java - 解析 Booking.uz.gov.ua 网站

标签 java html json parsing

此代码从 booking.uz.gov.ua 网站解析。但由于某种原因,他不想工作。谁能说明为什么不起作用,或者修复它? 谁可以提供一些建议?

线程“main”中出现异常 java.lang.ArrayIndexOutOfBoundsException: 0 位于 ua.gov.uz.booking.uz.main(uz.java:137)

package ua.gov.uz.booking;
import javax.script.ScriptEngine;
import javax.script.ScriptEngineManager;
import javax.script.ScriptException;
import java.io.BufferedReader;
import java.io.DataOutputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.text.MessageFormat;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.List;
import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class uz {

static String html   = "";
static String cookie = "";
static String token  = "";
static String error  = "";

static Map<String, List<String>> headers = null;

static void fetchHtml() {
    try {
        URL url = new URL("http://booking.uz.gov.ua/");
        HttpURLConnection conn = (HttpURLConnection) url.openConnection();
        conn.setRequestMethod("GET");
        BufferedReader rd = new BufferedReader(new InputStreamReader(conn.getInputStream()));
        headers = conn.getHeaderFields();
        String line;
        while ((line = rd.readLine()) != null) {
            html += line;
        }
        rd.close();
    } catch (Exception e) {
        error = e.getMessage();
    }
}

static void parseCookie() {
    List<String> cookies = headers.get("Set-Cookie");
    for (String current_cookie : cookies) {
        if (current_cookie.startsWith("_gv_sessid")) {
            cookie = current_cookie;
            break;
        }
    }
}

static void parseToken() {
    String adapter = "var token;localStorage={setItem:function(key, value){if(key==='gv-token')token=value}};";
    Pattern pattern = Pattern.compile("\\$\\$_=.*~\\[\\];.*\"\"\\)\\(\\)\\)\\(\\);");
    Matcher matcher = pattern.matcher(html);
    if (matcher.find()) {
        String obfuscated = matcher.group(0);
        ScriptEngineManager factory = new ScriptEngineManager();
        ScriptEngine engine = factory.getEngineByName("JavaScript");
        try {
            engine.eval(adapter + obfuscated);
        } catch (ScriptException e) {
            error = e.getMessage();
        }
        token = engine.get("token").toString();
    }
}

static String getStationId(String name) {
    String json = "";
    try {
        URL url = new URL("http://booking.uz.gov.ua/en/purchase/station/" + name + "/");
        HttpURLConnection conn = (HttpURLConnection) url.openConnection();
        conn.setRequestMethod("GET");
        BufferedReader rd = new BufferedReader(new InputStreamReader(conn.getInputStream()));
        String line;
        while ((line = rd.readLine()) != null) {
            json += line;
        }
        rd.close();
    } catch (Exception e) {
        error = e.getMessage();
    }
    ScriptEngineManager factory = new ScriptEngineManager();
    ScriptEngine engine = factory.getEngineByName("JavaScript");
    engine.put("json", json);
    try {
        engine.eval("var station_id = JSON.parse(json).value[0].station_id");
    } catch (ScriptException e) {
        error = e.getMessage();
    }
    return engine.get("station_id").toString();
}

static String getData(String fromName, String toName, String date) {
    fetchHtml();
    parseCookie();
    parseToken();
    String from = getStationId(fromName);
    String to = getStationId(toName);
    String json = "";
    try {
        URL url = new URL("http://booking.uz.gov.ua/en/purchase/search/");
        HttpURLConnection conn = (HttpURLConnection) url.openConnection();
        conn.setRequestProperty("Cookie", cookie);
        conn.setRequestProperty("GV-Token", token);
        conn.setRequestProperty("GV-Ajax", "1");
        conn.setRequestProperty("Content-Type", "application/x-www-form-urlencoded");
        conn.setRequestProperty("Referer", "http://booking.uz.gov.ua/en/");
        conn.setRequestMethod("POST");
        String urlParameters = MessageFormat.format("station_id_from={0}&station_id_till={1}&date_dep={2}" +
                                                    "&time_dep=00:00&time_dep_till=24:00", from, to, date);
        conn.setDoOutput(true);
        DataOutputStream wr = new DataOutputStream(conn.getOutputStream());
        wr.writeBytes(urlParameters);
        wr.flush();
        wr.close();
        BufferedReader rd = new BufferedReader(new InputStreamReader(conn.getInputStream()));
        String line;
        while ((line = rd.readLine()) != null) {
            json += line;
        }
        rd.close();
    } catch (Exception e) {
        error = e.getMessage();
    }
    return json;
}

static String getData(String fromName, String toName) {
    return getData(fromName, toName, new SimpleDateFormat("MM.dd.yyyy").format(new Date()));
}

public static void main(String[] args) {


if (args.length < 2) {
    System.out.println("Онлайн резервування та придбання квиткiв - Укрзалізниця");
    System.out.println("Введите: <start_station> <end_station> [MM.DD.YYYY]");
    System.exit(1);
}
String data;
if (args.length > 2)
    data = getData(args[0], args[1], args[2]);
else
    data = getData(args[0], args[1]);
System.out.println(data);
}


}

最佳答案

第 137 行是 args[0] = "dsa"。如果 0 是 IndexOutOfBound,则意味着 args 是一个大小为 0 的数组(即空数组)。因此,您无法访问其索引 0,因为这需要大小 >= 1 的数组。

启动程序的方式会影响 args 数组的内容(其中包含通过控制台启动时传递给程序的参数)。您检查过断点启动时 args 是什么吗?你如何启动你的程序? (在IDE中,还是通过控制台?)

关于java - 解析 Booking.uz.gov.ua 网站,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/31451141/

相关文章:

javascript - Webpack:通过文件加载器复制 JSON 文件

ios - 如何在swift中通过单元格解析json纬度和经度

java - Scala - IntelliJ IDEA 错误 : Could not find or load main class

java - boolean 帮助 : Testing the parameters for a password JAVA

java - 确定哪个网络接口(interface)将用于 JDK 上的给定主机名

java - 如何使用HTMLUnit登录vbulletin论坛?

html - 电子邮件发送者的表格问题

javascript - Html、Javascript或Css云滑动

javascript - 更改 id 但保留与 jQuery 中的旧 id 相关的 css

javascript - 如何使用 ViewBag 中的 JSON 填充 javascript 变量?