几个 java 爬虫

package com.oa.test;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;

import java.io.*;
import java.net.URL;
import java.net.URLConnection;
import java.util.ArrayList;
import java.util.List;


public class Demo02 {
    public static void main(String[] args) throws IOException {
        System.out.println("开始");
        Demo02 d = new Demo02();
        String str = d.getHtml();

        System.out.println(str);
        d.readHtml(str);

        System.out.println("结束");
    }

    public String getHtml() throws IOException {
        StringBuffer buffer = new StringBuffer();
        String path = "http://www.dyhjw.com/dyhjw/etf.html";
        URL url = new URL(path);
        URLConnection conn = url.openConnection();
        //获取输入流
        InputStream in = conn.getInputStream();
        //字节流-》字符流 InputStreamReader
        InputStreamReader reader = new InputStreamReader(in, "utf-8");
        //包装流,可以按行读取
        BufferedReader breader = new BufferedReader(reader);
        //读
        String line = "";
        while ((line = breader.readLine()) != null) {
            buffer.append(line);
        }
        return buffer + "";
    }

    public List<Object[]> readHtml(String html) {
        //1. 使用Jsoup解析html -> Document对象
        Document document = Jsoup.parse(html);

        //2. 从Document中找到id=newlist_list_content_table的element
        //  Element div = document.getElementById("newlist_list_content_table");

        //3. 在id=newlist_list_content_table下找到所有class=newslist的elements
//          Elements tables =document.getElementsByClass("sx_table");
//          直接获取整个table的内容
//          System.out.println("tables="+tables);
        Elements trs = document.select("table").select("tr");
        System.out.println("===" + trs.size());
        List<Object[]> list = new ArrayList<Object[]>();
        File file = new File("d://黄金.txt");
        FileWriter fWriter = null;
        try {
            fWriter = new FileWriter(file);
            fWriter.append("日期（北京）\t净持仓量（盎司）\t净持仓量（吨）\t总价值（美元）\t总价值（美元）\t影响（金银）\t\n");

            for (int i = 1; i < trs.size(); i++) {
                Elements tds = trs.get(i).select("td");
                Object[] obj = {
                        tds.get(0).text(),
                        Double.parseDouble(tds.get(1).text()),
                        Double.parseDouble(tds.get(2).text()),
                        Double.parseDouble(tds.get(3).text()),
                        tds.get(4).text()
                };
                list.add(obj);
                for (int j = 0; j < tds.size(); j++) {
                    String txt = tds.get(j).text();
                    fWriter.append(txt + "\t\n");
                }
            }

        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            try {
                fWriter.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
        return list;
    }

}

另一个版本

package com.oa.test;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;

import java.io.*;
import java.net.URL;
import java.net.URLConnection;


public class Demo03 {
    public static void main(String[] args) throws IOException {
        System.out.println("开始");
        Demo03 d = new Demo03();
        String str = d.getHtml();
        d.readHtml(str);
        System.out.println("结束");
    }

    public String getHtml() throws IOException {
        StringBuffer buffer = new StringBuffer();
        String path = "http://www.dyhjw.com/dyhjw/etf.html";
        URL url = new URL(path);
        URLConnection conn = url.openConnection();
        //获取输入流
        InputStream in = conn.getInputStream();
        //字节流-》字符流 InputStreamReader
        InputStreamReader reader = new InputStreamReader(in, "utf-8");
        //包装流,可以按行读取
        BufferedReader breader = new BufferedReader(reader);
        //读
        String line;
        while ((line = breader.readLine()) != null) {
            buffer.append(line);
        }
        return buffer.toString();
    }

    public void readHtml(String html) throws IOException {
        //1. 使用Jsoup解析html -> Document对象
        Document document = Jsoup.parse(html);
        //2. 从Document中找到整个table的内容
        Elements trs = document.select("table").select("tr");
        //3. 创建文件存储爬取的数据
        File file = new File("d://黄金.txt");
        FileWriter fWriter = new FileWriter(file);
        fWriter.append("日期(美国)\t净持仓量(吨)\t总价值(美元)\t增减(吨)\t影响(金银)\r\n");
        //循环所有的表格行
        for (int i = 1; i < trs.size(); i++) {
            //获取当前行的所有单元格
            Elements tds = trs.get(i).select("td");
            for (int j = 0; j < tds.size(); j++) {
                String txt = tds.get(j).text();
                fWriter.append(txt + "\t");//\t分隔符
            }
            fWriter.append("\r\n");//添加换行符
        }
        fWriter.close();
    }
}

下载图片的爬虫

package com.oa.test;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;

import java.io.*;
import java.net.URL;
import java.net.URLConnection;
import java.util.UUID;


public class Demo04 {
    public static void main(String[] args) throws Exception {
        System.out.println("开始");
        Demo04 d = new Demo04();
        String str = d.getHtml();
        d.readHtml(str);
        System.out.println("结束");
    }

    public String getHtml() throws Exception {
        StringBuffer buffer = new StringBuffer();
        //https://huaban.com/boards/favorite/beauty/
        String path = "https://huaban.com/favorite/beauty/";
        URL url = new URL(path);
        URLConnection conn = url.openConnection();
        //获取输入流
        InputStream in = conn.getInputStream();
        //字节流-》字符流 InputStreamReader
        InputStreamReader reader = new InputStreamReader(in, "utf-8");
        //包装流,可以按行读取
        BufferedReader breader = new BufferedReader(reader);
        //读
        String line;
        while ((line = breader.readLine()) != null) {
            buffer.append(line);
        }
        return buffer.toString();
    }

    public void readHtml(String html) throws Exception {
        //1. 使用Jsoup解析html -> Document对象
        Document document = Jsoup.parse(html);
        //2. 从Document中找到整个table的内容

        /*
        Elements images = document.select("div[id=waterfall]").select("img[class=large]");
        for (int i=0; i<images.size(); i++){
            String src = images.get(i).attr("src");
            System.out.println(src);
            downloadImages("http:" + src);
        }
        */
        Elements elements = document.select("div[class=pin wfc]");
        for (int i=0; i<elements.size(); i++){
            String src=elements.get(i).select("a[class=img  x layer-view]").select("img").attr("src");
            System.out.println(src);
            if (src.length()>0) {
                downloadImages("http:" + src);
            }
        }
    }
    public void downloadImages(String src) throws Exception {
        System.out.println("=="+src);
        URL url = new URL(src);
        InputStream is = url.openStream();

        FileOutputStream fos = new FileOutputStream("D:\\images\\"+ UUID.randomUUID()+".png");
        byte buf[] = new byte[1024];
        int length = 0;
        while ((length=is.read(buf))!=-1){
            fos.write(buf,0,length);
        }
        fos.close();
        is.close();
    }
}

 

来源：https://blog.csdn.net/kongfanyu/article/details/102778837