如何使用 Jsoup 从 API 获取网页内容

Question

我有一个 API，其响应位于 JSON，我需要从中获取一些内容，其中之一是来自各种新闻网站的 url。我希望从各种新闻网站 (url) 中获取各个段落，但我遇到了困难，因为将 url 从 JSON 传递到 Jsoup，因为 string 无法正常工作。

我尝试使用其他 url，但我注意到它们不起作用示例：使用 www.google.com 不起作用，但将 https:// 添加到 www.google.com 有效。

请问有没有人知道如何解决这个错误。

package wami.ikechukwu.kanu;

import android.os.Bundle;
import android.support.v7.app.AppCompatActivity;
import android.widget.ImageView;
import android.widget.TextView;

import com.android.volley.Request;
import com.android.volley.RequestQueue;
import com.android.volley.Response;
import com.android.volley.VolleyError;
import com.android.volley.toolbox.JsonObjectRequest;
import com.android.volley.toolbox.Volley;
import com.bumptech.glide.Glide;

import org.json.JSONArray;
import org.json.JSONException;
import org.json.JSONObject;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import java.io.IOException;

public class news_detail extends AppCompatActivity {

    //TODO: REMOVE THESE LINE IF THERE IS NO NEED FOR THEM IN THE APP
    // private final String KEY_AUTHOR = "author";
    private final String KEY_TITLE = "title";
    //private final String KEY_DESCRIPTION = "description";
    private final String KEY_URL = "url";
    private final String KEY_URL_TO_IMAGE = "urlToImage";
    private final String KEY_PUBLISHED_AT = "publishedAt";
    int itemPosition;
    //this string is appended to the url
    String urlLink = "buhari";
    String url;
    TextView newsDetail_Title, newDetail_Time_Posted, newsDetail_News;
    ImageView newsDetail_Image;

    @Override
    protected void onCreate(Bundle savedInstanceState) {

        super.onCreate(savedInstanceState);
        setContentView(R.layout.activity_news_detail);

        itemPosition = getIntent().getIntExtra("POSITION", 0);

        newsDetail_Title = findViewById(R.id.newsDetail_Title);
        newDetail_Time_Posted = findViewById(R.id.newDetail_Time_Posted);
        newsDetail_News = findViewById(R.id.newsDetail_News);
        newsDetail_Image = findViewById(R.id.newsDetail_Image);

        newsRequest();
    }

    public void newsRequest() {

        JsonObjectRequest jsonObjectRequest = new JsonObjectRequest(Request.Method.GET, "https://newsapi.org/v2/everything?q=" + urlLink + "&language=en&sortBy=publishedAt&pageSize=100&apiKey=a5f976b34089493abc8f97f088e5df64", null, new Response.Listener<JSONObject>() {

            @Override
            public void onResponse(JSONObject response) {

                try {
                    JSONArray jsonArray = response.getJSONArray("articles");

                    //Using a for loop to get the object (data) in the JSON
                    JSONObject jsonObject = jsonArray.getJSONObject(itemPosition);

                    newsDetail_Title.setText(jsonObject.getString(KEY_TITLE));
                    url = jsonObject.getString(KEY_URL);
                    Glide.with(getApplicationContext()).load(jsonObject.getString(KEY_URL_TO_IMAGE)).into(newsDetail_Image);

                } catch (JSONException e) {
                    e.printStackTrace();

                }
            }
        }, new Response.ErrorListener() {

            @Override
            public void onErrorResponse(VolleyError error) {

            }
        });
        RequestQueue requestQueue = Volley.newRequestQueue(this);
        requestQueue.add(jsonObjectRequest);

        new Thread(new Runnable() {

            final StringBuilder builder = new StringBuilder();
            String title;

            @Override
            public void run() {

                try {
                    Document document = Jsoup.connect(url).get();
                    Elements element = document.select("p");
                    for (Element paragraph : element) {
                        builder.append(paragraph.text());
                    }

                    // title = document.title();

                } catch (IOException e) {
                    e.printStackTrace();
                }

                runOnUiThread(new Runnable() {

                    @Override
                    public void run() {

                        newsDetail_News.setText(builder.toString());
                        // newsDetail_News.setText(title);

                    }
                });
            }
        }).start();
    }

}

Answer 1

是的，Jsoup 会抛出异常是 url 不包含 http 或 https。

试试这个（在 Kotlin 中），你也可以将代码转换为 java

previewUrl = if (!url.contains("http")) {
                if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.P)
                    "https://$url"
                else {
                    "http://$url"
                }
            } else {
                url
            }