在b站学习的webmagic代码
整体结构图
#=
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">
<parent>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-parent</artifactId>
<version>2.0.3.RELEASE</version>
</parent>
<groupId>cn.itcast</groupId>
<artifactId>itcast-crawler-webmagic</artifactId>
<version>1.0-SNAPSHOT</version>
<modelVersion>4.0.0</modelVersion>
<properties>
<java.version>1.8</java.version>
</properties>
<dependencies>
<!--SpringMVC-->
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-web</artifactId>
<version>2.0.3.RELEASE</version>
</dependency>
<!--SpringData Jpa-->
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-data-jpa</artifactId>
</dependency>
<!--MySQL连接包-->
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
</dependency>
<!--Webmagic 核心包-->
<dependency>
<groupId>us.codecraft</groupId>
<artifactId>webmagic-core</artifactId>
<version>0.7.3</version>
<!--排除日志-->
<exclusions>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
</exclusion>
</exclusions>
</dependency>
<!--Webmagic 扩展包-->
<dependency>
<groupId>us.codecraft</groupId>
<artifactId>webmagic-extension</artifactId>
<version>0.7.3</version>
</dependency>
<!--布隆过滤器的包-->
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
<version>16.0</version>
</dependency>
<!--工具包-->
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-lang3</artifactId>
</dependency>
</dependencies>
</project>
配置
#DB Configuration:
spring.datasource.driverClassName=com.mysql.jdbc.Driver
spring.datasource.url=jdbc:mysql://127.0.0.1:3306/crawler
spring.datasource.username=root
spring.datasource.password=woshiliujie1
#JPA configuration:
# spring.jpa.show-sql 配置在日志中打印出执行的 SQL 语句信息。
spring.jpa.database=mysql
spring.jpa.show-sql=true
#springboot jpa 会将驼峰式 自动修改为增加下划线
spring.jpa.hibernate.naming.physical-strategy=org.hibernate.boot.model.naming.PhysicalNamingStrategyStandardImpl
pojo层
package cn.itcast.job.pojo;
import javax.persistence.Entity;
import javax.persistence.GeneratedValue;
import javax.persistence.GenerationType;
import javax.persistence.Id;
@Entity
//@Entity(name="EntityName") 必须,用来标注一个数据库对应的实体,数据库中创建的表名默认和类名一致。
// 其中,name 为可选,对应数据库中一个表,使用此注解标记 Pojo 是一个 JPA 实体。
public class JobInfo {
// @Table(name = "AUTH_USER") 是一个可选的注解。
// 声明了数据库实体对应的表信息。包括表名称、索引信息等。这里声明这个实体类对应的表名是 AUTH_USER。
// 如果没有指定,则表名和实体的名称保持一致。
@Id
@GeneratedValue(strategy = GenerationType.IDENTITY)
private Long id;
private String companyName;
private String companyAddr;
private String companyInfo;
private String jobName;
private String jobAddr;
private String jobInfo;
private String url;
public Long getId() {
return id;
}
public void setId(Long id) {
this.id = id;
}
public String getCompanyName() {
return companyName;
}
public void setCompanyName(String companyName) {
this.companyName = companyName;
}
public String getCompanyAddr() {
return companyAddr;
}
public void setCompanyAddr(String companyAddr) {
this.companyAddr = companyAddr;
}
public String getCompanyInfo() {
return companyInfo;
}
public void setCompanyInfo(String companyInfo) {
this.companyInfo = companyInfo;
}
public String getJobName() {
return jobName;
}
public void setJobName(String jobName) {
this.jobName = jobName;
}
public String getJobAddr() {
return jobAddr;
}
public void setJobAddr(String jobAddr) {
this.jobAddr = jobAddr;
}
public String getJobInfo() {
return jobInfo;
}
public void setJobInfo(String jobInfo) {
this.jobInfo = jobInfo;
}
public String getUrl() {
return url;
}
public void setUrl(String url) {
this.url = url;
}
@Override
public String toString() {
return "JobInfo{" +
"id=" + id +
", companyName='" + companyName + '\'' +
", companyAddr='" + companyAddr + '\'' +
", companyInfo='" + companyInfo + '\'' +
", jobName='" + jobName + '\'' +
", jobAddr='" + jobAddr + '\'' +
", jobInfo='" + jobInfo + '\'' +
", url='" + url + '\'' +
'}';
}
}
dao层
package cn.itcast.job.dao;
import cn.itcast.job.pojo.JobInfo;
import org.springframework.data.jpa.repository.JpaRepository;
//其中 T 是数据库实体类(JobInfo),ID 是数据库实体类的主键
public interface JobInfoDao extends JpaRepository<JobInfo,Long> {
}
service层
package cn.itcast.job.service;
import cn.itcast.job.pojo.JobInfo;
import java.util.List;
public interface JobInfoService {
/**
* 保存工作信息
*/
public void save(JobInfo jobInfo);
/**
*根据条件查询工作信息
*/
public List<JobInfo> fineJobInfo(JobInfo jobInfo);
}
`
###
JobInfoSErviceImpl
package cn.itcast.job.service.impl;
import cn.itcast.job.dao.JobInfoDao;
import cn.itcast.job.pojo.JobInfo;
import cn.itcast.job.service.JobInfoService;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.data.domain.Example;
import org.springframework.stereotype.Service;
import javax.transaction.Transactional;
import java.util.List;
@Service
public class JobInfoServiceImpl implements JobInfoService {
// 注入dao
@Autowired
private JobInfoDao jobInfoDao;
@Override
@Transactional
public void save(JobInfo jobInfo) {
//根据url和发布时间查询数据
JobInfo param =new JobInfo();
param.setUrl(jobInfo.getUrl());
//查询
List<JobInfo> list = this.fineJobInfo(param);
//判断查询结果数据是否为空
if(list.size() == 0){
//如果查询结果为空 表示招聘信息不存在 或者已经更新 需要新增或者更新数据
this.jobInfoDao.saveAndFlush(jobInfo);
}
}
@Override
public List<JobInfo> fineJobInfo(JobInfo jobInfo) {
//设置查询条件
Example example = Example.of(jobInfo);
//执行查询
List list=this.jobInfoDao.findAll(example);
return list;
}
}
task
package cn.itcast.job.task;
import cn.itcast.job.pojo.JobInfo;
import org.jsoup.Jsoup;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.scheduling.annotation.Scheduled;
import org.springframework.stereotype.Component;
import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.Spider;
import us.codecraft.webmagic.processor.PageProcessor;
import us.codecraft.webmagic.scheduler.BloomFilterDuplicateRemover;
import us.codecraft.webmagic.scheduler.QueueScheduler;
import us.codecraft.webmagic.selector.Html;
import us.codecraft.webmagic.selector.Selectable;
import java.util.List;
@Component
public class JobProcessor implements PageProcessor {
private String url="https://search.51job.com/list/000000,000000,0000,00,9,99,java,2,1.html?lang=c&stype=1&postchannel=0000&workyear=99&cotype=99°reefrom=99&jobterm=01&companysize=99&lonlat=0%2C0&radius=-1&ord_field=0&confirmdate=9&fromType=22&dibiaoid=0&address=&line=&specialarea=00&from=&welfare=%E5%81%9A%E4%B8%80%E4%BC%91%E4%B8%80";
@Override
public void process(Page page) {
// 解析页面获取招聘信息详情的url地址
List<Selectable> list = page.getHtml().css("div#resultList div.el").nodes();
// 判断获取到的集合是否为空
if (list.size() == 0){
//如果为空表示招聘页 解析页面 获取招聘详情信息保存数据
this.saveJobInfo(page);
}else {
//不为空 解析url放到任务中
for (Selectable selectable:list){
//url
String jobInfourl = selectable.links().toString();
//把获取到的url放到任务列表中
page.addTargetRequest(jobInfourl);
}
//获取下一页的url
String bkUrl = page.getHtml().css("div.p_in li.bk").nodes().get(1).links().toString();
//将下一页的url放到任务队列中
page.addTargetRequest(bkUrl);
}
String html = page.getHtml().toString();
}
//解析获取招聘详情信息保存数据
private void saveJobInfo(Page page) {
//创建招聘详情对象
JobInfo jobInfo = new JobInfo();
//解析页面
Html html = page.getHtml();
//获取数据,封装到对象中
jobInfo.setCompanyName(html.css("div.cn p.cname a","text").toString());
jobInfo.setCompanyAddr(Jsoup.parse(html.css("div.bmsg").nodes().get(1).toString()).text() );
jobInfo.setCompanyInfo(Jsoup.parse(html.css("div.tmsg").toString()).text());//因为就一个 所以不用写是第几个
jobInfo.setJobName(html.css("div.cn h1","text").toString());
jobInfo.setJobAddr(Jsoup.parse(html.css("div.bmsg").nodes().get(1).toString()).text());
jobInfo.setJobInfo(Jsoup.parse(html.css("div.job_msg").toString()).text());
jobInfo.setUrl(page.getUrl().toString());
//获取发布时间 需要用到正则
// String time= Jsoup.parse(html.css("div.cn p.ltype").toString()).text();
// jobInfo.setTime(time.substring(0,time.length()-2));
//结果保存
page.putField("jobInfo",jobInfo);
// jobInfo.setId();
// jobInfo.setTime();
}
private Site site = Site.me()
.setCharset("gbk")
.setTimeOut(10000)//设置超时时间 单位是ms毫秒
.setRetrySleepTime(30000) //设置重试的间隔时间 1000为默认值
.setRetrySleepTime(3)
;
@Override
public Site getSite() {
return site;
}
@Autowired
private SpringDataPipeline springDataPipeline;
//initialDelay 当任务启动时候 等多久执行方法
//fixedDelay m每隔10秒 执行方法
@Scheduled(initialDelay = 1000,fixedDelay = 100*1000)
public void process(){
Spider.create(new JobProcessor())
.addUrl(url)
.setScheduler(new QueueScheduler().setDuplicateRemover(new BloomFilterDuplicateRemover(100000)))
.thread(10)
.addPipeline(this.springDataPipeline)
.run();
}
}
package cn.itcast.job.task;
import cn.itcast.job.pojo.JobInfo;
import cn.itcast.job.service.JobInfoService;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Component;
import us.codecraft.webmagic.ResultItems;
import us.codecraft.webmagic.Task;
import us.codecraft.webmagic.pipeline.Pipeline;
//Component 添加这个为创建实例
@Component
public class SpringDataPipeline implements Pipeline {
@Autowired
private JobInfoService jobInfoService;
// 处理最后的持久化操作,或者业务操作 实现Pipeline即可 处理结果集
@Override
public void process(ResultItems resultItems, Task task) {
//获取封装好的招聘详情
JobInfo jobInfo =resultItems.get("jobInfo");
if (jobInfo !=null){
this.jobInfoService.save(jobInfo);
}
//判断数据是否不为空
}
}
数据库查询结果
附:源码下载地址