piaoquan_crawler/xiaoniangao/xiaoniangao_main/run_xiaoniangao_hour_scheduling.py

# -*- coding: utf-8 -*-
# @Author: wangkun
# @Time: 2023/3/15
import argparse
import datetime
import os
import random
import sys
sys.path.append(os.getcwd())
from common.scheduling_db import MysqlHelper
from common.common import Common
from common.public import task_fun
from xiaoniangao.xiaoniangao_hour.xiaoniangao_hour_scheduling import XiaoniangaoHourScheduling


def main(log_type, crawler, task, env):
    task_dict = task_fun(task)['task_dict']
    rule_dict = task_fun(task)['rule_dict']
    task_id = task_dict['task_id']
    select_user_sql = f"""select * from crawler_user_v3 where task_id={task_id}"""
    user_list = MysqlHelper.get_values(log_type, crawler, select_user_sql, env, action="")
    our_uid_list = []
    for user in user_list:
        our_uid_list.append(user["uid"])
    our_uid = random.choice(our_uid_list)
    Common.logger(log_type, crawler).info(f"调度任务:\n{task_dict}")
    Common.logger(log_type, crawler).info(f"抓取规则:\n{rule_dict}")
    Common.logger(log_type, crawler).info(f'开始抓取 {task_dict["task_name"]}\n')
    # 获取符合规则的视频，写入小时级数据_feeds
    for i in range(1, 101):
        try:
            Common.logger(log_type, crawler).info(f"正在抓取第{i}页")
            XiaoniangaoHourScheduling.get_videoList(log_type, crawler, rule_dict, env)
        except Exception as e:
            Common.logger(log_type, crawler).info(f"抓取第{i}页时异常:{e}\n")
    now = datetime.datetime.now()
    if now.hour == 10 and 0 <= now.minute <= 10:
        Common.logger(log_type, crawler).info("开始更新/下载上升榜")
        XiaoniangaoHourScheduling.update_videoList(log_type=log_type,
                                                   crawler=crawler,
                                                   rule_dict=rule_dict,
                                                   our_uid=our_uid,
                                                   env=env)

    elif now.hour == 15 and now.minute <= 10:
        Common.logger(log_type, crawler).info("开始更新/下载上升榜")
        XiaoniangaoHourScheduling.update_videoList(log_type=log_type,
                                                   crawler=crawler,
                                                   rule_dict=rule_dict,
                                                   our_uid=our_uid,
                                                   env=env)

    elif now.hour == 20 and now.minute <= 10:
        Common.logger(log_type, crawler).info("开始更新/下载上升榜")
        XiaoniangaoHourScheduling.update_videoList(log_type=log_type,
                                                   crawler=crawler,
                                                   rule_dict=rule_dict,
                                                   our_uid=our_uid,
                                                   env=env)
    Common.del_logs(log_type, crawler)
    Common.logger(log_type, crawler).info("抓取完一轮\n")


if __name__ == "__main__":
    parser = argparse.ArgumentParser()  ## 新建参数解释器对象
    parser.add_argument('--log_type', type=str)  ## 添加参数,注明参数类型
    parser.add_argument('--crawler')  ## 添加参数
    parser.add_argument('--task')  ## 添加参数
    parser.add_argument('--env')  ## 添加参数
    args = parser.parse_args()  ### 参数赋值，也可以通过终端赋值
    main(log_type=args.log_type,
         crawler=args.crawler,
         task=args.task,
         env=args.env)