• JAVA爬虫系列

    目录

    准备工作

    yml

    1.入门程序（获取到静态页面）

    2.HttpClient---Get

    2.1 修改成连接池

    3.HttpClient---Get带参数

    3.1 修改成连接池

    4.HttpClient---Post

    4.1 修改成连接池

    5.HttpClient---Post带参数

    6.HttpClient-连接池

    7.设置请求信息

    8.jsoup介绍.

    9.jsoup解析url

    10.jsoup解析字符串

    11.jsoup解析文件

    12.所有dom方式获取元素

    13.元素中获取数据

    准备工作

    导入依赖

    1.  <dependency>
    2.             <groupId>org.apache.httpcomponentsgroupId>
    3.             <artifactId>httpclientartifactId>
    4.             <version>4.5.2version>
    5.         dependency>

    yml

    1. logging:
    2.   level:
    3.     root: info
    4.     com.lrm: debug

    1.入门程序（获取到静态页面）

    1. package com.itheima.reggie.utils;
    2.  
    3.  
    4. import org.apache.http.HttpEntity;
    5. import org.apache.http.client.methods.CloseableHttpResponse;
    6. import org.apache.http.client.methods.HttpGet;
    7. import org.apache.http.impl.client.CloseableHttpClient;
    8. import org.apache.http.impl.client.HttpClients;
    9. import org.apache.http.util.EntityUtils;
    10.  
    11. import java.io.IOException;
    12.  
    13. /**
    14.  * @Author lpc
    15.  **/
    16. public class CrawlerFirst {
    17.     public static void main(String[] args) throws Exception {
    18.  
    19.         //1.打开浏览器,创建Httpclient对象
    20.         CloseableHttpClient httpClient = HttpClients.createDefault();
    21.  
    22.        //2.输入网址,发起get请求创建HttpGet对象
    23.         HttpGet httpGet = new HttpGet("https://www.itcast.cn/");
    24.  
    25.         //3.按回车,发起请求,返回响应,使用Httpclient对象发起请求
    26.         CloseableHttpResponse response = httpClient.execute(httpGet);
    27.         //4.解析响应,获取数据
    28.         //判斯状态码是否是200
    29.         if (response.getStatusLine().getStatusCode()==200){
    30.             HttpEntity httpEntity = response.getEntity();
    31.             //获取前端静态页面
    32.             String content = EntityUtils.toString(httpEntity,"utf8");
    33.             System.out.println(content);
    34.         }
    35.  
    36.  
    37.     }
    38. }

    2.HttpClient---Get

    1. package com.itheima.reggie.utils;
    2.  
    3.  
    4. import org.apache.http.HttpEntity;
    5. import org.apache.http.client.methods.CloseableHttpResponse;
    6. import org.apache.http.client.methods.HttpGet;
    7. import org.apache.http.impl.client.CloseableHttpClient;
    8. import org.apache.http.impl.client.HttpClients;
    9. import org.apache.http.util.EntityUtils;
    10.  
    11. import java.io.IOException;
    12.  
    13. /**
    14.  * @Author lpc
    15.  * @Date 2024 03 12 00 23
    16.  **/
    17. public class CrawlerFirst {
    18.     public static void main(String[] args){
    19.  
    20.         //1.打开浏览器,创建Httpclient对象
    21.         CloseableHttpClient httpClient = HttpClients.createDefault();
    22.  
    23.        //2.输入网址,发起get请求创建HttpGet对象
    24.         HttpGet httpGet = new HttpGet("https://www.itcast.cn/");
    25.  
    26.         //3.按回车,发起请求,返回响应,使用Httpclient对象发起请求
    27.         CloseableHttpResponse response = null;
    28.  
    29.         try {
    30.             response = httpClient.execute(httpGet);
    31.             //4.解析响应,获取数据
    32.             //判斯状态码是否是200
    33.             if (response.getStatusLine().getStatusCode()==200){
    34.                 HttpEntity httpEntity = response.getEntity();
    35.                 //获取前端静态页面
    36.                 String content = EntityUtils.toString(httpEntity,"utf8");
    37.                 System.out.println(content.length());
    38.             }
    39.         } catch (IOException e) {
    40.             throw new RuntimeException(e);
    41.         }finally {
    42.             try {
    43.                 //关闭response
    44.                 response.close();
    45.             } catch (IOException e) {
    46.                 throw new RuntimeException(e);
    47.             }
    48.             try {
    49.                 //关闭浏览器
    50.                 httpClient.close();
    51.             } catch (IOException e) {
    52.                 throw new RuntimeException(e);
    53.             }
    54.         }
    55.  
    56.  
    57.     }
    58. }

    2.1 修改成连接池

    1. package org.example;
    2.  
    3. import org.apache.http.client.methods.CloseableHttpResponse;
    4. import org.apache.http.client.methods.HttpGet;
    5. import org.apache.http.impl.client.CloseableHttpClient;
    6. import org.apache.http.impl.client.HttpClients;
    7. import org.apache.http.impl.conn.PoolingHttpClientConnectionManager;
    8. import org.apache.http.util.EntityUtils;
    9.  
    10. import java.io.IOException;
    11.  
    12. /**
    13.  * @Author lpc
    14.  * @Date 2024 03 14 09 38
    15.  **/
    16. public class Test {
    17.  
    18.     public static void main(String[] args) {
    19.         //创建连接池
    20.         PoolingHttpClientConnectionManager cm = new PoolingHttpClientConnectionManager();
    21.         //设置最大连接数
    22.         cm.setMaxTotal(100);
    23.         //设置每个主机的最大连接数
    24.         cm.setDefaultMaxPerRoute(10);
    25.         //使用连接池管理器发起请求
    26.         doGet(cm);
    27.     }
    28.  
    29.     public static void doGet(PoolingHttpClientConnectionManager cm){
    30.         //不是每次创建新的httpClient,而是从连接池中获取HttpClient对象
    31.         CloseableHttpClient httpClient = HttpClients.custom().setConnectionManager(cm).build();
    32.         HttpGet httpGet = new HttpGet("http://www.itcast.cn");
    33.         CloseableHttpResponse response=null;
    34.         try {
    35.            response = httpClient.execute(httpGet);
    36.            if (response.getStatusLine().getStatusCode()==200){
    37.                String content = EntityUtils.toString(response.getEntity(), "utf8");
    38.                System.out.println(content.length());
    39.            }
    40.         } catch (IOException e) {
    41.             throw new RuntimeException(e);
    42.         }finally {
    43.            if (response!=null){
    44.                try {
    45.                    response.close();
    46.                } catch (IOException e) {
    47.                    throw new RuntimeException(e);
    48.                }
    49.                //不能关闭，由连接池管理
    50.              //  httpClient.close();
    51.            }
    52.         }
    53.  
    54.     }
    55. }

    3.HttpClient---Get带参数

    1. package org.example;
    2.  
    3. import org.apache.http.HttpEntity;
    4. import org.apache.http.client.methods.CloseableHttpResponse;
    5. import org.apache.http.client.methods.HttpGet;
    6. import org.apache.http.client.utils.URIBuilder;
    7. import org.apache.http.impl.client.CloseableHttpClient;
    8. import org.apache.http.impl.client.HttpClients;
    9. import org.apache.http.util.EntityUtils;
    10.  
    11. import java.io.IOException;
    12. import java.net.URISyntaxException;
    13.  
    14. /**
    15.  * @Author lpc
    16.  * @Date 2024 03 13 20 44
    17.  **/
    18. public class Test2 {
    19.     public static void main(String[] args) throws Exception {
    20.  
    21.         //1.打开浏览器
    22.         CloseableHttpClient httpClient = HttpClients.createDefault();
    23.         //设置请求地址是： http://yun.itheima.com/search?keys=Java
    24.         //带参数的get方法设置
    25.         //创建URIBuilder
    26.         URIBuilder uriBuilder = new URIBuilder("http://yun.itheima.com/search");
    27.         //设置参数  可以设置多个
    28.         uriBuilder.setParameter("keys","Java");
    29.  
    30.         //2.输入网址，发起get请求创建HttpGet对象
    31.         HttpGet httpGet = new HttpGet(uriBuilder.build());
    32.         System.out.println("发起请求的信息"+httpGet);
    33.         //3.
    34.         CloseableHttpResponse response=null;
    35.         try {
    36.             response = httpClient.execute(httpGet);
    37.             if (response.getStatusLine().getStatusCode()==200){
    38.                 HttpEntity httpEntity = response.getEntity();
    39.                 //
    40.                 String s = EntityUtils.toString(httpEntity, "utf8");
    41.                 System.out.println(s);
    42.             }
    43.         } catch (IOException e) {
    44.             throw new RuntimeException(e);
    45.         }finally {
    46.             try {
    47.                 response.close();
    48.             } catch (IOException e) {
    49.                 throw new RuntimeException(e);
    50.             }
    51.             try {
    52.                 httpClient.close();
    53.             } catch (IOException e) {
    54.                 throw new RuntimeException(e);
    55.             }
    56.         }
    57.     }
    58. }

    3.1 修改成连接池

    4.HttpClient---Post

    1. package org.example;
    2.  
    3. import org.apache.http.HttpEntity;
    4. import org.apache.http.client.methods.CloseableHttpResponse;
    5. import org.apache.http.client.methods.HttpGet;
    6. import org.apache.http.client.methods.HttpPost;
    7. import org.apache.http.client.utils.URIBuilder;
    8. import org.apache.http.impl.client.CloseableHttpClient;
    9. import org.apache.http.impl.client.HttpClients;
    10. import org.apache.http.util.EntityUtils;
    11.  
    12. import java.io.IOException;
    13.  
    14. /**
    15.  * @Author lpc
    16.  * @Date 2024 03 13 20 59
    17.  **/
    18. public class Post {
    19.     public static void main(String[] args) {
    20.  
    21.         //1.打开浏览器
    22.         CloseableHttpClient httpClient = HttpClients.createDefault();
    23.         //2.输入网址，发起get请求创建HttpGet对象
    24.         //HttpGet httpGet = new HttpGet("https://www.itcast.cn/");
    25.         HttpPost httpPost = new HttpPost("https://www.itcast.cn/");
    26.         //3.
    27.         CloseableHttpResponse response=null;
    28.         try {
    29.            // response = httpClient.execute(httpGet);
    30.             response = httpClient.execute(httpPost);
    31.             if (response.getStatusLine().getStatusCode()==200){
    32.                 HttpEntity httpEntity = response.getEntity();
    33.                 //
    34.                 String s = EntityUtils.toString(httpEntity, "utf8");
    35.                 System.out.println(s);
    36.             }
    37.         } catch (IOException e) {
    38.             throw new RuntimeException(e);
    39.         }finally {
    40.             try {
    41.                 response.close();
    42.             } catch (IOException e) {
    43.                 throw new RuntimeException(e);
    44.             }
    45.             try {
    46.                 httpClient.close();
    47.             } catch (IOException e) {
    48.                 throw new RuntimeException(e);
    49.             }
    50.         }
    51.     }
    52. }

    4.1 修改成连接池

    1. package org.example;
    2.  
    3. import org.apache.http.client.methods.CloseableHttpResponse;
    4. import org.apache.http.client.methods.HttpPost;
    5. import org.apache.http.impl.client.CloseableHttpClient;
    6. import org.apache.http.impl.client.HttpClients;
    7. import org.apache.http.impl.conn.PoolingHttpClientConnectionManager;
    8. import org.apache.http.util.EntityUtils;
    9.  
    10. import java.io.IOException;
    11.  
    12. /**
    13.  * @Author lpc
    14.  * @Date 2024 03 14 10 02
    15.  **/
    16. public class Postl {
    17.     public static void main(String[] args){
    18.  
    19.         //创建连接池管理器
    20.         PoolingHttpClientConnectionManager cm = new PoolingHttpClientConnectionManager();
    21.         //设置最大连接数
    22.         cm.setMaxTotal(100);
    23.         //设置每个主机最大连接数
    24.         cm.setDefaultMaxPerRoute(10);
    25.         //发起请求
    26.         doPost(cm);
    27.     }
    28.  
    29.     private static void doPost(PoolingHttpClientConnectionManager cm) {
    30.         //不是每次创建新的httpClient,而是从连接池中获取HttpClient对象
    31.         CloseableHttpClient httpClient = HttpClients.custom().setConnectionManager(cm).build();
    32.         //2.输入网址 发起Post请求
    33.         HttpPost httpPost = new HttpPost("http://yun.itheima.com/search");
    34.         CloseableHttpResponse response=null;
    35.         try {
    36.             response = httpClient.execute(httpPost);
    37.             if (response.getStatusLine().getStatusCode()==200){
    38.                 String s = EntityUtils.toString(response.getEntity());
    39.                 System.out.println(s.length());
    40.             }
    41.         } catch (IOException e) {
    42.             throw new RuntimeException(e);
    43.         }finally {
    44.             if (response!=null){
    45.                 try {
    46.                     response.close();
    47.                 } catch (IOException e) {
    48.                     throw new RuntimeException(e);
    49.                 }
    50.  
    51.             }
    52.             //不用关闭，由连接池管理
    53.            // httpClient.close();
    54.         }
    55.     }
    56. }

    5.HttpClient---Post带参数

    1. package org.example;
    2.  
    3. import org.apache.http.HttpEntity;
    4. import org.apache.http.NameValuePair;
    5. import org.apache.http.client.entity.UrlEncodedFormEntity;
    6. import org.apache.http.client.methods.CloseableHttpResponse;
    7. import org.apache.http.client.methods.HttpGet;
    8. import org.apache.http.client.methods.HttpPost;
    9. import org.apache.http.client.utils.URIBuilder;
    10. import org.apache.http.impl.client.CloseableHttpClient;
    11. import org.apache.http.impl.client.HttpClients;
    12. import org.apache.http.message.BasicNameValuePair;
    13. import org.apache.http.util.EntityUtils;
    14.  
    15. import java.io.IOException;
    16. import java.io.UnsupportedEncodingException;
    17. import java.util.ArrayList;
    18. import java.util.List;
    19.  
    20. /**
    21.  * @Author lpc
    22.  * @Date 2024 03 13 20 59
    23.  **/
    24. public class Post {
    25.     public static void main(String[] args) throws Exception {
    26.  
    27.         //1.打开浏览器
    28.         CloseableHttpClient httpClient = HttpClients.createDefault();
    29.         //2.输入网址 发起Post请求
    30.         HttpPost httpPost = new HttpPost("http://yun.itheima.com/search");
    31.         //声明List集合，封装表单中的参数
    32.         List params =new ArrayList();
    33.         //设置请求地址是： http://yun.itheima.com/search?keys=Java
    34.         params.add(new BasicNameValuePair("keys","Java"));
    35.         //创建表单的Entity对象，第一个参数就是封装的表单数据，第二个参数就是编码
    36.         UrlEncodedFormEntity urlEncodedFormEntity = new UrlEncodedFormEntity(params,"utf8");
    37.  
    38.         //设置表单的Entity对象到Post请求中
    39.         httpPost.setEntity(urlEncodedFormEntity);
    40.  
    41.         CloseableHttpResponse response=null;
    42.         try {
    43.            // response = httpClient.execute(httpGet);
    44.             response = httpClient.execute(httpPost);
    45.             if (response.getStatusLine().getStatusCode()==200){
    46.                 HttpEntity httpEntity = response.getEntity();
    47.                 //
    48.                 String s = EntityUtils.toString(httpEntity, "utf8");
    49.                 System.out.println(s);
    50.             }
    51.         } catch (IOException e) {
    52.             throw new RuntimeException(e);
    53.         }finally {
    54.             try {
    55.                 response.close();
    56.             } catch (IOException e) {
    57.                 throw new RuntimeException(e);
    58.             }
    59.             try {
    60.                 httpClient.close();
    61.             } catch (IOException e) {
    62.                 throw new RuntimeException(e);
    63.             }
    64.         }
    65.     }
    66. }

    6.HttpClient-连接池

    如果每次请求都要创建HttpClient，会有频繁创建和销毁的问题，可以使用连接池来解决这个问题。·
    测试以下代码，并断点查看每次获取的HttpClient都是不一样的。。

    1. package org.example;
    2.  
    3. import org.apache.http.client.methods.CloseableHttpResponse;
    4. import org.apache.http.client.methods.HttpGet;
    5. import org.apache.http.impl.client.CloseableHttpClient;
    6. import org.apache.http.impl.client.HttpClients;
    7. import org.apache.http.impl.conn.PoolingHttpClientConnectionManager;
    8. import org.apache.http.util.EntityUtils;
    9.  
    10. import java.io.IOException;
    11.  
    12. /**
    13.  * @Author lpc
    14.  * @Date 2024 03 14 09 38
    15.  **/
    16. public class Test {
    17.  
    18.     public static void main(String[] args) {
    19.         //创建连接池
    20.         PoolingHttpClientConnectionManager cm = new PoolingHttpClientConnectionManager();
    21.         //设置最大连接数
    22.         cm.setMaxTotal(100);
    23.         //设置每个主机的最大连接数
    24.         cm.setDefaultMaxPerRoute(10);
    25.         //使用连接池管理器发起请求
    26.         doGet(cm);
    27.     }
    28.  
    29.     public static void doGet(PoolingHttpClientConnectionManager cm){
    30.         //不是每次创建新的httpClient,而是从连接池中获取HttpClient对象
    31.         CloseableHttpClient httpClient = HttpClients.custom().setConnectionManager(cm).build();
    32.         HttpGet httpGet = new HttpGet("http://www.itcast.cn");
    33.         CloseableHttpResponse response=null;
    34.         try {
    35.            response = httpClient.execute(httpGet);
    36.            if (response.getStatusLine().getStatusCode()==200){
    37.                String content = EntityUtils.toString(response.getEntity(), "utf8");
    38.                System.out.println(content.length());
    39.            }
    40.         } catch (IOException e) {
    41.             throw new RuntimeException(e);
    42.         }finally {
    43.            if (response!=null){
    44.                try {
    45.                    response.close();
    46.                } catch (IOException e) {
    47.                    throw new RuntimeException(e);
    48.                }
    49.                //不能关闭，由连接池管理
    50.              //  httpClient.close();
    51.            }
    52.         }
    53.  
    54.     }
    55. }

    7.设置请求信息
     

    1. package org.example;
    2.  
    3. import org.apache.http.client.config.RequestConfig;
    4. import org.apache.http.client.methods.CloseableHttpResponse;
    5. import org.apache.http.client.methods.HttpGet;
    6. import org.apache.http.impl.client.CloseableHttpClient;
    7. import org.apache.http.impl.client.HttpClients;
    8. import org.apache.http.impl.conn.PoolingHttpClientConnectionManager;
    9. import org.apache.http.util.EntityUtils;
    10.  
    11. import java.io.IOException;
    12.  
    13. /**
    14.  * @Author lpc
    15.  * @Date 2024 03 14 09 38
    16.  **/
    17. public class Test {
    18.  
    19.     public static void main(String[] args) {
    20.         //创建连接池
    21.         PoolingHttpClientConnectionManager cm = new PoolingHttpClientConnectionManager();
    22.         //设置最大连接数
    23.         cm.setMaxTotal(100);
    24.         //设置每个主机的最大连接数
    25.         cm.setDefaultMaxPerRoute(10);
    26.         //使用连接池管理器发起请求
    27.         doGet(cm);
    28.     }
    29.  
    30.     public static void doGet(PoolingHttpClientConnectionManager cm){
    31.         //不是每次创建新的httpClient,而是从连接池中获取HttpClient对象
    32.         CloseableHttpClient httpClient = HttpClients.custom().setConnectionManager(cm).build();
    33.         HttpGet httpGet = new HttpGet("http://www.itcast.cn");
    34.         //配置请求信息
    35.         RequestConfig config=RequestConfig.custom().setConnectTimeout(1000) //创建连接的最长时间，单位是毫秒
    36.                 .setConnectionRequestTimeout(500)//设置获取连接的最长时间
    37.                 .setSocketTimeout(10*1000)//设置数据传输的最长时间
    38.                 .build();
    39.         //给请求设置请求信息
    40.         httpGet.setConfig(config);
    41.         CloseableHttpResponse response=null;
    42.         try {
    43.            response = httpClient.execute(httpGet);
    44.            if (response.getStatusLine().getStatusCode()==200){
    45.                String content = EntityUtils.toString(response.getEntity(), "utf8");
    46.                System.out.println(content.length());
    47.            }
    48.         } catch (IOException e) {
    49.             throw new RuntimeException(e);
    50.         }finally {
    51.            if (response!=null){
    52.                try {
    53.                    response.close();
    54.                } catch (IOException e) {
    55.                    throw new RuntimeException(e);
    56.                }
    57.                //不能关闭，由连接池管理
    58.              //  httpClient.close();
    59.            }
    60.         }
    61.  
    62.     }
    63. }

    8.jsoup介绍.

    jsoup是一款Java 的 HTML解析器，可直接解析某个URL地址、HTML文木内容。它提供了一套非常省力的API，可通过DOM，CSS以及类似于jQuery的操作方法来取出和操作数据。.

    jsoup 的主要功能如下:

    1.从一个 URL，文件或字符串中解析HTML;

    2.使用DOM或CSS选择器来查找、取出数据;

    3.可操作HTML元素、属性、文本;·

    依赖

    2. <dependency>
    3.     <groupId>org.jsoupgroupId>
    4.     <artifactId>jsoupartifactId>
    5.     <version>1.13.1version>
    6. dependency>
    7.  
    8. <dependency>
    9.     <groupId>junitgroupId>
    10.     <artifactId>junitartifactId>
    11.     <version>4.12version>
    12.     <scope>testscope>
    13. dependency>
    14.  
    15.  
    17. <dependency>
    18.     <groupId>commons-iogroupId>
    19.     <artifactId>commons-ioartifactId>
    20.     <version>2.4version>
    21. dependency>
    22.  
    23.  
    25.                  <dependency>
    26.                      <groupId>org.apache.commonsgroupId>
    27.                      <artifactId>commons-lang3artifactId>
    28.                      <version>3.8.1version>
    29.                  dependency>

    9.jsoup解析url

    1. package jsoup;
    2.  
    3. import org.jsoup.Jsoup;
    4. import org.jsoup.nodes.Document;
    5. import org.jsoup.nodes.Element;
    6. import org.junit.Test;
    7.  
    8. import java.net.MalformedURLException;
    9. import java.net.URL;
    10.  
    11. /**
    12.  * @Author lpc
    13.  * @Date 2024 03 14 10 44
    14.  **/
    15. public class jsoupTestFirst {
    16.  
    17.     @Test
    18.     public void testJsoupUrl() throws Exception {
    19.         //解析URL地址
    20.         Document parse = Jsoup.parse(new URL("http://www.itcast.cn"), 10*1000);
    21.  
    22.         //获取title的内容
    23.         Element title = parse.getElementsByTag("title").first();
    24.         System.out.println(title.text());
    25.  
    26.     }
    27.  
    28.  
    29.  
    30. }

    10.jsoup解析字符串

    1. package jsoup;
    2.  
    3. import org.apache.commons.io.FileUtils;
    4. import org.jsoup.Jsoup;
    5. import org.jsoup.nodes.Document;
    6. import org.jsoup.nodes.Element;
    7. import org.junit.Test;
    8.  
    9. import java.io.File;
    10. import java.net.MalformedURLException;
    11. import java.net.URL;
    12.  
    13. /**
    14.  * @Author lpc
    15.  * @Date 2024 03 14 10 44
    16.  **/
    17. public class jsoupTestFirst {
    18.  
    19.     @Test
    20.     public void testString() throws Exception {
    21.         //使用工具读取文件，获取字符串
    22.         String file = FileUtils.readFileToString(new File("D:\\file.html"), "utf8");
    23.         //解析字符串
    24.         Document document = Jsoup.parse(file);
    25.         //获取title的内容
    26.        String title = document.getElementsByTag("title").first().text();
    27.         System.out.println(title);
    28.  
    29.     }
    30.  
    31.  
    32.  
    33. }

    11.jsoup解析文件

    1. @Test
    2.     public void testFile() throws Exception {
    3.         //解析文件
    4.         Document parse = Jsoup.parse(new File("D:\\file.html"), "utf8");
    5.         String title = parse.getElementsByTag("title").first().text();
    6.         System.out.println(title);
    7.  
    8.     }

    12.所有dom方式获取元素

    1.  @Test
    2.     public void testDom() throws Exception {
    3.         //解析文件,获取Document对象
    4.         Document parse = Jsoup.parse(new File("D:\\file.html"), "utf8");
    5.         //获取元素
    6.         //1.
    7.         //Element elementById = parse.getElementById("popupMenu");
    8.         //2.
    9.         //Element elementById=parse.getElementsByTag("span").first();
    10.         //3.
    11.        // Elements elementById = parse.getElementsByClass("city_nav");
    12.         //4.
    13.         Elements elementById=parse.getElementsByAttribute("abc");
    14.  
    15.         System.out.println(elementById.text());
    16.  
    17.     }

    13.元素中获取数据

    1.  @Test
    2.     public void testData() throws Exception {
    3.         //解析文件
    4.         Document parse = Jsoup.parse(new File("D:\\file.html"), "utf8");
    5.         //根据id获取元素
    6.         Element elementById = parse.getElementById("test");
    7.         System.out.println(elementById);
    8.         //1.从元素中获取id
    9.         String str1=elementById.id();
    10.         System.out.println(str1);
    11.         //2.从元素中获取className
    12.         String str2=elementById.className();
    13.         System.out.println(str2);
    14.         //3.从元素获取attr的值
    15.         String str3=elementById.attr("id");
    16.         System.out.println(str3);
    17.         //4。从元素中获取所有属性
    18.         Attributes attributes = elementById.attributes();
    19.         System.out.println(attributes);
    20.         //5.从元素中获取文本内容
    21.         String str4=elementById.text();
    22.         System.out.println(str4);
    23.  
    24.     }

  • 相关阅读:
    前端培训丁鹿学堂：vue3中setup语法糖特性写法总结
    java毕业设计游戏社区设计Mybatis+系统+数据库+调试部署
    数组累加和问题
    华为数通HCIA-地址分类及子网划分
    YOLOV7详细解读（一）网络架构解读
    在Springboot HandlerInterceptor中获取GET和POST请求参数
    算法基础实验OJ—树的遍历
    一站式元数据治理平台——Datahub
    如何禁止在堆上和栈上创建对象
    时空智友企业流程化管控系统任意文件上传漏洞复现【附POC】
  • 原文地址：https://blog.csdn.net/m0_59690068/article/details/136643758