java - 使用HttpClient模拟HTTP POST时出现问题

我正在尝试使用httpclient以编程方式将http post请求发送到http://ojp.nationalrail.co.uk/en/s/planjourney/query，但它不喜欢我发送的请求。我从chrome浏览器发送的内容中复制了头部和正文，因此它是相同的，但它不喜欢我发送的内容，因为html提到有一个错误。

<div class="padding">
                    <h1 class="sifr"><strong>Sorry</strong>, something went wrong</h1>
                    <div class="error-message">
                        <div class="error-message-padding">
                            <h2>There is a problem with the page you are trying to access.</h2>
                            <p>It is possible that it was either moved, it doesn't exist or we are experiencing some technical difficulties.</p>
                            <p>We are sorry for the inconvenience.</p>
                        </div>
                    </div>
                </div>

下面是我使用httpclient的java程序：

package com.tixsnif;

import org.apache.http.*;
import org.apache.http.client.HttpClient;
import org.apache.http.client.entity.UrlEncodedFormEntity;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.message.BasicNameValuePair;
import org.apache.http.protocol.HTTP;

import java.io.*;
import java.util.*;
import java.util.zip.GZIPInputStream;

public class WebScrapingTesting {

public static void main(String[] args) throws Exception {
    String target = "http://ojp.nationalrail.co.uk/en/s/planjourney/query";

    HttpClient client = new DefaultHttpClient();

    HttpPost httpPost = new HttpPost(target);
    BasicNameValuePair[] params = {
            new BasicNameValuePair("jpState", "single"),
            new BasicNameValuePair("commandName", "journeyPlannerCommand"),
            new BasicNameValuePair("from.searchTerm", "Basingstoke"),
            new BasicNameValuePair("to.searchTerm", "Reading"),
            new BasicNameValuePair("timeOfOutwardJourney.arrivalOrDeparture", "DEPART"),
            new BasicNameValuePair("timeOfOutwardJourney.monthDay", "Today"),
            new BasicNameValuePair("timeOfOutwardJourney.hour", "10"),
            new BasicNameValuePair("timeOfOutwardJourney.minute", "15"),
            new BasicNameValuePair("timeOfReturnJourney.arrivalOrDeparture", "DEPART"),
            new BasicNameValuePair("timeOfReturnJourney.monthDay", "Today"),
            new BasicNameValuePair("timeOfReturnJourney.hour", "18"),
            new BasicNameValuePair("timeOfReturnJourney.minute", "15"),
            new BasicNameValuePair("_includeOvertakenTrains", "on"),
            new BasicNameValuePair("viaMode", "VIA"),
            new BasicNameValuePair("via.searchTerm", "Station name / code"),
            new BasicNameValuePair("offSetOption", "0"),
            new BasicNameValuePair("_reduceTransfers", "on"),
            new BasicNameValuePair("operatorMode", "SHOW"),
            new BasicNameValuePair("operator.code", ""),
            new BasicNameValuePair("_lookForSleeper", "on"),
            new BasicNameValuePair("_directTrains", "on")};

    httpPost.setHeader("Host", "ojp.nationalrail.co.uk");
    httpPost.setHeader("User-Agent", "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.10 (KHTML, like Gecko) Chrome/8.0.552.231 Safari/534.10");
    httpPost.setHeader("Accept-Encoding", "gzip,deflate,sdch");
    httpPost.setHeader("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,**/*//*;q=0.8");
    httpPost.setHeader("Accept-Language", "en-us,en;q=0.8");
    httpPost.setHeader("Accept-Charset", "ISO-8859-1,utf-8;q=0.7,*;q=0.7");
    httpPost.setHeader("Origin", "http://www.nationalrail.co.uk/");
    httpPost.setHeader("Referer", "http://www.nationalrail.co.uk/");
    httpPost.setHeader("Content-Type", "application/x-www-form-urlencoded");
    httpPost.setHeader("Cookie", "JSESSIONID=B2A3419B79C5D999CA4806B459675CCD.app201; Path=/");
    UrlEncodedFormEntity urlEncodedFormEntity = new UrlEncodedFormEntity(Arrays.asList(params));
    urlEncodedFormEntity.setContentEncoding(HTTP.UTF_8);
    httpPost.setEntity(urlEncodedFormEntity);
    HttpResponse response = client.execute(httpPost);

    InputStream input = response.getEntity().getContent();
    GZIPInputStream gzip = new GZIPInputStream(input);
    InputStreamReader isr = new InputStreamReader(gzip);
    BufferedReader br = new BufferedReader(isr);

    String line = null;
    while((line = br.readLine()) != null) {
        System.out.printf("\n%s", line);
    }

    client.getConnectionManager().shutdown();
}
}

如果jsession id过期，我会保持更新，但似乎还有另一个问题我看不到。我是不是漏掉了一些很明显的东西？
他

最佳答案

访问上面的链接并查看html源代码，看起来目标路径应该是/en/s/planjourney/plan。