Android开发---jsoup解析网页的使用方法

本文介绍如何利用JSoup库解析HTML页面,并通过Java实现将解析后的页面内容写入文件。包括解析步骤、代码实现及日志输出。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

解析html的解析步骤代码

package com.example.httputil;

import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.security.cert.CertificateException;
import java.security.cert.X509Certificate;
import java.util.ArrayList;
import java.util.List;

import javax.net.ssl.HostnameVerifier;
import javax.net.ssl.HttpsURLConnection;
import javax.net.ssl.SSLContext;
import javax.net.ssl.SSLSession;
import javax.net.ssl.TrustManager;
import javax.net.ssl.X509TrustManager;

import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.HttpStatus;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.params.HttpParams;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import com.example.myapplication.myApplication;

import android.graphics.AvoidXfermode.Mode;
import android.os.Handler;
import android.os.Message;
import android.provider.OpenableColumns;
import android.util.Log;

public class FoodsItemBiz {
    public List<FoodsItem> foodsItems = new ArrayList<FoodsItem>();

    public FoodsItemBiz() {
        // TODO Auto-generated constructor stub
    }

    public void jsoup_jiexi(String msg) {
        FoodsItem foodsItem = null;
        FileOutputStream fos = null;
        org.jsoup.nodes.Document doc = Jsoup.parse(msg);
        // Log.i("msg", msg.obj.toString());
        Elements units = doc.getElementsByClass("pic");
        Elements detail_units = doc.getElementsByClass("detail");
        Log.i("detail_units", detail_units.size() + "");
        Log.i("num", units.size() + "");
        try {
            fos = myApplication.GetContext().openFileOutput("food.html", 0);
            try {
                fos.write(msg.getBytes());
                fos.flush();
            } catch (IOException e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            }
        } catch (FileNotFoundException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } finally {
            if (fos != null) {
                try {
                    fos.close();
                } catch (IOException e) {
                    // TODO Auto-generated catch block
                    e.printStackTrace();
                }
            }
        }
        for (int i = 0; i < units.size(); i++) {
            foodsItem = new FoodsItem();
            Element detail_ele = detail_units.get(i);
            Element unit_ele = units.get(i);
            Elements detail_content = detail_ele
                    .getElementsByClass("subcontent");
            String content = detail_content.get(0).text();
            Elements personame_ele = detail_ele.getElementsByClass("subline");
            String PersonnameAndDate = personame_ele.get(0).text();
            String[] data = PersonnameAndDate.split("发");
            String Personname = data[0];
            String Date = "发" + data[1];
            Element h1_a_ele = unit_ele.child(0);
            String title = h1_a_ele.attr("title");
            String link = h1_a_ele.attr("href");
            Element imagelink_ele = h1_a_ele.getElementsByTag("img").get(0);
            String imagelink = imagelink_ele.attr("data-src");
            foodsItem.setTitle(title);
            foodsItem.setLink(link);
            foodsItem.setWriter(Personname);
            foodsItem.setDate(Date);
            foodsItem.setImgLink(imagelink);
            foodsItem.setContent(content);

            Log.i("title", title);
            Log.i("link", link);
            Log.i("Date", Date);
            Log.i("personname", Personname);
            Log.i("imagelink", imagelink);
            Log.i("content", content);
            foodsItems.add(foodsItem);
        }
    }     
}

未写先上传保存。

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值