编程语言
首页 > 编程语言> > JAVA 获取cnblogs新闻标题

JAVA 获取cnblogs新闻标题

作者:互联网

package com.powerX;

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

import java.io.*;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;

public class Main {

    public static void main(String[] args) {
        for (int i = 1; i < 101; i++) {
            String html = doGet("https://news.cnblogs.com/n/page/" + i);
            Elements elements = Jsoup.parse(html).getElementsByClass("news_block");
            for (Element element : elements){
                Element content = element.getElementsByClass("content").get(0);
                Element entity = content.getElementsByClass("news_entry").get(0).getElementsByTag("a").get(0);
                Element entity2 = content.getElementsByClass("entry_footer").get(0);
                System.out.println(Jsoup.parse(entity2.html().split("发布于")[1]).body().getElementsByTag("span").get(0).html() + '\t' + entity.html());
            }
        }
    }

    public static String doGet(String httpurl) {
        HttpURLConnection connection = null;
        InputStream is = null;
        BufferedReader br = null;
        String result = null;// 返回结果字符串
        try {
            // 创建远程url连接对象
            URL url = new URL(httpurl);
            // 通过远程url连接对象打开一个连接,强转成httpURLConnection类
            connection = (HttpURLConnection) url.openConnection();
            // 设置连接方式:get
            connection.setRequestMethod("GET");
            // 设置连接主机服务器的超时时间:15000毫秒
            connection.setConnectTimeout(15000);
            // 设置读取远程返回的数据时间:60000毫秒
            connection.setReadTimeout(60000);
            // 发送请求
            connection.connect();
            // 通过connection连接,获取输入流
            if (connection.getResponseCode() == 200) {
                is = connection.getInputStream();
                // 封装输入流is,并指定字符集
                br = new BufferedReader(new InputStreamReader(is, "UTF-8"));
                // 存放数据
                StringBuffer sbf = new StringBuffer();
                String temp = null;
                while ((temp = br.readLine()) != null) {
                    sbf.append(temp);
                    sbf.append("\r\n");
                }
                result = sbf.toString();
            }
        } catch (MalformedURLException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            // 关闭资源
            if (null != br) {
                try {
                    br.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }

            if (null != is) {
                try {
                    is.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }

            connection.disconnect();// 关闭远程连接
        }

        return result;
    }

    public static String doPost(String httpUrl, String param) {

        HttpURLConnection connection = null;
        InputStream is = null;
        OutputStream os = null;
        BufferedReader br = null;
        String result = null;
        try {
            URL url = new URL(httpUrl);
            // 通过远程url连接对象打开连接
            connection = (HttpURLConnection) url.openConnection();
            // 设置连接请求方式
            connection.setRequestMethod("POST");
            // 设置连接主机服务器超时时间:15000毫秒
            connection.setConnectTimeout(15000);
            // 设置读取主机服务器返回数据超时时间:60000毫秒
            connection.setReadTimeout(60000);

            // 默认值为:false,当向远程服务器传送数据/写数据时,需要设置为true
            connection.setDoOutput(true);
            // 默认值为:true,当前向远程服务读取数据时,设置为true,该参数可有可无
            connection.setDoInput(true);
            // 设置传入参数的格式:请求参数应该是 name1=value1&name2=value2 的形式。
            connection.setRequestProperty("Content-Type", "application/x-www-form-urlencoded");
            // 设置鉴权信息:Authorization: Bearer da3efcbf-0845-4fe3-8aba-ee040be542c0
            connection.setRequestProperty("Authorization", "Bearer da3efcbf-0845-4fe3-8aba-ee040be542c0");
            // 通过连接对象获取一个输出流
            os = connection.getOutputStream();
            // 通过输出流对象将参数写出去/传输出去,它是通过字节数组写出的
            os.write(param.getBytes());
            // 通过连接对象获取一个输入流,向远程读取
            if (connection.getResponseCode() == 200) {

                is = connection.getInputStream();
                // 对输入流对象进行包装:charset根据工作项目组的要求来设置
                br = new BufferedReader(new InputStreamReader(is, "UTF-8"));

                StringBuffer sbf = new StringBuffer();
                String temp = null;
                // 循环遍历一行一行读取数据
                while ((temp = br.readLine()) != null) {
                    sbf.append(temp);
                    sbf.append("\r\n");
                }
                result = sbf.toString();
            }
        } catch (MalformedURLException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            // 关闭资源
            if (null != br) {
                try {
                    br.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
            if (null != os) {
                try {
                    os.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
            if (null != is) {
                try {
                    is.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
            // 断开与远程地址url的连接
            connection.disconnect();
        }
        return result;
    }
}

需要引入包 jsoup

标签:JAVA,cnblogs,新闻标题,printStackTrace,connection,br,catch,null,String
来源: https://www.cnblogs.com/sunbingqiang/p/15966177.html