java微博爬虫

微博爬取要做到每日百万级的数据量，需要解决很多问题。

1.springboot自带@Scheduled注解是一个轻量级的quartz，可以完成定时任务。只需要在运行方法上加一个@Scheduled注解即可。

该注解有许多属性值

initiaDelay 从程序开始延长一定时间后首次执行。

fixedRate 首次后，该方法固定执行间隔。

cron 定时表达式。

等等

java微博爬虫

如果想要并发编程，在要执行定时任务的类上加注解@EnableAsync，在方法上加@Async。

java微博爬虫

接下来要设置线程池的大小。

package com.cnxunao.weibospider.configuration;

import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
import org.springframework.scheduling.annotation.EnableScheduling;
import org.springframework.scheduling.annotation.SchedulingConfigurer;
import org.springframework.scheduling.config.ScheduledTaskRegistrar;

import java.util.concurrent.Executor;
import java.util.concurrent.Executors;

@Configuration
@EnableScheduling
public class ScheduleConfig implements SchedulingConfigurer {

    @Override
    public void configureTasks(ScheduledTaskRegistrar taskRegistrar) {
        taskRegistrar.setScheduler(taskExecutor());
    }
    /*
     * 并行执行
     */
    @Bean(name = "TaskPool")
    public Executor taskExecutor() {
        return Executors.newScheduledThreadPool(5);
    }


}

最后在启动类上加一个注解

java微博爬虫

2.微博的反爬机制还是蛮严格的，亲自试验让代理服务器每6秒爬取一次是很稳定的，不会被封。

也可以建立一个user_agent池用于反爬。（都是亲测可用的）

//user_Agent池
    private static String[] userAgents = {
            "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.89 Safari/537.36",
            "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1",
            "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0",
            "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
            "Opera/9.80 (Windows NT 6.1; U; zh-cn) Presto/2.9.168 Version/11.50",
            "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 2.0.50727; SLCC2; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; Tablet PC 2.0; .NET4.0E)",
            "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; InfoPath.3)",
            "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; GTB7.0)",
            "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
            "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1)",
            "Mozilla/5.0 (Windows; U; Windows NT 6.1; ) AppleWebKit/534.12 (KHTML, like Gecko) Maxthon/3.0 Safari/534.12",
            "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.472.33 Safari/534.3 SE 2.X MetaSr 1.0",
            "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.41 Safari/535.1 QQBrowser/6.9.11079.201",
            "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0)"
    };
//随机获取总数为14useragent池中的一个
private String userAgent = userAgents[random.nextInt(14)];