目录
  • 6.crawlermapper.xml文件
  • 7.知乎页面内容处理类zhihupageprocessor
  • 8.知乎数据处理类zhihupipeline
  • 9.知乎爬虫任务类zhihutask
  • 10.spring boot程序启动类

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:。

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

<?xml version="1.0" encoding="utf-8"?>
<project xmlns="http://maven.apache.org/pom/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/xmlschema-instance"
         xsi:schemalocation="http://maven.apache.org/pom/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelversion>4.0.0</modelversion>

    <groupid>hyzx</groupid>
    <artifactid>qbasic-crawler</artifactid>
    <version>1.0.0</version>

    <parent>
        <groupid>org.springframework.boot</groupid>
        <artifactid>spring-boot-starter-parent</artifactid>
        <version>1.5.21.release</version>
        <relativepath/> <!-- lookup parent from repository -->
    </parent>

    <properties>
        <project.build.sourceencoding>utf-8</project.build.sourceencoding>
        <maven.test.skip>true</maven.test.skip>
        <java.version>1.8</java.version>
        <maven.compiler.plugin.version>3.8.1</maven.compiler.plugin.version>
        <maven.resources.plugin.version>3.1.0</maven.resources.plugin.version>

        <mysql.connector.version>5.1.47</mysql.connector.version>
        <druid.spring.boot.starter.version>1.1.17</druid.spring.boot.starter.version>
        <mybatis.spring.boot.starter.version>1.3.4</mybatis.spring.boot.starter.version>
        <fastjson.version>1.2.58</fastjson.version>
        <commons.lang3.version>3.9</commons.lang3.version>
        <joda.time.version>2.10.2</joda.time.version>
        <webmagic.core.version>0.7.3</webmagic.core.version>
    </properties>

    <dependencies>
        <dependency>
            <groupid>org.springframework.boot</groupid>
            <artifactid>spring-boot-devtools</artifactid>
            <scope>runtime</scope>
            <optional>true</optional>
        </dependency>

        <dependency>
            <groupid>org.springframework.boot</groupid>
            <artifactid>spring-boot-starter-test</artifactid>
            <scope>test</scope>
        </dependency>

        <dependency>
            <groupid>org.springframework.boot</groupid>
            <artifactid>spring-boot-configuration-processor</artifactid>
            <optional>true</optional>
        </dependency>

        <dependency>
            <groupid>mysql</groupid>
            <artifactid>mysql-connector-java</artifactid>
            <version>${mysql.connector.version}</version>
        </dependency>

        <dependency>
            <groupid>com.alibaba</groupid>
            <artifactid>druid-spring-boot-starter</artifactid>
            <version>${druid.spring.boot.starter.version}</version>
        </dependency>

        <dependency>
            <groupid>org.mybatis.spring.boot</groupid>
            <artifactid>mybatis-spring-boot-starter</artifactid>
            <version>${mybatis.spring.boot.starter.version}</version>
        </dependency>

        <dependency>
            <groupid>com.alibaba</groupid>
            <artifactid>fastjson</artifactid>
            <version>${fastjson.version}</version>
        </dependency>

        <dependency>
            <groupid>org.apache.commons</groupid>
            <artifactid>commons-lang3</artifactid>
            <version>${commons.lang3.version}</version>
        </dependency>

        <dependency>
            <groupid>joda-time</groupid>
            <artifactid>joda-time</artifactid>
            <version>${joda.time.version}</version>
        </dependency>

        <dependency>
            <groupid>us.codecraft</groupid>
            <artifactid>webmagic-core</artifactid>
            <version>${webmagic.core.version}</version>
            <exclusions>
                <exclusion>
                    <groupid>org.slf4j</groupid>
                    <artifactid>slf4j-log4j12</artifactid>
                </exclusion>
            </exclusions>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupid>org.apache.maven.plugins</groupid>
                <artifactid>maven-compiler-plugin</artifactid>
                <version>${maven.compiler.plugin.version}</version>
                <configuration>
                    <source>${java.version}</source>
                    <target>${java.version}</target>
                    <encoding>${project.build.sourceencoding}</encoding>
                </configuration>
            </plugin>

            <plugin>
                <groupid>org.apache.maven.plugins</groupid>
                <artifactid>maven-resources-plugin</artifactid>
                <version>${maven.resources.plugin.version}</version>
                <configuration>
                    <encoding>${project.build.sourceencoding}</encoding>
                </configuration>
            </plugin>

            <plugin>
                <groupid>org.springframework.boot</groupid>
                <artifactid>spring-boot-maven-plugin</artifactid>
                <configuration>
                    <fork>true</fork>
                    <addresources>true</addresources>
                </configuration>
                <executions>
                    <execution>
                        <goals>
                            <goal>repackage</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

    <repositories>
        <repository>
            <id>public</id>
            <name>aliyun nexus</name>
            <url>http://maven.aliyun.com/nexus/content/groups/public/</url>
            <releases>
                <enabled>true</enabled>
            </releases>
        </repository>
    </repositories>

    <pluginrepositories>
        <pluginrepository>
            <id>public</id>
            <name>aliyun nexus</name>
            <url>http://maven.aliyun.com/nexus/content/groups/public/</url>
            <releases>
                <enabled>true</enabled>
            </releases>
            <snapshots>
                <enabled>false</enabled>
            </snapshots>
        </pluginrepository>
    </pluginrepositories>
</project>

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

<?xml version="1.0" encoding="utf-8"?>
<!doctype mapper public "-//mybatis.org//dtd mapper 3.0//en" "http://mybatis.org/dtd/mybatis-3-mapper.dtd">
<mapper namespace="com.hyzx.qbasic.dao.crawlermapper">

    <insert id="addcmscontent" parametertype="com.hyzx.qbasic.model.cmscontentpo">
        insert into cms_content (contentid,
                                 title,
                                 releasedate,
                                 content)
        values (#{contentid,jdbctype=varchar},
                #{title,jdbctype=varchar},
                #{releasedate,jdbctype=timestamp},
                #{content,jdbctype=longvarchar})
    </insert>
</mapper>

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();
    }
}

到此这篇关于springboot+webmagic+mybatis爬虫框架的使用的文章就介绍到这了,更多相关springboot+webmagic+mybatis爬虫内容请搜索www.887551.com以前的文章或继续浏览下面的相关文章希望大家以后多多支持www.887551.com!