springboot+webmagic实现java爬虫jdbc及mysql的方法

前段时间需要爬取网页上的信息，自己对于爬虫没有任何了解，就了解了一下webmagic，写了个简单的爬虫。

一、首先介绍一下webmagic：

webmagic采用完全模块化的设计，功能覆盖整个爬虫的生命周期(链接提取、页面下载、内容抽取、持久化)，支持多线程抓取，分布式抓取，并支持自动重试、自定义UA/cookie等功能。

实现理念：

Maven依赖：

<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>us.codecraft</groupId>
   <artifactId>webmagic-extension</artifactId>
   <version>0.7.3</version>
   <exclusions>
    <exclusion>
     <groupId>org.slf4j</groupId>
     <artifactId>slf4j-log4j12</artifactId>
    </exclusion>
   </exclusions>
  </dependency>

jdbc模式：

ublic class CsdnBlogDao {
  private Connection conn = null;
  private Statement stmt = null;

  public CsdnBlogDao() {
    try {
      Class.forName("com.mysql.jdbc.Driver");
      String url = "jdbc:mysql://localhost:3306/test?"
          + "user=***&password=***3&useUnicode=true&characterEncoding=UTF8";
      conn = DriverManager.getConnection(url);
      stmt = conn.createStatement();
    } catch (ClassNotFoundException e) {
      e.printStackTrace();
    } catch (SQLException e) {
      e.printStackTrace();
    }

  }

  public int add(CsdnBlog csdnBlog) {
    try {
      String sql = "INSERT INTO `test`.`csdnblog` (`keyes`, `titles`, `content` , `dates`, `tags`, `category`, `views`, `comments`, `copyright`) VALUES (?, ?, ?, ?, ?, ?, ?, ?,?);";
      PreparedStatement ps = conn.prepareStatement(sql);
      ps.setInt(1, csdnBlog.getKey());
      ps.setString(2, csdnBlog.getTitle());
      ps.setString(3,csdnBlog.getContent());
      ps.setString(4, csdnBlog.getDates());
      ps.setString(5, csdnBlog.getTags());
      ps.setString(6, csdnBlog.getCategory());
      ps.setInt(7, csdnBlog.getView());
      ps.setInt(8, csdnBlog.getComments());
      ps.setInt(9, csdnBlog.getCopyright());
      return ps.executeUpdate();
    } catch (SQLException e) {
      e.printStackTrace();
    }
    return -1;
  }
}

实体类：

public class CsdnBlog {
  private int key;// 编号

  private String title;// 标题

  private String dates;// 日期

  private String tags;// 标签

  private String category;// 分类

  private int view;// 阅读人数

  private int comments;// 评论人数

  private int copyright;// 是否原创

  private String content; //文字内容

  public String getContent() {
    return content;
  }

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

  public int getKey() {
    return key;
  }

  public void setKey(int key) {
    this.key = key;
  }

  public String getTitle() {
    return title;
  }

  public void setTitle(String title) {
    this.title = title;
  }

  public String getDates() {
    return dates;
  }

  public void setDates(String dates) {
    this.dates = dates;
  }

  public String getTags() {
    return tags;
  }

  public void setTags(String tags) {
    this.tags = tags;
  }

  public String getCategory() {
    return category;
  }

  public void setCategory(String category) {
    this.category = category;
  }

  public int getView() {
    return view;
  }

  public void setView(int view) {
    this.view = view;
  }

  public int getComments() {
    return comments;
  }

  public void setComments(int comments) {
    this.comments = comments;
  }

  public int getCopyright() {
    return copyright;
  }

  public void setCopyright(int copyright) {
    this.copyright = copyright;
  }

  @Override
  public String toString() {
    return "CsdnBlog [key=" + key + ", title=" + title + ", content=" + content + ",dates=" + dates + ", tags=" + tags + ", category="
        + category + ", view=" + view + ", comments=" + comments + ", copyright=" + copyright + "]";
  }
}

启动类：

public class CsdnBlogPageProcessor implements PageProcessor {

  private static String username="CHENYUFENG1991"; // 设置csdn用户名

  private static int size = 0;// 共抓取到的文章数量

  // 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(3).setSleepTime(1000);

  public Site getSite() {
    return site;
  }

  // process是定制爬虫逻辑的核心接口，在这里编写抽取逻辑
  public void process(Page page) {
    // 列表页
    if (!page.getUrl().regex("http://blog\\.csdn\\.net/" + username + "/article/details/\\d+").match()) {
      // 添加所有文章页
      page.addTargetRequests(page.getHtml().xpath("//div[@id='article_list']").links()// 限定文章列表获取区域
          .regex("/" + username + "/article/details/\\d+")
          .replace("/" + username + "/", "http://blog.csdn.net/" + username + "/")// 巧用替换给把相对url转换成绝对url
          .all());
      // 添加其他列表页
      page.addTargetRequests(page.getHtml().xpath("//div[@id='papelist']").links()// 限定其他列表页获取区域
          .regex("/" + username + "/article/list/\\d+")
          .replace("/" + username + "/", "http://blog.csdn.net/" + username + "/")// 巧用替换给把相对url转换成绝对url
          .all());
      // 文章页
    } else {
      size++;// 文章数量加1
      // 用CsdnBlog类来存抓取到的数据，方便存入数据库
      CsdnBlog csdnBlog = new CsdnBlog();
      // 设置编号
      csdnBlog.setKey(Integer.parseInt(
          page.getUrl().regex("http://blog\\.csdn\\.net/" + username + "/article/details/(\\d+)").get()));
      // 设置标题
      csdnBlog.setTitle(
          page.getHtml().xpath("//div[@class='article_title']//span[@class='link_title']/a/text()").get());

      //设置内容
      csdnBlog.setContent(
          page.getHtml().xpath("//div[@class='article_content']/allText()").get());

      // 设置日期
      csdnBlog.setDates(
          page.getHtml().xpath("//div[@class='article_r']/span[@class='link_postdate']/text()").get());
      // 设置标签（可以有多个，用,来分割）
      csdnBlog.setTags(listToString(page.getHtml().xpath("//div[@class='article_l']/span[@class='link_categories']/a/allText()").all()));
      // 设置类别（可以有多个，用,来分割）
      csdnBlog.setCategory(listToString(page.getHtml().xpath("//div[@class='category_r']/label/span/text()").all()));
      // 设置阅读人数
      csdnBlog.setView(Integer.parseInt(page.getHtml().xpath("//div[@class='article_r']/span[@class='link_view']")
          .regex("(\\d+)人阅读").get()));
      // 设置评论人数
      csdnBlog.setComments(Integer.parseInt(page.getHtml()
          .xpath("//div[@class='article_r']/span[@class='link_comments']").regex("\\((\\d+)\\)").get()));
      // 设置是否原创
      csdnBlog.setCopyright(page.getHtml().regex("bog_copyright").match() ? 1 : 0);
      // 把对象存入数据库
      new CsdnBlogDao().add(csdnBlog);
      // 把对象输出控制台
      System.out.println(csdnBlog);
    }
  }

  // 把list转换为string，用,分割
  public static String listToString(List<String> stringList) {
    if (stringList == null) {
      return null;
    }
    StringBuilder result = new StringBuilder();
    boolean flag = false;
    for (String string : stringList) {
      if (flag) {
        result.append(",");
      } else {
        flag = true;
      }
      result.append(string);
    }
    return result.toString();
  }

  public static void main(String[] args) {
    long startTime, endTime;
    System.out.println("【爬虫开始】...");
    startTime = System.currentTimeMillis();
    // 从用户博客首页开始抓，开启5个线程，启动爬虫
    Spider.create(new CsdnBlogPageProcessor()).addUrl("http://blog.csdn.net/" + username).thread(5).run();
    endTime = System.currentTimeMillis();
    System.out.println("【爬虫结束】共抓取" + size + "篇文章，耗时约" + ((endTime - startTime) / 1000) + "秒，已保存到数据库，请查收！");
  }
}

使用mysql类型：

public class GamePageProcessor implements PageProcessor {

  private static final Logger logger = LoggerFactory.getLogger(GamePageProcessor.class);
  private static DianJingService d;
  private static BannerService bs;
  private static SportService ss;
  private static YuLeNewsService ys;

  private static UpdateService ud ;
  // 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(3).setSleepTime(1000);

  public Site getSite() {
    return site;
  }
  // process是定制爬虫逻辑的核心接口，在这里编写抽取逻辑
  public static void main(String[] args) {
    ConfigurableApplicationContext context= SpringApplication.run(GamePageProcessor.class, args);
     d = context.getBean(DianJingService.class);
    //Spider.create(new GamePageProcessor()).addUrl("网址").thread(5).run();
  }

  public void process(Page page) {
    Selectable url = page.getUrl();
    if (url.toString().equals("网址")) {
      DianJingVideo dv = new DianJingVideo();
      List<String> ls = page.getHtml().xpath("//div[@class='v']/div[@class='v-meta va']/div[@class='v-meta-title']/a/text()").all();
      //hrefs
      List<String> ls1 = page.getHtml().xpath("//div[@class='v']/div[@class='v-link']/a/@href").all();//获取a标签的href

      List<String> ls2 = page.getHtml().xpath("//div[@class='v']/div[@class='v-meta va']/div[@class='v-meta-entry']/div[@class='v-meta-data']/span[@class='r']/text()").all();
      //photo
      List<String> ls3 = page.getHtml().xpath("//div[@class='v']/div[@class='v-thumb']/img/@src").all();

      for (int i = 0; i < 5; i++) {
        dv.setTitles(ls.get(i));
        dv.setCategory("");
        dv.setDates(ls2.get(i));
        dv.setHrefs(ls1.get(i));
        dv.setPhoto(ls3.get(i));
        dv.setSources("");

        d.addVideo(dv);

      }
    }
}

Controller：

@Controller
@RequestMapping(value = "/dianjing")
public class DianJingController {
  @Autowired
  private DianJingService s;

    /*
    手游
     */
  @RequestMapping("/dianjing")
  @ResponseBody
  public Object dianjing(){
    List<DianJing> list = s.find2();
    JSONObject jo = new JSONObject();
    if(list!=null){

      jo.put("code",0);
      jo.put("success",true);
      jo.put("count",list.size());
      jo.put("list",list);
    }
    return jo;
  }
}

实体类就不展示了

dao层

@Insert("insert into dianjing (titles,dates,category,hrefs,photo,sources) values(#{titles},#{dates},#{category},#{hrefs},#{photo},#{sources})")
int adddj(DianJing dj);

以上这篇springboot+webmagic实现java爬虫jdbc及mysql的方法就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持我们。