2.0/Yjj/yjj_v2.py

from playwright.sync_api import sync_playwright, TimeoutError as PlaywrightTimeoutError
from logger_config import logger
from datetime import datetime
import random
import csv
import os
import time
import json
import sys
from config import *
from conn_mysql import MySQLPoolOnline
import re
import uuid
import requests
import base64
from io import BytesIO
from PIL import Image
import traceback
import oss2
from scheduler import CrawlerScheduler
import platform
# ==================== 调度器配置 ====================
PLATFORM_ID = "7"  # 药九九平台编码

# ==================== 从数据库获取可用账号 ====================
def get_account_from_db():
    """从 accounts_platform 表获取一个可用的药九九账号（platform=7, status=1）"""
    sql = """SELECT `name`, `phone`, `password` FROM `accounts_platform`
             WHERE `platform`=7 AND `status`=1
             ORDER BY `cookie_timestamp` ASC LIMIT 1"""
    rows = mysql_pool.select_data(sql)
    if not rows:
        logger.error("无可用药九九账号（platform=7, status=1）")
        return None
    return rows[0]

# ==================== 回告辅助函数 ====================
def _build_report_data(task_dict, **kwargs):
    return {
        "task_id": task_dict.get("id"),
        "platform": task_dict.get("_platform", PLATFORM_ID),
        "username": task_dict.get("_device_id", "unknown"),
        **kwargs,
    }

def _report_page_progress(scheduler, task_dict, page, crawled_count, is_finished=0, total_pages=0):
    """逐页回告，返回 True=code=error 需停止"""
    if not scheduler:
        return False
    data = _build_report_data(task_dict,
        current_page=page, crawled_count=crawled_count, is_finished=is_finished)
    if total_pages:
        data["total_pages"] = total_pages
    scheduler.post_report(data)
    return scheduler.end

def _report_exception(scheduler, task_dict, page, exception_type, remark="", crawled_count=0):
    """异常回告"""
    if not scheduler:
        return
    data = _build_report_data(task_dict,
        current_page=page, is_finished=0,
        exception_type=exception_type, remark=remark)
    if page:
        data["total_pages"] = page
    if crawled_count:
        data["crawled_count"] = crawled_count
    scheduler.post_report(data)
# from faker import Faker

# 代理IP池
PROXY_POOL_URL = ""
PROXY_VALIDATION_URL = ""  # 用于验证代理有效性的URL
PROXY_TIMEOUT = 10  # 代理验证超时时间(秒)

mysql_pool = MySQLPoolOnline()
finished_task_ids = set()


def _chromium_launch_args(chrome_major=None):
    """Playwright Chromium 启动参数（反自动化 + 随机 UA 主版本）。"""
    major = chrome_major if chrome_major is not None else random.randint(110, 120)
    return [
        "--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 "
        f"(KHTML, like Gecko) Chrome/{major}.0.0.0 Safari/537.36",
    ]


def get_random_proxy():
    """从代理池获取随机代理IP"""
    if not PROXY_POOL_URL.strip():
        return None
    try:
        response = requests.get(PROXY_POOL_URL, timeout=10)
        if response.status_code == 200:
            proxy = response.text.strip()
            if validate_proxy(proxy):
                logger.info(f"获取到有效代理: {proxy}")
                return proxy
            logger.warning(f"代理无效: {proxy}")
    except Exception as e:
        logger.error(f"获取代理失败: {str(e)}")
    return None

def validate_proxy(proxy):
    """验证代理IP有效性"""
    if not PROXY_VALIDATION_URL.strip():
        return False
    try:
        proxies = {
            "http": f"http://{proxy}",
            "https": f"https://{proxy}"
        }
        response = requests.get(
            PROXY_VALIDATION_URL,
            proxies=proxies,
            timeout=PROXY_TIMEOUT
        )
        return response.status_code == 200
    except Exception:
        return False

def init_browser_with_proxy(playwright):
    proxy = get_random_proxy()
    proxy_config = None
    if proxy:
        proxy_server, proxy_port = proxy.split(":")
        proxy_config = {
        "server": f"http://{proxy_server}:{proxy_port}",
        # "username": "your_proxy_username",
        # "password": "your_proxy_password"
        }
        logger.info(f"使用代理: {proxy_server}:{proxy_port}")
    else:
        logger.warning("未获取到有效代理，将使用本地IP")

    # 启动浏览器（保留原有反爬配置）
    return playwright.chromium.launch(
        headless=True,  # 非无头模式
        channel="chrome",  # 使用Chrome内核
        slow_mo=random.randint(100, 300),  # 随机操作延迟
        proxy=proxy_config,  # 代理配置（None则不使用代理）
        args=_chromium_launch_args(),
    )


# ==================== 2. 反爬工具函数 ====================
def random_delay(min_seconds, max_seconds):
    """生成随机延迟（核心反爬：避免固定间隔）"""
    delay = random.uniform(min_seconds, max_seconds)
    time.sleep(delay)
    return delay


def simulate_human_typing(page, locator, text):
    """模拟真人打字（逐个字符输入，带随机间隔）"""
    try:
        locator.click()
        locator.clear()
        for char in text:
            locator.type(char, delay=random.uniform(MIN_INPUT_DELAY, MAX_INPUT_DELAY))
            random_delay(0.05, 0.1)  # 字符间额外小延迟
        logger.info(f" 模拟真人输入完成：{text}")
    except Exception as e:
        logger.error(f"模拟打字失败：{e}")
        locator.fill(text)  # 兜底：直接填充


def save_cookies(context, cookie_path=COOKIE_FILE_PATH):
    """保存Cookie到本地JSON文件"""
    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):
    """从本地JSON文件加载Cookie到浏览器上下文"""
    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 is_login(page):
    """验证是否已登录（核心：检测登录态）"""
    try:
        # 访问需要登录的页面
        page.goto(LOGIN_VALIDATE_URL, timeout=ELEMENT_TIMEOUT)
        time.sleep(5)
        page.wait_for_load_state("networkidle")

        # 检测是否跳转到登录页（URL包含login则未登录）
        if "login" in page.url.lower():
            logger.warning(" Cookie失效，需要重新登录")
            return False

        # 可选：检测登录后的专属元素（比如用户名、个人中心等）
        # if page.locator("用户中心选择器").count() > 0:
        #     return True
        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

# ==================== 滚动函数重构（核心修改） ====================
def slow_scroll_400px(page,scroll_distance1=400):
    """
    慢速滚动400px±50px（模拟真人滑动）
    :param page: 页面对象
    :return: 滚动是否成功
    """
    try:
        # 生成400±50px的随机滚动距离
        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）"
        )

        # 渐进式滚动（每步50px，间隔0.05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)

        # 处理剩余不足一步的距离
        if remaining_distance > 0:
            page.evaluate(f"window.scrollBy(0, {remaining_distance});")
            time.sleep(SCROLL_INTERVAL)

        # 滚动后等待懒加载完成
        page.wait_for_load_state("networkidle", timeout=8000)
        random_delay(2.0, 3.0)  # 滚动后额外停顿，模拟真人
        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

# CSV配置
CSV_FILE_PATH = f"yjj_collect_data_{datetime.now().strftime('%Y%m%d_%H%M%S')}.csv" # CSV保存路径
CSV_HEADERS = [
    "商品标题", "商品采购价格", "商品折扣价格", "规格", "盒数",
    "店铺名称", "公司名称",
    "有效日期", "生产日期", "批准文号", "采集时间"
]    #表头



# ==================== 登录函数 ====================
def login_operation(page, username, password):
    """登录操作函数"""
    try:
        # 输入手机号（直接用单个变量）
        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")

        # 输入密码
        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")

        # 点击登录按钮
        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



def kill_masks(page):
    """
    强制清理残留遮罩层/覆盖层，并恢复 body 可滚动、可点击状态
    """
    page.evaluate(r"""
    () => {
      const removed = [];
      const hidden = [];

      // 1) 先处理已知常见遮罩
      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 => {
          // v-modal / overlay 直接 remove 最省事
          removed.push(sel);
          el.remove();
        });
      }

      // 2) 再做一次“泛化兜底”：全屏 fixed/absolute + 高 z-index 的覆盖层
      //    注意：不要误删页面正常的固定导航，所以加上“近似全屏”的判断
      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);
        const pos = s.position;
        const pe = s.pointerEvents;

        if ((pos === 'fixed' || pos === 'absolute') && z >= 1000 && pe !== 'none') {
          const r = el.getBoundingClientRect();
          const nearFullScreen =
            r.width >= window.innerWidth * 0.8 &&
            r.height >= window.innerHeight * 0.8 &&
            r.left <= window.innerWidth * 0.1 &&
            r.top <= window.innerHeight * 0.1;

          // 常见遮罩是半透明背景色，或者透明但拦截点击
          const bg = s.backgroundColor || '';
          const looksLikeMask =
            nearFullScreen && (bg.includes('rgba') || bg.includes('rgb') || s.opacity !== '1');

          if (nearFullScreen) {
            // 不管透明不透明，只要近似全屏且高 z-index，就先让它不拦截点击
            el.style.pointerEvents = 'none';
            el.style.display = 'none';
            hidden.push(el.tagName + '.' + (el.className || ''));
          }
        }
      }

      // 3) 恢复 body / html 的滚动与交互（很多弹窗会锁滚动）
      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';

      // 4) 去掉 Element-UI 常见的锁定 class
      document.body.classList.remove('el-popup-parent--hidden');

      return { removed, hiddenCount: hidden.length, hidden };
    }
    """)




def force_close_popup(page):
    """关闭新手引导/遮罩（多步：下一步/完成/我知道了），并兜底移除遮罩层"""
    try:
        # 1) 尝试连续点“下一步/完成/我知道了/关闭”
        for _ in range(5):  # 最多点5次，足够覆盖多步引导
            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

            # 有些引导是右上角 X（如果存在就点）
            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

        # 2) 兜底：移除常见遮罩层（element-ui / 通用 mask/overlay）
        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);
            // 只移除“覆盖层”倾向的元素：fixed/absolute 且 z-index 很高
            if ((s.position === 'fixed' || s.position === 'absolute') && parseInt(s.zIndex || '0', 10) >= 1000) {
              el.remove();
            }
          });
        }
        """)
    except Exception:
        pass


def pick_search_input(page):
    """优先选可见且可用的搜索输入框；第一个不行就尝试第二个"""
    inputs = page.locator(SEARCH_INPUT_SELECTOR)
    cnt = inputs.count()

    # 优先检查前两个（你说只有两个）
    for i in range(min(cnt, 2)):
        candidate = inputs.nth(i)
        try:
            candidate.wait_for(state="visible", timeout=1500)  # 小超时快速试探
            if candidate.is_enabled():
                return candidate
        except PlaywrightTimeoutError:
            continue

    # 兜底：直接找任意可见的（避免命中 hidden 模板）
    candidate = page.locator(f"{SEARCH_INPUT_SELECTOR}:visible").first
    candidate.wait_for(state="visible", timeout=ELEMENT_TIMEOUT)
    return candidate



def type_slow(locator, text, min_delay=0.06, max_delay=0.18):
    """逐字输入，模拟真人打字"""
    for ch in text:
        locator.type(ch, delay=int(random.uniform(min_delay, max_delay) * 1000))


# ==================== 搜索操作函数 ====================
def search_operation(page, keyword):
    """搜索框填充+提交搜索"""
    try:

        search_url = f"https://www.yyjzt.com/search?keyword={keyword}"
        page.goto(search_url)
        page.wait_for_timeout(600)
        try:
            page.wait_for_load_state("networkidle", timeout=10000)
        except Exception:
            pass
        force_close_popup(page)
        kill_masks(page)
        logger.info("✅ 已触发搜索")
        return True

    except PlaywrightTimeoutError as e:
        logger.error(f" 搜索失败：元素定位超时 - {str(e)}")
        return False
    except Exception as e:
        logger.error(f" 搜索异常：{str(e)}")
        return False



#翻下一页
def goto_next_page(page):
    """
    尝试翻到下一页；成功返回True，没下一页/翻页失败返回False
    适配常见 ElementUI: .el-pagination .btn-next / .el-pagination__next
    """
    # 多写几个候选，哪个能用就用哪个
    candidates = [
        ".el-pagination button.btn-next:not(.is-disabled)",
        ".el-pagination__next:not(.is-disabled)",
        "button:has-text('下一页'):not([disabled])",
        "a:has-text('下一页')",
    ]


    next_btn = None
    for sel in candidates:
        loc = page.locator(sel).first
        if loc.count() > 0:
            next_btn = loc
            break

    if not next_btn:
        return False

    # 用“当前页第一个商品标题”做翻页完成的判据（比只等networkidle更稳）
    first_title = page.locator(PRODUCT_TITLE_SELECTOR).first
    before = ""
    try:
        if first_title.count() > 0:
            before = first_title.inner_text(timeout=2000).strip()
    except:
        pass

    try:
        page.evaluate("window.scrollTo(0, 0);")
        next_btn.click(timeout=5000)
        page.wait_for_load_state("networkidle")

        # 等列表发生变化（标题变了 / 或者至少第一个标题重新出现）
        if before:
            page.wait_for_function(
                """(sel, oldText) => {
                    const el = document.querySelector(sel);
                    return el && el.innerText && el.innerText.trim() !== oldText;
                }""",
                arg=(PRODUCT_TITLE_SELECTOR, before),
                timeout=5000
            )
        else:
            first_title.wait_for(timeout=1000)

        return True
    except Exception as e:
        logger.warning(f" 翻页失败：{e}")
        return False



def popup_guard(page, tag=""):
    """
    全局弹窗/遮罩守卫：多步引导 + 关闭按钮 + 遮罩清理 + 恢复滚动
    tag 仅用于日志区分调用位置
    """
    try:
        # 给弹窗一点出现时间
        page.wait_for_timeout(300)

        # 1) 连续点“下一步/完成/我知道了/关闭”
        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

            # 2) 常见的 close icon
            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

        # 3) 清遮罩 + 恢复滚动/交互
        page.evaluate(r"""
        () => {
          // 第一步：精准清理已知的遮罩/弹窗类名（Element UI框架常用）
          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()));

          // 泛化兜底：近似全屏 + 高 z-index 的层直接屏蔽
          const all = Array.from(document.querySelectorAll('body *'));
          for (const el of all) {
            const s = getComputedStyle(el); // 获取元素的实际样式（含CSS生效的样式）
            const z = parseInt(s.zIndex || '0', 10);    // 取元素的层级（z-index），默认0
            // 条件1：元素是固定/绝对定位（弹窗/遮罩常见定位方式）+ 层级≥1000（高优先级遮挡）+ 能拦截鼠标事件
            if ((s.position === 'fixed' || s.position === 'absolute') && z >= 1000 && s.pointerEvents !== 'none') {
              const r = el.getBoundingClientRect();     // 获取元素的尺寸和位置
                // 条件2：元素宽度/高度≥屏幕80%（近似全屏遮罩）
              const nearFull = r.width >= innerWidth * 0.8 && r.height >= innerHeight * 0.8;
              if (nearFull) {
                el.style.pointerEvents = 'none';    // 让元素不拦截鼠标点击
                el.style.display = 'none';          // 隐藏元素
              }
            }
          }
        // 第三步：恢复页面滚动功能（弹窗常把页面设为不可滚动）
          document.documentElement.style.overflow = 'auto';     // html标签恢复滚动
          document.body.style.overflow = 'auto';    // body标签恢复滚动
          document.body.classList.remove('el-popup-parent--hidden');  // 移除Element UI的滚动禁用类
        }
        """)

        logger.info("杀除弹窗成功")
    except Exception:
        pass




def open_detail_page(list_page, item, keyword, idx, *, timeout=15000):
    """
    点击商品进入详情页，兼容：
    1) 新开 tab（返回 detail_page != list_page, opened_new_tab=True）
    2) 同 tab 跳转（detail_page == list_page, opened_new_tab=False）
    """
    ctx = list_page.context
    list_url = list_page.url
    detail_page = None
    opened_new_tab = False

    try:
        # 期望新开 tab（很多站点会这样）
        with ctx.expect_page(timeout=timeout) as p:
            item.click(delay=random.uniform(0.1, 0.3))
        detail_page = p.value
        opened_new_tab = True
        logger.info(f" 「{keyword}」第{idx}个商品 - 新开标签页进入详情")
    except PlaywrightTimeoutError:
        # 兜底：没新开 tab，大概率是同页跳转/弹层
        detail_page = list_page
        opened_new_tab = False
        logger.info(f" 「{keyword}」第{idx}个商品 - 未新开标签页，按同页进入详情处理")

    return detail_page, opened_new_tab, list_url




def return_to_list(list_page, detail_page, opened_new_tab, list_url, keyword, idx):
    """
    从详情页返回列表页：
    - 新 tab：关闭 tab，然后 bring_to_front 切回
    - 同 tab：尽量 go_back 回到 list_url；如果没跳转而是弹层，尝试 ESC
    """
    # 如果浏览器/页面已经被关了，直接退出，避免二次异常
    if list_page is None or list_page.is_closed():
        logger.warning(f" 「{keyword}」第{idx}个商品 - 列表页已关闭，无法切回")
        return

    if opened_new_tab:
        # 只关“新开的详情 tab”，绝不关 list_page
        try:
            if detail_page and (detail_page is not list_page) and (not detail_page.is_closed()):
                detail_page.close()
                logger.info(f"📌 「{keyword}」第{idx}个商品 - 已关闭详情页标签页")
        except Exception as e:
            logger.warning(f" 「{keyword}」第{idx}个商品 - 关闭详情页失败：{e}")

        # 切回列表页
        try:
            list_page.bring_to_front()
            list_page.mouse.move(random.randint(100, 300), random.randint(200, 400))
            random_delay(0.3, 0.8)
            list_page.wait_for_load_state("networkidle")
            logger.info(f" 「{keyword}」第{idx}个商品 - 已切回列表页（新tab模式）")
        except Exception as e:
            logger.warning(f" 「{keyword}」第{idx}个商品 - 切回列表页失败：{e}")
        return

    # 同 tab：detail_page == list_page
    try:
        # 1) 如果 URL 变了，说明确实跳转了 → go_back 回去
        if list_page.url != list_url:
            for _ in range(3):  # 最多退 3 次，防止死循环
                list_page.go_back(timeout=15000)
                list_page.wait_for_load_state("domcontentloaded", timeout=15000)
                random_delay(0.2, 0.5)
                if list_page.url == list_url:
                    break
            logger.info(f" 「{keyword}」第{idx}个商品 - 已返回列表页（同tab跳转模式）")
        else:
            # 2) URL 没变：可能是弹层详情 → 尝试 ESC 关闭弹层
            list_page.keyboard.press("Escape")
            random_delay(0.2, 0.5)
            logger.info(f" 「{keyword}」第{idx}个商品 - 已尝试关闭弹层并留在列表页（同tab弹层模式）")

        list_page.bring_to_front()
        list_page.wait_for_load_state("networkidle")
    except Exception as e:
        logger.warning(f" 「{keyword}」第{idx}个商品 - 同tab返回列表页失败：{e}")



#判断店名是否已经在数据库
def shop_is_exists_database(shop):
    query_sql = """
            SELECT province, city, business_license_company, qualification_number
            FROM retrieve_yjj_shop_info_middle
            WHERE shop = %s
            """
    try:
        rows = mysql_pool.select_data(query_sql, (shop,))
        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):
    """
    把字段插入到yjj_shop_info_middle表
    :param 各参数: 你要插入的字段值（空字符串也可）
    :return: bool - 插入成功返回True，失败返回False
    """
    sql = """
        INSERT INTO retrieve_yjj_shop_info_middle (
            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,
    )

    try:
        n = mysql_pool.execute(sql, params)
        if n > 0:
            logger.info("店铺信息已入库 | shop=%s", shop)
            return True
        logger.error("店铺信息插入失败：受影响行数为 0 | shop=%s", shop)
        return False
    except Exception as e:
        logger.error("店铺信息插入失败：%s", e)
        return False


def insert_single_to_mysql(single_data):
    """
    逐条插入单条数据到MySQL数据库
    :param single_data: 单条商品数据元组
    :return: 插入是否成功
    """
    insert_sql = """
        INSERT INTO retrieve_scrape_data
        (enterprise_id,product_name, min_price, manufacture_date,
         expiry_date, store_name, company_name, province_name, city_name, manufacturer, product_specs, approval_number, link_url,
             scrape_date, is_sold_out, qualification_number, platform_id, number, sales,inventory,snapshot_url,search_name,product_brand,collect_config_info,task_id,insert_time,update_time,collect_equipment_account_id,collect_region_id,collect_round) VALUES (%s, %s, %s, %s,%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s,%s, %s, %s);
        """

    values = (
        single_data["company_id"],
        single_data["product"],
        single_data["min_price"],
        single_data["manufacture_date"],
        single_data["expiry_date"],
        single_data["shop"],
        single_data["business_license_company"],
        single_data["province"],
        single_data["city"],
        single_data["manufacturer"],
        single_data["specification"],
        single_data["approval_number"],
        single_data["product_link"],
        single_data["scrape_date"],
        single_data["is_sold_out"],
        single_data["credit_code"],
        7,
        single_data["number"],
        single_data["sales"],
        single_data["inventory"],
        single_data["snapshot_url"],
        single_data["search_name"],
        single_data["product_brand"],
        single_data["collect_config_info"],
        single_data["task_id"],
        single_data["insert_time"],
        single_data["update_time"],
        single_data["collect_equipment_account_id"],
        single_data["collect_region_id"],
        single_data["collect_round"],
    )

    try:
        n = mysql_pool.execute(insert_sql, values)
        if n > 0:
            logger.info("单条采集数据已入库 | product=%s", single_data.get("product", "")[:80])
            return True
        logger.error("单条数据插入失败：受影响行数为 0")
        return False
    except Exception as e:
        logger.error("单条数据插入失败：%s", e)
        return False




def check_dup_in_biz_db(product_link, discount_price_val, scrape_date,keyword_dict):
    """直接查询业务表是否存在该商品链接+价格"""
    log_context = (
        f"【去重校验】商品链接：{product_link.strip()} | 价格：{discount_price_val} "
        f"采集日期：{scrape_date.strip()}"
    )
    collect_round = keyword_dict["collect_round"]
    collect_equipment_account_id = keyword_dict["collect_equipment_account_id"]
    collect_region_id = keyword_dict["collect_region_id"]
    sql = """
            SELECT 1 FROM retrieve_scrape_data
            WHERE link_url = %s AND min_price = %s AND scrape_date = %s AND platform_id = %s
              AND collect_round = %s AND collect_equipment_account_id = %s AND collect_region_id = %s
            LIMIT 1
            """
    params = (
        product_link.strip(),
        discount_price_val,
        scrape_date.strip(),
        7,
        collect_round,
        collect_equipment_account_id,
        collect_region_id,
    )
    try:
        rows = mysql_pool.select_data(sql, params)
        is_dup = bool(rows)

        if is_dup:
            logger.warning(f"{log_context} - 表中已存在重复记录，跳过本次采集")
        else:
            logger.info(f"{log_context} - 表中无重复记录，正常采集")

        return is_dup

    except Exception as e:
        logger.error(f"查询业务表去重失败：{str(e)}")
        return False


# 压缩图片函数
def compress_image(image_data, max_size=4*1024*1024):  # 4MB上限
    try:
        img = Image.open(BytesIO(image_data))

        # 将RGBA模式转为RGB（兼容JPEG）
        if img.mode in ('RGBA', 'P'):  # P是PNG的调色板模式，也需转换
            # 新建白色背景的RGB图片，把透明图贴上去（避免透明区域变黑）
            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

        # 缩小分辨率（按比例缩到宽≤1000px）
        if img.width > 1000:
            ratio = 1000 / img.width
            new_size = (int(img.width*ratio), int(img.height*ratio))
            img = img.resize(new_size, 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  # 压缩失败返回原始数据


def download_image_to_base64(image_url, save_dir = "./download_images"):
    """下载网络图片，返回图片二进制数据（BytesIO）"""
    try:
        if not os.path.exists(save_dir):
            os.makedirs(save_dir)  # 创建多级目录（比如a/b/c）
            print(f"创建本地保存目录：{save_dir}")
    except Exception as e:
        print(f"创建保存目录失败：{str(e)}")
        return None

    try:
        # 模拟浏览器请求头，避免被服务器拦截
        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

        # 步骤3：提取图片文件名（从URL中截取，避免重复）
        # 示例URL：https://xxx.com/123.jpg → 文件名：123.jpg
        file_name = image_url.split("/")[-1]
        # 处理特殊字符（避免文件名非法）
        file_name = file_name.replace("?", "").replace("&", "").replace("=", "")
        save_path = os.path.join(save_dir, file_name)  # 完整保存路径

        # 步骤4：保存图片到本地
        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_ocr_res(img):
    try:
        #img地址
        print(f'开始识别图片:{img}')
        request_url = request_url_config

        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

        # 获取access_token
        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
        params = {"image": img_base64}
        request_url = request_url + "?access_token=" + access_token
        headers = {'content-type': 'application/x-www-form-urlencoded'}
        response = requests.post(request_url, data=params, headers=headers)

        if response:
            res = response.json()
            # 检查OCR返回是否有错误
            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
            # 解析识别结果
            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:
            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

def get_access_token():
    AppKey = AppKey_config
    AppSrcret = AppSecret_config
    token_url =token_url_config
    url = f"{token_url}?grant_type=client_credentials&client_id={AppKey}&client_secret={AppSrcret}"

    payload = ""
    headers = {
        'Content-Type': 'application/json',
        'Accept': 'application/json'
    }
    try:
        response = requests.request("POST", url, headers=headers, data=payload)
        response.raise_for_status()  # 触发HTTP错误
        return response.json()['access_token']
    except Exception as e:
        print(f"获取access_token失败：{str(e)}")
        return None

def extract_province_city(address):
    """
    从地址中提取省份和城市
    :param address: 营业执照地址（如"福建省福州市马尾区"）
    :return: (province, city) - 提取到的省份/城市，提取失败返回空字符串
    """
    if not address:  # 地址为空，直接返回空
        return "", ""

    # 正则1：匹配省份（兼容省/自治区/直辖市/特别行政区）
    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 ""

    # 正则2：匹配城市（兼容市/自治州/地区/盟，且排除省份已匹配的部分）
    # 先去掉已匹配的省份，再匹配城市
    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 ""

    # 兼容直辖市（如"北京市朝阳区"→city=北京市）
    if province in ["北京市", "上海市", "天津市", "重庆市"]:
        city = province

    # 兼容地址不规范的情况（如"福建福州马尾区"，无"省"/"市"字）
    if not province and not city:
        # 匹配前两个地名（如"福建福州"→province=福建，city=福州）
        simple_pattern = re.compile(r'^([^\d区县镇]+)')
        simple_match = simple_pattern.search(address)
        if simple_match:
            city = simple_match.group(1).strip()  # 只有城市，省份留空

    if city and province in city:
        city = city.replace(province, "").strip()

    return province.strip(), city.strip()


#采集数据核心
def collect_data(page, keyword, keyword_dict, scheduler=None):
    """
    1) 先获取当前页商品个数（count）
    2) 按循环次数采集；每循环15次滚动一次 slow_scroll_1200px
    3) 当前页循环完 -> goto_next_page；有下一页继续；无下一页结束该关键词
    """
    collect_result = []
    # seen = set()
     # ========== 初始化异常关键词存储 ==========
    error_keywords = []
    kw = ''     # 单个异常关键词变量

    logger.info(f"📊 开始采集「{keyword}」的商品数据")
    page.wait_for_load_state("networkidle")
    #没有找到商品就跳过这个商品


    page_no = keyword_dict.get("start_page", 1)  # 续传起始页
    while True:

        logger.info(f"\n📄 「{keyword}」开始采集第 {page_no} 页")

        #  记录列表页URL（可用于你后续兜底）
        list_page_url = page.url
        logger.info(f"📌 已记录商品列表页URL：{list_page_url}")

        # ✅ 先获取当前页商品个数
        page.wait_for_load_state("networkidle")
        total_limit = page.locator(PRODUCT_ITEM_SELECTOR).count()
        logger.info(f"📌 「{keyword}」第{page_no}页 初始商品个数（count）：{total_limit}")

        #获取该商品的总个数
        total_goods_nums_elem = page.locator("div.sr-page_turner-pagination-total")
        if total_goods_nums_elem.count() > 0:
            total_goods_nums = total_goods_nums_elem.inner_text().strip()
            logger.info(f"📌 「{keyword} 商品个数（count）：{total_goods_nums}")
        else:
            logger.info(f"📌 「{keyword} 商品个数（count）：不超过60个")
        # 重置当前页的采集计数
        collected_count = 0


        # ========= 初始化无匹配计数器（记录标题不包含核心关键词的次数） =========
        no_match_count = 0  # 无匹配次数初始化为0
        MAX_NO_MATCH = 20   # 最大无匹配次数阈值



        for idx in range(total_limit):
            detail_page = None
            try:
                item = page.locator(PRODUCT_ITEM_SELECTOR).nth(idx)
                collected_count += 1  # 实际采集计数（用于日志）
                # ========= 反爬随机延迟（保留你的原逻辑也行） =========
                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）")


                # 1. 初始化所有字段默认值
                title = "无标题"
                price = "0.00"
                shop = "无店名"
                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"
                # discount_price = "0.00"
                spec = "未知规格"
                num = 1  # ✅ 默认 1
                platform = '药九九'
                current_time = datetime.now().strftime("%Y-%m-%d")
                is_sold_out = 0


                # ========= 售罄不跳过 =========
                sold_locator = item.locator('div.gc-l1-cirle_tip')
                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")

                # 提取商品标题（处理空值）
                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，使用默认值：{title}")


                if no_match_count >= MAX_NO_MATCH:
                    logger.error(f"❌ 关键词「{keyword}」无匹配商品次数已达{MAX_NO_MATCH}次，直接终止当前关键词采集，进入下一个关键词")
                    return []

                # 关键词不在标题中，跳过当前商品
                product_brand = keyword_dict.get("product_brand")
                if product_brand not in title:
                    no_match_count += 1
                    logger.warning(f" 「{keyword}」第{collected_count}个商品 - 标题「{title}」不包含品牌「{product_brand}」（无匹配次数：{no_match_count}/{MAX_NO_MATCH}），跳过本次循环")
                    continue

                product_name = keyword_dict.get("product_name")
                if product_name not in title:
                    no_match_count += 1
                    logger.warning(f" 「{keyword}」第{collected_count}个商品 - 标题「{title}」不包含核心关键词「{product_name}」（无匹配次数：{no_match_count}/{MAX_NO_MATCH}），跳过本次循环")
                    continue




                # 提取价格（带缺失日志）
                price_locator = item.locator(PRODUCT_PRICE_SELECTOR).nth(0)
                if price_locator.count() > 0:
                    price = price_locator.inner_text(timeout=3000).strip()
                    logger.info(f"{'='*10}「{keyword}」第{collected_count}个商品 - 列表页采购价格：{price}{'='*10}")
                else:
                    price = "0.00"  # 初始化默认值，避免后续报错
                    logger.warning(f" 「{keyword}」第{collected_count}个商品「{title}」- 列表页采购价格元素未找到，使用默认值：{price}")

                # 5. 提取公司名称（带缺失日志）
                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，使用默认值：{manufacturer}")



                #提取店铺名称
                shop_locator = item.locator(PRODUCT_STORE_SELECTOR)
                if shop_locator.count() > 0:
                    shop = shop_locator.inner_text(timeout=3000).strip()
                    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，使用默认值：{shop}")

                #提取折扣价
                discount_price_val_origin = ""
                discount_price = ""
                discount_price_locator = item.locator('span.gc-l2-discount_price').first
                if discount_price_locator.count() > 0:
                    discount_price = discount_price_locator.inner_text(timeout=3000).strip()
                    discount_price_val_origin = discount_price
                    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:
                    #如果没有拿原价替换
                    price = float(price.replace("￥", "").replace(",", "")) if price.replace("￥", "").replace(",", "").replace(".", "") else "0.00"
                    discount_price_val = float(price)
                    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}")

                merged_price = f"{price}{discount_price_val_origin}" if discount_price_val_origin else price

                # ========= 模拟点击商品进入详情页 =========
                logger.info(
                    f"📌 「{keyword}」第{page_no}页 第{collected_count}个商品「{title}」- 模拟鼠标移动并点击"
                )

                # 点击商品项容器，触发详情展示
                # ========== 点击商品跳详情页 ==========
                # 反爬：模拟真人鼠标移动到商品上再点击（不是直接点击）
                item.hover()  # 先悬停
                random_delay(0.2, 0.5)  # 悬停后延迟
                item.dispatch_event("mousedown")
                random_delay(0.05, 0.15)  # 鼠标按下后延迟
                item.dispatch_event("mouseup")
                random_delay(0.05, 0.1)   # 鼠标松开后延迟



                try:
                    with 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  # 标记为无新标签页，避免关闭列表页


                # 等待详情加载（优先用新标签页，无则用列表页）
                target_page = detail_page if detail_page else 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）"
                )
                # 反爬：检测详情页反爬验证
                # check_anti_crawl(page)
                # ========== 采集详情页的专属信息（有效期/生产日期/批准文号） ==========





                #获取商品详情页链接
                product_link = target_page.url
                logger.info(f"{'='*10}「{keyword}」第{collected_count}个商品 - 详情页链接：{product_link}{'='*10}")



                #如果有需要，还可能要加兜底。

                # ========= ✅ 去重逻辑，拿商品链接和折扣价和有效期和采集日期 =========
                if check_dup_in_biz_db(product_link, discount_price_val, current_time,keyword_dict):
                    logger.warning(f" 「{keyword}」第{page_no}页 第{collected_count}个商品（重复）：{title}，跳过")
                    # ========== 关闭新标签页，切回列表页 ==========
                    if detail_page and not detail_page.is_closed():
                        detail_page.close()  # 关闭详情页标签
                        logger.info(f"📌 「{keyword}」第{collected_count}个商品 - 已关闭详情页标签页")
                    # 切回原列表页（第一个标签页）
                    page.bring_to_front()  # 激活列表页
                    page.mouse.move(random.randint(100, 300), random.randint(200, 400))  # 随机移动鼠标
                    random_delay(0.5, 1.0)  # 增加切换后延迟
                    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")
                    if collected_count % 5 == 0 and collected_count > 0:
                            logger.info("采满5个往下滑")
                            slow_scroll_400px(page)
                            page.wait_for_load_state("networkidle")
                    continue

                # 提取有效期（处理空值）
                expiry_date_locator = target_page.locator("//span[contains(text(), '有效期')]/following-sibling::span[contains(@class, 'gdb-desc-value4')]")
                if expiry_date_locator.count() > 0:
                    expiry_date = expiry_date_locator.inner_text(timeout=3000).strip().replace('-', '')    #.replace('近效期','')
                    logger.info(f"{'='*10}「{keyword}」第{collected_count}个商品 - 详情页有效期：{expiry_date}{'='*10}")
                else:
                    # 修复：替换未定义的i为collected_count
                    logger.warning(f" 「{keyword}」第{collected_count}个商品「{title}」- 有效期元素未找到，使用默认值：{expiry_date}")





                # 提取生产日期（修复完成）
                manufacture_date_locator = target_page.locator("//span[@class='gdb-desc-label' and text()='生产日期']/following-sibling::span[1]")
                if manufacture_date_locator.count() > 0:
                    manufacture_date = manufacture_date_locator.inner_text(timeout=3000).strip().replace('-', "")
                    logger.info(f"{'='*10}「{keyword}」第{collected_count}个商品 - 详情页生产日期：{manufacture_date}{'='*10}")
                else:
                    # 修复：替换未定义的i为collected_count
                    logger.warning(f" 「{keyword}」第{collected_count}个商品「{title}」- 生产日期元素未找到，使用默认值：{manufacture_date}")


                # 提取批准文号
                approval_number_locator = target_page.locator("//span[contains(text(), '国药准字')]").first
                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:
                    # 修复：替换未定义的i为collected_count
                    logger.warning(f" 「{keyword}」第{collected_count}个商品「{title}」- 批准文号元素未找到，使用默认值：{approval_number}")



                #提取规格
                spec_locator = target_page.locator('span.gddd-params_text_line_1[title]')
                if spec_locator.count() > 0:
                    spec = spec_locator.nth(2).inner_text(timeout=3000).strip()
                    logger.info(f"{'='*10}「{keyword}」第{collected_count}个商品 - 详情页规格：{spec}{'='*10}")
                else:
                    # 修复：替换未定义的i为collected_count，补充规格数量不足的提示
                    logger.warning(f" 「{keyword}」第{collected_count}个商品「{title}」- 规格元素数量不足，使用默认值：{spec}")




                #提取库存
                storage = ''
                storage_locator = target_page.locator("span.gdb-desc-value7")
                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}")
                else:
                    logger.warning(f" 「{keyword}」第{collected_count}个商品「{title}」- 库存元素数量不足，使用默认值：{storage}")




                #提取销量
                sell = ''
                sell_locator = target_page.locator('.has-join-group span.packUnit-class')
                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}")
                else:
                    logger.warning(f" 「{keyword}」第{collected_count}个商品「{title}」- 没有销量元素，使用默认值：{sell}")



                oss_url = ""
                try:
                    local_path, oss_url = screenshot_target_page_to_local_then_oss(
                        target_page=target_page,
                        full_page=True  # 截取全屏
                    )
                    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)

                shop_exists, shop_info = shop_is_exists_database(shop)
                #店铺名不是药品预约中心且店铺名不在数据库就要点击
                if shop != "药品预约中心" and not shop_exists :
                    logger.info("店铺名不是药品预约中心且数据库没有该公司的营业执照")
                    # 获取营业执照图片 li[data-v-4f79abe8].nth(2)
                    # 进入店铺
                    random_delay(MIN_CLICK_DELAY, MAX_CLICK_DELAY)
                    entershop_btn = target_page.locator('[data-v-c5790f48].btn-text')
                    # 增强：先等待进入店铺按钮可见
                    entershop_btn.wait_for(state="visible", timeout=10000)
                    entershop_btn.scroll_into_view_if_needed()  # 确保按钮在视口内
                    entershop_btn.hover()  # 先悬停
                    random_delay(0.2, 0.5)  # 悬停后延迟
                    entershop_btn.click()
                    # entershop_btn.dispatch_event("mousedown")
                    random_delay(0.05, 0.15)  # 鼠标按下后延迟
                    # entershop_btn.dispatch_event("mouseup")
                    random_delay(0.05, 0.1)   # 鼠标松开后延迟
                    target_page.wait_for_load_state("domcontentloaded")  # 等DOM加载（比networkidle更适合页面内切换）


                    #点击店铺资质
                    random_delay(MIN_CLICK_DELAY, MAX_CLICK_DELAY)
                    shop_license_page = target_page.locator('li:has-text("店铺资质")')
                    shop_license_page.wait_for(state="visible", timeout=10000)  # 等待元素加载完成
                    shop_license_page.hover()  # 先悬停
                    random_delay(0.2, 0.5)  # 悬停后延迟
                    # shop_license_page.dispatch_event("mousedown")
                    shop_license_page.click()
                    random_delay(0.05, 0.15)  # 鼠标按下后延迟
                    # shop_license_page.dispatch_event("mouseup")
                    random_delay(0.05, 0.1)   # 鼠标松开后延迟
                    target_page.wait_for_load_state("networkidle")
                    slow_scroll_400px(target_page, scroll_distance1=700)


                    #获取营业执照图片
                    target_page.wait_for_load_state("load")
                    ocr_res = None
                    shop_license_div = target_page.locator('div.shop-licensesImg').nth(0)
                    shop_license_div.wait_for(state="visible", timeout=60000)
                    shop_license_img = shop_license_div.locator('img')
                    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)
                            # print(f'ocr_res:{ocr_res}')
                        else:
                            shop_license_src = None
                    except Exception as e:
                            # 捕获定位/提取失败的异常，避免程序崩溃
                            logger.warning(f"提取营业执照图片src失败：{e}")
                            shop_license_src = None
                    print("营业执照图片链接：", shop_license_src)
                    # input("..")

                    contact_address = ''
                    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 ''
                    # scrape_date = ''

                    # 调用提取函数，获取省份和城市
                    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}")
                    insert_result = insert_shop_info_to_db(
                        shop=shop,
                        contact_address=contact_address,
                        qualification_number=qualification_number,
                        business_license_company=business_license_company,
                        business_license_address=business_license_address,
                        scrape_date=current_time,
                        platform=platform,
                        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")
                                                            )
                elif shop == "药品预约中心":
                    province, city = "未知", "未知"
                    business_license_company, qualification_number = "", ""
                    if shop_info:
                        province = shop_info["province"]
                        city = shop_info["city"]
                        business_license_company = shop_info["business_license_company"]
                        qualification_number = shop_info["qualification_number"]
                else:
                    logger.info("数据库有该店名，在数据库拿取对应字段填充yjj_drug_middle表")
                    province, city = "", ""
                    business_license_company, qualification_number = "", ""
                    if shop_info:
                        province = shop_info["province"]
                        city = shop_info["city"]
                        business_license_company = shop_info["business_license_company"]
                        qualification_number = shop_info["qualification_number"]

                # ========== 关闭新标签页，切回列表页 ==========
                if detail_page and not detail_page.is_closed():
                    detail_page.close()  # 关闭详情页标签
                    logger.info(f"📌 「{keyword}」第{collected_count}个商品 - 已关闭详情页标签页")
                # 切回原列表页（第一个标签页）
                page.bring_to_front()  # 激活列表页
                page.mouse.move(random.randint(100, 300), random.randint(200, 400))  # 随机移动鼠标
                random_delay(0.5, 1.0)  # 增加切换后延迟
                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")

                # credit_code = ""
                availability = ""

                # 组装单条数据（仅新增生产日期/批准文号字段，原有字段顺序/逻辑不变）
                # 构造单条数据元组（适配MySQL字段）
                single_data = {
                    # 核心商品信息
                        "product": title,  # 商品名称
                        "my_good_price": merged_price,  # 自定义价格（可与min_price相同或单独提取）
                        "min_price": discount_price_val,  # 最低价格
                        "manufacture_date": manufacture_date,  # 生产日期
                        "expiry_date": expiry_date,  # 有效期
                        "shop": shop,  # 店铺名
                        "business_license_company": business_license_company,  # 营业执照主体（公司名称）
                        "province": province,  # 省份
                        "city": city,  # 城市
                        "manufacturer": manufacturer,  # 生产厂家
                        "specification": spec,  # 规格
                        "approval_number": approval_number,  # 批准文号
                        "product_link": product_link,  # 商品链接
                        "scrape_date": current_time,  # 采集日期
                        "scrape_province": "",  # 采集省份（可留空或根据IP获取）
                        "availability": availability,  # 库存状态
                        "credit_code": qualification_number,  # 统一信用代码（如有可补充提取）
                        "platform": platform,  # 平台名称（固定或动态获取）
                        "search_key": keyword,  # 搜索关键词
                        "number": num,  # 数量（盒数）
                        "is_sold_out": is_sold_out,  # 售罄标记（0/1）
                        "sales": sell,      #销量
                        "inventory": storage,       #库存
                        "snapshot_url": oss_url,         #快照链接
                        "update_time": time.strftime("%Y-%m-%d %H:%M:%S"),  # 更新时间
                        "insert_time": time.strftime("%Y-%m-%d %H:%M:%S"),   # 创建时间
                        "task_id": keyword_dict["id"],  # 任务id
                        "company_id": keyword_dict["company_id"],  # 平台id
                        "product_brand": keyword_dict["product_brand"],  # 创建时间
                        "search_name": keyword_dict["product_name"], # 创建时间
                        "collect_config_info": json.dumps(
                        {"sampling_cycle": keyword_dict["sampling_cycle"], "sampling_start_time":keyword_dict["sampling_start_time"],
                         "sampling_end_time":keyword_dict["sampling_end_time"]}),
                        "collect_equipment_account_id": keyword_dict["collect_equipment_account_id"],
                        "collect_region_id": keyword_dict["collect_region_id"],
                        "collect_round": keyword_dict["collect_round"],

            }
                # 调用逐条插入函数
                insert_single_to_mysql(single_data)
                collect_result.append(single_data)
                logger.info(f" 「{keyword}」第{collected_count}个商品「{title}」采集完成")

            except Exception as e:
                kw = keyword
                if kw not in error_keywords:
                    error_keywords.append(kw)
                _report_exception(scheduler, keyword_dict, page_no, 5, f"商品采集异常: {e}", crawled_count=len(collect_result))
                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()
                        logger.info(f"📌 「{keyword}」第{collected_count}个商品 - 异常时关闭详情页标签页")
                    if page and not page.is_closed():
                        page.bring_to_front()  # 切回列表页
                    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15次滚动一次（修复：用collected_count，且排除0的情况）
            if collected_count % 5 == 0 and collected_count > 0 and collected_count != total_limit:
                logger.info("采满5个往下滑")
                slow_scroll_400px(page,)
                page.wait_for_load_state("networkidle")



        # ====== 当前页采集完毕，逐页回告 ======
        if _report_page_progress(scheduler, keyword_dict, page_no, len(collect_result)) == True:
            logger.error("逐页回告返回error，停止采集")
            break

        delay = random_delay(1.5, 3.0)
        logger.info(f"⏳ 翻页前随机等待 {delay:.2f}s（反爬）")

        if goto_next_page(page):
            page_no += 1
            continue
        else:
            logger.info(f" 「{keyword}」已无下一页，关键词采集结束")
            break
    # 关键词采集完成回告
    _report_page_progress(scheduler, keyword_dict, page_no, len(collect_result),
                          is_finished=1, total_pages=page_no)
    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，等待{long_delay:.2f}秒后继续下一个关键词（反爬）")
    result_data = {
        "real_count": len(collect_result),
        "end_page": page_no,
        "start_page": 1,
    }
    return result_data


# ==================== 主函数（登录+调度器拉任务） ====================
def main():
    logger.info("\n" + "="*50)
    logger.info("🚀 药九九采集程序启动")
    logger.info(f"⏰ 启动时间：{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
    logger.info("="*50)

    # 从数据库获取可用账号
    account = get_account_from_db()
    if not account:
        logger.error("无可用药九九账号，退出本轮")
        return
    device_id = account["phone"]  # phone 作为 DEVICE_ID，回告接口的 username 也是这个
    username = account["phone"]
    password = account["password"]
    logger.info("获取到账号: %s, phone=%s", account["name"], device_id)

    # 创建调度器，启动心跳（先上报心跳再拉任务）
    scheduler = CrawlerScheduler(DEVICE_ID=username, platform=PLATFORM_ID)
    scheduler.start()
    time.sleep(2)
    logger.info("调度器已启动，心跳已就绪")

    with sync_playwright() as p:
        is_headless = (platform.system() == "Linux" and not os.environ.get("DISPLAY"))

        browser = p.chromium.launch(
            headless=is_headless,  # 根据环境自动切换
            channel="chrome",
            slow_mo=random.randint(100, 300),
            args=_chromium_launch_args(),
        )
        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": 1600, "height": 1400},
            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);
                };
            })();
""")

        keyword_dict = None
        try:
            # ========== Cookie复用 + 登录 ==========
            load_cookies(context)
            if not is_login(page):
                page.goto(TARGET_LOGIN_URL)
                time.sleep(5)
                page.wait_for_load_state("networkidle")
                logger.info("🔑 开始执行登录流程，账号=%s", username)
                login_success = login_operation(page, username, password)
                if not login_success:
                    logger.error("登录失败，程序终止")
                    _report_exception(scheduler, {}, 0, 1, "登录失败")
                    return
                save_cookies(context)
                logger.info("登录并保存Cookie成功！")

            # ========== 循环拉取任务 ==========
            while True:
                task = scheduler.get_task()
                if not task:
                    logger.info("暂无任务，本轮结束")
                    break

                # 构建 keyword_dict（兼容原有字段）
                current_page = task.get("current_page", 0)
                start_page = current_page if current_page > 0 else 1
                keyword_dict = {
                    "id": task.get("id"),
                    "company_id": task.get("company_id"),
                    "product_name": task.get("product_name", ""),
                    "product_specs": task.get("product_specs", ""),
                    "product_brand": task.get("product_brand", ""),
                    "product_keyword": task.get("product_keyword", ""),
                    "current_page": current_page,
                    "start_offset": task.get("start_offset", 0),
                    "start_page": start_page,
                    "end_page": 0,
                    "_platform": PLATFORM_ID,
                    "_device_id": device_id,
                    "collect_task_id": str(task.get("id", "")),
                    "snapshot_collect_status": 1,
                    "sampling_cycle": "",
                    "sampling_start_time": "",
                    "sampling_end_time": "",
                    "collect_equipment_account_id": 0,
                    "collect_region_id": 0,
                    "collect_equipment_id": 0,
                    "collect_round": 0,
                }


                keyword = f"{keyword_dict['product_brand']} {keyword_dict['product_name']} {keyword_dict['product_specs']}".strip()
                logger.info(f"\n{'='*40}\n🔍 开始处理：{keyword}\n{'='*40}")

                # 执行搜索
                popup_guard(page, "before_search")
                search_success = search_operation(page, keyword)
                popup_guard(page, "after_search")

                if not search_success:
                    logger.warning(f"「{keyword}」搜索失败，跳过")
                    _report_exception(scheduler, keyword_dict, 0, 4, "搜索失败")
                    continue

                page.wait_for_load_state("domcontentloaded")
                page.wait_for_load_state('networkidle')

                # 采集数据（内部含逐页回告）
                collect_data(page, keyword, keyword_dict, scheduler=scheduler)

                finished_task_ids.add(keyword_dict["id"])
                logger.info(f"任务 {keyword_dict['id']} 完成")

                # 任务间隔
                time.sleep(random.randint(180, 300))

        except Exception as e:
            if keyword_dict is not None:
                _report_exception(scheduler, keyword_dict, 0, 5, f"程序异常: {e}")
            logger.exception("程序异常：%s", e)
        finally:
            browser.close()
            logger.info("浏览器已关闭，程序结束")

# ==================== 程序入口 ====================
if __name__ == '__main__':
    while True:
        try:
            print(f"【任务开始】时间: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
            main()
            print(f"【任务结束】时间: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
        except Exception as e:
            print(f"【异常】: {e}")
        time.sleep(random.randint(180, 300))