无法使用 Android 个意图从互联网上抓取数据

Question

我无法使用 Android 中的 intents 从网页中抓取标题。目前，我只想从 URL 中提取标题文本（h1 标签文本）。我在 onHandleIntent(Intent intent) 中写了一段用于提取标题文本的代码，但我认为我做错了什么。我的基本目的是在 Android 上写一个网络爬虫。有人能帮我吗？这是我的代码

MainActivity.java class

package com.example.awais.check2;

import android.app.Activity;
import android.content.BroadcastReceiver;
import android.content.Context;
import android.content.Intent;
import android.content.IntentFilter;
import android.os.Bundle;
import android.view.View;
import android.widget.Button;

public class MainActivity extends Activity {

    private MyWebRequestReceiver receiver;

    @Override
    public void onCreate(Bundle savedInstanceState) {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.activity_main);

        IntentFilter filter = new IntentFilter(MyWebRequestReceiver.PROCESS_RESPONSE);
        filter.addCategory(Intent.CATEGORY_DEFAULT);

        receiver = new MyWebRequestReceiver();
        registerReceiver(receiver, filter);

        Button addButton = (Button) findViewById(R.id.sendRequest);
        addButton.setOnClickListener(new View.OnClickListener() {
            public void onClick(View view) {
                System.out.println("Clicked");

                Intent msgIntent = new Intent(MainActivity.this, MyWebRequest.class);

                msgIntent.putExtra(MyWebRequest.REQUEST_STRING, "http://tribune.com.pk");
                startService(msgIntent);
            }
        });

    }

    @Override
    public void onDestroy() {
        this.unregisterReceiver(receiver);
        super.onDestroy();
    }

    public class MyWebRequestReceiver extends BroadcastReceiver{

        public static final String PROCESS_RESPONSE = "com.example.check.intent.action.PROCESS_RESPONSE";

        @Override
        public void onReceive(Context context, Intent intent) {
            String responseString = intent.getStringExtra(MyWebRequest.RESPONSE_STRING);
            String reponseMessage = intent.getStringExtra(MyWebRequest.RESPONSE_MESSAGE);

            System.out.println(reponseMessage);
            System.out.println(responseString);
        }
    }
}

MyWebRequest.javaclass代码

package com.example.awais.check2;

import android.app.IntentService;
import android.content.Intent;
import android.os.SystemClock;
import android.text.format.DateFormat;
import android.util.Log;

import com.example.awais.check2.MainActivity.MyWebRequestReceiver;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;

import java.io.IOException;

public class MyWebRequest  extends IntentService {

    public static final String REQUEST_STRING = "myRequest";
    public static final String RESPONSE_STRING = "myResponse";
    public static final String RESPONSE_MESSAGE = "myResponseMessage";

    private String URL = null;

    public MyWebRequest() {
        super("MyWebRequest");
    }

    @Override
    protected void onHandleIntent(Intent intent) {

        String requestString = intent.getStringExtra(REQUEST_STRING);
        String responseString = requestString + " " + DateFormat.format("MM/dd/yy h:mmaa", System.currentTimeMillis());
        String responseMessage = "";

        try {
            Document doc;
            URL = requestString;
            doc = Jsoup.connect(URL).timeout(20 * 1000).get();
//            System.out.println(doc.text());
            Elements links = doc.select("h1");
            responseMessage = links.text();
//            System.out.println(links.text());
        } catch (IOException e) {
            responseMessage = e.getMessage();
        }


        Intent broadcastIntent = new Intent();
        broadcastIntent.setAction(MyWebRequestReceiver.PROCESS_RESPONSE);
        broadcastIntent.addCategory(Intent.CATEGORY_DEFAULT);
        broadcastIntent.putExtra(RESPONSE_STRING, responseString);
        broadcastIntent.putExtra(RESPONSE_MESSAGE, responseMessage);
        sendBroadcast(broadcastIntent);
    }
}

Content.xml代码

<?xml version="1.0" encoding="utf-8"?>
<LinearLayout xmlns:android="http://schemas.android.com/apk/res/android"
    android:orientation="vertical" android:layout_width="fill_parent"
    android:layout_height="fill_parent"
    android:paddingLeft="10dp">


    <Button android:text="Send Request " android:id="@+id/sendRequest"
        android:layout_width="wrap_content" android:layout_height="wrap_content" />


</LinearLayout>

Answer 1

您是否考虑过为 Android 使用 http 框架？它的代码少了很多，并且还在后台运行请求。此示例使用 loopj async client

build.gradle:

compile 'com.loopj.android:android-async-http:1.4.9'
compile 'cz.msebera.android:httpclient:4.4.1.2'

测试代码：

@Test
public void parseHttp() throws Exception {

    AsyncHttpClient client = new AsyncHttpClient();
    final CountDownLatch latch = new CountDownLatch(1);

    String url = "";

    client.get(url, new AsyncHttpResponseHandler(Looper.getMainLooper()) {
        @Override
        public void onSuccess(int statusCode, Header[] headers, byte[] responseBody) {
            String body = new String(responseBody);
            Pattern p = Pattern.compile("<h1(.*)<\/h1>");
            Matcher m = p.matcher(body);
            Log.d("tag", "success");
            if ( m.find() ) {
                String match = m.group(1);
                Log.d("tag", match);
            }
            latch.countDown();
        }

        @Override
        public void onFailure(int statusCode, Header[] headers, byte[] responseBody, Throwable error) {

            Log.d("tag", "failure");
            latch.countDown();
        }
    });

    latch.await();
}

更新：

在上面添加了额外的导入：compile 'cz.msebera.android:httpclient:4.4.1.2'

import cz.msebera.android.httpclient.Header;
import cz.msebera.android.httpclient.HttpRequest;
import cz.msebera.android.httpclient.HttpResponse;
import cz.msebera.android.httpclient.HttpStatus;

无法使用 Android 个意图从互联网上抓取数据

Unable to scrape data from Internet using Android intents

java

android

android-intent

android-intentservice