网络爬虫准备1

最新推荐文章于 2024-12-05 21:07:24 发布

原创最新推荐文章于 2024-12-05 21:07:24 发布 · 104 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#网络爬虫准

网络爬虫准专栏收录该内容

1 篇文章

订阅专栏

本文介绍如何利用Apache HttpClient库实现网页内容的获取，并将获取到的内容保存为本地文件。通过设置请求头模拟浏览器行为，确保请求的顺利进行。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

package test;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;

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;

public class test {

	private static String HOST = "www.jd.com";
	private static String BASE_URL = "http://" + HOST + "/";

	public static String downloadPage(String url, String outputPath) throws ClientProtocolException, IOException {
		CloseableHttpClient httpClient = HttpClients.createDefault();
		/// 设置GET请求参数，URL一定要以"http://"开头
		HttpGet getReq = new HttpGet(url);
		/// 设置请求报头，模拟Chrome浏览器
		getReq.addHeader("Accept", "application/json, text/javascript, */*; q=0.01");
		getReq.addHeader("Accept-Encoding", "gzip,deflate,sdch");
		getReq.addHeader("Accept-Language", "zh-CN,zh;q=0.8");
		getReq.addHeader("Content-Type", "text/html; charset=UTF-8");
		getReq.addHeader("Host", HOST);
		getReq.addHeader("User-Agent",
				"Mozilla/5.0 (Windows NT 5.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1700.76 Safari/537.36");
		/// 发送GET请求
		CloseableHttpResponse rep = httpClient.execute(getReq);
		/// 从HTTP响应中取出页面内容
		HttpEntity repEntity = rep.getEntity();
		String content = EntityUtils.toString(repEntity);

		File outputFile = new File(outputPath);
		FileOutputStream fos = new FileOutputStream(outputFile);
		fos.write(content.getBytes());
		fos.close();

		/// 打印出页面的内容：
		System.out.println(content);
		/// 关闭连接
		rep.close();
		httpClient.close();

		return content;
	}

	public static void main(String[] args) {
		try {
			downloadPage(BASE_URL, "e:\\output.html");
		} catch (ClientProtocolException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}

}