httpClient爬虫

package httpClient.client;

import java.io.File;
import java.io.IOException;
import java.io.InputStream;
import java.util.UUID;

import org.apache.commons.io.FileUtils;
import org.apache.http.HttpEntity;
import org.apache.http.client.ClientProtocolException;
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 org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public class HttpClinet {

    public static void main(String[] args) throws ClientProtocolException, IOException {
        // 图片路径
        String url = "https://www.mzitu.com/";
        // 创建httpClient实例
        CloseableHttpClient httpClient = HttpClients.createDefault();
        HttpClinet t = new HttpClinet();
        HttpEntity httpEntity = t.getEntity(httpClient, url);
        String html = EntityUtils.toString(httpEntity, "UTF-8");
        Document document = Jsoup.parse(html);
        // 像js一样，通过标签获取title
        // System.out.println(document.getElementsByTag("title").first());
        // 像js一样，通过id 获取文章列表元素对象
        Element postList = document.getElementById("pins");
        // 像js一样，通过class 获取列表下的所有博客
        Elements postItems = postList.select("li a");
        // 循环处理每篇博客
        String s = "0";
        for (Element postItem : postItems) {
            String urls = postItem.attr("href").trim();
            if (!s.equals(urls)) {
                s = urls;
                HttpEntity httpEntitys = t.getEntity(httpClient, urls);
                String htmls = EntityUtils.toString(httpEntitys, "UTF-8");
                Document documents = Jsoup.parse(htmls);
                String postLists = documents.getElementsByClass("main-image").first().select("p a img").attr("src");
                if (postLists != null) {
                    System.out.println(postLists);
                    t.save(postLists, httpClient);
                }
            }
        }
        t.close(httpClient);
    }

    public void save(String url, CloseableHttpClient httpClient) throws ClientProtocolException, IOException {
        String fileName = url.substring(url.lastIndexOf("."), url.length());
        HttpEntity entity = this.getEntity(httpClient, url); // 获取返回实体
        if (entity != null) {
            System.out.println("Content-Type:" + entity.getContentType().getValue());
            InputStream inputStream = entity.getContent();
            // 文件复制，common io 包下，需要 引入依赖
            FileUtils.copyToFile(inputStream, new File(UUID.randomUUID() + fileName));
        }
    }

    public void close(CloseableHttpClient httpClient) throws IOException {
        if (httpClient != null) {
            httpClient.close();
        }
    }

    public HttpEntity getEntity(CloseableHttpClient httpClient, String url) throws ClientProtocolException, IOException {
        HttpGet httpGet = new HttpGet(url);
        httpGet.setHeader("If-None-Match", "W/\"5cc2cd8f-2c58");
        httpGet.setHeader("Referer", "http://www.mzitu.com/all/");
        httpGet.setHeader("User-Agent",
                "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36");
        CloseableHttpResponse response = httpClient.execute(httpGet);
        return response.getEntity();
    }
}

pom.xml

 

<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>httpClient</groupId>
  <artifactId>client</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  <packaging>jar</packaging>

  <name>client</name>
  <url>http://maven.apache.org</url>

  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
  </properties>

  <dependencies>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>3.8.1</version>
      <scope>test</scope>
    </dependency>
    
    <dependency>
    <groupId>org.apache.httpcomponents</groupId>
    <artifactId>httpclient</artifactId>
    <version>4.5.8</version>
</dependency>
<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.12.1</version>
</dependency>    
  <dependency>
        <groupId>commons-io</groupId>
        <artifactId>commons-io</artifactId>
        <version>2.5</version>
    </dependency>
  </dependencies>
</project>