SpringBoot和VW-Crawler抓取csdn的文章

 

 

一：工程介绍

使用Springboot做架构，redis做数据存储，vw-crawler做爬虫模块抓取csdn的文章，pom配置如下：

<parent>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-parent</artifactId>
        <version>1.4.3.RELEASE</version>
        <relativePath/> 
    </parent>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
        <java.version>1.8</java.version>
        <vw-crawler.version>0.0.4</vw-crawler.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
            <exclusions>
                <exclusion>
                    <groupId>org.springframework.boot</groupId>
                    <artifactId>spring-boot-starter-tomcat</artifactId>
                </exclusion>
            </exclusions>
        </dependency>
        <dependency>
            <groupId>com.github.vector4wang</groupId>
            <artifactId>vw-crawler</artifactId>
            <version>0.0.5</version>
        </dependency>

        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-redis</artifactId>
        </dependency>
        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.31</version>
        </dependency>
    </dependencies>

redis相关配置

# Redis数据库索引（默认为0）
spring.redis.database=0
# Redis服务器地址
spring.redis.host=localhost
# Redis服务器连接端口
spring.redis.port=6379
# Redis服务器连接密码（默认为空）
spring.redis.password=
# 连接池最大连接数（使用负值表示没有限制）
spring.redis.pool.max-active=8
# 连接池最大阻塞等待时间（使用负值表示没有限制）
spring.redis.pool.max-wait=-1
# 连接池中的最大空闲连接
spring.redis.pool.max-idle=8
# 连接池中的最小空闲连接
spring.redis.pool.min-idle=0
# 连接超时时间（毫秒）
spring.redis.timeout=0

redis操作封装

@Component
public class DataCache {

  @Autowired
  private StringRedisTemplate redisTemplate;

  /**
   * url作为key保存到redis
   */
  public void save(Blog blog) {
    redisTemplate.opsForValue().set(blog.getUrlMd5(), JSON.toJSONString(blog));
  }

  /**
   * 根据url获取
   */
  public Blog get(String url) {
    String md5Url = Md5Util.getMD5(url.getBytes());
    String blogStr = redisTemplate.opsForValue().get(md5Url);
    if (StringUtils.isEmpty(blogStr)) {
      return new Blog();
    }
    return JSON.parseObject(blogStr, Blog.class);
  }

}

 

二：爬虫操作

1：页面模型，cssSelector定位数据

public class Blog implements Serializable {

  @CssSelector(selector = "#mainBox > main > div.blog-content-box > div.article-header-box > div > div.article-info-box > div > span.time", dateFormat = "yyyy年MM月dd日 HH:mm:ss")
  private Date publishDate;

  @CssSelector(selector = "main > div.blog-content-box > div.article-header-box > div.article-header>div.article-title-box > h1", resultType = SelectType.TEXT)
  private String title;

  @CssSelector(selector = "main > div.blog-content-box > div.article-header-box > div.article-header>div.article-info-box > div > div > span.read-count", resultType = SelectType.TEXT)
  private String readCountStr;

  private int readCount;

  @CssSelector(selector = "#article_content",resultType = SelectType.TEXT)
  private String content;

  @CssSelector(selector = "body > div.tool-box > ul > li:nth-child(1) > button > p",resultType = SelectType.TEXT)
  private int likeCount;

  /**
   * 暂时不支持自动解析列表的功能，所以加个中间变量，需要二次解析下
   */
  @CssSelector(selector = "#mainBox > main > div.comment-box > div.comment-list-container > div.comment-list-box",resultType = SelectType.HTML)
  private String comentTmp;

  private String url;

  private String urlMd5;

  private List<String> comment;

2：配置请求头、爬虫线程数、超时时间等等，并实现CrawlerService爬虫接口

@Component
@Order
public class Crawler implements CommandLineRunner {

  @Autowired
  private DataCache dataCache;
 
  @Override
  public void run(String... strs) {
    new VWCrawler.Builder().setUrl("https://blog.csdn.net/qqHJQS").setHeader("User-Agent",
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36")
        .setTargetUrlRex("https://blog.csdn.net/zhang__l/article/details/[0-9]+")
        .setThreadCount(5)
        .setTimeOut(5000).setPageParser(new CrawlerService<Blog>() {

      @Override
      public void parsePage(Document doc, Blog pageObj) {
        pageObj.setReadCount(Integer.parseInt(pageObj.getReadCountStr().replace("阅读数：", "").replace("", "0")));
        pageObj.setUrl(doc.baseUri());
        pageObj.setUrlMd5(Md5Util.getMD5(pageObj.getUrl().getBytes()));
        /**
         * TODO 评论列表还未处理
         */
      }

      @Override
      public void save(Blog pageObj) {
        dataCache.save(pageObj);
      }
    }).build().start();
  }

}

3：启动执行

 右键执行CrawlerApplication

 

 

入群二维码（失效请加：13128600812，备注：ljs）