java读取网站内容的两种方法
发布时间：2010/10/26 10:28:35 来源：城市学习网 编辑：ziteng
1，HttpClient
利用apache的虚拟客户端包获取某个地址的内容 1import java.io.UnsupportedEncodingException;
2import java.util.HashSet;
3import java.util.Iterator;
4import java.util.Set;
5import java.util.regex.Matcher;
6import java.util.regex.Pattern;
7
8import org.apache.commons.httpclient.HttpClient;
9import org.apache.commons.httpclient.NameValuePair;
10import org.apache.commons.httpclient.methods.PostMethod;
11
12public class catchMain {
13
14 /** *//**
15 * @param args
16 */
17 public static void main(String[] args) {
18
19
20 String url = "http://search.foodqs.com/companysearch.asp";
21 String keyword="食";
22 String response=createhttpClient(url,keyword);
23 }
24
25public static String createhttpClient(String url,String param){
26 HttpClient client = new HttpClient();
27 String response=null;
28 String keyword=null;
29 PostMethod postMethod = new PostMethod(url);
30 try {
31 if(param!=null)
32 keyword = new String(param.getBytes("gb2312"),"ISO-8859-1");
33 } catch (UnsupportedEncodingException e1) {
34 // TODO Auto-generated catch block
35 e1.printStackTrace();
36 }
37
38 NameValuePair[] data = { new NameValuePair("keyword", keyword) };
39 // 将表单的值放入postMethod中
40 postMethod.setRequestBody(data);
41
42 try {
43 int statusCode = client.executeMethod(postMethod);
44 response = new String(postMethod.getResponseBodyAsString()
45 .getBytes("ISO-8859-1"), "GBK");
46 } catch (Exception e) {
47
48 e.printStackTrace();
49 }
50 return response;
51
52 }
53
2.java自带的HttpURLConnection
1public static String getPageContent(String strUrl, String strPostRequest,
2 int maxLength) {
3 //读取结果网页
4 StringBuffer buffer = new StringBuffer();
5 System.setProperty("sun.net.client.defaultConnectTimeout", "5000");
6 System.setProperty("sun.net.client.defaultReadTimeout", "5000");
7 try {
8 URL newUrl = new URL(strUrl);
9 HttpURLConnection hConnect = (HttpURLConnection) newUrl
10 .openConnection();
11 //POST方式的额外数据
12 if (strPostRequest.length() > 0) {
13 hConnect.setDoOutput(true);
14 OutputStreamWriter out = new OutputStreamWriter(hConnect
15 .getOutputStream());
16 out.write(strPostRequest);
17 out.flush();
18 out.close();
19 }
20 //读取内容
21 BufferedReader rd = new BufferedReader(new InputStreamReader(
22 hConnect.getInputStream()));
23 int ch;
24 for (int length = 0; (ch = rd.read()) > -1
25 && (maxLength <= 0 || length < maxLength); length++)
26 buffer.append((char) ch);
27 rd.close();
28 hConnect.disconnect();
29 return buffer.toString().trim();
30 } catch (Exception e) {
31 // return "错误:读取网页失败！";
32 return null;
33 }
34 }
