在上面网址中最后874589732820为每次抓取要替换的参数
package ups.test;
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
import java.net.HttpURLConnection;
import java.net.URL;
public class Test {
public String getPageContent(String strUrl, String strPostRequest,int maxLength) {
// 读取结果网页
StringBuffer buffer = new StringBuffer();
System.setProperty("sun.net.client.defaultConnectTimeout", "5000");
System.setProperty("sun.net.client.defaultReadTimeout", "5000");
try {
URL newUrl = new URL(strUrl);
HttpURLConnection hConnect = (HttpURLConnection) newUrl.openConnection();
// POST方式的额外数据
if (strPostRequest.length() > 0) {
hConnect.setDoOutput(true);
OutputStreamWriter out = new OutputStreamWriter(hConnect.getOutputStream());
out.write(strPostRequest);
out.flush();
out.close();
}
// 读取内容
BufferedReader rd = new BufferedReader(new InputStreamReader(hConnect.getInputStream(),"utf-8"));
int ch;
for (int length = 0; (ch = rd.read()) > -1 && (maxLength <= 0 || length < maxLength); length++)
buffer.append((char) ch);
String s = buffer.toString();
s.replaceAll("//&[a-zA-Z]{1,10};", "").replaceAll("<[^>]*>", "");
System.out.println(s);
rd.close();
hConnect.disconnect();
return buffer.toString().trim();
} catch (Exception e) {
return "错误:读取网页失败！";
//
}
}
}
package ups.test;
public class Test1 {
public static void main(String[] args) {
String url = "http://www.fedex.com/Tracking?clienttype=dotcomreg&ascend_header=1&cntry_code=cn&language=sim&mi=n&tracknumbers=874589732820";
Test p = new Test();
p.getPageContent(url, "post", 100500);
System.out.print("已经执行！");
}
}
现在能够抓取到网页的所有代码，但需要货件托运历史中里面的信息：日期/时间 活动 地点 详细信息 不知道怎么提取 求指导
