Jsoup解析html终于成功了!!!
package com.eric.pickupjoke.activity; import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.Calendar;
import java.util.HashMap;
import java.util.List;
import java.util.Locale;
import java.util.Map; 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.util.EntityUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.nodes.TextNode;
import org.jsoup.select.Elements; import android.app.Activity;
import android.graphics.drawable.ColorDrawable;
import android.os.AsyncTask;
import android.os.Bundle;
import android.util.Log;
import android.view.Menu;
import android.widget.SimpleAdapter;
import android.widget.Toast; import com.eric.pickupjoke.conn.IsConnection;
import com.eric.pickupjoke.listview.MyListView;
import com.eric.pickupjoke.listview.MyListView.OnMoreListener;
import com.eric.pickupjoke.listview.MyListView.OnRefreshListener; public class AdultJokeActivity extends Activity {
MyListView articleListView;
List<HashMap<String, String>> articleList;
SimpleAdapter adapter;
OnRefreshListener mOnRefreshListener;
OnMoreListener mOnMoreListener;
static int index = 2; @Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_adult_joke);
init();
} void init() {
getWindow().setBackgroundDrawable(new ColorDrawable(-1));
articleListView = (MyListView) findViewById(R.id.article_list_view);
articleList = new ArrayList<HashMap<String, String>>();
InputStream is;
try {
is = this.getResources().getAssets().open("source_html.html");
Document doc = Jsoup.parse(is, "GBK", "http://www.haha365.com");
Log.i("AsyncTask in AdultJokeActivity", "5");
Elements twoArticleElements = doc
.select("div.content>div.left>div.r_c>div.cat_llb");
Log.i("AsyncTask in AdultJokeActivity", "6");
if (twoArticleElements != null && twoArticleElements.size() > 0) {
for (Element twoArticleElement : twoArticleElements) {
Log.i("AsyncTask in AdultJokeActivity", "7");
List<TextNode> textList = twoArticleElement.textNodes();
Map<String, String> map1 = new HashMap<String, String>();
Map<String, String> map2 = new HashMap<String, String>();
Log.i("AsyncTask in AdultJokeActivity", "8");
map1.put("time", textList.get(0).text());
map1.put("title", twoArticleElement.child(1).text());
map1.put("content", twoArticleElement.child(3).text());
map2.put("time", textList.get(4).text());
map2.put("title", twoArticleElement.child(6).text());
map2.put("content", twoArticleElement.child(8).text());
Log.i("AsyncTask in AdultJokeActivity", "9");
articleList.add((HashMap<String, String>) map1);
articleList.add((HashMap<String, String>) map2);
Log.i("AsyncTask in AdultJokeActivity", "10");
}
}
} catch (IOException e) {
e.printStackTrace();
}
Log.i("init() in AdultJokeActivity", "1");
adapter = new SimpleAdapter(this, articleList,
R.layout.article_list_item, new String[] { "title", "content",
"time" }, new int[] { R.id.title, R.id.content,
R.id.time });
articleListView.setAdapter(adapter);
Log.i("init() in AdultJokeActivity", "2"); mOnRefreshListener = new OnRefreshListener() {
@Override
public void onRefresh() {
Log.i("onRefresh in AdultJokeActivity", "1");
if (new IsConnection(AdultJokeActivity.this).isConnected()) {
new LoadArticleTask()
.execute("http://www.haha365.com/Adult_joke/"); }
}
};
mOnMoreListener = new OnMoreListener() {
@Override
public void onMore() {
Log.i("onMore in AdultJokeActivity", "1");
if (new IsConnection(AdultJokeActivity.this).isConnected()
&& index <= 18) {
new LoadArticleTask()
.execute("http://www.haha365.com/Adult_joke/index_"
+ String.valueOf(index) + ".htm");
index++;
} }
};
articleListView.setOnRefreshListener(mOnRefreshListener);
articleListView.setOnMoreListener(mOnMoreListener);
} private class LoadArticleTask extends AsyncTask<String, Void, String> {
@Override
protected String doInBackground(String... urls) {
try {
Log.i("AsyncTask in AdultJokeActivity", "1");
HttpClient httpClient = new DefaultHttpClient();
HttpGet httpGet = new HttpGet(urls[0]);
HttpResponse httpResponse = httpClient.execute(httpGet);
Log.i("AsyncTask in AdultJokeActivity", "2");
if (httpResponse.getStatusLine().getStatusCode() == HttpStatus.SC_OK) {
Log.i("AsyncTask in AdultJokeActivity", "3");
String html = EntityUtils.toString(
httpResponse.getEntity(), "GBK");
// System.out.println(html);
Log.i("AsyncTask in AdultJokeActivity", "4");
return html;
} else {
Toast.makeText(AdultJokeActivity.this, "获取HTML文档失败",
Toast.LENGTH_SHORT).show();
return null;
}
} catch (ClientProtocolException e) {
e.printStackTrace();
return null;
} catch (IOException e) {
e.printStackTrace();
return null;
}
} @Override
protected void onPostExecute(String html) {
Document doc = Jsoup.parse(html);
Log.i("AsyncTask in AdultJokeActivity", "5");
Elements twoArticleElements = doc
.select("div.content>div.left>div.r_c>div.cat_llb");
Log.i("AsyncTask in AdultJokeActivity", "6");
if (twoArticleElements != null && twoArticleElements.size() > 0) {
for (Element twoArticleElement : twoArticleElements) {
Log.i("AsyncTask in AdultJokeActivity", "7");
List<TextNode> textList = twoArticleElement.textNodes();
Map<String, String> map1 = new HashMap<String, String>();
Map<String, String> map2 = new HashMap<String, String>();
Log.i("AsyncTask in AdultJokeActivity", "8");
map1.put("time", textList.get(0).text());
map1.put("title", twoArticleElement.child(1).text());
map1.put("content", twoArticleElement.child(3).text());
map2.put("time", textList.get(4).text());
map2.put("title", twoArticleElement.child(6).text());
map2.put("content", twoArticleElement.child(8).text());
Log.i("AsyncTask in AdultJokeActivity", "9");
articleList.add((HashMap<String, String>) map1);
articleList.add((HashMap<String, String>) map2);
Log.i("AsyncTask in AdultJokeActivity", "10");
}
} else {
Log.i("AsyncTask in AdultJokeActivity", "8");
}
adapter.notifyDataSetChanged();
articleListView.onRefreshComplete("更新时间:" + getCalendarString());
articleListView.onMoreComplete();
Log.i("AsyncTask in AdultJokeActivity", "11");
}
} @Override
public boolean onCreateOptionsMenu(Menu menu) {
// Inflate the menu; this adds items to the action bar if it is present.
getMenuInflater().inflate(R.menu.adult_joke, menu);
return true;
} public String getCalendarString() {
Calendar c = Calendar.getInstance(Locale.CHINA);
int mHour = c.get(Calendar.HOUR_OF_DAY);
int mMinter = c.get(Calendar.MINUTE);
return String.valueOf(mHour) + ":" + String.valueOf(mMinter);
} }
Jsoup解析html终于成功了!!!的更多相关文章
- 一步步教你为网站开发Android客户端---HttpWatch抓包,HttpClient模拟POST请求,Jsoup解析HTML代码,动态更新ListView
本文面向Android初级开发者,有一定的Java和Android知识即可. 文章覆盖知识点:HttpWatch抓包,HttpClient模拟POST请求,Jsoup解析HTML代码,动态更新List ...
- Android利用Jsoup解析html 开发网站客户端小记。
这些天业余时间比较多,闲来无事,想起了以前看过开发任意网站客户端的一篇文章,就是利用jsoup解析网站网页,通过标签获取想要的内容.好了废话不多说,用到的工具为 jsoup-1.7.2.jar包,具体 ...
- [java] jsoup 解析网页获取省市区域信息
到国家统计局抓取数据, 到该class下解析数据 /** * jsoup解析网页 * @author xwolf * @date 2016-12-13 18:11 * @since V1.0.0 */ ...
- jsoup解析HTML及简单实例
jsoup 中文参考文献 http://www.open-open.com/jsoup/ 本文将利用jsoup,简单实现网络抓取的功能,并给出一个小实例,该实例效果为:获取作者本人在博客园写的所 ...
- jsoup解析HTML
Connection conn = Jsoup.connect(String url); conn.data("txtBill", key);// 设置关键字查询字段 Docume ...
- Android开发探秘之三:利用jsoup解析HTML页面
这节主要是讲解jsoup解析HTML页面.由于在android开发过程中,不可避免的涉及到web页面的抓取,解析,展示等等,所以,在这里我主要展示下利用jsoup jar包来抓取cnbeta.com网 ...
- 终于成功仿了一次Kalman滤波器
终于成功仿了一次Kalman滤波器 首先是测试了从网上down的一段代码 % KALMANF - updates a system state vector estimate based upon a ...
- Jsoup 解析 HTML
Jsoup 文档 方法 要取得一个属性的值,可以使用Node.attr(String key) 方法 对于一个元素中的文本,可以使用Element.text()方法 对于要取得元素或属性中的HTML内 ...
- Jsoup解析HTML、加载文档等实例
一.引入jsoup的jar包:http://jsoup.org/download 补充:http://jsoup.org/apidocs/ Jsoup API 可以了解更详细的内容 二.Js ...
随机推荐
- angular开发者吐槽react+redux的复杂:“一个demo证明你的开发效率低下”
曾经看到一篇文章,写的是jquery开发者吐槽angular的复杂.作为一个angular开发者,我来吐槽一下react+redux的复杂. 例子 为了让大家看得舒服,我用最简单的一个demo来展示r ...
- Puppet简易入门
一.查看官方提供的下载源 https://docs.puppet.com/guides/puppetlabs_package_repositories.html 二. 选择对应系统的下载源 因为本机是 ...
- CentOS初始化Mysql5.7密码
/etc/init.d/mysql stopmysqld_safe --user=mysql --skip-grant-tables --skip-networking &mysql -u r ...
- struts2学习笔记--使用servletAPI实现ajax的一个小Demo
这个例子是点击网页上的一个button,然后调用action,使用response项前台打印"哎呦 不错哦",当然是以异步形式实现. jsp页面: <head> < ...
- 一张图看懂normal,static,sealed,abstract 的 区别
+-------------------------+---+--------+--------+--------+----------+ | Class Type | | normal | stat ...
- 【Android】直播必备之YUV使用总结 —— Android常用的几种格式:NV21/NV12/YV12/YUV420P的区别
说明 因工作方面接触到图像处理这一块,需要对手机摄像头采集的原始帧做Rotate或者Scale,但无奈对此的了解少之又少,于是网上搜了一顿,完事后将最近所学总结一下,以方便之后的人别踩太多坑. 首先想 ...
- java枚举类型学习
用的不多,但用的时候仅仅简单的使用,不太明白原理,今天就系统的学一下枚举.参考:java编程思想. Update: 枚举可以当做数据字典来存储,通常只要一个字段即instance本身,toString ...
- jQuery-1.9.1源码分析系列(三) Sizzle选择器引擎——词法解析
jQuery源码9600多行,而Sizzle引擎就独占近2000行,占了1/5.Sizzle引擎.jQuery事件机制.ajax是整个jQuery的核心,也是jQuery技术精华的体现.里面的有些策略 ...
- GUI 和 GUILayout 的区别
GUI 和 GUILayout 的区别 A~ GUI是Unity中的基础控件类,其中包含了常用的GUI控件,列如Button,Label,PasswordField,slider,Window等等~ ...
- Hadoop源码编译过程
一. 为什么要编译Hadoop源码 Hadoop是使用Java语言开发的,但是有一些需求和操作并不适合使用java,所以就引入了本地库(Native Libraries)的概念,通 ...