piaoquan_crawler/xigua/xigua_main/run_xg_author.py

import argparse
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 get_consumer, ack_message, task_fun_mq
from common.scheduling_db import MysqlHelper
from xigua.xigua_author import XiGuaAuthor
from common.aliyun_log import AliyunLogger


def main(log_type, crawler, 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=crawler,
        mode=log_type,
        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:
                xg_author_start_time = int(time.time())
                AliyunLogger.logging(
                    code="1000",
                    platform=crawler,
                    mode=log_type,
                    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=log_type,
                    crawler=crawler,
                    recv_msgs=recv_msgs,
                    consumer=consumer,
                )

                # 处理爬虫业务
                task_dict = task_fun_mq(msg.message_body)["task_dict"]
                rule_dict = task_fun_mq(msg.message_body)["rule_dict"]
                task_id = task_dict["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=""
                )
                AliyunLogger.logging(
                    code="1000",
                    platform=crawler,
                    mode=log_type,
                    env=env,
                    message=f"调度任务:{task_dict}",
                )
                AliyunLogger.logging(
                    code="1000",
                    platform=crawler,
                    mode=log_type,
                    env=env,
                    message=f"用户列表:{user_list}",
                )
                AliyunLogger.logging(
                    code="1000",
                    platform=crawler,
                    mode=log_type,
                    env=env,
                    message=f"抓取规则:{rule_dict}",
                )
                AliyunLogger.logging(
                    code="1003",
                    platform=crawler,
                    mode=log_type,
                    env=env,
                    message=f'开始抓取:{task_dict["taskName"]}\n',
                )
                Xg = XiGuaAuthor(
                    mode=log_type,
                    platform=crawler,
                    rule_dict=rule_dict,
                    user_list=user_list,
                    env=env,
                )
                Xg.get_author_list()
                xg_author_end_time = int(time.time())
                AliyunLogger.logging(
                    code="1004",
                    platform=crawler,
                    mode=log_type,
                    env=env,
                    message=f'完成抓取:{task_dict["taskName"]}\n',
                )
                xg_author_duration = xg_author_start_time - xg_author_end_time
                AliyunLogger.logging(
                    code="1000",
                    platform=crawler,
                    mode=log_type,
                    env=env,
                    message=f"duration {xg_author_duration}",
                )

        except MQExceptionBase as err:
            # Topic中没有消息可消费。
            if err.type == "MessageNotExist":
                AliyunLogger.logging(
                    code="1000",
                    platform=crawler,
                    mode=log_type,
                    env=env,
                    message=f"No new message! RequestId:{err.req_id}\n",
                )
                continue
            AliyunLogger.logging(
                code="1000",
                platform=crawler,
                mode=log_type,
                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(
        log_type=args.log_type,
        crawler=args.crawler,
        topic_name=args.topic_name,
        group_id=args.group_id,
        env=args.env,
    )