piaoquan_crawler/xiaoniangao/xiaoniangao_main/run_xiaoniangao_hour.py

# -*- coding: utf-8 -*-
# @Author: wangkun
# @Time: 2023/3/15
import argparse
import datetime
import os
import sys
import time
sys.path.append(os.getcwd())
from common.common import Common
from xiaoniangao.xiaoniangao_hour.xiaoniangao_hour import XiaoniangaoHour


def main(log_type, crawler, strategy, oss_endpoint, env, machine):
    while True:
        # 今天的日期:年-月-日
        today = datetime.datetime.now().strftime("%Y/%m/%d")
        # 昨天
        yesterday = (datetime.date.today() + datetime.timedelta(days=-1)).strftime("%Y/%m/%d")
        # 前天
        before_yesterday = (datetime.date.today() + datetime.timedelta(days=-2)).strftime("%Y/%m/%d")

        Common.logger(log_type, crawler).info("检查今日上升榜日期是否存在")
        XiaoniangaoHour.check_data(log_type, crawler, today)

        while True:
            # 获取符合规则的视频，写入小时级数据_feeds
            XiaoniangaoHour.get_videoList(log_type, crawler, env, machine)

            now = datetime.datetime.now()
            if now.hour == 10 and 0 <= now.minute <= 10:
                Common.logger(log_type, crawler).info("开始更新上升榜")
                XiaoniangaoHour.update_videoList(log_type, crawler, today, yesterday, before_yesterday)
                Common.logger(log_type, crawler).info("开始下载上升榜")
                XiaoniangaoHour.download_publish(log_type, crawler, strategy, oss_endpoint, env, machine)

            elif now.hour == 15 and now.minute <= 10:
                Common.logger(log_type, crawler).info("开始更新上升榜")
                XiaoniangaoHour.update_videoList(log_type, crawler, today, yesterday, before_yesterday)
                Common.logger(log_type, crawler).info("开始下载上升榜")
                XiaoniangaoHour.download_publish(log_type, crawler, strategy, oss_endpoint, env, machine)

            elif now.hour == 20 and now.minute <= 10:
                Common.logger(log_type, crawler).info("开始更新上升榜")
                XiaoniangaoHour.update_videoList(log_type, crawler, today, yesterday, before_yesterday)
                Common.logger(log_type, crawler).info("开始下载上升榜")
                XiaoniangaoHour.download_publish(log_type, crawler, strategy, oss_endpoint, env, machine)

            elif 1 >= now.hour >= 0:
                time.sleep(3600)
                break


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('--strategy')  ## 添加参数
    parser.add_argument('--oss_endpoint')  ## 添加参数
    parser.add_argument('--env')  ## 添加参数
    parser.add_argument('--machine')  ## 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,
         strategy=args.strategy,
         oss_endpoint=args.oss_endpoint,
         env=args.env,
         machine=args.machine)