按照以上几点的,推荐一款非常好用的java爬虫框架webmgic
使用webgic爬取 爱电影 电影列表资源信息 示例源码地址
<dependencies>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter</artifactId>
</dependency>
<dependency>
<groupId>org.projectlombok</groupId>
<artifactId>lombok</artifactId>
<optional>true</optional>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-test</artifactId>
<scope>test</scope>
</dependency>
<!-- webmagic start -->
<dependency>
<groupId>us.codecraft</groupId>
<artifactId>webmagic-core</artifactId>
<version>0.7.3</version>
<exclusions>
<exclusion>
<artifactId>fastjson</artifactId>
<groupId>com.alibaba</groupId>
</exclusion>
<exclusion>
<artifactId>commons-io</artifactId>
<groupId>commons-io</groupId>
</exclusion>
<exclusion>
<artifactId>commons-io</artifactId>
<groupId>commons-io</groupId>
</exclusion>
<exclusion>
<artifactId>fastjson</artifactId>
<groupId>com.alibaba</groupId>
</exclusion>
<exclusion>
<artifactId>fastjson</artifactId>
<groupId>com.alibaba</groupId>
</exclusion>
<exclusion>
<artifactId>log4j</artifactId>
<groupId>log4j</groupId>
</exclusion>
<exclusion>
<artifactId>slf4j-log4j12</artifactId>
<groupId>org.slf4j</groupId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>us.codecraft</groupId>
<artifactId>webmagic-extension</artifactId>
<version>0.7.3</version>
</dependency>
<dependency>
<groupId>us.codecraft</groupId>
<artifactId>webmagic-selenium</artifactId>
<version>0.7.3</version>
</dependency>
<dependency>
<groupId>net.minidev</groupId>
<artifactId>json-smart</artifactId>
<version>2.2.1</version>
</dependency>
<!-- webmagic end -->
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.49</version>
</dependency>
<dependency>
<groupId>commons-lang</groupId>
<artifactId>commons-lang</artifactId>
<version>2.6</version>
</dependency>
<dependency>
<groupId>commons-io</groupId>
<artifactId>commons-io</artifactId>
<version>2.6</version>
</dependency>
<dependency>
<groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId>
<version>1.11</version>
</dependency>
<dependency>
<groupId>commons-collections</groupId>
<artifactId>commons-collections</artifactId>
<version>3.2.2</version>
</dependency>
</dependencies>
package com.ady01.demo1;
import lombok.extern.slf4j.Slf4j;
import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.Spider;
import us.codecraft.webmagic.processor.PageProcessor;
/**
* <b>description</b>:第一个爬虫示例,爬去动作片列表信息 <br>
* <b>time</b>:2019/4/20 10:58 <br>
* <b>author</b>:ready likun_557@163.com
*/
@Slf4j
public class Ady01comPageProcessor implements PageProcessor {
@Override
public void process(Page page) {
log.info("爬取成功!");
log.info("爬取的内容:" + page.getRawText());
}
@Override
public Site getSite() {
return Site.me().setSleepTime(1000).setRetryTimes(3);
}
public static void main(String[] args) {
String url = "http://m.ady01.com/rs/film/listJson/1/2?_=1555726508180";
Spider.create(new Ady01comPageProcessor()).addUrl(url).thread(1).run();
}
}
运行Ady01comPageProcessor中的main方法,执行结果如下: