上传文件至 'spiders/ybm'

spiders/ybm/ybm_crawl.py

@@ -0,0 +1,1682 @@
+# ====================================================================================
+# ybm_crawl.py — 药帮忙平台爬虫
+# 遵循 commons1 调度框架，平台专属逻辑保留在类内
+# 由 CollectScheduleRunner / run_scheduled_loop 调度执行
+# ====================================================================================
+
+# ==================== SECTION 1: IMPORTS ====================
+import base64
+import json
+import os
+import random
+import re
+import threading
+import time
+import traceback
+from datetime import datetime
+from io import BytesIO
+
+import oss2
+import requests
+from PIL import Image
+from playwright.sync_api import sync_playwright, TimeoutError as PlaywrightTimeoutError
+
+# ---- commons1 公共能力 ----
+from commons.Logger import get_spider_logger
+from commons.conn_mysql import MySQLPoolOn2
+from commons.feishu_webhook import send_text as feishu_send_text, send_error_card as feishu_send_error_card
+from commons.scheduler import CrawlerScheduler
+
+# ---- pipelines (基于 commons) ----
+from pipelines.drug_pipelines import DrugPipeline
+
+logger = get_spider_logger("ybm")
+
+# ==================== SECTION 2: PLATFORM CONFIG ====================
+
+# MySQL（供店铺信息直接读写；商品数据走 DrugPipeline）
+mysql_pool = MySQLPoolOn2()
+
+# 平台标识
+PLATFORM_ID = 9
+YBM_DEVICE_ID = "18008650300"
+
+# API（内部调度系统）
+TASK_API_BASE = "http://192.168.2.246:8080/api/collect_task"
+TASK_API_TOKEN = "zhijiayun_crawler_2026"
+
+TASK_PULL_URL = TASK_API_BASE + "/pull"
+TASK_HEARTBEAT_URL = TASK_API_BASE + "/heartbeat"
+TASK_REPORT_URL = TASK_API_BASE + "/report"
+
+# 手动任务（调试用）
+USE_MANUAL_TASK = False
+MANUAL_TASK = {
+    "id": 2001,
+    "collect_task_id": 5000,
+    "company_id": 1,
+    "product_name": "三九胃泰颗粒",
+    "product_specs": "10",
+    "product_keyword": "",
+    "product_brand": "999",
+    "sampling_cycle": 1,
+    "sampling_start_time": 1778083200,
+    "sampling_end_time": 1778342399,
+    "collect_equipment_account_id": 0,
+    "collect_region_id": 0,
+    "collect_equipment_id": 2,
+    "collect_round": 1,
+}
+
+# 反爬参数
+MIN_CLICK_DELAY = 1.5
+MAX_CLICK_DELAY = 3.5
+MIN_INPUT_DELAY = 0.1
+MAX_INPUT_DELAY = 0.3
+MIN_PAGE_DELAY = 2.0
+MAX_PAGE_DELAY = 4.0
+MIN_KEYWORD_DELAY = 8.0
+MAX_KEYWORD_DELAY = 15.0
+
+SCROLL_TARGET_DISTANCE = 400
+SCROLL_OFFSET_RANGE = 50
+SCROLL_STEP = 50
+SCROLL_INTERVAL = 0.05
+
+# Cookie & 登录
+COOKIE_FILE_PATH = "ybm_cookies.json"
+LOGIN_VALIDATE_URL = "https://www.ybm100.com/new/"
+USERNAME = "18008650300"
+PASSWORD = "12345678"
+TARGET_LOGIN_URL = "https://www.ybm100.com/new/login"
+
+# 选择器
+USERNAME_SELECTOR = "input[placeholder*=请输入账号]"
+PASSWORD_SELECTOR = "input[placeholder*=请输入密码]"
+LOGIN_BTN_SELECTOR = "button:has(span:text('登录'))"
+SEARCH_INPUT_SELECTOR = "input[placeholder*='药品名称/厂家名称']"
+SEARCH_INPUT_SELECTOR2 = "div.home-search-container-search-head"
+SEARCH_BTN_SELECTOR = "div.home-search-container-search-head-btn[data-scmd=\"text-搜索\"]"
+
+PRODUCT_ITEM_SELECTOR = "div.product-list-item"
+PRODUCT_TITLE_SELECTOR = "div.product-name"
+PRODUCT_PRICE_SELECTOR = "div.main-price"
+PRODUCT_STORE_SELECTOR = 'div.prduct-shop-name div.shop-name'
+PRODUCT_COMPANY_SELECTOR = "div.product-manufacturer"
+PRODUCT_VALIDITY_SELECTOR = "div.product-period"
+
+# 等待时间
+ELEMENT_TIMEOUT = 10000
+LOGIN_AFTER_CLICK = 5000
+SEARCH_BTN_TIMEOUT = 5000
+COLLECT_DELAY = 3000
+DETAIL_LOAD_TIMEOUT = 5000
+
+# 浏览器
+BROWSER_HEADLESS = False
+BROWSER_CHANNEL = "chrome"
+SLOW_MO_MIN = 50
+SLOW_MO_MAX = 100
+
+# 百度 OCR
+request_url_config = "https://aip.baidubce.com/rest/2.0/ocr/v1/business_license"
+AppKey_config = "tRK2RhyItCSh6BzyT4CNVXQa"
+AppSecret_config = "TDgKiPo94i2mOM1sDqOuDnlcK1bG66jh"
+token_url_config = 'https://aip.baidubce.com/oauth/2.0/token'
+
+# OSS
+OSS_ACCESS_KEY_ID = 'LTAI5tDwjfteBvivYN41r8sJ'
+OSS_ACCESS_KEY_SECRET = 'yowuOGi2nYYnrqGpO3qcz94C4brcPp'
+OSS_ENDPOINT = "oss-cn-shenzhen.aliyuncs.com"
+OSS_BUCKET_NAME = "zhijiayun-jiansuo"
+OSS_PREFIX = "scrape_data/"
+LOCAL_SCREENSHOT_DIR = "local_screenshots"
+LOCAL_CROPPED_DIR = "./local_cropped_screenshots"
+IMAGE_COMPRESS_ENABLE = True
+IMAGE_COMPRESS_QUALITY = 30
+IMAGE_COMPRESS_PNG_LEVEL = 9
+
+# 心跳上报间隔（秒）
+HEARTBEAT_INTERVAL_SECONDS = 60
+
+
+# ==================== SECTION 3: OSS / SCREENSHOT HELPERS ====================
+
+def init_local_screenshot_dir():
+    if not os.path.exists(LOCAL_SCREENSHOT_DIR):
+        os.makedirs(LOCAL_SCREENSHOT_DIR)
+        logger.info(f"本地截图目录已创建: {LOCAL_SCREENSHOT_DIR}")
+    else:
+        logger.debug(f"本地截图目录已存在: {LOCAL_SCREENSHOT_DIR}")
+
+
+def init_oss_bucket():
+    try:
+        auth = oss2.Auth(OSS_ACCESS_KEY_ID, OSS_ACCESS_KEY_SECRET)
+        bucket = oss2.Bucket(auth, OSS_ENDPOINT, OSS_BUCKET_NAME)
+        bucket.get_bucket_info()
+        logger.info("OSS Bucket 初始化成功")
+        return bucket
+    except Exception as e:
+        logger.error(f"OSS Bucket 初始化失败: {str(e)}")
+        raise
+
+
+def upload_local_screenshot_to_oss(bucket, local_file_path, oss_file_path=None):
+    if not os.path.exists(local_file_path):
+        raise FileNotFoundError(f"本地截图文件不存在: {local_file_path}")
+    if not oss_file_path:
+        local_file_name = os.path.basename(local_file_path)
+        oss_file_path = f"screenshots/{local_file_name}"
+    try:
+        bucket.put_object_from_file(oss_file_path, local_file_path)
+        oss_file_url = f"https://{OSS_BUCKET_NAME}.{OSS_ENDPOINT}/{oss_file_path}"
+        logger.info(f"截图上传 OSS 成功: {oss_file_url}")
+        return oss_file_url
+    except Exception as e:
+        logger.error(f"截图上传 OSS 失败: {str(e)}")
+        raise
+
+
+def crop_local_screenshot(local_file_path, cropped_file_path=None, crop_region=None):
+    if not os.path.exists(local_file_path):
+        raise FileNotFoundError(f"原始截图文件不存在: {local_file_path}")
+    os.makedirs(LOCAL_CROPPED_DIR, exist_ok=True)
+    if not cropped_file_path:
+        file_name = os.path.basename(local_file_path)
+        file_name_no_ext, file_ext = os.path.splitext(file_name)
+        cropped_file_name = f"{file_name_no_ext}_cropped{file_ext}"
+        cropped_file_path = os.path.join(LOCAL_CROPPED_DIR, cropped_file_name)
+    with Image.open(local_file_path) as img:
+        img_width, img_height = img.size
+        if not crop_region:
+            crop_region = (0, 0, int(img_width), int(img_height * 0.3))
+        c_left, c_upper, c_right, c_lower = crop_region
+        if c_right > img_width or c_lower > img_height or c_left < 0 or c_upper < 0:
+            raise ValueError(f"裁剪区域超出图片范围，图片尺寸=({img_width}, {img_height})，裁剪区域={crop_region}")
+        cropped_img = img.crop(crop_region)
+        file_ext = os.path.splitext(cropped_file_path)[1].lower()
+        try:
+            if IMAGE_COMPRESS_ENABLE:
+                if file_ext in ['.jpg', '.jpeg']:
+                    cropped_img.save(cropped_file_path, format='JPEG', quality=IMAGE_COMPRESS_QUALITY, optimize=True, progressive=True)
+                else:
+                    cropped_img.save(cropped_file_path)
+            else:
+                cropped_img.save(cropped_file_path, format='JPEG')
+        except Exception:
+            cropped_img.save(cropped_file_path, format='JPEG')
+    try:
+        if os.path.exists(cropped_file_path):
+            os.remove(local_file_path)
+    except OSError:
+        pass
+    return cropped_file_path
+
+
+def screenshot_target_page_to_local_then_oss(target_page, local_file_path=None, oss_file_path=None, full_page=True, crop_region=None):
+    os.makedirs(LOCAL_SCREENSHOT_DIR, exist_ok=True)
+    if not local_file_path:
+        current_time = datetime.now().strftime("%Y%m%d_%H%M%S")
+        local_file_name = f"{current_time}_p{PLATFORM_ID}_target_page.jpg"
+        local_file_path = os.path.join(LOCAL_SCREENSHOT_DIR, local_file_name)
+    logger.info(f"开始页面截图: {local_file_path}")
+    target_page.screenshot(path=local_file_path, full_page=full_page, omit_background=False, timeout=10000)
+    cropped_file_path = crop_local_screenshot(local_file_path=local_file_path, crop_region=crop_region)
+    bucket = init_oss_bucket()
+    oss_file_url = upload_local_screenshot_to_oss(bucket, cropped_file_path, oss_file_path)
+    return cropped_file_path, oss_file_url
+
+
+# ==================== SECTION 4: CITY / PROVINCE MAPPING ====================
+
+CITY_JSON_PATH = os.path.join(os.path.dirname(os.path.abspath(__file__)), "..", "..", "commons", "city.json")
+
+PROVINCE_ID_MAP = {}
+CITY_ID_MAP = {}
+CITY_TO_PROVINCES_MAP = {}
+DIRECT_MUNICIPALITIES = {"北京市", "上海市", "天津市", "重庆市"}
+DIRECT_MUNICIPALITY_BASE_NAMES = {"北京", "上海", "天津", "重庆"}
+DIRECT_MUNICIPALITY_ALIAS = {
+    "北京": "北京市", "上海": "上海市", "天津": "天津市", "重庆": "重庆市",
+}
+
+
+def load_city_mapping():
+    global PROVINCE_ID_MAP, CITY_ID_MAP, CITY_TO_PROVINCES_MAP
+    PROVINCE_ID_MAP.clear()
+    CITY_ID_MAP.clear()
+    CITY_TO_PROVINCES_MAP.clear()
+    if not os.path.exists(CITY_JSON_PATH):
+        logger.error(f"❌ 城市JSON文件不存在：{CITY_JSON_PATH}")
+        return
+    try:
+        with open(CITY_JSON_PATH, "r", encoding="utf-8") as f:
+            data = json.load(f)
+        for province_item in data:
+            p_name = province_item['name']
+            PROVINCE_ID_MAP[p_name] = province_item['id']
+            for city_item in province_item.get('sons', []):
+                c_name = city_item['name']
+                CITY_ID_MAP[(p_name, c_name)] = city_item['id']
+                CITY_TO_PROVINCES_MAP.setdefault(c_name, set()).add(p_name)
+        logger.info(f"✅ 城市映射加载完成，共 {len(PROVINCE_ID_MAP)} 个省份，{len(CITY_ID_MAP)} 个城市")
+    except Exception as e:
+        logger.error(f"❌ 加载城市JSON失败：{str(e)}")
+
+
+def _clean_province_name(name: str) -> str:
+    return (name or "").replace("省", "").replace("市", "").replace("自治区", "").replace("特别行政区", "").strip()
+
+
+def _clean_city_name(name: str) -> str:
+    return (name or "").replace("市", "").replace("自治州", "").replace("地区", "").replace("盟", "").strip()
+
+
+def normalize_province_city_names(province_name: str, city_name: str):
+    province = (province_name or "").strip()
+    city = (city_name or "").strip()
+    if province and province not in DIRECT_MUNICIPALITIES and province not in PROVINCE_ID_MAP:
+        clean_p = _clean_province_name(province)
+        for standard_name in PROVINCE_ID_MAP.keys():
+            if clean_p and clean_p == _clean_province_name(standard_name):
+                province = standard_name
+                break
+    if not province and city:
+        matched_provinces = CITY_TO_PROVINCES_MAP.get(city, set())
+        if not matched_provinces:
+            clean_c = _clean_city_name(city)
+            if clean_c:
+                matched_provinces = {
+                    p_name
+                    for (p_name, c_name) in CITY_ID_MAP.keys()
+                    if _clean_city_name(c_name) == clean_c
+                }
+        if len(matched_provinces) == 1:
+            province = next(iter(matched_provinces))
+        elif len(matched_provinces) > 1:
+            logger.warning(f"⚠️ 城市名存在跨省重名，无法唯一反推省份: city={city}, candidates={sorted(matched_provinces)}")
+    if province in DIRECT_MUNICIPALITY_BASE_NAMES:
+        province = DIRECT_MUNICIPALITY_ALIAS[province]
+    if province and city and (province, city) not in CITY_ID_MAP:
+        clean_c = _clean_city_name(city)
+        for (p_name, c_name), _ in CITY_ID_MAP.items():
+            if _clean_province_name(p_name) == _clean_province_name(province) and clean_c and _clean_city_name(c_name) == clean_c:
+                city = c_name
+                break
+    if province in DIRECT_MUNICIPALITIES and not city:
+        city = province
+    return province, city
+
+
+def get_province_city_ids(province_name, city_name):
+    province_name, city_name = normalize_province_city_names(province_name, city_name)
+    province_id = PROVINCE_ID_MAP.get(province_name) if province_name else None
+    if province_name and province_id is None:
+        clean_p = _clean_province_name(province_name)
+        for name, pid in PROVINCE_ID_MAP.items():
+            if clean_p and clean_p == _clean_province_name(name):
+                province_id = pid
+                province_name = name
+                break
+        if province_id is None:
+            logger.warning(f"⚠️ 未找到省份ID: {province_name}")
+            province_id = 0
+    elif province_id is None:
+        province_id = 0
+    if _clean_province_name(province_name) in DIRECT_MUNICIPALITY_BASE_NAMES and not city_name:
+        city_name = f"{_clean_province_name(province_name)}市"
+    city_id = CITY_ID_MAP.get((province_name, city_name)) if province_name and city_name else None
+    if province_name and city_name and city_id is None:
+        clean_c = _clean_city_name(city_name)
+        for (p_name, c_name), cid in CITY_ID_MAP.items():
+            if p_name == province_name:
+                if clean_c and clean_c == _clean_city_name(c_name):
+                    city_id = cid
+                    city_name = c_name
+                    break
+        if city_id is None:
+            if _clean_province_name(province_name) in DIRECT_MUNICIPALITY_BASE_NAMES and province_id:
+                city_id = province_id
+            else:
+                logger.warning(f"⚠️ 未找到城市ID: {province_name} - {city_name}")
+                city_id = 0
+    elif city_id is None:
+        city_id = 0
+    return province_id, city_id
+
+
+def extract_province_city(address):
+    if not address:
+        return "", ""
+    province_pattern = re.compile(r'([^省]+省|.+自治区|北京市|上海市|天津市|重庆市|.+特别行政区)')
+    province_match = province_pattern.search(address)
+    province = province_match.group(1) if province_match else ""
+    address_remain = address.replace(province, "").strip() if province else address.strip()
+    city_pattern = re.compile(r'([^市]+市|.+自治州|.+地区|.+盟|^[^\d区县镇]+)')
+    city_match = city_pattern.search(address_remain)
+    city = city_match.group(1).strip() if city_match else ""
+    if province in ["北京市", "上海市", "天津市", "重庆市"]:
+        city = province
+    if not province and not city:
+        simple_pattern = re.compile(r'^([^\d区县镇]+)')
+        simple_match = simple_pattern.search(address)
+        if simple_match:
+            city = simple_match.group(1).strip()
+    if city and province and city != province and province in city:
+        city = city.replace(province, "").strip()
+    province, city = normalize_province_city_names(province, city)
+    return province.strip(), city.strip()
+
+
+# ==================== SECTION 5: ANTI-CRAWL UTILITIES ====================
+
+def get_current_time():
+    return datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+
+
+def random_delay(min_seconds, max_seconds):
+    delay = random.uniform(min_seconds, max_seconds)
+    time.sleep(delay)
+    return delay
+
+
+def save_cookies(context, cookie_path=COOKIE_FILE_PATH):
+    try:
+        cookies = context.cookies()
+        with open(cookie_path, "w", encoding="utf-8") as f:
+            json.dump(cookies, f, ensure_ascii=False, indent=2)
+        logger.info(f"Cookie已保存到：{cookie_path}")
+        return True
+    except Exception as e:
+        logger.error(f" 保存Cookie失败：{e}")
+        return False
+
+
+def load_cookies(context, cookie_path=COOKIE_FILE_PATH):
+    if not os.path.exists(cookie_path):
+        logger.warning(f" Cookie文件不存在：{cookie_path}")
+        return False
+    try:
+        with open(cookie_path, "r", encoding="utf-8") as f:
+            cookies = json.load(f)
+        context.add_cookies(cookies)
+        logger.info(f"✅ 已从{cookie_path}加载Cookie")
+        return True
+    except Exception as e:
+        logger.error(f" 加载Cookie失败：{e}")
+        return False
+
+
+def slow_scroll_400px(page, scroll_distance1=400):
+    try:
+        scroll_distance = random.randint(scroll_distance1 - SCROLL_OFFSET_RANGE, scroll_distance1 + SCROLL_OFFSET_RANGE)
+        remaining_distance = scroll_distance
+        total_steps = int(scroll_distance / SCROLL_STEP)
+        logger.info(f"📜 开始慢速滚动（目标距离：{scroll_distance}px，总步数：{total_steps}，总时长约{total_steps*SCROLL_INTERVAL:.2f}秒）")
+        for _ in range(total_steps):
+            step = min(SCROLL_STEP, remaining_distance)
+            page.evaluate(f"window.scrollBy(0, {step});")
+            remaining_distance -= step
+            time.sleep(SCROLL_INTERVAL)
+        if remaining_distance > 0:
+            page.evaluate(f"window.scrollBy(0, {remaining_distance});")
+            time.sleep(SCROLL_INTERVAL)
+        page.wait_for_load_state("networkidle", timeout=8000)
+        random_delay(2.0, 3.0)
+        logger.info(f" 慢速滚动完成，实际滚动距离：{scroll_distance - remaining_distance}px")
+        return True
+    except Exception as e:
+        logger.warning(f" 慢速滚动失败：{e}")
+        return False
+
+
+def type_slow(locator, text: str, min_delay=0.06, max_delay=0.18):
+    for ch in text:
+        locator.type(ch, delay=int(random.uniform(min_delay, max_delay) * 1000))
+
+
+def kill_masks(page):
+    page.evaluate(r"""
+    () => {
+      const knownSelectors = [
+        '.v-modal', '.el-overlay', '.el-overlay-dialog', '.el-dialog__wrapper',
+        '.el-message-box__wrapper', '.el-loading-mask', '.el-popup-parent--hidden'
+      ];
+      for (const sel of knownSelectors) {
+        document.querySelectorAll(sel).forEach(el => el.remove());
+      }
+      const all = Array.from(document.querySelectorAll('body *'));
+      for (const el of all) {
+        const s = window.getComputedStyle(el);
+        if (!s) continue;
+        const z = parseInt(s.zIndex || '0', 10);
+        if ((s.position === 'fixed' || s.position === 'absolute') && z >= 1000 && s.pointerEvents !== 'none') {
+          const r = el.getBoundingClientRect();
+          const nearFullScreen = r.width >= window.innerWidth * 0.8 && r.height >= window.innerHeight * 0.8;
+          if (nearFullScreen) {
+            el.style.pointerEvents = 'none';
+            el.style.display = 'none';
+          }
+        }
+      }
+      document.documentElement.style.overflow = 'auto';
+      document.body.style.overflow = 'auto';
+      document.body.style.position = 'static';
+      document.body.style.width = 'auto';
+      document.body.style.paddingRight = '0px';
+      document.body.classList.remove('el-popup-parent--hidden');
+    }
+    """)
+
+
+def force_close_popup(page):
+    try:
+        for _ in range(5):
+            btn = page.locator(
+                "//button[normalize-space()='下一步' or normalize-space()='完成' or normalize-space()='我知道了' or normalize-space()='关闭']"
+            ).first
+            if btn.count() > 0 and btn.is_visible():
+                btn.click(timeout=1500)
+                page.wait_for_timeout(300)
+                continue
+            close_icon = page.locator(
+                "xpath=//*[contains(@class,'close') or contains(@class,'el-icon-close') or name()='svg' or name()='i'][1]"
+            ).first
+            if close_icon.count() > 0 and close_icon.is_visible():
+                close_icon.click(timeout=1000)
+                page.wait_for_timeout(300)
+                continue
+            break
+        page.evaluate("""
+        const selectors = [
+          '.v-modal', '.el-overlay', '.el-overlay-dialog', '.el-dialog__wrapper',
+          '[class*="mask"]', '[class*="overlay"]', '[style*="z-index"]'
+        ];
+        for (const sel of selectors) {
+          document.querySelectorAll(sel).forEach(el => {
+            const s = window.getComputedStyle(el);
+            if ((s.position === 'fixed' || s.position === 'absolute') && parseInt(s.zIndex || '0', 10) >= 1000) {
+              el.remove();
+            }
+          });
+        }
+        """)
+    except Exception:
+        pass
+
+
+def popup_guard(page, tag=""):
+    try:
+        page.wait_for_timeout(300)
+        for _ in range(6):
+            btn = page.locator(
+                "xpath=//button[normalize-space()='下一步' or normalize-space()='完成' or normalize-space()='我知道了' or normalize-space()='关闭']"
+            ).first
+            if btn.count() > 0 and btn.is_visible():
+                btn.click(timeout=1500)
+                page.wait_for_timeout(250)
+                continue
+            close_btn = page.locator(
+                "css=.el-dialog__headerbtn, .el-message-box__headerbtn, .close, .icon-close, .el-icon-close"
+            ).first
+            if close_btn.count() > 0 and close_btn.is_visible():
+                close_btn.click(timeout=1200)
+                page.wait_for_timeout(250)
+                continue
+            break
+        page.evaluate(r"""
+        () => {
+          const selectors = [
+            '.v-modal', '.el-overlay', '.el-overlay-dialog', '.el-dialog__wrapper',
+            '.el-message-box__wrapper', '.el-loading-mask'
+          ];
+          selectors.forEach(sel => document.querySelectorAll(sel).forEach(e => e.remove()));
+          const all = Array.from(document.querySelectorAll('body *'));
+          for (const el of all) {
+            const s = getComputedStyle(el);
+            const z = parseInt(s.zIndex || '0', 10);
+            if ((s.position === 'fixed' || s.position === 'absolute') && z >= 1000 && s.pointerEvents !== 'none') {
+              const r = el.getBoundingClientRect();
+              const nearFull = r.width >= innerWidth * 0.8 && r.height >= innerHeight * 0.8;
+              if (nearFull) {
+                el.style.pointerEvents = 'none';
+                el.style.display = 'none';
+              }
+            }
+          }
+          document.documentElement.style.overflow = 'auto';
+          document.body.style.overflow = 'auto';
+          document.body.classList.remove('el-popup-parent--hidden');
+        }
+        """)
+        logger.info("杀除弹窗成功")
+    except Exception:
+        pass
+
+
+# ==================== SECTION 6: OCR HELPERS ====================
+
+def compress_image(image_data, max_size=4*1024*1024):
+    try:
+        img = Image.open(BytesIO(image_data))
+        if img.mode in ('RGBA', 'P'):
+            bg_img = Image.new('RGB', img.size, (255, 255, 255))
+            bg_img.paste(img, mask=img.split()[-1] if img.mode == 'RGBA' else None)
+            img = bg_img
+        if img.width > 1000:
+            ratio = 1000 / img.width
+            img = img.resize((int(img.width * ratio), int(img.height * ratio)), Image.Resampling.LANCZOS)
+        output = BytesIO()
+        img.save(output, format='JPEG', quality=80)
+        compressed_data = output.getvalue()
+        if len(compressed_data) > max_size:
+            output2 = BytesIO()
+            img.save(output2, format='JPEG', quality=60)
+            compressed_data = output2.getvalue()
+        return compressed_data
+    except Exception as e:
+        logger.debug(f"图片压缩失败：{e}")
+        return image_data
+
+
+def download_image_to_base64(image_url, save_dir="./download_images"):
+    try:
+        if not os.path.exists(save_dir):
+            os.makedirs(save_dir)
+    except Exception as e:
+        print(f"创建保存目录失败：{str(e)}")
+        return None
+    try:
+        headers = {
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
+        }
+        response = requests.get(image_url, headers=headers, timeout=15)
+        response.raise_for_status()
+        compressed_data = compress_image(response.content)
+        image_base64 = base64.b64encode(compressed_data).decode("utf-8")
+        image_data = compressed_data
+        file_name = image_url.split("/")[-1]
+        file_name = file_name.replace("?", "").replace("&", "").replace("=", "")
+        save_path = os.path.join(save_dir, file_name)
+        with open(save_path, "wb") as f:
+            f.write(image_data)
+        print(f"图片已保存到本地：{save_path}")
+        return image_base64
+    except requests.exceptions.Timeout:
+        print(f"下载图片超时：{image_url}")
+        return None
+    except requests.exceptions.HTTPError as e:
+        code = e.response.status_code if e.response is not None else "?"
+        logger.warning("下载图片 HTTP 错误 url=%s status=%s", image_url, code)
+        return None
+    except Exception as e:
+        print(f"下载图片失败：{str(e)}")
+        return None
+
+
+def get_access_token():
+    url = f"{token_url_config}?grant_type=client_credentials&client_id={AppKey_config}&client_secret={AppSecret_config}"
+    headers = {'Content-Type': 'application/json', 'Accept': 'application/json'}
+    try:
+        response = requests.request("POST", url, headers=headers, data="")
+        response.raise_for_status()
+        return response.json()['access_token']
+    except Exception as e:
+        print(f"获取access_token失败：{str(e)}")
+        return None
+
+
+def get_ocr_res(img):
+    try:
+        print(f'开始识别图片:{img}')
+        img_base64 = download_image_to_base64(img)
+        if not img_base64:
+            print("图片下载/转Base64失败，终止OCR识别")
+            return None
+        access_token = get_access_token()
+        if not access_token:
+            print("获取access_token失败，无法调用OCR接口")
+            return None
+        request_url = request_url_config + "?access_token=" + access_token
+        headers = {'content-type': 'application/x-www-form-urlencoded'}
+        response = requests.post(request_url, data={"image": img_base64}, headers=headers)
+        if response:
+            res = response.json()
+            if "error_code" in res:
+                print(f"百度OCR接口错误：{res['error_msg']}（错误码：{res['error_code']}）")
+                return None
+            new_dic = {}
+            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:
+            print("OCR接口返回空响应")
+            return None
+    except requests.exceptions.RequestException as e:
+        print(f"网络错误（图片下载/OCR请求失败）：{str(e)}")
+        return None
+    except KeyError as e:
+        print(f"OCR响应格式异常，缺失字段：{str(e)}")
+        return None
+    except Exception as e:
+        print(f"OCR识别未知错误：{str(e)}")
+        return None
+
+
+# ==================== SECTION 7: SHOP HELPERS ====================
+
+def clean_shop_name(raw_shop_name):
+    if not raw_shop_name:
+        return ''
+    pattern = r'【.*?】|\(.*?\)|\[.*?\]'
+    cleaned = re.sub(pattern, '', raw_shop_name)
+    cleaned = cleaned.strip().replace('\n', '').replace('\r', '')
+    cleaned = re.sub(r'\s+', ' ', cleaned)
+    return cleaned if cleaned else raw_shop_name
+
+
+def shop_is_exists_database(shop):
+    query_sql = """
+        SELECT province, city, business_license_company, qualification_number, business_license_address
+        FROM retrieve_scrape_shop_info
+        WHERE shop = %s and platform = %s
+    """
+    try:
+        rows = mysql_pool.select_data(query_sql, (shop, 9))
+        result = rows[0] if rows else None
+        logger.debug("店铺存在校验 shop=%r result=%s", shop, result)
+        is_exists = bool(result)
+        if is_exists:
+            logger.info(f"【店铺存在校验】店铺已存在 | 店铺名：{repr(shop)} | 结果：存在（True）不要执行采集店铺")
+        else:
+            logger.info(f"【店铺存在校验】店铺不存在 | 店铺名：{repr(shop)} | 结果：不存在（False）")
+        return is_exists, result
+    except Exception as e:
+        logger.error(f"查询店铺失败：{e}")
+        return False, None
+
+
+def insert_shop_info_to_db(shop, contact_address, qualification_number, business_license_company,
+                           business_license_address, scrape_date, platform, province, city, create_time, update_time):
+    sql = """
+        INSERT INTO retrieve_scrape_shop_info (
+            shop, contact_address, qualification_number, business_license_company,
+            business_license_address, scrape_date, platform, province, city, create_time, update_time
+        ) VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
+        ON DUPLICATE KEY UPDATE
+        contact_address = VALUES(contact_address),
+        qualification_number = VALUES(qualification_number),
+        business_license_company = VALUES(business_license_company),
+        business_license_address = VALUES(business_license_address),
+        scrape_date = VALUES(scrape_date),
+        platform = VALUES(platform),
+        province = VALUES(province),
+        city = VALUES(city),
+        update_time = VALUES(update_time)
+    """
+    params = (shop, contact_address, qualification_number, business_license_company,
+              business_license_address, scrape_date, platform, province, city, create_time, update_time)
+    conn = None
+    cursor = None
+    try:
+        conn = mysql_pool.get_conn()
+        cursor = conn.cursor()
+        cursor.execute(sql, params)
+        conn.commit()
+        logger.info("店铺信息写入成功 shop=%s company=%s", shop, business_license_company)
+        return True
+    except Exception as e:
+        logger.error("插入店铺失败：%s\n%s", e, traceback.format_exc())
+        if conn:
+            conn.rollback()
+        return False
+    finally:
+        if cursor:
+            cursor.close()
+        if conn:
+            conn.close()
+
+
+# ==================== SECTION 8: YbmCrawler CLASS ====================
+
+class YbmCrawler:
+    """药帮忙平台爬虫 —— 遵循 commons1 调度框架。
+
+    由 CollectScheduleRunner 调用：
+        crawler = YbmCrawler(task_dict)
+        count, is_success = crawler.run()
+    """
+
+    def __init__(self, drug_dict=None):
+        self.task_dict = drug_dict or {}
+        self.platform_id = PLATFORM_ID
+        self.username = YBM_DEVICE_ID
+        self.platform_name = '药帮忙'
+
+        # Pipeline（商品数据走 DrugPipeline，做去重入库）
+        self.pipeline = DrugPipeline("ybm")
+        self.is_success = True
+
+        # 由 CrawlerScheduler 管理心跳和停止信号
+        self.scheduler = CrawlerScheduler(YBM_DEVICE_ID, str(PLATFORM_ID), heartbeat_interval=HEARTBEAT_INTERVAL_SECONDS)
+
+        if self.task_dict:
+            self._extract_task_params()
+
+    # ---------- task params ----------
+
+    def _extract_task_params(self):
+        t = self.task_dict
+        self.task_id = t.get("id", 0)
+        self.collect_task_id = t.get("collect_task_id", 0)
+        self.company_id = t.get("company_id", 0)
+        self.product_name = t.get("product_name", "")
+        self.product_specs = t.get("product_specs", "")
+        self.product_keyword = t.get("product_keyword", "")
+        self.product_brand = t.get("product_brand", "")
+        self.sampling_cycle = t.get("sampling_cycle", 1)
+        self.sampling_start_time = t.get("sampling_start_time", 0)
+        self.sampling_end_time = t.get("sampling_end_time", 0)
+        self.collect_equipment_account_id = t.get("collect_equipment_account_id", 0)
+        self.collect_region_id = t.get("collect_region_id", 0)
+        self.collect_round = t.get("collect_round", 1)
+        self.api_current_page = t.get("current_page", 0) or 0
+
+        self.keyword = self.product_brand + self.product_name
+
+        self.collect_config_info = json.dumps({
+            "sampling_cycle": self.sampling_cycle,
+            "sampling_start_time": self.sampling_start_time,
+            "sampling_end_time": self.sampling_end_time,
+        }, ensure_ascii=False, default=str)
+
+    # ---------- API report helpers ----------
+
+    def _send_report(self, params: dict, log_msg: str):
+        """通用回告方法，POST 到内部调度 API"""
+        try:
+            resp = requests.post(
+                TASK_REPORT_URL, json=params, timeout=10,
+                headers={'X-Crawler-Token': TASK_API_TOKEN},
+            )
+            if resp.status_code == 200:
+                try:
+                    data = resp.json()
+                    if data.get("code") == "success":
+                        logger.info("✅ 回告成功：%s", log_msg)
+                        return "success"
+                    else:
+                        msg = data.get("msg", "")
+                        if "已达平台限额" in msg or "限额" in msg:
+                            logger.warning("⛔ 回告接口返回限额错误：code=%s, msg=%s，参数：%s", data.get('code'), msg, params)
+                            return "limit_reached"
+                        else:
+                            logger.warning("⚠️ 回告接口返回错误：code=%s, msg=%s，参数：%s", data.get('code'), msg, params)
+                            return "error"
+                except ValueError:
+                    logger.warning("⚠️ 回告响应非 JSON：%s，参数：%s", resp.text[:200], params)
+                    return "error"
+            else:
+                logger.warning("⚠️ 回告 HTTP %s，参数：%s", resp.status_code, params)
+                return "error"
+        except Exception as e:
+            logger.error("❌ 回告失败：%s，错误：%s", log_msg, str(e))
+            return "error"
+
+    def _report_start(self):
+        """上报采集开始（is_finished=0）"""
+        payload = {
+            "task_id": self.task_id,
+            "platform": str(self.platform_id),
+            "username": self.username,
+            "current_page": 0,
+            "total_pages": 0,
+            "is_finished": 0,
+        }
+        logger.info("上报开始 task_id=%s keyword=%s", self.task_id, self.keyword)
+        return self._send_report(payload, f"开始上报（is_finished=0）关键词：{self.keyword}")
+
+    def _report_progress(self, current_page: int, total_pages: int = 0):
+        """上报采集进度"""
+        payload = {
+            "task_id": self.task_id,
+            "platform": str(self.platform_id),
+            "username": self.username,
+            "current_page": current_page,
+            "total_pages": total_pages,
+            "is_finished": 0,
+        }
+        return self._send_report(payload, f"进度上报 page={current_page}")
+
+    def _report_end(self, success: bool, real_count: int, page_no: int = 0,
+                    exception_type: int = None, need_reassign: int = None, total_pages: int = 0):
+        """上报采集结束（is_finished=1 或 0）"""
+        payload = {
+            "task_id": self.task_id,
+            "platform": str(self.platform_id),
+            "username": self.username,
+            "current_page": page_no,
+            "total_pages": total_pages if total_pages > 0 else page_no,
+            "crawled_count": real_count,
+            "is_finished": 1 if success else 0,
+        }
+        if exception_type is not None:
+            payload["exception_type"] = exception_type
+        if need_reassign is not None:
+            payload["need_reassign"] = need_reassign
+        logger.info("上报结束 task_id=%s keyword=%s payload=%s", self.task_id, self.keyword, payload)
+        self._send_report(payload, f"结束上报（is_finished=1）关键词：{self.keyword}")
+
+    # ---------- login ----------
+
+    def _is_login(self, page):
+        try:
+            page.goto(LOGIN_VALIDATE_URL, timeout=300000)
+            page.wait_for_load_state("networkidle")
+            if "login" in page.url.lower():
+                logger.warning(" Cookie失效，需要重新登录")
+                return False
+            logger.info(" Cookie有效，已保持登录状态")
+            return True
+        except Exception as e:
+            logger.error(f" 验证登录状态失败：{e}")
+            return False
+
+    def _login_operation(self, page):
+        try:
+            page.wait_for_selector(USERNAME_SELECTOR, timeout=ELEMENT_TIMEOUT, state="visible")
+            page.wait_for_timeout(timeout=3000)
+            page.fill(USERNAME_SELECTOR, USERNAME)
+            logger.info(" 已输入登录账号")
+            page.wait_for_selector(PASSWORD_SELECTOR, timeout=ELEMENT_TIMEOUT, state="visible")
+            page.wait_for_timeout(timeout=3000)
+            page.fill(PASSWORD_SELECTOR, PASSWORD)
+            logger.info(" 已输入登录密码")
+            random_delay(1, 2)
+            agree_btn = page.locator('span.el-checkbox__inner')
+            agree_btn.click()
+            page.wait_for_selector(LOGIN_BTN_SELECTOR, timeout=ELEMENT_TIMEOUT)
+            page.wait_for_timeout(timeout=3000)
+            page.click(LOGIN_BTN_SELECTOR)
+            logger.info(" 已点击登录按钮")
+            page.wait_for_timeout(LOGIN_AFTER_CLICK)
+            return True
+        except PlaywrightTimeoutError as e:
+            logger.error(f" 登录失败：元素定位超时 - {str(e)}")
+            return False
+        except Exception as e:
+            logger.error(f" 登录异常：{str(e)}")
+            return False
+
+    # ---------- search ----------
+
+    @staticmethod
+    def _pick_search_input(page):
+        inputs = page.locator(SEARCH_INPUT_SELECTOR)
+        cnt = inputs.count()
+        for i in range(min(cnt, 2)):
+            candidate = inputs.nth(i)
+            try:
+                candidate.wait_for(state="visible", timeout=1500)
+                if candidate.is_enabled():
+                    return candidate
+            except PlaywrightTimeoutError:
+                continue
+        candidate = page.locator(f"{SEARCH_INPUT_SELECTOR}:visible").first
+        candidate.wait_for(state="visible", timeout=ELEMENT_TIMEOUT)
+        return candidate
+
+    def _search_operation(self, page, keyword, is_first_search=True):
+        try:
+            search_locator = self._pick_search_input(page)
+            search_locator.wait_for(timeout=ELEMENT_TIMEOUT)
+            search_locator.click(force=True)
+            search_locator.fill("")
+            page.keyboard.down("Control")
+            page.keyboard.press("a")
+            page.keyboard.up("Control")
+            page.keyboard.press("Backspace")
+            type_slow(search_locator, keyword, min_delay=0.06, max_delay=0.18)
+            logger.info(f"📝 已输入搜索关键词：{keyword}")
+            btn = page.locator(SEARCH_BTN_SELECTOR)
+            btn.wait_for(state="visible", timeout=SEARCH_BTN_TIMEOUT)
+            page.wait_for_timeout(3000)
+            detail_page = page
+            if is_first_search:
+                try:
+                    with page.context.expect_page(timeout=60000) as new_page_info:
+                        btn.click()
+                    detail_page = new_page_info.value
+                    detail_page.wait_for_load_state("networkidle", timeout=20000)
+                except PlaywrightTimeoutError:
+                    logger.warning(f"{get_current_time()}   未检测到新标签页")
+                    return None, False
+                except Exception as e:
+                    logger.warning(f"{get_current_time()}   等待新标签页异常：{e}")
+                    return None, False
+            else:
+                btn.click()
+                page.wait_for_load_state("networkidle", timeout=20000)
+                detail_page = page
+                logger.info("✅ 后续搜索：已在原页面完成跳转加载")
+            test_btn = detail_page.locator("div[data-v-c65c36bc].first-time-highlight-message-btn button")
+            if test_btn.count() > 0:
+                test_btn.wait_for(state="attached", timeout=5000)
+                test_btn.click()
+            force_close_popup(detail_page)
+            kill_masks(detail_page)
+            logger.info("✅ 已触发搜索")
+            return detail_page, True
+        except PlaywrightTimeoutError as e:
+            logger.error(f" 搜索失败：元素定位超时 - {str(e)}")
+            return None, False
+        except Exception as e:
+            logger.error(f" 搜索异常：{str(e)}")
+            return None, False
+
+    # ---------- pagination ----------
+
+    @staticmethod
+    def _goto_next_page(page) -> bool:
+        try:
+            next_btn = page.locator("button.btn-next").first
+            next_btn.wait_for(state="attached", timeout=3000)
+            aria_disabled = next_btn.get_attribute("aria-disabled")
+            logger.info(f"下一页按钮 aria-disabled 属性值：{aria_disabled}")
+            if aria_disabled == "true":
+                logger.warning("⚠️ 下一页按钮 aria-disabled=true，已无更多页面")
+                return False
+            page.wait_for_timeout(500)
+            if next_btn.is_visible() and next_btn.is_enabled():
+                next_btn.click(timeout=5000)
+            else:
+                next_btn.click(force=True, timeout=5000)
+            logger.info("✅ 翻页成功，下一页按钮 aria-disabled=false")
+            return True
+        except PlaywrightTimeoutError:
+            logger.warning("⚠️ 下一页按钮加载超时，判定无更多页面")
+            return False
+        except Exception as e:
+            logger.warning(f"⚠️ 翻页操作异常：{e}，判定无更多页面")
+            return False
+
+    @staticmethod
+    def _get_total_pages(page):
+        """从分页组件提取总页数，失败返回 None"""
+        try:
+            total_elem = page.locator("div.filter-panel-tags-pagination-number-total").first
+            total_elem.wait_for(state="attached", timeout=3000)
+            if total_elem.count() > 0:
+                text = total_elem.inner_text(timeout=2000).strip()
+                total = int(text)
+                logger.info(f"📊 检测到总页数：{total}")
+                return total
+        except PlaywrightTimeoutError:
+            logger.warning("⚠️ 总页数元素加载超时，降级为盲翻")
+        except (ValueError, TypeError) as e:
+            logger.warning(f"⚠️ 总页数解析失败：{e}，降级为盲翻")
+        except Exception as e:
+            logger.warning(f"⚠️ 获取总页数异常：{e}，降级为盲翻")
+        return None
+
+    # ---------- shop license collection ----------
+
+    @staticmethod
+    def _collect_shop_license(target_page, shop):
+        """采集店铺营业执照信息（OCR识别），返回 dict 或 None"""
+        random_delay(MIN_CLICK_DELAY, MAX_CLICK_DELAY)
+        entershop_btn = target_page.locator('div[data-v-5485589c].shop-info-container-left-info')
+        entershop_btn.wait_for(state="visible", timeout=10000)
+        entershop_btn.scroll_into_view_if_needed()
+        entershop_btn.hover()
+        random_delay(0.2, 0.5)
+        try:
+            with target_page.expect_popup(timeout=15000) as pop:
+                entershop_btn.click()
+                random_delay(0.05, 0.15)
+            shop_page = pop.value
+        except PlaywrightTimeoutError:
+            logger.warning("⚠️ 店铺弹窗未出现")
+            return None
+        shop_page.wait_for_load_state("domcontentloaded")
+        store_url = shop_page.url
+        logger.info(f"📌 获取到店铺链接：{store_url}")
+
+        random_delay(MIN_CLICK_DELAY, MAX_CLICK_DELAY)
+        shop_license_page = shop_page.locator(
+            '//div[contains(@class, "shop-info-container-right-btns-item") and contains(span, "资质/售后")]')
+        shop_license_page.wait_for(state="attached", timeout=15000)
+        shop_license_page.scroll_into_view_if_needed()
+        shop_license_page.hover()
+        random_delay(0.2, 0.5)
+        shop_license_page.click()
+        random_delay(0.05, 0.15)
+        random_delay(0.05, 0.1)
+        shop_page.wait_for_load_state("networkidle")
+        shop_page.wait_for_load_state("load")
+
+        shop_license_img = shop_page.locator(
+            '//span[contains(text(), "企业营业执照") or contains(text(), "营业执照（正本）")]/ancestor::div[@class="shop-info-drawer-zz-tab1-list-item"]/img'
+        ).first
+        shop_license_img.wait_for(state="visible", timeout=60000)
+        shop_license_src = None
+        ocr_res = None
+        try:
+            if shop_license_img.count() > 0:
+                shop_license_src = shop_license_img.get_attribute('src')
+                shop_license_src = shop_license_src.strip() if shop_license_src else None
+                ocr_res = get_ocr_res(shop_license_src)
+        except Exception as e:
+            logger.warning(f"提取营业执照图片src失败：{e}")
+        logger.debug("营业执照图片链接：%s", shop_license_src)
+
+        qualification_number = ocr_res.get('社会信用代码', '') if ocr_res else ''
+        business_license_company = ocr_res.get('单位名称', '') if ocr_res else ''
+        business_license_address = ocr_res.get('地址', '') if ocr_res else ''
+
+        province, city = extract_province_city(business_license_address)
+        logger.info(f"原始地址：{business_license_address}")
+        logger.info(f"提取的省份：{province} | 城市：{city}")
+
+        current_time = datetime.now().strftime("%Y-%m-%d")
+        insert_shop_info_to_db(
+            shop=shop, contact_address=store_url,
+            qualification_number=qualification_number,
+            business_license_company=business_license_company,
+            business_license_address=business_license_address,
+            scrape_date=current_time, platform='药帮忙',
+            province=province, city=city,
+            create_time=datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+            update_time=datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+        )
+
+        return {
+            "shop_page": shop_page,
+            "store_url": store_url,
+            "province": province,
+            "city": city,
+            "business_license_company": business_license_company,
+            "qualification_number": qualification_number,
+            "business_license_address": business_license_address,
+        }
+
+    # ---------- core collection ----------
+
+    def _collect_data(self, store_page):
+        """核心采集循环：遍历翻页 → 逐商品采集 → 走 DrugPipeline 入库"""
+        brand = self.product_brand
+        name = self.product_name
+        keyword = self.keyword
+        collect_result = []
+
+        logger.info(f"📊 开始采集「{keyword}」的商品数据")
+        store_page.wait_for_load_state("networkidle")
+
+        page_no = 1
+        start_page = self.api_current_page + 1 if self.api_current_page > 0 else 1
+
+        # 任务续爬：翻到起始页
+        if start_page > 1:
+            logger.info(f"⏩ 任务续爬：从第 {start_page} 页开始，正在翻页...")
+            while page_no < start_page:
+                if self.scheduler.end:
+                    logger.warning("⛔ 翻页过程中收到停止信号，终止采集")
+                    return collect_result, page_no
+                if self._goto_next_page(store_page):
+                    page_no += 1
+                    store_page.wait_for_load_state("networkidle")
+                    logger.info(f"⏩ 已翻到第 {page_no} 页")
+                else:
+                    logger.warning(f"⚠️ 无法翻到第 {start_page} 页（当前仅 {page_no} 页），从当前页开始采集")
+                    break
+
+        total_pages = 0
+
+        while True:
+            if self.scheduler.end:
+                logger.warning("⛔ 收到停止信号，终止采集")
+                break
+
+            logger.info(f"\n📄 「{keyword}」开始采集第 {page_no} 页")
+            list_page_url = store_page.url
+            logger.info(f"📌 已记录商品列表页URL：{list_page_url}")
+
+            store_page.wait_for_load_state("domcontentloaded")
+            store_page.wait_for_load_state("networkidle")
+            store_page.wait_for_timeout(500)
+
+            # 首次提取总页数
+            if total_pages == 0:
+                extracted_total = self._get_total_pages(store_page)
+                if extracted_total is not None:
+                    total_pages = extracted_total
+                    # 读到总页数立刻回报进度
+                    prog_status = self._report_progress(page_no, total_pages=total_pages)
+                    if prog_status == "limit_reached":
+                        logger.warning("⛔ 进度上报检测到限额，通知停止")
+                        self.scheduler.set_flag(True)
+
+            total_limit = store_page.locator(PRODUCT_ITEM_SELECTOR).count()
+            logger.info(f"📌 「{keyword}」第{page_no}页 初始商品个数（count）：{total_limit}")
+            collected_count = 0
+
+            not_found_keywords = store_page.locator("div.filter-panel-container-empty-text")
+            if not_found_keywords.count() > 0:
+                logger.warning(f"⚠️ 关键词「{keyword}」无匹配商品，直接跳过整个关键词采集")
+                return [], 0
+
+            for idx in range(total_limit):
+                if self.scheduler.end:
+                    logger.warning("⛔ 收到停止信号，终止当前页采集")
+                    break
+
+                detail_page = None
+                try:
+                    item = store_page.locator(PRODUCT_ITEM_SELECTOR).nth(idx)
+                    collected_count += 1
+                    store_page.wait_for_load_state("networkidle")
+                    delay = random_delay(MIN_CLICK_DELAY, MAX_CLICK_DELAY)
+                    logger.info(f"📌 「{keyword}」第{page_no}页 第{collected_count}/{total_limit}个商品 - 等待{delay:.2f}秒后采集（反爬）")
+
+                    # ---- 初始化默认值 ----
+                    title = ""
+                    shop = ""
+                    expiry_date = "无有效期"
+                    manufacture_date = "无生产日期"
+                    approval_number = "无批准文号"
+                    manufacturer = "未知公司"
+                    spec = "未知规格"
+                    current_time = datetime.now().strftime("%Y-%m-%d")
+                    is_sold_out = 0
+                    business_license_address = ''
+
+                    # 售罄
+                    sold_locator = item.locator('div.product-status')
+                    if sold_locator.count() > 0:
+                        is_sold_out = 1
+                        logger.warning(f" 「{keyword}」第{page_no}页 第{collected_count}个商品已售罄")
+
+                    # 商品ID (platform_item_id)
+                    product_id = ''
+                    product_id_elem = item.locator('div.product-card[data-product-id]')
+                    if product_id_elem.count() > 0:
+                        product_id = product_id_elem.get_attribute("data-product-id")
+
+                    # 标题
+                    product_locator = item.locator(PRODUCT_TITLE_SELECTOR)
+                    if product_locator.count() > 0:
+                        title = product_locator.inner_text(timeout=3000).strip()
+                        logger.info(f"{'='*10}「{keyword}」第{collected_count}个商品 - 列表页标题：{title}{'='*10}")
+                    else:
+                        logger.warning(f" 「{keyword}」第{collected_count}个商品 - 列表页标题元素未找到")
+
+                    # 品牌/名称筛选
+                    if not (brand in title and name in title):
+                        logger.warning(f" 「{keyword}」第{collected_count}个商品 - 标题「{title}」不包含品牌「{brand}」、名称「{name}」，跳过")
+                        continue
+
+                    # 价格
+                    price_int = item.locator('//span[@class="price-int"]').text_content().strip()
+                    price_decimal_elem = item.locator('//span[@class="price-decimal"]')
+                    price_decimal = price_decimal_elem.text_content().strip() if price_decimal_elem.count() > 0 else ''
+                    full_price = f"{price_int}{price_decimal}".strip()
+                    try:
+                        full_price_num = float(full_price)
+                    except ValueError:
+                        full_price_num = 0.0
+                        logger.warning(f" 「{keyword}」第{collected_count}个商品「{title}」- 列表页价格无法解析 raw={full_price!r}，按 0 处理")
+                    logger.info(f"✅ 提取到价格：{full_price_num}")
+
+                    # 公司名
+                    manufacturer_locator = item.locator(PRODUCT_COMPANY_SELECTOR)
+                    if manufacturer_locator.count() > 0:
+                        manufacturer = manufacturer_locator.inner_text(timeout=3000).strip()
+                        logger.info(f"{'='*10}「{keyword}」第{collected_count}个商品 - 列表页公司名：{manufacturer}{'='*10}")
+                    else:
+                        logger.warning(f" 「{keyword}」第{collected_count}个商品「{title}」- 列表页公司名称元素未找到")
+
+                    # 店铺名
+                    shop_locator = item.locator(PRODUCT_STORE_SELECTOR)
+                    if shop_locator.count() > 0:
+                        raw_shop = shop_locator.inner_text(timeout=3000).strip()
+                        shop = clean_shop_name(raw_shop)
+                        logger.info(f"{'='*10}「{keyword}」第{collected_count}个商品 - 列表页店名：{shop}{'='*10}")
+                    else:
+                        logger.warning(f" 「{keyword}」第{collected_count}个商品「{title}」- 列表页店铺名称元素未找到")
+
+                    # 折扣价
+                    discount_price_locator = item.locator('span[data-v-4cb6cc1f].discount-int').first
+                    if discount_price_locator.count() > 0:
+                        discount_price_val_origin = discount_price_locator.inner_text(timeout=3000).strip()
+                        match = re.search(r'\d+\.?\d*', str(discount_price_val_origin))
+                        discount_price_val = float(match.group()) if match else 0.00
+                        logger.info(f"{'='*10}「{keyword}」第{collected_count}个商品 - 详情页折扣价：{discount_price_val}{'='*10}")
+                    else:
+                        discount_price_val = full_price_num
+                        logger.warning(f" 「{keyword}」第{collected_count}个商品「{title}」- 折扣价元素未找到，使用采购价兜底：{discount_price_val}")
+
+                    # 有效期
+                    expiry_date_locator = item.locator(PRODUCT_VALIDITY_SELECTOR)
+                    if expiry_date_locator.count() > 0:
+                        expiry_date = expiry_date_locator.inner_text(timeout=3000).strip().replace('-', '')
+                        logger.info(f"{'='*10}「{keyword}」第{collected_count}个商品 - 详情页有效期：{expiry_date}{'='*10}")
+                    else:
+                        logger.warning(f" 「{keyword}」第{collected_count}个商品「{title}」- 有效期元素未找到")
+
+                    # ---- 点击进入详情页 ----
+                    logger.info(f"📌 「{keyword}」第{page_no}页 第{collected_count}个商品「{title}」- 模拟鼠标移动并点击")
+                    item.hover()
+                    random_delay(0.2, 0.5)
+                    item.dispatch_event("mousedown")
+                    random_delay(0.05, 0.15)
+                    item.dispatch_event("mouseup")
+                    random_delay(0.05, 0.1)
+
+                    try:
+                        with store_page.context.expect_page(timeout=60000) as p:
+                            item.click(delay=random.uniform(0.1, 0.3))
+                        detail_page = p.value
+                    except PlaywrightTimeoutError:
+                        logger.warning(f" 「{keyword}」第{page_no}页 第{collected_count}个商品「{title}」- 未检测到新标签页，使用当前页采集详情")
+                        detail_page = None
+
+                    target_page = detail_page if detail_page else store_page
+                    target_page.wait_for_load_state("networkidle", timeout=20000)
+                    delay = random_delay(MIN_PAGE_DELAY, MAX_PAGE_DELAY)
+                    logger.info(f"📌 「{keyword}」第{page_no}页 第{collected_count}个商品「{title}」- 详情页加载完成，等待{delay:.2f}秒（反爬）")
+
+                    # 详情页链接
+                    product_link = target_page.url
+                    logger.info(f"{'='*10}「{keyword}」第{collected_count}个商品 - 详情页链接：{product_link}{'='*10}")
+
+                    # 生产日期
+                    manufacture_date_locator = target_page.locator(
+                        '//div[contains(@class, "spec-info-item") and .//div[contains(@class, "spec-info-item-label") and normalize-space(.)="生产日期"]]//div[contains(@class, "spec-info-item-value-text")]')
+                    if manufacture_date_locator.count() > 0:
+                        manufacture_date = manufacture_date_locator.inner_text(timeout=3000).strip()
+                        logger.info(f"{'='*10}「{keyword}」第{collected_count}个商品 - 详情页生产日期：{manufacture_date}{'='*10}")
+                    else:
+                        logger.warning(f" 「{keyword}」第{collected_count}个商品「{title}」- 生产日期元素未找到")
+
+                    # 批准文号
+                    approval_number_locator = target_page.locator(
+                        '//div[contains(@class, "spec-info-item") and .//div[contains(@class, "spec-info-item-label") and normalize-space(.)="批准文号"]]//div[contains(@class, "spec-info-item-value-text")]')
+                    if approval_number_locator.count() > 0:
+                        approval_number = approval_number_locator.inner_text(timeout=3000).strip()
+                        logger.info(f"{'='*10}「{keyword}」第{collected_count}个商品 - 详情页批准文号：{approval_number}{'='*10}")
+                    else:
+                        logger.warning(f" 「{keyword}」第{collected_count}个商品「{title}」- 批准文号元素未找到")
+
+                    # 规格
+                    spec_locator = target_page.locator(
+                        '//div[contains(@class, "spec-info-item") and .//div[contains(@class, "spec-info-item-label") and normalize-space(.)="规格"]]//div[contains(@class, "spec-info-item-value-text")]')
+                    if spec_locator.count() > 0:
+                        spec = spec_locator.inner_text(timeout=3000).strip()
+                        logger.info(f"{'='*10}「{keyword}」第{collected_count}个商品 - 详情页规格：{spec}{'='*10}")
+                    else:
+                        logger.warning(f" 「{keyword}」第{collected_count}个商品「{title}」- 规格元素数量不足")
+
+                    # 库存
+                    storage = ''
+                    storage_locator = target_page.locator('[data-v-51f0e85d].detail-input-num-right-title')
+                    if storage_locator.count() > 0:
+                        storage = storage_locator.inner_text(timeout=3000).strip()
+                        logger.info(f"{'='*10}「{keyword}」第{collected_count}个商品 - 详情页库存：{storage}{'='*10}")
+
+                    # 销量
+                    sell = ''
+                    sell_locator = target_page.locator('div.detail-info-content-item-value-price-top-right div[data-v-95163d4a]', has_text='已售')
+                    if sell_locator.count() > 0:
+                        sell = sell_locator.inner_text(timeout=3000).strip()
+                        logger.info(f"{'='*10}「{keyword}」第{collected_count}个商品 - 详情页销量：{sell}{'='*10}")
+
+                    # 快照
+                    oss_url = ""
+                    try:
+                        local_path, oss_url = screenshot_target_page_to_local_then_oss(target_page=target_page, full_page=True)
+                        logger.info("详情页快照已上传 local=%s oss=%s", local_path, oss_url)
+                    except Exception as e:
+                        logger.warning("详情页快照上传失败：%s", e)
+
+                    # ---- 店铺资质采集 ----
+                    province = ""
+                    city = ""
+                    business_license_company = ""
+                    qualification_number = ''
+                    shop_exists, shop_info = shop_is_exists_database(shop)
+                    shop_page = None
+                    store_url = ''
+
+                    if not shop_exists:
+                        logger.info("数据库没有该店铺的营业执照，开始采集店铺资质")
+                        license_info = self._collect_shop_license(target_page, shop)
+                        if license_info:
+                            shop_page = license_info["shop_page"]
+                            store_url = license_info["store_url"]
+                            province = license_info["province"]
+                            city = license_info["city"]
+                            business_license_company = license_info["business_license_company"]
+                            qualification_number = license_info["qualification_number"]
+                            business_license_address = license_info["business_license_address"]
+                    else:
+                        logger.info("数据库有该店名，在数据库拿取对应字段填充")
+                        if shop_info:
+                            province = shop_info.get("province", "") or ""
+                            city = shop_info.get("city", "") or ""
+                            business_license_company = shop_info.get("business_license_company", "") or ""
+                            qualification_number = shop_info.get("qualification_number", "") or ""
+                            business_license_address = shop_info.get("business_license_address", "") or ""
+
+                    # 关闭店铺页
+                    try:
+                        if shop_page and not shop_page.is_closed():
+                            random_delay(4, 8)
+                            shop_page.close()
+                            logger.info(f"📌 「{keyword}」第{collected_count}个商品 - 已关闭店铺页标签 shop_page")
+                    except Exception as e:
+                        logger.warning(f"⚠️ 关闭 shop_page 失败：{e}")
+
+                    random_delay(5, 8)
+
+                    # 关闭详情页，切回列表页
+                    if detail_page and not detail_page.is_closed():
+                        detail_page.close()
+                        logger.info(f"📌 「{keyword}」第{collected_count}个商品 - 已关闭详情页标签页")
+                    store_page.bring_to_front()
+                    store_page.mouse.move(random.randint(100, 300), random.randint(200, 400))
+                    random_delay(0.5, 1.0)
+                    store_page.wait_for_load_state("networkidle")
+                    random_delay(MIN_CLICK_DELAY, MAX_CLICK_DELAY)
+                    logger.info(f" 「{keyword}」第{collected_count}个商品「{title}」- 已切回列表页")
+                    random_delay(2, 4)
+
+                    # 省市ID
+                    province_id, city_id = get_province_city_ids(province, city)
+
+                    # ---- 组装 product dict（兼容 DrugPipeline） ----
+                    now_str = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+                    product = {
+                        "platform": self.platform_id,
+                        "item_id": product_id,
+                        "enterprise_id": self.company_id,
+                        "product_name": title,
+                        "spec": spec,
+                        "one_price": discount_price_val,
+                        "detail_url": product_link,
+                        "shop_name": shop,
+                        "anonymous_store_name": "",
+                        "shop_url": store_url,
+                        "city_name": city,
+                        "city_id": city_id,
+                        "province_name": province,
+                        "province_id": province_id,
+                        "shipment_city_name": "",
+                        "shipment_city_id": 0,
+                        "shipment_province_name": "",
+                        "shipment_province_id": 0,
+                        "area_info": business_license_address,
+                        "factory_name": manufacturer,
+                        "scrape_date": current_time,
+                        "price": discount_price_val,
+                        "sales": sell,
+                        "stock_count": storage,
+                        "snapshot_url": oss_url,
+                        "approval_num": approval_number,
+                        "produced_time": manufacture_date,
+                        "deadline": expiry_date,
+                        "update_time": now_str,
+                        "insert_time": now_str,
+                        "number": 1,
+                        "product_brand": brand,
+                        "collect_task_id": self.collect_task_id,
+                        "search_name": keyword,
+                        "company_name": business_license_company,
+                        "collect_config_info": self.collect_config_info,
+                        "account_id": self.collect_equipment_account_id,
+                        "collect_region_id": self.collect_region_id,
+                        "collect_round": self.collect_round,
+                        "is_sold_out": is_sold_out,
+                    }
+
+                    # 走 DrugPipeline 入库（含去重 + 店铺城市补全）
+                    self.pipeline.storge_data(product)
+                    collect_result.append(product)
+                    logger.info(f" 「{keyword}」第{collected_count}个商品「{title}」采集完成")
+
+                except Exception as e:
+                    logger.exception(f" 「{keyword}」第{collected_count}个商品采集核心异常：{str(e)}")
+                    try:
+                        if detail_page and not detail_page.is_closed():
+                            detail_page.close()
+                        if store_page and not store_page.is_closed():
+                            store_page.bring_to_front()
+                        store_page.wait_for_load_state("networkidle")
+                        random_delay(MIN_CLICK_DELAY, MAX_CLICK_DELAY)
+                    except Exception as e2:
+                        logger.error(f" 「{keyword}」第{collected_count}个商品详情采集异常（处理时）：{str(e2)}，原异常：{str(e)}")
+                        continue
+
+                # 每采6个商品滚动一次
+                if collected_count % 6 == 0 and collected_count > 0 and collected_count != total_limit:
+                    logger.info("采满6个往下滑")
+                    slow_scroll_400px(store_page)
+                    store_page.wait_for_load_state("networkidle")
+
+            if self.scheduler.end:
+                break
+
+            delay = random_delay(1.5, 3.0)
+            logger.info(f"⏳ 翻页前随机等待 {delay:.2f}s（反爬）")
+
+            # 每页结束上报进度
+            prog_status = self._report_progress(page_no, total_pages=total_pages)
+            if prog_status == "limit_reached":
+                logger.warning("⛔ 进度上报检测到限额，通知停止")
+                self.scheduler.set_flag(True)
+
+            # 翻页
+            if self._goto_next_page(store_page):
+                logger.info(f"「{keyword}」还有下一页")
+                page_no += 1
+                store_page.wait_for_load_state("networkidle")
+                total_limit = store_page.locator(PRODUCT_ITEM_SELECTOR).count()
+                logger.info(f"📌 「{keyword}」第{page_no}页 商品个数更新为：{total_limit}")
+                continue
+            else:
+                logger.info(f" 「{keyword}」已无下一页，关键词采集结束")
+                break
+
+        long_delay = random_delay(MIN_KEYWORD_DELAY, MAX_KEYWORD_DELAY)
+        logger.info(f" 「{keyword}」采集完成，共{len(collect_result)}条数据（pipeline 实际入库 {self.pipeline.crawl_count} 条），等待{long_delay:.2f}秒后继续下一个关键词（反爬）")
+        return collect_result, page_no
+
+    # ---------- main entry ----------
+
+    def run(self):
+        """蜘蛛主入口，返回 (crawl_count, is_success)。
+
+        由 CollectScheduleRunner 调用：
+            count, is_success = YbmCrawler(task_dict).run()
+        """
+        load_city_mapping()
+        logger.info("\n" + "=" * 50)
+        logger.info("🚀 药帮忙采集程序启动")
+        logger.info(f"⏰ 启动时间：{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
+        logger.info("=" * 50)
+
+        with sync_playwright() as p:
+            browser = p.chromium.launch(
+                channel="chrome",
+                headless=True,
+                slow_mo=random.randint(100, 300),
+                args=[
+                    "--disable-blink-features=AutomationControlled",
+                    "--enable-automation=false",
+                    "--disable-infobars",
+                    "--remote-debugging-port=0",
+                    "--start-maximized",
+                    "--disable-extensions",
+                    "--disable-plugins-discovery",
+                    "--no-sandbox",
+                    "--disable-dev-shm-usage",
+                    f"--user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/{random.randint(110, 120)}.0.0.0 Safari/537.36",
+                ],
+            )
+            context = browser.new_context(
+                locale="zh-CN",
+                timezone_id="Asia/Shanghai",
+                geolocation={"latitude": 31.230416, "longitude": 121.473701},
+                permissions=["geolocation"],
+                user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+                viewport={"width": 1800, "height": 1000},
+                java_script_enabled=True,
+                bypass_csp=True,
+            )
+            page = context.new_page()
+
+            page.add_init_script("""
+                Object.defineProperty(navigator, 'webdriver', { get: () => undefined });
+                Object.defineProperty(navigator, 'plugins', { get: () => [1, 2, 3] });
+                Object.defineProperty(navigator, 'mimeTypes', { get: () => [1, 2, 3] });
+                window.chrome = { runtime: {}, loadTimes: () => ({}) };
+                delete window.navigator.languages;
+                window.navigator.languages = ['zh-CN', 'zh'];
+                (() => {
+                    const originalAddEventListener = EventTarget.prototype.addEventListener;
+                    EventTarget.prototype.addEventListener = function(type, listener) {
+                        if (type === 'mousemove') {
+                            return originalAddEventListener.call(this, type, (e) => {
+                                e._automation = undefined;
+                                listener(e);
+                            });
+                        }
+                        return originalAddEventListener.call(this, type, listener);
+                    };
+                })();
+            """)
+
+            try:
+                # 登录
+                load_cookies(context)
+                if not self._is_login(page):
+                    page.goto(TARGET_LOGIN_URL)
+                    page.wait_for_load_state("networkidle")
+                    logger.info("🔑 开始执行登录流程")
+                    login_success = self._login_operation(page)
+                    if not login_success:
+                        logger.error(" 登录失败，程序终止")
+                        self.is_success = False
+                        self._page_no = 0
+                        return 0, False
+                    save_cookies(context)
+                    logger.info(" 登录并保存Cookie成功！")
+
+                # 启动心跳守护线程（CrawlerScheduler）
+                self.scheduler.start()
+
+                # 搜索
+                popup_guard(page, "before_search")
+                store_page, search_success = self._search_operation(page, self.keyword, is_first_search=True)
+                if store_page:
+                    popup_guard(store_page, "after_search")
+
+                if store_page is None:
+                    logger.warning(f" 「{self.keyword}」搜索页面为空，任务失败")
+                    self.is_success = False
+                    self._page_no = 0
+                    return 0, False
+
+                if not search_success:
+                    logger.warning(f" 「{self.keyword}」搜索失败，跳过采集")
+                    self.is_success = False
+                    self._page_no = 0
+                    return 0, False
+
+                store_page.wait_for_load_state("domcontentloaded")
+                store_page.wait_for_load_state('networkidle')
+
+                # 上报采集开始，检查是否限额
+                report_status = self._report_start()
+                if report_status == "limit_reached":
+                    logger.warning("⛔ 任务 %s 开始上报时账号已达限额，退出当前任务", self.task_id)
+                    self.is_success = False
+                    self._page_no = 0
+                    return 0, False
+
+                # 核心采集
+                data_list, page_no = self._collect_data(store_page)
+                self._page_no = page_no
+                real_count = len(data_list)
+                self.is_success = True
+                logger.info(f"关键词「{self.keyword}」采集完成，共 {real_count} 条数据（pipeline 实际入库 {self.pipeline.crawl_count} 条），共 {page_no} 页")
+
+            except Exception as e:
+                logger.exception("程序异常：%s", e)
+                self.is_success = False
+            finally:
+                self.scheduler.stop()
+                # 上报采集结束
+                try:
+                    self._report_end(
+                        success=self.is_success,
+                        real_count=self.pipeline.crawl_count,
+                        page_no=getattr(self, '_page_no', 0),
+                        total_pages=0,
+                    )
+                except Exception:
+                    pass
+                browser.close()
+                logger.info(" 浏览器已关闭，程序结束")
+
+        return self.pipeline.crawl_count, self.is_success
+
+
+# ==================== SECTION 9: ENTRY POINT (测试/直接运行) ====================
+
+if __name__ == '__main__':
+    # 直接运行：使用手动任务进行测试
+    load_city_mapping()
+    if USE_MANUAL_TASK:
+        task = MANUAL_TASK
+    else:
+        # 从内部 API 拉取任务
+        try:
+            resp = requests.get(
+                TASK_PULL_URL,
+                params={'platform': PLATFORM_ID, 'username': YBM_DEVICE_ID},
+                headers={'X-Crawler-Token': TASK_API_TOKEN},
+                timeout=15,
+            )
+            result = resp.json()
+            task = result.get('data', {}).get('task') or {}
+        except Exception as e:
+            logger.error(f"拉取任务失败：{e}")
+            task = {}
+
+    if not task:
+        logger.error("未获取到任何任务，程序退出")
+    else:
+        crawler = YbmCrawler(task)
+        count, success = crawler.run()
+        logger.info(f"测试完成：crawl_count={count}, is_success={success}")
+
+        # 发送飞书通知
+        try:
+            spec_items = [item.strip() for item in re.split(r"[|、，,\n\r]+", task.get("product_specs", "") or "") if item.strip()]
+            display_spec = "、".join(spec_items)
+            notice_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+            if success:
+                feishu_send_text(
+                    f"{notice_time} 通知:\n"
+                    f"平台: 药帮忙, 药品: {task.get('product_name', '')}, 品规: {display_spec}, 爬取数据: {count}条"
+                )
+            else:
+                feishu_send_error_card(
+                    task_name=task.get("product_name", ""),
+                    err_msg=f"task_id={task.get('id')}, company_id={task.get('company_id')}, crawl_count={count}",
+                    mention_all=False,
+                )
+        except Exception as e:
+            logger.warning(f"飞书通知发送失败：{e}")