初探HttpClient——把百度首页扒下来放到本地

闲着没事,找点东西学习,呵呵^^

用HttpClient生成静态页面Demo:

package tests;

import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.io.Writer;
import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.util.EntityUtils;

/**
 * HttpClient生成静态页测试
 * 
 * @author Java
 * @date 2012-02-07 22:55
 */
public class TestHttpClient {

	/**
	 * 测试将百度首页生成到C:\\test\\baidu.html
	 * 
	 * @param args
	 */
	public static void main(String[] args) {

		try {

			writeHTML(getSiteContent("http://www.baidu.com"),"C:\\test\\baidu.html");
			System.out.println("OK,生成静态页成功!");

		} catch (Exception e) {
			e.printStackTrace();
		}
	}

	/**
	 * 根据指定的URL获取网页的内容
	 * 
	 * @param url 访问地址URL
	 *            
	 * @return 载有内容的字符串
	 */
	public static String getSiteContent(String url) {
		HttpClient httpClient = new DefaultHttpClient();
		HttpGet request = new HttpGet(url);
		String content = null;
		try {

			HttpResponse response = httpClient.execute(request);
			HttpEntity entity = response.getEntity();
			content = EntityUtils.toString(entity);
			// System.out.println(EntityUtils.getContentCharSet(entity));
			// System.out.println(EntityUtils.getContentMimeType(entity));
			// System.out.println(EntityUtils.toString(entity));

		} catch (ClientProtocolException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}

		return content;

	}

	/**
	 * 将指定的文本写入指定的目录的文件
	 * 
	 * @param content 将要写入的文本
	 *            
	 * @param filePath 文件路径
	 *             
	 * @throws IOException IO异常
	 *             
	 */
	public static void writeHTML(String content, String filePath)
			throws IOException {
		
		File file = new File(filePath);
		File fileParent = file.getParentFile();
		if(!fileParent.exists()) 
		{
			fileParent.mkdirs();
		}
			
		Writer writer = new FileWriter(file);
		writer.write(content);
		writer.close();

	}

}

相关推荐