piaoquan_crawler/youlegaoxiaoxiaoshipin/youlegaoxiaoxiaoshipin_main/run_ylgxxsp_recommend.py

# -*- coding: utf-8 -*-
# @Author: luojunhui
# @Time: 2023/10/23
import argparse
import random
from mq_http_sdk.mq_client import *
from mq_http_sdk.mq_consumer import *
from mq_http_sdk.mq_exception import MQExceptionBase

sys.path.append(os.getcwd())
from common.public import task_fun_mq, get_consumer, ack_message
from common.scheduling_db import MysqlHelper
from common.aliyun_log import AliyunLogger
from youlegaoxiaoxiaoshipin.youlegaoxiaoxiaoshipin_recommend import YLGXXSPScheduling


def main(my_platform, mode, topic_name, group_id, env):
    consumer = get_consumer(topic_name, group_id)
    # 长轮询表示如果Topic没有消息，则客户端请求会在服务端挂起3秒，3秒内如果有消息可以消费则立即返回响应。
    # 长轮询时间3秒（最多可设置为30秒）。
    wait_seconds = 30
    # 一次最多消费3条（最多可设置为16条）。
    batch = 1
    AliyunLogger.logging(
        code="1000",
        platform=my_platform,
        mode=mode,
        env=env,
        message=f'{10 * "="}Consume And Ack Message From Topic{10 * "="}\n'
        f"WaitSeconds:{wait_seconds}\n"
        f"TopicName:{topic_name}\n"
        f"MQConsumer:{group_id}",
    )
    while True:
        try:
            # 长轮询消费消息。
            recv_msgs = consumer.consume_message(batch, wait_seconds)
            for msg in recv_msgs:
                AliyunLogger.logging(
                    code="1000",
                    platform=my_platform,
                    mode=mode,
                    env=env,
                    message=f"Receive\n"
                    f"MessageId:{msg.message_id}\n"
                    f"MessageBodyMD5:{msg.message_body_md5}\n"
                    f"MessageTag:{msg.message_tag}\n"
                    f"ConsumedTimes:{msg.consumed_times}\n"
                    f"PublishTime:{msg.publish_time}\n"
                    f"Body:{msg.message_body}\n"
                    f"NextConsumeTime:{msg.next_consume_time}\n"
                    f"ReceiptHandle:{msg.receipt_handle}\n"
                    f"Properties:{msg.properties}",
                )
                # ack_mq_message
                ack_message(
                    log_type=mode,
                    crawler=my_platform,
                    recv_msgs=recv_msgs,
                    consumer=consumer,
                )
                # 解析 task_dict
                task_dict = task_fun_mq(msg.message_body)["task_dict"]
                AliyunLogger.logging(
                    "1000", my_platform, mode, env, f"调度任务:{task_dict}"
                )
                # 解析 rule_dict
                rule_dict = task_fun_mq(msg.message_body)["rule_dict"]
                AliyunLogger.logging(
                    "1000", my_platform, mode, env, f"抓取规则:{rule_dict}\n"
                )
                # 解析 user_list
                task_id = task_dict["id"]
                select_user_sql = (
                    f"""select * from crawler_user_v3 where task_id={task_id}"""
                )
                user_list = MysqlHelper.get_values(
                    mode, my_platform, select_user_sql, env, action=""
                )
                our_uid_list = []
                for user in user_list:
                    our_uid_list.append(user["uid"])
                AliyunLogger.logging(
                    code="1003",
                    platform=my_platform,
                    mode=mode,
                    env=env,
                    message="成功获取信息，启动爬虫，开始一轮抓取",
                )
                YLGXXSP = YLGXXSPScheduling(
                    platform=my_platform,
                    mode=mode,
                    env=env,
                    rule_dict=rule_dict,
                    our_uid=our_uid_list,
                )
                for i in range(50):
                    try:
                        if YLGXXSP.download_count >= int(rule_dict.get("videos_cnt", {}).get("min", 10)):
                            YLGXXSP.download_count = 0
                            break
                        else:
                            YLGXXSP.get_videoList(page_id=i + 1)
                            time.sleep(60)
                    except:
                        AliyunLogger.logging(
                            code="2001",
                            platform=my_platform,
                            mode=mode,
                            env=env,
                            message="未在此页获取到视频列表"
                        )

                AliyunLogger.logging(
                    code="1004",
                    platform=my_platform,
                    mode=mode,
                    env=env,
                    message="成功抓取完一轮",
                )

        except MQExceptionBase as err:
            # Topic中没有消息可消费。
            if err.type == "MessageNotExist":
                AliyunLogger.logging(
                    code="1000",
                    platform=my_platform,
                    mode=mode,
                    env=env,
                    message=f"No new message! RequestId:{err.req_id}\n",
                )
                continue
            AliyunLogger.logging(
                code="1000",
                platform=my_platform,
                mode=mode,
                env=env,
                message=f"Consume Message Fail! Exception:{err}\n",
            )
            time.sleep(2)
            continue


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("--topic_name")  ## 添加参数
    parser.add_argument("--group_id")  ## 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(
        my_platform=args.crawler,
        mode=args.log_type,
        topic_name=args.topic_name,
        group_id=args.group_id,
        env=args.env,
    )