jsoup httpclient 爬取网页并下载google图标

jsoup下载地址 http://www.jsoup.org

httpclient下载地址 http://hc.apache.org/downloads.cgi

其他jar包见附件

package jsoup;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.HashMap;
import java.util.Map;

import org.apache.commons.io.FileUtils;
import org.apache.commons.io.IOUtils;
import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.HttpStatus;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.params.HttpProtocolParams;
import org.apache.http.util.EntityUtils;

import com.google.api.translate.Language;
import com.google.api.translate.Translate;

/**
 * google logo 下载程序
 */
public abstract class Crawler {

	/**
	 * 使用google 翻译api
	 * 
	 * @param en
	 * @return
	 */
	public String translateEnToCinese(String en) {
		Translate.setHttpReferrer("http://www.xxx.com");
		try {
			return Translate.execute(en, Language.ENGLISH, Language.CHINESE);
		} catch (Exception e) {
			e.printStackTrace();
		}
		return "";
	}

	/**
	 * 获取一个Map
	 * 
	 * @return
	 */
	public Map<String, Object> getMap() {
		return new HashMap<String, Object>(0);
	}

	/**
	 * 下载文件
	 * 
	 * @param url
	 *            文件http地址
	 * @param dir
	 *            目标文件
	 * @throws IOException
	 */
	public void downloadFile(String url, String dir) throws Exception {
		DefaultHttpClient httpClient = new DefaultHttpClient();
		HttpProtocolParams.setUserAgent(httpClient.getParams(),
						"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.1.9) Gecko/20100315 Firefox/3.5.9");
		HttpGet httpGet = new HttpGet();
		httpGet.setURI(new java.net.URI(url));
		
		InputStream input = null;
		FileOutputStream output = null;
		try {
			HttpResponse response = httpClient.execute(httpGet);
			HttpEntity entity = response.getEntity();
			input = entity.getContent();
			File file = new File(dir);
			output = FileUtils.openOutputStream(file);
			IOUtils.copy(input, output);
		} catch (Exception e){
			e.printStackTrace();
		} finally {
			IOUtils.closeQuietly(output);
			IOUtils.closeQuietly(input);
		}
	}

	/**
	 * 处理GET请求，返回整个页面
	 * 
	 * @param url
	 *            访问地址
	 * @param params
	 *            编码参数
	 * @return
	 * @throws Exception
	 */
	public synchronized String doGet(String url, String... params)
			throws Exception {
		DefaultHttpClient httpClient = new DefaultHttpClient(); // 创建httpClient实例
		HttpProtocolParams.setUserAgent(httpClient.getParams(),
						"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.1.9) Gecko/20100315 Firefox/3.5.9");
		String charset = "UTF-8";
		if (null != params && params.length >= 1) {
			charset = params[0];
		}
		HttpGet httpGet = new HttpGet(); // 创建get方法实例
		String content = "";
		httpGet.setURI(new java.net.URI(url));
		try {
			HttpResponse response = httpClient.execute(httpGet); // 执行请求，得到response对象
			int resStatu = response.getStatusLine().getStatusCode(); // 得到返回的状态码
			if (resStatu == HttpStatus.SC_OK) { // 200正常
				HttpEntity entity = response.getEntity(); // 获得相应的实体
				if (entity != null) {
					// 使用EntityUtils的toString方法，传递默认编码，在EntityUtils中的默认编码是ISO-8859-1
					content = EntityUtils.toString(entity, charset);
				}
			}
		} catch (Exception e) {
			System.out.println("访问【" + url + "】出现异常!");
			e.printStackTrace();
		} finally {
			// 关闭资源
			httpGet.abort();
			httpClient.getConnectionManager().shutdown();
		}
		return content;
	}
}

 

 

package jsoup;

import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;
import java.util.Map;

import org.apache.commons.io.FileUtils;
import org.apache.commons.lang.StringUtils;
import org.json.JSONArray;
import org.json.JSONObject;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

/**
 * google logo 下载程序
 */
public class GoogleLogoCrawler extends Crawler {
	
	private static final String URL = "http://www.logocollect.com/google/year.php?key=%y&page=%p"; 

	private static final String LOGO_URL = "http://www.logocollect.com/google/";

	private static final String[] YEARS = new String[] { 
			//"1998", "1999", "2000",
			//"2001", "2002", "2003", "2004", "2005", "2006", "2007", "2008", 
			"2009", "2010", "2011", "2012" };

	private static final String INDEX = "http://www.logocollect.com/google/year.php?key=%y"; 

	private static final String DIR_PATH = "D:\\googlelogos\\";

	public void doStart() {
		JSONArray array = new JSONArray();
		for (String year : YEARS) {
			String ind = INDEX.replaceAll("%y", year);
			int pageCount = getPageCount(ind);
			for (int i = 1; i < pageCount+1; i++) {
				String url = URL.replaceAll("%y", year).replaceAll("%p", i + "");
				String path = year + "_" + i;
				start(url, array, DIR_PATH + path + "\\", path);
			}
		}
		try {
			FileUtils.writeStringToFile(new File(DIR_PATH + "json"), array.toString(), "UTF-8");
		} catch (IOException e) {
			e.printStackTrace();
		}
		System.out.println(array);
	}
	
	public int getPageCount(String url) {
		int pageCount = 1;
		try {
			org.jsoup.nodes.Document doc = Jsoup.connect(url).get();
			
			String els = doc.html().toString();
			int start = els.indexOf("总页数") + 4;
			String temp = els.substring(start);
			int end = temp.indexOf("，");
			pageCount = Integer.parseInt(els.substring(start,start+end));
			System.out.println(pageCount);
		} catch (IOException e) {
			e.printStackTrace();
		}
		return pageCount;
	}

	public void start(String url, JSONArray array, String dir, String path) {
		try {
			String content = super.doGet(url);
			Document doc = Jsoup.parse(content);
			Elements dds = doc.select(".img img");
			List<Map<String, Object>> list = new ArrayList<Map<String, Object>>(0);
			for (int i = 0; i < dds.size(); i++) {
				Element img = dds.get(i);
				String src = img.select("img").first().attr("src");
				String title = img.select("img").first().attr("title");
				Map<String, Object> map = super.getMap();
				
				map.put("url", LOGO_URL + src);
				map.put("title", title);
				
				list.add(map);
			}
			JSONArray tempJsonArray = new JSONArray();
			for (Map<String, Object> map : list) {
				JSONObject jsonObject = new JSONObject();
				String proxy = StringUtils.substringAfterLast(map.get("url")
						.toString(), ".");
				long date = new Date().getTime();
				String name = date + "." + proxy;
				jsonObject.put("url", map.get("url").toString());
				jsonObject.put("dir", name);
				jsonObject.put("title", map.get("title").toString());
				
				// 翻译
//				String dateZh = super.translateEnToCinese(map.get("date")
//						.toString());
//				String titleZh = super.translateEnToCinese(map.get("title")
//						.toString());
//				json.put("title_zh_cn", dateZh + " - " + titleZh);
				
				// 下载图片
				super.downloadFile(map.get("url").toString(), dir + name);
				tempJsonArray.put(jsonObject);
			}
			array.put(new JSONObject().put(path, tempJsonArray));
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

	public static void main(String[] args) throws Exception {
		new GoogleLogoCrawler().doStart();
	}

}