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 23 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

redis的八种使用场景

前言:redis是我们工作开发中,经常要打交道的,下面对redis的使用场景做总结介绍也是对redis举报的功能做梳理。缓存Redis最常见的用途是作为缓存,用于加速应用程序的响应速度。...

基于Redis的3种分布式ID生成策略

在分布式系统设计中,全局唯一ID是一个基础而关键的组件。随着业务规模扩大和系统架构向微服务演进,传统的单机自增ID已无法满足需求。高并发、高可用的分布式ID生成方案成为构建可靠分布式系统的必要条件。R...

基于OpenWrt系统路由器的模式切换与网页设计

摘要:目前商用WiFi路由器已应用到多个领域,商家通过给用户提供一个稳定免费WiFi热点达到吸引客户、提升服务的目标。传统路由器自带的Luci界面提供了工厂模式的Web界面,用户可通过该界面配置路...

这篇文章教你看明白 nginx-ingress 控制器

主机nginx一般nginx做主机反向代理(网关)有以下配置...

如何用redis实现注册中心

一句话总结使用Redis实现注册中心:服务注册...

爱可可老师24小时热门分享(2020.5.10)

No1.看自己以前写的代码是种什么体验?No2.DooM-chip!国外网友SylvainLefebvre自制的无CPU、无操作码、无指令计数器...No3.我认为CS学位可以更好,如...

Apportable:拯救程序员,IOS一秒变安卓

摘要:还在为了跨平台使用cocos2d-x吗,拯救objc程序员的奇葩来了,ApportableSDK:FreeAndroidsupportforcocos2d-iPhone。App...

JAVA实现超买超卖方案汇总,那个最适合你,一篇文章彻底讲透

以下是几种Java实现超买超卖问题的核心解决方案及代码示例,针对高并发场景下的库存扣减问题:方案一:Redis原子操作+Lua脚本(推荐)//使用Redis+Lua保证原子性publicbo...

3月26日更新 快速施法自动施法可独立设置

2016年3月26日DOTA2有一个79.6MB的更新主要是针对自动施法和快速施法的调整本来内容不多不少朋友都有自动施法和快速施法的困扰英文更新日志一些视觉BUG修复就不翻译了主要翻译自动施...

Redis 是如何提供服务的

在刚刚接触Redis的时候,最想要知道的是一个’setnameJhon’命令到达Redis服务器的时候,它是如何返回’OK’的?里面命令处理的流程如何,具体细节怎么样?你一定有问过自己...

lua _G、_VERSION使用

到这里我们已经把lua基础库中的函数介绍完了,除了函数外基础库中还有两个常量,一个是_G,另一个是_VERSION。_G是基础库本身,指向自己,这个变量很有意思,可以无限引用自己,最后得到的还是自己,...

China's top diplomat to chair third China-Pacific Island countries foreign ministers' meeting

BEIJING,May21(Xinhua)--ChineseForeignMinisterWangYi,alsoamemberofthePoliticalBureau...

移动工作交流工具Lua推出Insights数据分析产品

Lua是一个适用于各种职业人士的移动交流平台,它在今天推出了一项叫做Insights的全新功能。Insights是一个数据平台,客户可以在上面实时看到员工之间的交流情况,并分析这些情况对公司发展的影响...

Redis 7新武器:用Redis Stack实现向量搜索的极限压测

当传统关系型数据库还在为向量相似度搜索的性能挣扎时,Redis7的RedisStack...

Nginx/OpenResty详解,Nginx Lua编程,重定向与内部子请求

重定向与内部子请求Nginx的rewrite指令不仅可以在Nginx内部的server、location之间进行跳转,还可以进行外部链接的重定向。通过ngx_lua模块的Lua函数除了能实现Nginx...