊':
- expiry_date = '24个月'
- manufacturer = '北京红林制药有限公司'
- approval_number = '国药准字H20074172'
- elif self.search_key == '999复方板蓝根颗粒15g*15袋/盒':
- expiry_date = '24个月'
- manufacturer = '重庆科瑞东和制药有限责任公司'
- approval_number = '国药准字Z50020420'
- elif self.search_key == '999必无忧盐酸特比萘芬乳膏15g/支':
- expiry_date = '24个月'
- manufacturer = '华润三九(南昌)药业有限公司'
- approval_number = '国药准字H20073954'
- elif self.search_key == '佳美舒阿奇霉素肠溶胶囊4':
- expiry_date = '24个月'
- manufacturer = '浙江华润三九众益制药有限公司'
- approval_number = '国药准字H20090152'
- 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)
- self.swipe_back(2) #需要回退2步到列表页
- 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'
- }
- self.save_to_database(save_data)
- time.sleep(1)
- self.swipe_back(2) #需要回退2步到列表页
- # time.sleep(100000)
- if self.distinct_target():
- print('已到达搜索列表页')
- else:
- for i in range(1):
- # self.swipe_back(1)
- self.swipe_back(2) #需要回退2步到列表页
- # 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.enter_target_page_ex()
- # 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
- # break
-
- # 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 <= 1559: # 默认高度241的才行
- # 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}")
-
- self.safe_exec(drug_one.click)
- print('点击目标药品完毕')
- time.sleep(5)
- #还需要再点击一次商品
- #//*[@resource-id="com.sankuai.meituan:id/ll_stickyfoodList_adapter_food_food"]
- #'//*[contains(@text, "广告")]'
- # if '999' in self.search_key:
- # temp_search_key = self.search_key.replace('999', '')
- # self.d.xpath(f'//*[contains(@text, {temp_search_key})]').click()
- #点击店铺商品
-
- # content_frame = self.d.xpath('//android.widget.FrameLayout[2]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[4]/android.widget.RelativeLayout[1]').exists
- # print(content_frame)
- # content_frame_1 = self.d.xpath('//android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[4]/android.widget.RelativeLayout[1]').exists
- # print(content_frame_1)
- # content_frame_2 = self.d.xpath('//android.widget.FrameLayout[3]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[4]/android.widget.RelativeLayout[1]').exists
- # print(content_frame_2)
- #通过页面的相关结果来定位需要点击的位置
- if self.d.xpath('//*[contains(@text, "相关结果")]'):
- print("存在相关结果")
- # 通过关键字定位元素
- element= self.d.xpath('//*[contains(@text, "相关结果")]')
- # 获取元素的属性信息
- info = element.info
-
- # 获取元素的坐标
- # 获取元素的边界坐标
- bounds = info['bounds']
- x1, y1 = bounds['left'], bounds['top']
- x2, y2 = bounds['right'], bounds['bottom']
- print(f"元素的边界坐标为:左上角({x1}, {y1}),右下角({x2}, {y2})")
- center_x = (x1 + x2) / 2
- center_y = (y1 + y2) / 2
- # 计算距离元素下方150像素的位置
- target_y = center_y + 150
- # 执行点击操作 #点击页面的元素
- self.d.click(center_x, target_y)
- print(f"已点击位置:({center_x}, {target_y})")
- # test_frame = self.d.xpath('//*[@resource-id="com.sankuai.meituan:id/layout_shop_root_scroll_container"]')
- # print(test_frame)
- # time.sleep(100000)
-
- # product_xpath = '//*[@resource-id="com.sankuai.meituan:id/layout_shop_root_scroll_container"]/android.widget.RelativeLayout[1]/android.view.ViewGroup[1]/android.widget.ScrollView[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[3]/android.widget.LinearLayout[1]/android.support.v4.view.ViewPager[3]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.ScrollView[2]/android.widget.LinearLayout[1]/android.widget.FrameLayout[1]/android.widget.RelativeLayout[1]/android.widget.FrameLayout[2]/android.support.v7.widget.RecyclerView[1]/android.widget.FrameLayout[2]'
- # if self.d.xpath(product_xpath).exists:
- # self.d.xpath(product_xpath).click()
- # else:
- # print('product_xpath bu cun zai')
- # time.sleep(self.get_sleep_time())
- # print('点击店铺的药品')
- # 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,
- #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15',
- # '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必无忧盐酸特比萘芬乳膏15g/支'
- # '999止泻利颗粒15g*8'
- # '999复方板蓝根颗粒15g*15袋/盒'
- # '史达功右美沙芬愈创甘油醚糖浆120'
- # '999复方氨酚烷胺胶囊6粒'
- # '999可调式生理性海水鼻腔喷雾50'
- '999速复康布洛芬缓释胶囊'
-
- ]
-
- #美团手机号:
- # device_id = '21885f5' # 设备序列号
- # device_id = 'ea4e4eb8' # 设备序列号
- device_id = '97ae80e0' # 设备序列号
- # device_id = '2e58510' # 设备序列号
- # device_id = 'UCQGF6CQFMU8WKHI'
- # device_id = 'B6JVE6AYSWU4LRLZ'
- # device_id = '2e58510'
- 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')
- 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
|