java抓取网站数据，存放到Excel中

今天工作需要做了个在www.chemicalbook.com上抓取数据的任务啊！

步骤为：1、先弄清抓取网站的url规则；2、设置正则表达式抓取规则；3、存放到同一个Excel中

代码如下:

import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

import org.apache.poi.hssf.usermodel.HSSFRow;
import org.apache.poi.hssf.usermodel.HSSFSheet;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;

public class GetChemicalbookSiteCompanyUtil {
	
 public static void main(String[] args) {
	 try{
		 String tUrl = "";
		 String strUrl = "http://www.chemicalbook.com/ProductSupplierlist_";
		 HSSFWorkbook hssfworkbook = new HSSFWorkbook(); 
         HSSFSheet hssfsheet    = hssfworkbook.createSheet("公司基本信息");
		 //公司网址索引a-z
	 	 for (int j = 36; j <= 61; j++) {//61
	 		tUrl = "";
	 		for (int i = 0; i < 700; i=i+100) {
	 			tUrl = strUrl+j+"_"+i+".htm";
	 			System.out.println(tUrl);
	 			String pageData = "";
				int len;
				URL url = new URL(tUrl);
				HttpURLConnection url_con = null;
				url_con = (HttpURLConnection) url.openConnection();
	 			url_con.setFollowRedirects(true);
	 			url_con.setInstanceFollowRedirects(false);
		        url_con.setRequestMethod("GET");
		        if(url_con.getResponseCode()==200){
		        	InputStream in = url_con.getInputStream();
		        	byte[] by = new byte[1024];
		        	while((len=in.read(by))!=-1){
		        		pageData +=new String(by,0,len);
		        	}
		        	in.close();
		        	url_con.disconnect();
		        	//设置抓取规则
		        	String regEx = 
		        		"<tr><tdwidth=\"230\">(.+?)</td>" +
		        		"<tdwidth=\"230\">(.+?)</td>"+
		        		"<tdwidth=\"210\">(.+?)</td>"+
		        		"<tdwidth=\"200\">(.+?)</td>"+
		        		"<tdwidth=\"80\">(.+?)</td></tr>";
	 	      		String companyName = null;
	 	      		String tel = null;
	 	      		String email = null;
	 	      		String website = null;
	 	      		String country = null;
	 	      		pageData=pageData.replaceAll("\\s|\\t|\\r", "");
	 	      		Matcher mat=Pattern.compile(regEx).matcher(pageData);
	 	      		while(mat.find()){
	 	      			companyName = mat.group(1).replaceAll("<a.*?>|</a>", "");
	 	      			tel = mat.group(2).replaceAll("<span.*?>|</span>", "");
	 	      			email = mat.group(3).replaceAll("<span.*?>|</span>", "");
	 	      			website = mat.group(4).replaceAll("<a.*?>|</a>", "");
	 	      			country = mat.group(5).replaceAll("<span.*?>|</span>", "");
	 	      			if(country.equals("中国")){
		 	      			HSSFRow  hssfrow = hssfsheet.createRow(hssfsheet.getLastRowNum()+1);
		 					hssfrow.createCell((short)0).setCellValue(companyName);
		 	        		hssfrow.createCell((short)1).setCellValue(email);
		 	        		hssfrow.createCell((short)2).setCellValue(tel);
		 	        		hssfrow.createCell((short)3).setCellValue(website);
		 	        		hssfrow.createCell((short)4).setCellValue(country);
		 	        		url_con.disconnect();
	 	      			}
	 	      		}
	 	      		url_con.disconnect();
		        }
		        //将数据导入到excel中
		        File fileName = new File("F:\\材料\\chemicalbook_DBinfo.xls");
		        if(!fileName.exists()){
		        	fileName.mkdir();
		        }
		        FileOutputStream output = new FileOutputStream(fileName);
		        hssfworkbook.write(output);
		        output.close();
		 	}
	 	}
	 }catch (Exception e) {
		e.printStackTrace();
	}
 }
}