基于spring boot+WebMagic+MyBatis的爬虫框架

WebMagic是一个开源的java爬虫框架。WebMagic框架的使用并不是本文的重点，具体如何使用请参考官方文档：http://webmagic.io/docs/。
本文是对spring boot+WebMagic+MyBatis做了整合，使用WebMagic爬取数据，然后通过MyBatis持久化爬取的数据到mysql数据库。本文提供的源代码可以作为java爬虫项目的脚手架。

1.添加maven依赖

    4.0.0

    hyzx
    qbasic-crawler
    1.0.0

    
        org.springframework.boot
        spring-boot-starter-parent
        1.5.21.RELEASE
         
    

    
        UTF-8
        true
        1.8
        3.8.1
        3.1.0

        5.1.47
        1.1.17
        1.3.4
        1.2.58
        3.9
        2.10.2
        0.7.3
    

    
        
            org.springframework.boot
            spring-boot-devtools
            runtime
            true
        

        
            org.springframework.boot
            spring-boot-starter-test
            test
        

        
            org.springframework.boot
            spring-boot-configuration-processor
            true
        

        
            mysql
            mysql-connector-java
            ${mysql.connector.version}
        

        
            com.alibaba
            druid-spring-boot-starter
            ${druid.spring.boot.starter.version}
        

        
            org.mybatis.spring.boot
            mybatis-spring-boot-starter
            ${mybatis.spring.boot.starter.version}
        

        
            com.alibaba
            fastjson
            ${fastjson.version}
        

        
            org.apache.commons
            commons-lang3
            ${commons.lang3.version}
        

        
            joda-time
            joda-time
            ${joda.time.version}
        

        
            us.codecraft
            webmagic-core
            ${webmagic.core.version}
            
                
                    org.slf4j
                    slf4j-log4j12
                
            
        
    

    
        
            
                org.apache.maven.plugins
                maven-compiler-plugin
                ${maven.compiler.plugin.version}
                
                    ${java.version}
                    ${java.version}
                    ${project.build.sourceEncoding}
                
            

            
                org.apache.maven.plugins
                maven-resources-plugin
                ${maven.resources.plugin.version}
                
                    ${project.build.sourceEncoding}
                
            

            
                org.springframework.boot
                spring-boot-maven-plugin
                
                    true
                    true
                
                
                    
                        
                            repackage
                        
                    
                
            
        
    

    
        
            public
            aliyun nexus
            http://maven.aliyun.com/nexus/content/groups/public/
            
                true
            
        
    

    
        
            public
            aliyun nexus
            http://maven.aliyun.com/nexus/content/groups/public/
            
                true
            
            
                false
            
        
    

2.项目配置文件 application.properties

配置mysql数据源，druid数据库连接池以及MyBatis的mapper文件的位置。

# mysql数据源配置
spring.datasource.name=mysql
spring.datasource.type=com.alibaba.druid.pool.DruidDataSource
spring.datasource.driver-class-name=com.mysql.jdbc.Driver
spring.datasource.url=jdbc:mysql://192.168.0.63:3306/gjhzjl?useUnicode=true&characterEncoding=utf8&useSSL=false&allowMultiQueries=true
spring.datasource.username=root
spring.datasource.password=root

# druid数据库连接池配置
spring.datasource.druid.initial-size=5
spring.datasource.druid.min-idle=5
spring.datasource.druid.max-active=10
spring.datasource.druid.max-wait=60000
spring.datasource.druid.validation-query=SELECT 1 FROM DUAL
spring.datasource.druid.test-on-borrow=false
spring.datasource.druid.test-on-return=false
spring.datasource.druid.test-while-idle=true
spring.datasource.druid.time-between-eviction-runs-millis=60000
spring.datasource.druid.min-evictable-idle-time-millis=300000
spring.datasource.druid.max-evictable-idle-time-millis=600000

# mybatis配置
mybatis.mapperLocations=classpath:mapper/**/*.xml

3.数据库表结构

CREATE TABLE `cms_content` (
  `contentId` varchar(40) NOT NULL COMMENT '内容ID',
  `title` varchar(150) NOT NULL COMMENT '标题',
  `content` longtext COMMENT '文章内容',
  `releaseDate` datetime NOT NULL COMMENT '发布日期',
  PRIMARY KEY (`contentId`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8 COMMENT='CMS内容表';

4.实体类

import java.util.Date;

public class CmsContentPO {
    private String contentId;

    private String title;

    private String content;

    private Date releaseDate;

    public String getContentId() {
        return contentId;
    }

    public void setContentId(String contentId) {
        this.contentId = contentId;
    }

    public String getTitle() {
        return title;
    }

    public void setTitle(String title) {
        this.title = title;
    }

    public String getContent() {
        return content;
    }

    public void setContent(String content) {
        this.content = content;
    }

    public Date getReleaseDate() {
        return releaseDate;
    }

    public void setReleaseDate(Date releaseDate) {
        this.releaseDate = releaseDate;
    }
}

5.mapper接口

public interface CrawlerMapper {
    int addCmsContent(CmsContentPO record);
}

6.CrawlerMapper.xml文件

    
        insert into cms_content (contentId,
                                 title,
                                 releaseDate,
                                 content)
        values (#{contentId,jdbcType=VARCHAR},
                #{title,jdbcType=VARCHAR},
                #{releaseDate,jdbcType=TIMESTAMP},
                #{content,jdbcType=LONGVARCHAR})
    

7.知乎页面内容处理类ZhihuPageProcessor

主要用于解析爬取到的知乎html页面。

@Component
public class ZhihuPageProcessor implements PageProcessor {

    private Site site = Site.me().setRetryTimes(3).setSleepTime(1000);

    @Override
    public void process(Page page) {
        page.addTargetRequests(page.getHtml().links().regex("https://www\\.zhihu\\.com/question/\\d+/answer/\\d+.*").all());
        page.putField("title", page.getHtml().xpath("//h1[@class='QuestionHeader-title']/text()").toString());
        page.putField("answer", page.getHtml().xpath("//div[@class='QuestionAnswer-content']/tidyText()").toString());
        if (page.getResultItems().get("title") == null) {
            // 如果是列表页，跳过此页，pipeline不进行后续处理
            page.setSkip(true);
        }
    }

    @Override
    public Site getSite() {
        return site;
    }
}

8.知乎数据处理类ZhihuPipeline

主要用于将知乎html页面解析出的数据存储到mysql数据库。

@Component
public class ZhihuPipeline implements Pipeline {
    private static final Logger LOGGER = LoggerFactory.getLogger(ZhihuPipeline.class);

    @Autowired
    private CrawlerMapper crawlerMapper;

    public void process(ResultItems resultItems, Task task) {
        String title = resultItems.get("title");
        String answer = resultItems.get("answer");

        CmsContentPO contentPO = new CmsContentPO();
        contentPO.setContentId(UUID.randomUUID().toString());
        contentPO.setTitle(title);
        contentPO.setReleaseDate(new Date());
        contentPO.setContent(answer);

        try {
            boolean success = crawlerMapper.addCmsContent(contentPO) > 0;
            LOGGER.info("保存知乎文章成功：{}", title);
        } catch (Exception ex) {
            LOGGER.error("保存知乎文章失败", ex);
        }
    }
}

9.知乎爬虫任务类ZhihuTask

每十分钟启动一次爬虫。

@Component
public class ZhihuTask {
    private static final Logger LOGGER = LoggerFactory.getLogger(ZhihuPipeline.class);

    @Autowired
    private ZhihuPipeline zhihuPipeline;

    @Autowired
    private ZhihuPageProcessor zhihuPageProcessor;

    private ScheduledExecutorService timer = Executors.newSingleThreadScheduledExecutor();

    public void crawl() {
        // 定时任务，每10分钟爬取一次
        timer.scheduleWithFixedDelay(() -> {
            Thread.currentThread().setName("zhihuCrawlerThread");

            try {
                Spider.create(zhihuPageProcessor)
                        // 从https://www.zhihu.com/explore开始抓
                        .addUrl("https://www.zhihu.com/explore")
                        // 抓取到的数据存数据库
                        .addPipeline(zhihuPipeline)
                        // 开启2个线程抓取
                        .thread(2)
                        // 异步启动爬虫
                        .start();
            } catch (Exception ex) {
                LOGGER.error("定时抓取知乎数据线程执行异常", ex);
            }
        }, 0, 10, TimeUnit.MINUTES);
    }
}

10.Spring boot程序启动类

@SpringBootApplication
@MapperScan(basePackages = "com.hyzx.qbasic.dao")
public class Application implements CommandLineRunner {

    @Autowired
    private ZhihuTask zhihuTask;

    public static void main(String[] args) throws IOException {
        SpringApplication.run(Application.class, args);
    }

    @Override
    public void run(String... strings) throws Exception {
        // 爬取知乎数据
        zhihuTask.crawl();
    }
}