WebMagic爬虫入门教程（二）一个完整的爬取动漫之家的实例

（一）前言

         我的上一篇博客已经说明如何爬取某一个网页的动漫数据，这里重点说一下一个完整的爬虫实例。

       和上一篇文章相比，多了的就是动画种类，日文名什么的。

    推荐这个爬取博客的：http://blog.csdn.net/qq598535550/article/details/51287630

                                              我也是根据这个学的。

            用到的工具有：Intellij IDEA，mySQL， webmagic0.73等

   项目github地址：https://github.com/yongzhuo/JavaLearning/tree/master/src/java/Webmagic

（二）详细过程

             爬取的内容有：标题，动画种类，日文名，别名，播放时间，播放状态，类型，

            原作，监督，制作公司，官网，剧情简介，剧情简介，评分，评分人数，相关url等。

     爬取图片如下：

     

推荐

   （1）首先mySQL建表dmzjAnimation

maven依赖：

  
    us.codecraft  
    webmagic-core  
    0.7.3  
  
  
    us.codecraft  
    webmagic-extension  
    0.7.3  
  

 

CREATE TABLE `dmzjAnimation` (  
  `id` int(11) unsigned NOT NULL auto_increment, 
  `hahawebname` varchar(127) default NULL,  
  `antag` varchar(255) default NULL,  
  `japanname` varchar(255) default NULL, 
  `allname` varchar(255) default NULL, 
  `year` varchar(255) default NULL,  
   `state` varchar(255) default NULL,
  `tag` varchar(643) default NULL,
  `original` varchar(255) default NULL, 
  `Screenwriter` varchar(255) default NULL, 
  `company` varchar(255) default NULL,
  `website` varchar(511) default NULL,
  `content` varchar(2559) default NULL,
  `contentdetail` varchar(10240) default NULL,
  `goal` varchar(255) default NULL,
  `mentotal` varchar(255) default NULL,
  `url` varchar(255) default NULL,
  PRIMARY KEY  (`id`)  
) ENGINE=InnoDB DEFAULT CHARSET=utf8; 

 

     用Navicat for MySQL查看是这样子的

（2）第二步就开始写java代码，主要包括DmzjAnimationProcessor(核心类)，DmzjAnimationDao(java连接MySQL类)和DmzjAnimation（数据实体类）

 

（2.1）dmzjAnimation，实体类对应

 

package Webmagic.donghua.dmzj.com;

/***Created by mo
 *On 2017/10/23  ***12:08.
 ******/
public class DmzjAnimation {
    private int id;
    private String hahawebname;// 标题
    private String antag;//动画种类
    private String japanname;//日文名
    private String allname;//别名
    private String year;//播放时间
    private String state;//播放状态
    private String tag;//类型
    private String original;//原作
    private String screenwriter;//监督
    private String company;//制作公司
    private String website;//官网
    private String content;//剧情简介
    private String contentdetail;//剧情简介
    private String goal;//评分
    private String mentotal;//评分人数
    private String url;//相关url

    @Override
    public String toString() {
        return "DmzjAnimation{" +
                "id=" + id +
                ", hahawebname='" + hahawebname + '\'' +
                ", antag='" + antag + '\'' +
                ", japanname='" + japanname + '\'' +
                ", allname='" + allname + '\'' +
                ", year='" + year + '\'' +
                ", state='" + state + '\'' +
                ", tag='" + tag + '\'' +
                ", original='" + original + '\'' +
                ", screenwriter='" + screenwriter + '\'' +
                ", company='" + company + '\'' +
                ", website='" + website + '\'' +
                ", content='" + content + '\'' +
                ", contentdetail='" + contentdetail + '\'' +
                ", goal=" + goal +
                ", mentotal=" + mentotal +
                ", url='" + url + '\'' +
                '}';
    }


    public int getId() {
        return id;
    }

    public void setId(int id) {
        this.id = id;
    }

    public String getHahawebname() {
        return hahawebname;
    }

    public void setHahawebname(String hahawebname) {
        this.hahawebname = hahawebname;
    }

    public String getAntag() {
        return antag;
    }

    public void setAntag(String antag) {
        this.antag = antag;
    }

    public String getJapanname() {
        return japanname;
    }

    public void setJapanname(String japanname) {
        this.japanname = japanname;
    }

    public String getAllname() {
        return allname;
    }

    public void setAllname(String allname) {
        this.allname = allname;
    }

    public String getYear() {
        return year;
    }

    public void setYear(String year) {
        this.year = year;
    }

    public String getState() {
        return state;
    }

    public void setState(String state) {
        this.state = state;
    }

    public String getTag() {
        return tag;
    }

    public void setTag(String tag) {
        this.tag = tag;
    }

    public String getOriginal() {
        return original;
    }

    public void setOriginal(String original) {
        this.original = original;
    }

    public String getScreenwriter() {
        return screenwriter;
    }

    public void setScreenwriter(String screenwriter) {
        this.screenwriter = screenwriter;
    }

    public String getCompany() {
        return company;
    }

    public void setCompany(String company) {
        this.company = company;
    }

    public String getWebsite() {
        return website;
    }

    public void setWebsite(String website) {
        this.website = website;
    }

    public String getContent() {
        return content;
    }

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

    public String getContentdetail() {
        return contentdetail;
    }

    public void setContentdetail(String contentdetail) {
        this.contentdetail = contentdetail;
    }

    public String getGoal() {
        return goal;
    }

    public void setGoal(String goal) {
        this.goal = goal;
    }

    public String getMentotal() {
        return mentotal;
    }

    public void setMentotal(String mentotal) {
        this.mentotal = mentotal;
    }

    public String getUrl() {
        return url;
    }

    public void setUrl(String url) {
        this.url = url;
    }



}

 

 

 

 

 

 

（2.2）DmzjAnimationProcessor，爬虫逻辑,核心类

 

package Webmagic.donghua.dmzj.com;

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.selector.Html;
import us.codecraft.webmagic.selector.Selectable;

import java.util.List;

/***Created by mo
 *On 2017/10/23  ***12:09.
 ******/
public class DmzjAnimationProcessor implements PageProcessor {
    int myid = 0;
    int size =10;
    // 抓取网站的相关配置，包括编码、抓取间隔、重试次数等
    private Site site = Site.me().setRetryTimes(1000).setSleepTime(1000).setCharset("utf8");
    @Override
    public Site getSite() {
        return site;
    }

    @Override
    public void process(Page page) {
        DmzjAnimation dmzjAnimation = new DmzjAnimation();
        Html html = page.getHtml();
        size++;
        myid++;
        int id = myid;
        dmzjAnimation.setId(id);
        String hahawebname = html.xpath("//div[@class=\"odd_anim_title_tnew\"]/div[@class=\"tvversion\"]/a/span[@class=\"anim_title_text\"]/h1/text()").get();//得分
        dmzjAnimation.setHahawebname(hahawebname);
        String goal = html.xpath("//div[@class=\"anim_star\"]/ul/li[@id=\"anim_score_info\"]/span[@class=\"points_text\"]/text()").get();//得分
        dmzjAnimation.setGoal(goal);
        String mentotalold = html.xpath("//div[@class=\"anim_star\"]/ul/li[@id=\"score_statistics\"]/span[@id=\"score_count_span\"]/text()").get();//人数
        String mentotal = mentotalold.replaceAll("人评分","");
        dmzjAnimation.setMentotal(mentotal);
        String content = html.xpath("//div[@class=\"odd_anim_title_mnew\"]/p/span[@id=\"gamedescshort\"]/text()").get();//内容
        dmzjAnimation.setContent(content);
        String contentdetail = html.xpath("//div[@class=\"odd_anim_title_mnew\"]/p/span[@id=\"gamedescall\"]/text()").get();//内容
        dmzjAnimation.setContentdetail(contentdetail);
        System.out.println("hahawebname: "+ hahawebname);
        System.out.println("goal: "+goal);
        System.out.println("mentotal: "+ mentotal);
        System.out.println("content: "+ content);
        System.out.println("contentdetail: "+ contentdetail);
        List nodes = html.xpath("//div[@class=\"anim_attributenew_text\"]/ul/li").nodes();
        for(Selectable item : nodes){
            String tmp = item.get();
            if(tmp.contains("动画种类")) {//动画种类 : 剧场版
                String antag11 = tmp.replaceAll("]+>","");
                String antag = antag11.replaceAll("动画种类 : ","");
                System.out.println(antag);
                dmzjAnimation.setAntag(antag);
            }//日文名 : 暂无
            if(tmp.contains("日文名")) {
                String japanname11 = tmp.replaceAll("]+>","");
                String japanname = japanname11.replaceAll("日文名 : ","");
                if(japanname.contains("暂无")){japanname = null;}
                System.out.println(japanname);
              dmzjAnimation.setJapanname(japanname);
            }//别名 : 大闹天宫 上下集 / The Monkey King
            if(tmp.contains("别名")) {
                String allname11 = tmp.replaceAll("]+>","");
                String allname = allname11.replaceAll("别名 : ","");
                if(allname.contains("暂无")){allname = null;}
                System.out.println(allname);
                dmzjAnimation.setAllname(allname);
            }//首播时间 : 暂无
            if(tmp.contains("首播")) {
                String year11 = tmp.replaceAll("]+>","");
                String year1111 = year11.replaceAll("首播时间 : ","");
                String year = year1111;
                if(year1111.contains("暂无")){year = null;}
                System.out.println(year);
                dmzjAnimation.setYear(year);
            }
            if(tmp.contains("播放状态")) {
                String state11 = tmp.replaceAll("]+>","");
                String state1111 = state11.replaceAll("播放状态 : ","");
                String state = state1111;
                if(state.contains("暂无")){state = null;}
                System.out.println(state);
                dmzjAnimation.setState(state);
            }
            if(tmp.contains("剧情类型")) {
                String tag11 = tmp.replaceAll("]+>","");
                String tag1111 = tag11.replaceAll("剧情类型 : ","");
                String tag = tag1111.replaceAll(" "," / ");
                System.out.println(tag);
                dmzjAnimation.setTag(tag);
            }//原作 : 暂无
            if(tmp.contains("原作")) {
                String original11 = tmp.replaceAll("]+>","");
                String original1111 = original11.replaceAll("原作 :","");
                String original = original1111;
                if(original.contains("暂无")){original = null;}
                System.out.println(original);
                dmzjAnimation.setOriginal(original);
            }//监督 : 万籁鸣 / 唐澄
            if(tmp.contains("监督")) {
                String screenwriter11 = tmp.replaceAll("]+>","");
                String screenwriter1111 = screenwriter11.replaceAll("监督 :","");
                String screenwriter = screenwriter1111;
                if(screenwriter.contains("暂无")){screenwriter = null;}
                dmzjAnimation.setScreenwriter(screenwriter);
                System.out.println(screenwriter);
            }//制作公司 : 上海美术电影制片厂
            if(tmp.contains("制作公司")) {
                String company11 = tmp.replaceAll("]+>","");
                String company1111 = company11.replaceAll("制作公司 :","");
                company1111 = company1111 +" / "+ company1111 +"公司";
                String company = company1111;
                if(company.contains("暂无")){company = null;}
                System.out.println(company);
                dmzjAnimation.setCompany(company);
            }//官方网站 : 暂无
            if(tmp.contains("官方网站")) {
                String website =  tmp.replaceAll(".*?href=|target(.*)","");
                if(website.contains("暂无")){website = null;}
                System.out.println(website);
                dmzjAnimation.setWebsite(website);
            }
        }
        String url = "http://donghua.dmzj.com/donghua_info/"+size+".html";
        dmzjAnimation.setUrl(url);
        //new DmzjAnimationDao().add(dmzjAnimation);这个是fangdaomysql数据库的，你可以设置其他形式，比如说txt文件什么的
    }



    public static void main(String[] args) {
        int username = 10;
        DmzjAnimationProcessor my = new DmzjAnimationProcessor();
        long startTime, endTime;
        System.out.println("开始爬取...");
        for(;username<=15000;username++) {
            startTime = System.currentTimeMillis();
            Spider.create(my).addUrl("http://donghua.dmzj.com/donghua_info/" + username + ".html").thread(5).run();
            endTime = System.currentTimeMillis();
            System.out.println("爬取结束，耗时约" + ((endTime - startTime) / 1000) + "秒");
        }
    }
}

 

 

 

 

 

 

（2.3）DmzjAnimationDao，java连接MySQL类，

 

package Webmagic.donghua.dmzj.com;

/***Created by mo
 *On 2017/10/23  ***12:08.
 ******/
import java.sql.*;

    public class  DmzjAnimationDao {

        private Connection conn = null;
        private Statement stmt = null;

        public  DmzjAnimationDao() {
            try {
                Class.forName("com.mysql.jdbc.Driver");
                //spider是数据库，用户名，密码，数据格式，要自己配置自己的
                String url = "jdbc:mysql://localhost:3306/spider?user=root&password=xiemo&useUnicode=true&characterEncoding=UTF8";
                conn = (Connection) DriverManager.getConnection(url);
                stmt = conn.createStatement();
            } catch (ClassNotFoundException e) {
                e.printStackTrace();
            } catch (SQLException e) {
                e.printStackTrace();
            }
            System.out.println("连接数据库成功");
        }

        public int add(DmzjAnimation dmzjAnimation) {
            try {
                //dmzjAnimation是表名
                String sql = "INSERT INTO `spider`.`dmzjAnimation` (`id`,`hahawebname`,`antag`,`japanname`, `allname`, `year`,`state`,`tag`, `original`,`screenwriter`,`company`, `website`, `content`,`contentdetail`,`goal`,`mentotal`,`url`) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?);";
                PreparedStatement ps = conn.prepareStatement(sql);
                ps.setInt(1, dmzjAnimation.getId());
                ps.setString(2, dmzjAnimation.getHahawebname());
                ps.setString(3, dmzjAnimation.getAntag());
                ps.setString(4, dmzjAnimation.getJapanname());
                ps.setString(5, dmzjAnimation.getAllname());
                ps.setString(6, dmzjAnimation.getYear());
                ps.setString(7, dmzjAnimation.getState());
                ps.setString(8, dmzjAnimation.getTag());

                ps.setString(9, dmzjAnimation.getOriginal());
                ps.setString(10, dmzjAnimation.getScreenwriter());
                ps.setString(11, dmzjAnimation.getCompany());
                ps.setString(12, dmzjAnimation.getWebsite());
                ps.setString(13, dmzjAnimation.getContent());
                ps.setString(14, dmzjAnimation.getContentdetail());
                ps.setString(15, dmzjAnimation.getGoal());

                ps.setString(16, dmzjAnimation.getMentotal());
                ps.setString(17, dmzjAnimation.getUrl());
                return ps.executeUpdate();
            } catch (SQLException e) {
                e.printStackTrace();
            }
            return -1;
        }

}

 

 

 

 

 

 

（2.4）结果

IDEA：

 

 

 

MySQL:

 

希望对你有所帮助！