JAVA 爬取京东评论和图片

编程语言 2019-04-08 15:10:51 阅读次数: 0

pom.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>

  <groupId>com.spider</groupId>
  <artifactId>spider</artifactId>
  <version>1.0-SNAPSHOT</version>

  <name>spider</name>
  <!-- FIXME change it to the project's website -->
  <url>http://www.example.com</url>
  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <maven.compiler.source>1.7</maven.compiler.source>
    <maven.compiler.target>1.7</maven.compiler.target>
  </properties>

  <dependencies>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>4.11</version>
      <scope>test</scope>
    </dependency>
    <dependency>
      <groupId>org.apache.httpcomponents</groupId>
      <artifactId>httpclient</artifactId>
      <version>4.5.2</version>
    </dependency>
    <dependency>
      <groupId>org.jsoup</groupId>
      <artifactId>jsoup</artifactId>
      <version>1.7.3</version>
    </dependency>
    <dependency>
      <groupId>org.junit.jupiter</groupId>
      <artifactId>junit-jupiter-api</artifactId>
      <version>5.0.3</version>
      <scope>compile</scope>
    </dependency>
    <!-- https://mvnrepository.com/artifact/net.sf.json-lib/json-lib -->
    <dependency>
      <groupId>net.sf.json-lib</groupId>
      <artifactId>json-lib</artifactId>
      <version>2.4</version>
    </dependency>
    <!-- https://mvnrepository.com/artifact/com.google.code.gson/gson -->
    <dependency>
      <groupId>com.google.code.gson</groupId>
      <artifactId>gson</artifactId>
      <version>2.8.0</version>
    </dependency>
    <dependency>
      <groupId>com.alibaba</groupId>
      <artifactId>fastjson</artifactId>
      <version>1.2.53</version>
    </dependency>

    <dependency>
      <groupId>com.spider</groupId>
      <artifactId>spider</artifactId>
      <version>1.0-SNAPSHOT</version>
    </dependency>


  </dependencies>

  <build>
    <pluginManagement><!-- lock down plugins versions to avoid using Maven defaults (may be moved to parent pom) -->
      <plugins>
        <plugin>
          <artifactId>maven-clean-plugin</artifactId>
          <version>3.0.0</version>
        </plugin>
        <!-- see http://maven.apache.org/ref/current/maven-core/default-bindings.html#Plugin_bindings_for_jar_packaging -->
        <plugin>
          <artifactId>maven-resources-plugin</artifactId>
          <version>3.0.2</version>
        </plugin>
        <plugin>
          <artifactId>maven-compiler-plugin</artifactId>
          <version>3.7.0</version>
        </plugin>
        <plugin>
          <artifactId>maven-surefire-plugin</artifactId>
          <version>2.20.1</version>
        </plugin>
        <plugin>
          <artifactId>maven-jar-plugin</artifactId>
          <version>3.0.2</version>
        </plugin>
        <plugin>
          <artifactId>maven-install-plugin</artifactId>
          <version>2.5.2</version>
        </plugin>
        <plugin>
          <artifactId>maven-deploy-plugin</artifactId>
          <version>2.8.2</version>
        </plugin>
      </plugins>
    </pluginManagement>
    <plugins>
      <plugin>
        <groupId>org.apache.maven.plugins</groupId>
        <artifactId>maven-compiler-plugin</artifactId>
        <configuration>
          <source>6</source>
          <target>6</target>
        </configuration>
      </plugin>
    </plugins>
  </build>
</project>

代码：

package com.spider;
import com.alibaba.fastjson.JSON;
import com.alibaba.fastjson.JSONArray;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;
import java.io.*;
import java.net.URL;
import java.util.Date;
/**
 * @author 赵鑫
 * @Time: 2018/7/14
 * @Email:[email protected]
 */
public class JD {
    public static void main(String[] args) throws Exception{
        for (int i=0;i<3;i++){
        BufferedWriter bw1=new BufferedWriter(new FileWriter("spider/comment/第"+(i+1)+"页评论内容"+".txt"));
        BufferedWriter bw2=new BufferedWriter(new FileWriter("第"+(i+1)+"页评论图片连接"+".txt"));
//     1.用Jsoup解析网页
        String url="https://sclub.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98vv73104&productId=7437788&score=0&sortType=5&page="+i+"&pageSize=10&isShadowSku=0&fold=1";
        CloseableHttpResponse indexRes = sendGet(url);
//        获取json内容，将其转换为字符串
        String indexHtml = EntityUtils.toString(indexRes.getEntity(), "UTF-8");
//        截取成json字符串
        String json2=indexHtml.substring(indexHtml.indexOf('(')+1,indexHtml.lastIndexOf(')'));
//        获取评论
        JSONArray array = JSON.parseObject(json2).getJSONArray("comments");
        for (Object item : array) {
            //获取评论中的内容
            System.out.println(JSON.parseObject(item.toString()).getString("content"));
            bw1.write(JSON.parseObject(item.toString()).getString("content"));
            JSONArray array1 = JSON.parseObject(item.toString()).getJSONArray("images");
            System.out.println(array1.size());
            for (Object item1 : array1) {
                String s=JSON.parseObject(item1.toString()).getString("imgUrl");
                System.out.println(s);
                Download("http:"+s);
                bw2.write(JSON.parseObject(item1.toString()).getString("imgUrl")+"\n");
            }
        }
        bw1.close();
        bw2.close();
        }
    }
    //发送get请求,获取响应结果
    public static CloseableHttpResponse sendGet(String url) throws IOException {
        //创建httpClient客户端
        CloseableHttpClient httpClient = HttpClients.createDefault();
        //创建请求对象,发送请求
        HttpGet httpGet = new HttpGet(url);
        httpGet.setHeader("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.92 Safari/537.36");
        httpGet.setHeader("Cookie", "__jdu=1011906297; shshshfpa=546abe25-2650-27ef-387c-cbbd473fdf61-1541645859; shshshfpb=010d34f55e5d106e8262dc1639c7243399901f2c0392299fd5be3a6228; ipLoc-djd=1-72-2799-0; unpl=V2_ZzNtbUBTFkV9XxUDLEkMA2IGQVpLBBRAd19ABi4QWgIwVkZZclRCFXwURlRnGloUZAEZWUVcQBRFCEdkexhdBGYBGlhLVXNILGYFAX5SCQBXMxFdcl9zFXQIRlx6Hl8NYTMiWnJnHk0qUh8EI1wMW1cFFlhBV0YUfQh2VUsYbE4JAl9dQ1dDHXQPRVx9KV01ZA%3d%3d; __jda=122270672.1011906297.1537011991.1543032744.1543334183.4; __jdc=122270672; __jdv=122270672|www.linkhaitao.com|t_1000039483_lh_rd4zd4|tuiguang|35da9fbffaa744b68bfd3f7cd876fde5|1543334183097; PCSYCityID=412; _gcl_au=1.1.1618589019.1543334587; wlfstk_smdl=kpyxn7dgfu7ntzeriqf1nuoyf1pvmmz6; _pst=%E9%AD%82%E5%AF%84%E6%A2%A6%E4%B9%A1; logintype=wx; unick=%E9%AD%82%E5%AF%84%E6%A2%A6%E4%B9%A1; pin=%E9%AD%82%E5%AF%84%E6%A2%A6%E4%B9%A1; npin=%E9%AD%82%E5%AF%84%E6%A2%A6%E4%B9%A1; _tp=Zj9a6fHTft48nybOFAAH4sbL2FOhPiV6ww52%2BkgoNl8MBXdBGCUdKuMfROuV8QHU; pinId=KCcQw4HqqMKLC3rBXJmYjQ; 3AB9D23F7A4B3C9B=GPGP3C2BU4NAMC7CA2PZAKXKNW6757AO6KM6ENFTRAQ47S4RFIN3BMNNUQ2B3CUWAEQKVQEI5GA7Z245JTB2BIDIBU; mt_xid=V2_52007VwMTUl1QU10cQR9sB2NQRwVbUAJGSkkcCBliBBdXQVECWB9VS19SblEUWlkMB1tKeRpdBW4fElJBW1tLHkgSXAxsBhBiX2hSahxMHFoMZQYSV21YV1wY; shshshfp=cc874848aa1eb0d35dfd56e0e4ba0fb3; JSESSIONID=3AD0CE01D03F107D0B4F45BED45F806D.s1; shshshsID=52730810bd55258389660fdba736586f_15_1543337522651; __jdb=122270672.17.1011906297|4.1543334183; thor=__jdu=1011906297; shshshfpa=546abe25-2650-27ef-387c-cbbd473fdf61-1541645859; shshshfpb=010d34f55e5d106e8262dc1639c7243399901f2c0392299fd5be3a6228; ipLoc-djd=1-72-2799-0; PCSYCityID=412; _pst=%E9%AD%82%E5%AF%84%E6%A2%A6%E4%B9%A1; unick=%E9%AD%82%E5%AF%84%E6%A2%A6%E4%B9%A1; pin=%E9%AD%82%E5%AF%84%E6%A2%A6%E4%B9%A1; _tp=Zj9a6fHTft48nybOFAAH4sbL2FOhPiV6ww52%2BkgoNl8MBXdBGCUdKuMfROuV8QHU; jwotest_product=99; unpl=V2_ZzNtbRVUQBAmD0EGexlVBmJQQlsSBEQUcQxCXHxKXVFnBEFZclRCFXwURlRnGlQUZwEZXkJcRhJFCEdkexhdBGYBGlhLVXNILGYFAX1BDFlXMxFdcl9zFXQIRlx6Hl8NYTMiWnJnHk0qUh8EI1wMW1cFFlhBV0YUfQh2VUsYbE4JAl9dQ1dDHXQPRVx9KV01ZA%3d%3d; __jda=122270672.1011906297.1537011991.1543342650.1543440108.7; __jdc=122270672; thor=EBE4F58722D3C53DD96909AC59EFA6D1BC94658FBAC118C866693EA1EBF5169985038D47FF0615A96C39E195C704E4269C0AE2B142F2A6CF58BFF0E3C588B282CFE4B6DB95B893DBB7528C8A117BF09C2BB8B1A6955DEA1B2D00A191464B5CC90B094977CD8D55F54EAE17D856F65E1A4577319BD2627227472617F7462C4E24; pinId=KCcQw4HqqMKLC3rBXJmYjQ; __jdv=122270672|www.linkhaitao.com|t_1000039483_lh_rd7iam|tuiguang|f224b66c11824ba7ab6055596b0e16b5|1543440132756; 3AB9D23F7A4B3C9B=GPGP3C2BU4NAMC7CA2PZAKXKNW6757AO6KM6ENFTRAQ47S4RFIN3BMNNUQ2B3CUWAEQKVQEI5GA7Z245JTB2BIDIBU; mt_xid=V2_52007VwMTUl1QU10cQR9sUWJRElFbDAFGHkgRXRliAxMCQVFSXEtVGl8GYFYbWloIUwkceRpdBW4fElJBW1pLH0sSXwZsABRiX2hSahxMHFoMZQYSV21YV1wY; shshshfp=cc874848aa1eb0d35dfd56e0e4ba0fb3; _gcl_au=1.1.816281936.1543440149; shshshsID=d687c8924c94ae61b9d19c6054056eef_4_1543440174304; __jdb=122270672.7.1011906297|7.1543440108");
        httpGet.setHeader("Connection", "keep-alive");
        CloseableHttpResponse response = httpClient.execute(httpGet);
        return response;
    }
    //下载图片
    private static void Download(String listImgSrc) throws Exception {
        try {
            String url=listImgSrc;
            String imageName = url.substring(url.lastIndexOf("/") + 1, url.length());
            URL uri = new URL(url);
            InputStream in = uri.openStream();
            FileOutputStream fo = new FileOutputStream(new File("spider/img/"+imageName));//文件输出流
            byte[] buf = new byte[1024];
            int length = 0;
            System.out.println("开始下载:" + url);
            while ((length = in.read(buf, 0, buf.length)) != -1) {
                fo.write(buf, 0, length);
            }
            in.close();
            fo.close();
            System.out.println(imageName + "下载完成");
            Date overdate = new Date();
        } catch (Exception e) {
            System.out.println("下载失败");
        }
    }
}

猜你喜欢

转载自blog.csdn.net/qq_37668945/article/details/84640903
今日推荐
火速冲上 GitHub 热榜 —— 开源编程语言、框架哪有这么可爱？
北京人形机器人创新中心发布全球首个纯电驱拟人奔跑的全尺寸人形机器人“天工”
LFOSSA 源来如此公开课 | 掌握云原生未来：CNCF 认证全面攻略与备考秘籍
国产云输入法——仅华为无云端数据上传安全问题
开源日报 | 工业开源项目OGG 1.0；姐姐，你要和我一起配置火狐吗；苹果AI遥遥落后？Fedora 40
开放签电子签章：停止新增，优化体验，前进更进（五一假期前工作）
开源日报 | 中学生开源前端动画引擎；全球首个Llama3 8B中文版开源模型；联想电脑恐出局；Linus讽刺AI炒作
周排行
浏览器对同一域名进行请求的最大并发连接数
React Hook之自定义Hook
【转】MyBatis缓存机制
-Java-泛型
自动化测试常用脚本-发送邮件
LeetCode#859: Buddy Strings
java、Python处理字符串
第二篇の博客
Hadoop伪分布式环境安装
SQL Server进阶（十一）临时表、表变量
每日归档
更多
2024-04-27(56)
2024-04-26(39)
2024-04-25(22)
2024-04-24(36)
2024-04-23(26)
2024-04-22(39)
2024-04-21(0)
2024-04-20(6)
2024-04-19(5)
2024-04-18(0)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022