2.0/start_run_yaoshibang_v2.py

"""药师帮统一入口 — 根据任务 snapshot_collect_status 字段自动切换普通/快照模式。

与公共类 collect_schedule_runner 不同：本入口直接对接 CrawlerScheduler API
（拉取任务/心跳/进度上报），并支持快照模式切换、账号注入等药师帮定制逻辑，
不再依赖 CollectScheduleRunner。
"""
import random
import time
import json

from spiders.yaoshibang.ysbang_crawl import YsbSpider
from spiders.yaoshibang.ysb_snapshot_crawl import YaoShiBangSnapshot
from commons.scheduler import CrawlerScheduler
from commons.conn_mysql import MySQLPoolOnline
from commons.Logger import logger
from commons.feishu_webhook import send_text

PLATFORM_NAME = "药师帮"
PLATFORM_ID = 5


def get_device_id_from_db():
    """从 accounts_platform 表获取一个可用的药师帮账号（platform=5, status=1, equipment_id=3），
    用 phone 作为 DEVICE_ID（回告接口的 username 也用它），同时返回密码供 spider 登录。"""
    db = MySQLPoolOnline()
    sql = """SELECT `name`, `phone`, `password` FROM `accounts_platform`
             WHERE `platform`=5 AND `status`=1 AND `equipment_id`=3
             ORDER BY `cookie_timestamp` ASC LIMIT 1"""
    rows = db.select_data(sql)
    if not rows:
        logger.error("无可用药师帮账号（platform=5, status=1, equipment_id=3）")
        return None
    account = rows[0]
    logger.info("获取到药师帮账号: name=%s, phone=%s", account["name"], account["phone"])
    return account["phone"], account["password"], account["name"]


def _build_task_dict(api_task, device_id, account_password, account_name, scheduler):
    """将调度 API 返回的原始任务字段组装为 spider 需要的 task_dict。"""
    current_page = api_task.get("current_page", 0)
    start_page = current_page if current_page > 0 else 1
    task_dict = {
        # 新 API 字段
        "id": api_task.get("id"),
        "company_id": api_task.get("company_id"),
        "product_name": api_task.get("product_name", ""),
        "product_specs": api_task.get("product_specs", ""),
        "product_brand": api_task.get("product_brand", ""),
        "product_keyword": api_task.get("product_keyword", ""),
        "current_page": current_page,
        "start_offset": api_task.get("start_offset", 0),
        # 兼容旧字段
        "start_page": start_page,
        "end_page": 0,
        # spider 逐页回告用
        "scheduler": scheduler,
        "_device_id": device_id,
        "_platform": str(PLATFORM_ID),
        "collect_task_id": str(api_task.get("id", "")),
        "snapshot_collect_status": api_task.get("snapshot_collect_status", 1),
        "sampling_cycle": "",
        "sampling_start_time": "",
        "sampling_end_time": "",
        "collect_equipment_account_id": "",
        "collect_region_id": "",
        "collect_equipment_id": "",
        "collect_round": 1,
        # 入口传入的账号信息，spider 可复用避免重复查 DB
        "account_phone": device_id,
        "account_password": account_password,
        "account_name": account_name,
    }
    return task_dict


def _report_progress(scheduler, task_id, is_finished, crawled_count=0,
                     current_page=0, total_pages=0,
                     exception_type=None, remark=None):
    """通过调度器 API 上报任务进度。"""
    data = {
        "task_id": task_id,
        "platform": str(PLATFORM_ID),
        "username": scheduler.username,
        "current_page": current_page,
        "is_finished": is_finished,
        "total_pages": total_pages,
    }
    if crawled_count:
        data["crawled_count"] = crawled_count
    if exception_type is not None:
        data["exception_type"] = exception_type
    if remark:
        data["remark"] = remark
    try:
        scheduler.post_report(data)
        logger.info("任务状态上报成功: is_finished=%s, crawled_count=%s",
                    is_finished, crawled_count)
    except Exception as e:
        logger.warning("任务状态上报失败: %s", e)


def run_one_task(scheduler, device_id, account_password, account_name):
    """拉取一个任务，根据 snapshot_collect_status 选 spider 执行并上报。"""
    # 拉取任务
    api_task = scheduler.get_task()
    if not api_task:
        logger.info("%s暂无任务", PLATFORM_NAME)
        return

    task_id = api_task.get("id", "")
    task_dict = _build_task_dict(api_task, device_id, account_password,
                                 account_name, scheduler)

    # 打印任务信息（隐藏不可序列化的 scheduler）
    log_dict = {k: v for k, v in task_dict.items() if k != "scheduler"}
    logger.info("拉取到任务: %s", json.dumps(log_dict, ensure_ascii=False))

    # 根据 snapshot_collect_status 决定走普通爬虫还是快照爬虫
    snapshot_status = task_dict.get("snapshot_collect_status", 1)
    if snapshot_status == 0:
        spider_cls = YaoShiBangSnapshot
        logger.info("任务 %s 启用快照模式", task_id)
    else:
        spider_cls = YsbSpider
        logger.info("任务 %s 使用普通模式", task_id)

    # 执行爬虫
    result = spider_cls(task_dict).run()
    if len(result) == 3:
        crawl_count, is_success, total_pages = result
    else:
        crawl_count, is_success = result
        total_pages = 0

    # 飞书通知
    send_text(
        f"{time.strftime('%Y-%m-%d %H:%M:%S')} 通知:\n"
        f"平台: {PLATFORM_NAME}, 药品: {task_dict.get('product_name')}, "
        f"爬取数据: {crawl_count}条"
    )

    # 上报任务结果
    if is_success:
        _report_progress(scheduler, task_id, is_finished=1,
                         crawled_count=crawl_count,
                         current_page=total_pages, total_pages=total_pages)
    else:
        _report_progress(scheduler, task_id, is_finished=0,
                         crawled_count=crawl_count,
                         current_page=total_pages, total_pages=total_pages)


if __name__ == "__main__":
    # 1. 获取账号
    result = get_device_id_from_db()
    if result:
        device_id, account_password, account_name = result
    else:
        device_id, account_password, account_name = "YSB", None, None

    # 2. 初始化调度器（心跳 + 拉任务 + 上报）
    scheduler = CrawlerScheduler(
        DEVICE_ID=device_id,
        platform=str(PLATFORM_ID),
    )
    scheduler.start()
    time.sleep(2)  # 等待首次心跳完成
    logger.info("调度器已启动，device_id=%s，心跳已就绪", device_id)

    # 3. 循环执行
    idle_seconds = random.randint(180, 300)
    logger.info("循环任务已启动，平台=%s，每轮间隔 %s 秒", PLATFORM_NAME, idle_seconds)

    while True:
        try:
            logger.info("开始执行%s爬虫任务", PLATFORM_NAME)
            run_one_task(scheduler, device_id, account_password, account_name)
            logger.info("%s爬虫任务执行完成", PLATFORM_NAME)
        except Exception as e:
            logger.error("%s爬虫任务执行失败: %s", PLATFORM_NAME, e, exc_info=True)
        time.sleep(idle_seconds)