Java获取网页内容、图片、JavaScript和CSS文件工具类

最新推荐文章于 2023-04-26 19:06:11 发布

HY-Code

最新推荐文章于 2023-04-26 19:06:11 发布

阅读量952

点赞数 1

文章标签： Java获取html源码 Java爬取网

本文链接：https://blog.csdn.net/hongchongyuan/article/details/9200435

版权

package com.ixysm.util;

import java.io.BufferedReader;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;

/**
 * Web资源供给类
 * 
 * @author hongcy
 * @date 2013-6-25
 * @time 上午10:29:46
 */
public class WebResourceUtils
{
 
	/**
	 * 获取网络上的文件，下载并保存
	 * 
	 * @param urlString
	 *            网址
	 * @param file
	 *            被保存到本地文件
	 * @throws Exception
	 */
	public static void saveUrlFile(String urlString, String file)
			throws Exception
	{
		File toFile = new File(file);
		if (toFile.exists())
		{
			return;
		}
		toFile.createNewFile();
		FileOutputStream outImgStream = new FileOutputStream(toFile);
		outImgStream.write(getUrlFileData(urlString));
		outImgStream.close();
	}

	/**
	 * 获取链接地址的数据，以byte数组方式返回
	 * 
	 * @param urlString
	 *            链接地址
	 * @return byte数组
	 * @throws Exception
	 */
	public static byte[] getUrlFileData(String urlString) throws Exception
	{
		URL url = new URL(urlString);
		HttpURLConnection httpConn = (HttpURLConnection) url.openConnection();
		httpConn.connect();
		InputStream cin = httpConn.getInputStream();
		ByteArrayOutputStream outStream = new ByteArrayOutputStream();
		byte[] buffer = new byte[1024];
		int len = 0;
		while ((len = cin.read(buffer)) != -1)
		{
			outStream.write(buffer, 0, len);
		}
		cin.close();
		byte[] fileData = outStream.toByteArray();
		outStream.close();
		return fileData;
	}

	/**
	 * 获取链接地址的字符数据
	 * 
	 * @param urlStr
	 *            链接地址
	 * @param withSeparator
	 *            是否换行标记
	 * @return 字符串数据
	 * @throws Exception
	 */
	public static String getUrlDetail(String urlStr, boolean withSep)
			throws Exception
	{
		URL url = new URL(urlStr);
		HttpURLConnection httpConn = (HttpURLConnection) url.openConnection();
		httpConn.connect();
		InputStream cin = httpConn.getInputStream();
		BufferedReader reader = new BufferedReader(new InputStreamReader(cin,
				"UTF-8"));
		StringBuffer sb = new StringBuffer();
		String rl = null;
		while ((rl = reader.readLine()) != null)
		{
			if (withSep)
			{
				sb.append(rl).append(System.getProperty("line.separator"));
			} else
			{
				sb.append(rl);
			}
		}
		return sb.toString();
	}

}

此工具类可获取网页资源。

转自：http://ixysm.com/xy_doc/java/0085.php