JAVA爬虫代码

• Z时代
• 2024-01-10
• 分类：综合

工程目录：

所需要的jar包为：   jsoup-1.10.2.jar

/**
 * Created by wangzheng on 2017/2/19.
 */
public class Article {
    /**
     * 文章链接的相对地址
     */
    private String address;
    /**
     * 文章标题
     */
    private String title;
    /**
     * 文章简介
     */
    private String desption;
    /**
     * 文章发表时间
     */
    private String time;
    public String getAddress() {
        return address;
    }
    public void setAddress(String address) {
        this.address = address;
    }
    public String getTitle() {
        return title;
    }
    public void setTitle(String title) {
        this.title = title;
    }
    public String getDesption() {
        return desption;
    }
    public void setDesption(String desption) {
        this.desption = desption;
    }
    public String getTime() {
        return time;
    }
    public void setTime(String time) {
        this.time = time;
    }
}

/**
 * Created by wangzheng on 2017/2/19.
 */
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import org.jsoup.Connection;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
public class First {
    // 需要进行爬取得博客首页
    // private static final String URL = "http://blog.csdn.net/guolin_blog";
    private static final String URL = "http://blog.csdn.net/qq_33599520/article/list/1";
    public static void main(String[] args) throws IOException {
        // 获取url地址的http链接Connection
        Connection conn = Jsoup.connect(URL)    // 博客首页的url地址
                .userAgent("Mozilla/5.0 (Windows NT 6.1; rv:47.0) Gecko/20100101 Firefox/47.0") // http请求的浏览器设置
                .timeout(5000)   // http连接时长
                .method(Connection.Method.GET);  // 请求类型是get请求，http请求还是post,delete等方式
        //获取页面的html文档
        Document doc = conn.get();
        Element body = doc.body();
        // 将爬取出来的文章封装到Artcle中，并放到ArrayList里面去
        List<Article> resultList = new ArrayList<Article>();
        Element articleListDiv = body.getElementById("article_list");
        Elements articleList = articleListDiv.getElementsByClass("list_item");
        for(Element article : articleList){
            Article articleEntity = new Article();
            Element linkNode = (article.select("div h1 a")).get(0);
            Element desptionNode = (article.getElementsByClass("article_description")).get(0);
            Element articleManageNode = (article.getElementsByClass("article_manage")).get(0);
            articleEntity.setAddress(linkNode.attr("href"));
            articleEntity.setTitle(linkNode.text());
            articleEntity.setDesption(desptionNode.text());
            articleEntity.setTime(articleManageNode.select("span:eq(0").text());
            resultList.add(articleEntity);
        }
        // 遍历输出ArrayList里面的爬取到的文章
        System.out.println("文章总数:" + resultList.size());
        for(Article article : resultList) {
            System.out.println("文章绝对路劲地址:http://blog.csdn.net" + article.getAddress());
        }
    }
}

/**
 * Created by wangzheng on 2017/2/19.
 */
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import org.jsoup.*;
import org.jsoup.nodes.*;
import org.jsoup.select.*;
public class Main {
    private static final String URL = "http://blog.csdn.net/qq_33599520";
    public static void main(String[] args) throws IOException {
        Connection conn = Jsoup.connect(URL)
                .userAgent("Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:50.0) Gecko/20100101 Firefox/50.0")
                .timeout(5000)
                .method(Connection.Method.GET);
        Document doc = conn.get();
        Element body = doc.body();
        // 获取总页数
        String totalPageStr = body.getElementById("papelist").select("span:eq(0)").text();
        String regex = ".+共(\\d+)页";
        totalPageStr = totalPageStr.replaceAll(regex, "$1");
        int totalPage = Integer.parseInt(totalPageStr);
        int pageNow = 1;
        List<Article> articleList = new ArrayList<Article>();
        for(pageNow = 1; pageNow <= totalPage; pageNow++){
            articleList.addAll(getArtitcleByPage(pageNow));
        }
        // 遍历输出博主所有的文章
        for(Article article : articleList) {
            System.out.println("文章标题:" + article.getTitle());
            System.out.println("文章绝对路劲地址:http://blog.csdn.net" + article.getAddress());
            System.out.println("文章简介:" + article.getDesption());
            System.out.println("发表时间:" + article.getTime());
        }
    }
    public static List<Article> getArtitcleByPage(int pageNow) throws IOException{
        Connection conn = Jsoup.connect(URL + "/article/list/" + pageNow)
                .userAgent("Mozilla/5.0 (Windows NT 6.1; rv:47.0) Gecko/20100101 Firefox/47.")
                .timeout(5000)
                .method(Connection.Method.GET);
        Document doc = conn.get();
        Element body = doc.body();
        List<Article> resultList = new ArrayList<Article>();
        Element articleListDiv = body.getElementById("article_list");
        Elements articleList = articleListDiv.getElementsByClass("list_item");
        for(Element article : articleList){
            Article articleEntity = new Article();
            Element linkNode = (article.select("div h1 a")).get(0);
            Element desptionNode = (article.getElementsByClass("article_description")).get(0);
            Element articleManageNode = (article.getElementsByClass("article_manage")).get(0);
            articleEntity.setAddress(linkNode.attr("href"));
            articleEntity.setTitle(linkNode.text());
            articleEntity.setDesption(desptionNode.text());
            articleEntity.setTime(articleManageNode.select("span:eq(0").text());
            resultList.add(articleEntity);
        }
        return resultList;
    }
}

以上是 JAVA爬虫代码 的全部内容， 来源链接： utcz.com/z/394489.html