百度360必应搜狗淘宝本站头条
当前位置:网站首页 > IT技术 > 正文

jsoup 抓取 iteye 网站_js抓取网页内容

wptr33 2025-02-20 18:17 20 浏览

jsoup 效果

http://knight-black-bob.iteye.com/blog/2312411

比较 tika 和正则 ,我更喜欢jsoup

正则 比较难写 ,, ,,,,

下面有jar 包下载

org.jsoup

jsoup

1.9.2

IteyeItemEntity [
userName=wosyingjun,
userPicLink=http://www.iteye.com/upload/logo/user/1184026/fa9a8493-f9a7-3e3b-9630-12ad8f65d277-thumb.png?1467599214,
userBlogLink=http://wosyingjun.iteye.com, 
title=推荐几个自己写的Java后端相关的范例项目, 
content=推荐几个自己写的范例项目 这里推荐几个自己写的范例项目,主要采用SSM(Spring+SpringMVC+Mybatis)框架,分布式架构采用的是(dubbo+zookeeper)。范例项目的好处是简单易懂,在架构一个新的项目的时候可以直接当成脚手架来用,方便快速开发,另外项目中涉及到以及未来可能涉及到的知识点都会不断完善。 三个项目是互相发展而来的,目前仍在不断完善中,依次为: ..., 
articleLink=http://wosyingjun.iteye.com/blog/2312553, 
seeNum=有2871人浏览, 
goodNum=7顶, 
badNum=0踩, 
insertTime=2016-07-21 09:04
]



//Connection connection = Jsoup.connect(url);  
			//Document document = connection.get; 
			Document document = Jsoup.parse(data); 
			Elements indexmain = document.select(".blog");
			 Iterator blogIter = indexmain.iterator;  
			 IteyeItemEntity item = null;
 while (blogIter.hasNext) { 
 Element element = blogIter.next; 
 
 String userName = element.select(".content .blog_info a[title]").text;
 String userPicLink = element.select(".content .logo img").attr("src");
 String userBlogLink = element.select(".content .blog_info a").attr("href");
 String title = element.select(".content h3 a[title]").text; 
 String content = element.select(".content  div").iterator.next.text; 
 String articleLink =    element.select(".content h3 a").last.attr("href");
 String seeNum = element.select(".content .blog_info .view").text;
 String goodNum = element.select(".content .blog_info .digged .digg").text;
 String badNum = element.select(".content .blog_info .digged .bury").text;
 String insertTime = element.select(".content .blog_info .date").text;
 item = new IteyeItemEntity(userName, userPicLink, userBlogLink, title, content, articleLink, seeNum, goodNum, badNum, insertTime);
 list.add(item);
package com.couriousby.iteyedemo.util;

import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;

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

import android.util.Log;
import android.widget.Toast;

import com.couriousby.iteyedemo.MyApplication;
import com.couriousby.iteyedemo.entity.IteyeItemEntity;

/**
 * @author baoyou E-mail:curiousby@163.com
 * @version 2016-7-22 上午10:58:49
 *
 * desc: ...
 */
public class IteyeJsoupPerformer {
	
	public static List getListIteyeEntity(String data){
		List list = new ArrayList;
		try{ 
			//Connection connection = Jsoup.connect(url);  
			//Document document = connection.get; 
			Document document = Jsoup.parse(data); 
			Elements indexmain = document.select(".blog");
			 Iterator blogIter = indexmain.iterator;  
			 IteyeItemEntity item = null;
 while (blogIter.hasNext) { 
 Element element = blogIter.next; 
 
 String userName = element.select(".content .blog_info a[title]").text;
 String userPicLink = element.select(".content .logo img").attr("src");
 String userBlogLink = element.select(".content .blog_info a").attr("href");
 String title = element.select(".content h3 a[title]").text; 
 String content = element.select(".content  div").iterator.next.text; 
 String articleLink =    element.select(".content h3 a").last.attr("href");
 String seeNum = element.select(".content .blog_info .view").text;
 String goodNum = element.select(".content .blog_info .digged .digg").text;
 String badNum = element.select(".content .blog_info .digged .bury").text;
 String insertTime = element.select(".content .blog_info .date").text;
 item = new IteyeItemEntity(userName, userPicLink, userBlogLink, title, content, articleLink, seeNum, goodNum, badNum, insertTime);
 list.add(item);
 }
			
			
		}catch(Exception e){
			e.printStackTrace; 
		}
		return list;
	}


package com.couriousby.iteyedemo.util;

import java.util.ArrayList;
import java.util.List;

import com.couriousby.iteyedemo.R;
import com.couriousby.iteyedemo.entity.GridEntity;

/**
 * @author baoyou E-mail:curiousby@163.com
 * @version 2016-7-22 下午1:10:55
 *
 * desc: ...
 */
public class Constants {

	final static String URL_BASE = "http://www.iteye.com/blogs"; 
	
	public static String getIteyeCategory(int category ) { 
		switch (category) {
		case 0:
			return "";
		case 1:
			return "/category/mobile"; 
		case 2:
			return "/category/web"; 
		case 3:
			return "/category/architecture"; 
		case 4:
			return "/category/language"; 
		case 5:
			return "/category/internet"; 
		case 6:
			return "/category/opensource"; 
		case 7:
			return "/category/os"; 
		case 8:
			return "/category/database"; 
		case 9:
			return "/category/develop"; 
		case 10:
			return "/category/industry"; 
		case 11:
			return "/category/other"; 

		default: 
			return "";
		} 
	}
	
	public static String getIteyeUrl(int category,int page) { 
		return URL_BASE + getIteyeCategory(category)+"?page="+page;
	}
	
	
	
	public static List getGridItem {
		List list = new ArrayList;
		list.add(new GridEntity(0, "全部分类", R.drawable.iteye_all, 0)); 
		list.add(new GridEntity(1, "移动开发", R.drawable.iteye_mobile, 1)); 
		list.add(new GridEntity(2, "web前端", R.drawable.iteye_web, 2)); 
		list.add(new GridEntity(3, "企业架构", R.drawable.iteye_architecture, 3)); 
		list.add(new GridEntity(4, "编程语言", R.drawable.iteye_language, 4)); 
		list.add(new GridEntity(5, "互联网", R.drawable.iteye_internet, 5)); 
		list.add(new GridEntity(6, "开源软件", R.drawable.iteye_opensource, 6)); 
		list.add(new GridEntity(7, "操作系统", R.drawable.iteye_os, 7)); 
		list.add(new GridEntity(8, "数据库", R.drawable.iteye_database, 8)); 
		list.add(new GridEntity(9, "研发管理", R.drawable.iteye_develop, 9)); 
		list.add(new GridEntity(10, "行业应用", R.drawable.iteye_industry, 10)); 
		list.add(new GridEntity(11, "非技术", R.drawable.iteye_other, 11)); 

		return list;
	}
}
package com.couriousby.iteyedemo.activity;

import java.util.ArrayList;
import java.util.List;

import android.app.Activity;
import android.content.Context;
import android.content.Intent;
import android.graphics.Color;
import android.graphics.drawable.BitmapDrawable;
import android.graphics.drawable.ColorDrawable;
import android.os.Bundle;
import android.view.View;
import android.view.View.OnClickListener;
import android.widget.AdapterView;
import android.widget.AdapterView.OnItemClickListener;
import android.widget.AdapterView.OnItemSelectedListener;
import android.widget.LinearLayout.LayoutParams;
import android.widget.GridView;
import android.widget.PopupWindow;
import android.widget.TextView;

import com.couriousby.iteyedemo.MyApplication;
import com.couriousby.iteyedemo.R;
import com.couriousby.iteyedemo.adapter.IteyeAdapter;
import com.couriousby.iteyedemo.adapter.IteyePopwindowGridListAdapter;
import com.couriousby.iteyedemo.entity.GridEntity;
import com.couriousby.iteyedemo.entity.IteyeItemEntity;
import com.couriousby.iteyedemo.listener.OnIteyeGridViewItemclickListener;
import com.couriousby.iteyedemo.quote.xlistview.MsgListView;
import com.couriousby.iteyedemo.quote.xlistview.MsgListView.IXListViewListener;
import com.couriousby.iteyedemo.request.event.IteyeStringHttpEvent;
import com.couriousby.iteyedemo.request.event.base.RequestEvent;
import com.couriousby.iteyedemo.request.http.IteyeHttpRequest;
import com.couriousby.iteyedemo.util.Constants;
import com.couriousby.iteyedemo.util.IteyeJsoupPerformer;

import de.greenrobot.event.EventBus;

public class IteyeMainActivity extends Activity  implements IXListViewListener ,OnItemClickListener,OnClickListener,OnIteyeGridViewItemclickListener{
	
	
	final static String ITEYE_DETAIL_URL = "iteye_detail_url";
	
	private static int start = 1; 
	private static int category = 0; 
	
	private Context mContext;
	
	
	private MsgListView mListView;
	private List mDataList;
	private IteyeAdapter mAdapter;
	
	
	 private TextView mTopChooseBar;
	 private PopupWindow mPopupWindow;
	 
	 
	 private IteyePopwindowGridListAdapter gridAdapter;
	 private GridView gridView;
	 private List mGridList;
	 
	@Override
	protected void onCreate(Bundle savedInstanceState) {
		super.onCreate(savedInstanceState);
		setContentView(R.layout.iteye_list);
		
		this.mContext = IteyeMainActivity.this;
		
		initUtils;
		initView;
		initListeners;
		
		EventBus.getDefault.register( this );
		start =1;
		category=0;
		IteyeHttpRequest.getIteyeDate(category, start);
	}
	
	private void initUtils {  
		mDataList =  new ArrayList;
		mAdapter = new IteyeAdapter(mContext); 
		mAdapter.setmDataList(mDataList); 
		
		mGridList = Constants.getGridItem;
		gridAdapter = new IteyePopwindowGridListAdapter(mContext);
		gridAdapter.setOnIteyeGridViewItemclickListener(this);
		gridAdapter.setmList(mGridList);
	}
	private void initView { 
		mListView = (MsgListView) this.findViewById(R.id.qq_news_list);   
		mListView.setAdapter(mAdapter);
		
		
        
		
		View baseView = View.inflate( this, R.layout.iteye_topbar, null );
		
		mTopChooseBar = (TextView) this.findViewById( R.id.tv_iteye_topbar);
		mPopupWindow = new PopupWindow(baseView ,LayoutParams.MATCH_PARENT,
 LayoutParams.WRAP_CONTENT, false );
        mPopupWindow.setBackgroundDrawable( new BitmapDrawable );
        mPopupWindow.setOutsideTouchable( true );
        mPopupWindow.setFocusable( true );
		
		gridView = (GridView) baseView.findViewById(R.id.iteye_gr_mlist);
		gridView.setAdapter(gridAdapter);
	}
	private void initListeners {  

	    mTopChooseBar.setOnClickListener(this); 
	    
		mListView.setPullLoadEnable(true);
		mListView.setPullRefreshEnable(true);
		mListView.setXListViewListener(this);
		mListView.setAdapter(mAdapter); 
		mListView.setOnItemClickListener(this);
		 
		gridView.setSelector(new ColorDrawable(Color.TRANSPARENT));
	}

	@Override
    public void onDestroy {
        EventBus.getDefault.unregister( this );
        super.onDestroy;
    }
	public void onEventMainThread(RequestEvent requestEvent){
			
			if(requestEvent instanceof IteyeStringHttpEvent){
				IteyeStringHttpEvent event = (IteyeStringHttpEvent) requestEvent;
				switch(event.status){
				case HTTP_ERROR:
					mListView.stopRefresh; 
					mListView.stopLoadMore;
					mListView.setPullLoadEnable(false);
					break;
				case HTTP_START:
				{
					mListView.stopRefresh; 
					mListView.stopLoadMore;
					String result = event.data;
					mAdapter.clearMDataList;
					 List list = IteyeJsoupPerformer.getListIteyeEntity(result);
					mAdapter.setmDataList(list);
					mAdapter.notifyDataSetChanged; 
					 
					   
				}
				break;
				case HTTP_SUCCESS: {   
					mListView.stopRefresh; 
					mListView.stopLoadMore;
					String result = event.data;
					mAdapter.clearMDataList;
					 List list = IteyeJsoupPerformer.getListIteyeEntity(result);
					mAdapter.addMDataList(list);
					mAdapter.notifyDataSetChanged; 
				}
				  break;
				default:
					break;
				}
			}else{
				
			}
	}

	@Override
	public void onItemClick(AdapterView parent, View v, int position, long id) { 
		IteyeItemEntity  item = mAdapter.getItem(position - 1 );
		 if (item != null) {
				Intent msgIntent  = new Intent;   
				Bundle bundle = new Bundle; // Bundle的底层是一个HashMap

相关推荐

威信Chronosonic XVX全新旗舰全球首发 设计特点彻底公开

第一眼看到WilsonAudio新推出的ChronosonicXVX音箱,相信大家都会直觉认为它是两年前超级旗舰WAMMMasterChronosonic的缩小版,不过这个推测并不完全正确。C...

C#高精度Timer和Delay以及时间测量

在PCHMI7.0后在工具箱里会多一个MsTimer,以及Delay和Microsecond两个类。...

python教程从基础到精通,第9课—日期与时间

Hello,小伙伴们,祝大家五.一玩得快乐!刚学习完了七大数据类型,今天咱们来学习日期与时间的表示方法。Python标准库中提供了时间和日期的支持:calendar:日历相关;time、datetim...

软件测试|教你轻松玩转Python日期时间

Python基础之日期时间处理...

Go语言中互斥锁与读写锁,你知多少?

简述Golang中的锁机制主要包含互斥锁和读写锁互斥锁互斥锁是传统并发程序对共享资源进行控制访问的主要手段。在Go中主要使用sync.Mutex的结构体表示。一个简单的示例:funcmutex()...

变形金刚动画大电影——经典台词赏析

YOURDAYSARENUMBEREDNOW,DECEPTI-CREEPS你们活不了多久了,霸天虎小子。-{铁皮说的话,体现了铁皮的嫉恶如仇,可是后来铁皮在飞船上遇袭身亡,可谓是出师未捷身先...

Python时间日期模块使用教程(python3日期)

1.时间日期处理概述在日常编程中,时间日期处理是非常常见的需求,比如:记录日志时间...

亚马逊介绍AWS“无服务器”云服务改进:数据库可线上扩充容量等

IT之家11月29日消息,在今天于美国拉斯维加斯展开的亚马逊“AWSre:Invent2023”活动中,亚马逊计算部门资深副总裁PeterDeSantis,介绍了旗下三款云端服务,IT...

2.日期格式 datetime(日期时间显示格式)

fromdatetimeimportdatetime1.获取当前日期和时间now=datetime.now()#2025-05-3110:56:01.4687822.格式化日期...

【科普】时间单位大盘点(时间单位都有哪些?)

时间单位,是7种基本单位之一,长度、时间、质量、物质的量、光照度、电流和(热力学)温度是七种基本单位。本词条中时间单位以时间从大到小列。今天我们来盘点下时间的单位换算...

基于PHP的Laravel框架,盘点Github高星Web管理后台,效率为王!

在Web开发工作中,选择一个高效、稳定的后台管理系统是提高开发效率的关键。虽然PHP在近些年中的热度有所减退,但其上手简单、开源、灵活且被广泛应用的特点,仍然使其在编程语言排行榜中保持前十的位置。这表...

如何使用PHP编写一个简单的留言板?

留言板是一个常见的Web应用程序,允许用户在网站上发布和查看留言。在本文中,我们将使用PHP编写一个简单的留言板,介绍构建过程中的关键步骤和技巧。一、准备工作在开始编写留言板之前,我们需要准备好以下工...

产品经理提需求时要考虑的 15 个隐性需求

虽然世界充满未知的变化,但是有一些大的方向还是可以把握的,本文跟大家谈谈产品经理提需求时要考虑的15个隐性需求,enjoy~俗话说,计划赶不上变化快,无论需求文档做得如何细致,考虑得如何周全,总会...

关于 PHP 启动 MongoDb 找不到指定模块问题

前言:最近有一个小demo,需要通过PHP将用户行为记录储存到MongoDB,再用Spark做协同过滤。由于以前处理跨语言交互是通过消息中间件,这次本地使用MongoDB却弄出了几个问...

PHP程序员老鸟面试经历(php程序员怎么样)

在任何时代找任何工作都有面试这么一说的。特别是高端技术类的工种对技术理论和技术实操能力要求很严格。大部分公司招收技术员工的要求也越来愈高。至于PHP程序员也是如此,我估计大多数PHP老鸟已经不在意所...