java网页抓取提取网页部分信息

0 0

java网页抓取提取网页部分信息 5

http://www.fedex.com/Tracking?clienttype=dotcomreg&ascend_header=1&cntry_code=cn&language=sim&mi=n&tracknumbers=874589732820

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

2012年7月02日 14:23

qizi456258
1
0 0 5

3个答案按时间排序按投票排序

0 0

采纳的答案

仔细查看该页面的HTML代码，你就会发现货件托运历史记录被保存在一个叫 detailInfoObject 的JavaScript对象中，所以不需要特殊的HTML解析器，使用正则即可截取到这个对象，然后用jackson这样的JSON解析器即可反解析到Bean。

解析HTML代码一定要观察代码的构成，才能有效的解析出你要的信息。

var detailInfoObject = {"shipDate":"Jun 16, 2012","emailResults":false,"scans":[{"scanStatus":"已送达","scanLocation":"CANADA, ON","scanTime":"11:36 AM","GMTOffset":"-04:00","showReturnToShipper":false,"scanDate":"Jun 19, 2012"},{"scanStatus":"货件已装车，派送途中","scanLocation":"MISSISSAUGA, ON","scanTime":"9:30 AM","GMTOffset":"-04:00","showReturnToShipper":false,"scanDate":"Jun 19, 2012"},{"scanStatus":"位于当地的FedEx工作地点","scanLocation":"MISSISSAUGA, ON","scanTime":"8:44 AM","GMTOffset":"-04:00","showReturnToShipper":false,"scanDate":"Jun 19, 2012"},{"scanStatus":"国际货物放行 - 进口","scanLocation":"MISSISSAUGA, ON","scanTime":"6:35 AM","GMTOffset":"-04:00","showReturnToShipper":false,"scanDate":"Jun 19, 2012"},{"scanStatus":"位于目的地分拣中心","scanLocation":"MISSISSAUGA, ON","scanTime":"5:27 AM","GMTOffset":"-04:00","showReturnToShipper":false,"scanDate":"Jun 19, 2012"},{"scanStatus":"正在运输","scanLocation":"INDIANAPOLIS, IN","scanTime":"3:55 AM","GMTOffset":"-04:00","showReturnToShipper":false,"scanDate":"Jun 19, 2012"},{"scanStatus":"离开联邦快递工作地点","scanLocation":"INDIANAPOLIS, IN","scanTime":"3:32 AM","GMTOffset":"-04:00","showReturnToShipper":false,"scanDate":"Jun 19, 2012"},{"scanStatus":"到达联邦快递工作地点","scanLocation":"INDIANAPOLIS, IN","scanTime":"2:00 AM","GMTOffset":"-04:00","showReturnToShipper":false,"scanDate":"Jun 19, 2012"},{"scanStatus":"离开联邦快递工作地点","scanLocation":"ANCHORAGE, AK","scanTime":"4:15 PM","GMTOffset":"-08:00","showReturnToShipper":false,"scanDate":"Jun 18, 2012"},{"scanStatus":"到达联邦快递工作地点","scanLocation":"ANCHORAGE, AK","scanTime":"12:06 PM","GMTOffset":"-08:00","showReturnToShipper":false,"scanDate":"Jun 18, 2012"},{"scanStatus":"正在运输","scanLocation":"NARITA-SHI JP","scanTime":"10:38 PM","GMTOffset":"+09:00","showReturnToShipper":false,"scanDate":"Jun 18, 2012"},{"scanStatus":"清关延误 - 进口","scanLocation":"MISSISSAUGA, ON","scanTime":"4:16 AM","GMTOffset":"-04:00","showReturnToShipper":false,"scanDate":"Jun 18, 2012"},{"scanStatus":"正在运输","scanLocation":"SHANGHAI CN","scanTime":"4:58 AM","GMTOffset":"+08:00","showReturnToShipper":false,"scanDate":"Jun 18, 2012"},{"scanStatus":"正在运输","scanLocation":"SHANGHAI CN","scanTime":"12:06 AM","GMTOffset":"+08:00","showReturnToShipper":false,"scanDate":"Jun 18, 2012"},{"scanStatus":"国际货物放行 - 出口","scanLocation":"SHANGHAI CN","scanTime":"11:40 PM","GMTOffset":"+08:00","showReturnToShipper":false,"scanDate":"Jun 17, 2012"},{"scanStatus":"已离开发件地FedEx站点","scanLocation":"SHANGHAI CN","scanTime":"4:40 PM","GMTOffset":"+08:00","showReturnToShipper":false,"scanDate":"Jun 16, 2012"},{"scanStatus":"已取件","scanComments":"在FedEx截件时间之后才收到包裹","scanLocation":"SHANGHAI CN","scanTime":"3:34 PM","GMTOffset":"+08:00","showReturnToShipper":false,"scanDate":"Jun 16, 2012"},{"scanStatus":"托运资讯发送给FedEx ","scanTime":"12:40 AM","GMTOffset":"-05:00","showReturnToShipper":false,"scanDate":"Jun 16, 2012"}],......

2012年7月03日 09:06