webmagic文本处理(爬虫项目)

<?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>org.example</groupId>
    <artifactId>SpiderJava</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <dependency>
            <groupId>us.codecraft</groupId>
            <artifactId>webmagic-core</artifactId>
            <version>0.7.3</version>
        </dependency>
        <dependency>
            <groupId>us.codecraft</groupId>
            <artifactId>webmagic-extension</artifactId>
            <version>0.7.3</version>
        </dependency>
        <dependency>
            <groupId>org.apache.commons</groupId>
            <artifactId>commons-lang3</artifactId>
            <version>3.10</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.projectlombok/lombok -->
        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <version>1.18.12</version>
            <scope>provided</scope>
        </dependency>





    </dependencies>


</project>
package spider.pojo.po;

import lombok.Data;
import spider.common.annotation.CssSelector;
import spider.common.annotation.Html;

import java.util.List;

/**
 * @Author lyr
 * @create 2020/6/23 19:42
 */
@Html
@Data
public class SimpleBlogHtml {
    @CssSelector(selector = ".oneline span")
    private List<String> title;

}

package spider.common.bean;

import lombok.SneakyThrows;
import lombok.extern.slf4j.Slf4j;
import spider.common.annotation.CssSelector;
import spider.pojo.po.SimpleBlogHtml;
import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.processor.PageProcessor;

import java.lang.reflect.Field;
import java.util.List;

/**
 * @Author lyr
 * @create 2020/6/23 18:50
 * 处理器
 */
@Slf4j
public class HtmlProcessor implements PageProcessor {
    @SneakyThrows
    public void process(Page page) {
        page.setCharset("UTF-8");
        SimpleBlogHtml blogHtml = new SimpleBlogHtml();
        for(Field field: SimpleBlogHtml.class.getDeclaredFields()) {
            field.setAccessible(true);
            CssSelector cssSelector = field.getAnnotation(CssSelector.class);
            System.out.println(cssSelector);
            if(cssSelector!=null) {
                String selector = cssSelector.selector();
                List<String> result = page.getHtml().css(selector).xpath("//span/text()").all();
                field.set(blogHtml,result);
            }
        }
        // log.info(page.getHtml().css("div").all().toString());
        System.out.println(blogHtml.getTitle());



        page.putField("html",blogHtml);



    }
    private final Site site = new Site();
    {
        site.setCharset("UTF-8");
    }

    public Site getSite() {
        return site;
    }
}

package spider.common.bean;

import lombok.extern.slf4j.Slf4j;
import us.codecraft.webmagic.ResultItems;
import us.codecraft.webmagic.Task;
import us.codecraft.webmagic.pipeline.Pipeline;

/**
 * @Author lyr
 * @create 2020/6/23 19:53
 */
@Slf4j
public class DownloadPipeLine<T> implements Pipeline {
    public void process(ResultItems resultItems, Task task) {
        T data = resultItems.get("html");
        log.info("data {}",data);
    }
}

package spider;

import spider.common.bean.DownloadPipeLine;
import spider.common.bean.HtmlProcessor;
import spider.pojo.po.SimpleBlogHtml;
import us.codecraft.webmagic.Spider;
import us.codecraft.webmagic.pipeline.FilePipeline;

/**
 * @Author lyr
 * @create 2020/6/23 18:52
 */
public class Main {
    public static void main(String[] args) {
        Spider.create(new HtmlProcessor())

                .addUrl("https://blog.csdn.net/qq_43923045")
                .addPipeline(new DownloadPipeLine<SimpleBlogHtml>())
                .run();

    }
}

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值