(比较 tika 和正则 ,我更喜欢jsoup ) jsoup 抓取 iteye 网站

简介:  jsoup  效果     qq新闻 内容抓取 正则表达 (正则) 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  效果

 

  

qq新闻 内容抓取 正则表达 (正则)

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

 <dependency>

    <groupId>org.jsoup</groupId>

    <artifactId>jsoup</artifactId>

    <version>1.9.2</version>

</dependency>

 

 

  

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<Element> 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<IteyeItemEntity> getListIteyeEntity(String data){
		List<IteyeItemEntity> list = new ArrayList<IteyeItemEntity>();
		try{ 
			//Connection connection = Jsoup.connect(url);  
			//Document document = connection.get(); 
			Document document = Jsoup.parse(data); 
			Elements indexmain = document.select(".blog");
			 Iterator<Element> 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<GridEntity> getGridItem() {
		List<GridEntity> list = new ArrayList<GridEntity>();
		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<IteyeItemEntity> mDataList;
	private IteyeAdapter mAdapter;
	
	
	 private TextView                   mTopChooseBar;
	 private PopupWindow                mPopupWindow;
	 
	 
	 private IteyePopwindowGridListAdapter gridAdapter;
	 private GridView gridView;
	 private List<GridEntity> 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<IteyeItemEntity>();
		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<IteyeItemEntity> list = IteyeJsoupPerformer.getListIteyeEntity(result);
					mAdapter.setmDataList(list);
					mAdapter.notifyDataSetChanged(); 
					 
					   
				}
				break;
				case HTTP_SUCCESS: {   
					mListView.stopRefresh(); 
					mListView.stopLoadMore();
					String result = event.data;
					mAdapter.clearMDataList();
					 List<IteyeItemEntity> 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<String, Object
	            bundle.putString(IteyeMainActivity.ITEYE_DETAIL_URL, item.getArticleLink() );
	            msgIntent.putExtra("bundle", bundle);
	            msgIntent.setClass(MyApplication.newInstance(), IteyeDetailActivity.class);
	            startActivityForResult( msgIntent, 1000 );
			}
	}

	@Override
	public void onRefresh() { 
		start =1; 
		mListView.setPullLoadEnable(true);
		mListView.setPullRefreshEnable(true);
		IteyeHttpRequest.getIteyeDate(category, start);
	}


	@Override
	public void onLoadMore() { 
		start += 1;  
		IteyeHttpRequest.getIteyeDate(category, start);
	}

	@Override
	public void onClick(View view) {
		switch (view.getId()) {
		case R.id.tv_iteye_topbar:
			if (mPopupWindow.isShowing()) {
				mPopupWindow.dismiss();
			} else {
				mPopupWindow.showAsDropDown(view);
			}
			break;
		default:
			break;
		}
	}
 

	@Override
	public void OnIteyeGridViewItemclick(GridEntity item) {
		mTopChooseBar.setText(item.getName() );
        mPopupWindow.dismiss();
        start = 1;
        category = item.getId();
        IteyeHttpRequest.getIteyeDate(category, start);
	}
	
}

 

 

 

package com.couriousby.iteyedemo.request.http;

import com.android.volley.Response.ErrorListener;
import com.android.volley.Response.Listener;
import com.android.volley.VolleyError;
import com.android.volley.toolbox.StringRequest;
import com.android.volley.toolbox.Volley;
import com.couriousby.iteyedemo.MyApplication;
import com.couriousby.iteyedemo.request.manager.IteyeHttpManager;
import com.couriousby.iteyedemo.util.Constants;

public class IteyeHttpRequest {

	
	public  static void getIteyeDate(int catgory ,final int page){
		String url =  Constants.getIteyeUrl(catgory,page);
		StringRequest request = new StringRequest(url, new Listener<String>() {
 
			@Override
			public void onResponse(String response) { 
				if (page ==1 )
					IteyeHttpManager.getIteyeByPageFirst(response);
				else
					IteyeHttpManager.getIteyeByPage(response);	
			}
		}, new ErrorListener() { 
			@Override
			public void onErrorResponse(VolleyError error) { 
				IteyeHttpManager.getIteyeByPageError();
			}
		})
	/*	{
			@Override
			protected Response<String> parseNetworkResponse(
					NetworkResponse response) {
				String str = null;
		        try {
		            str = new String(response.data,"utf-8");
		        } catch (UnsupportedEncodingException e) { 
		            e.printStackTrace();
		        }
		        return Response.success(str, HttpHeaderParser.parseCacheHeaders(response));
			}
		}*/
		;
		Volley.newRequestQueue(MyApplication.newInstance()).add(request); 
	}
	
}

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

捐助开发者

在兴趣的驱动下,写一个免费的东西,有欣喜,也还有汗水,希望你喜欢我的作品,同时也能支持一下。 当然,有钱捧个钱场(右上角的爱心标志,支持支付宝和PayPal捐助),没钱捧个人场,谢谢各位。



 
 
 谢谢您的赞助,我会做的更好!

 

 

 

 

目录
相关文章
|
4月前
|
数据采集
JSoup 爬虫遇到的 404 错误解决方案
JSoup 爬虫遇到的 404 错误解决方案
|
7月前
|
Java Maven
在Java中,我们可以使用Jsoup库来解析和分析网页
在Java中,我们可以使用Jsoup库来解析和分析网页。以下是一个简单的示例,演示如何使用Jsoup库获取网页的标题
46 1
|
6月前
|
移动开发 JavaScript 前端开发
jsoup爬取HTML数据
jsoup是一个用于处理真实世界HTML的Java库。它提供了一个非常方便的API,用于获取URL、提取和操作数据,使用最好的HTML5 DOM方法和CSS选择器。
38 0
jsoup爬取HTML数据
|
8月前
|
数据采集 JSON JavaScript
jsoup爬虫发送get、post请求、解析html、获取json
jsoup爬虫发送get、post请求、解析html、获取json
339 0
|
10月前
|
数据采集 Web App开发 存储
Java爬虫第四篇:使用selenium、Jsoup 抓取图片
Java爬虫第四篇:使用selenium、Jsoup 抓取图片
264 0
|
9月前
|
移动开发 JavaScript 前端开发
Java使用Jsoup爬取数据
Java使用Jsoup爬取数据
121 0
|
10月前
|
数据采集 Java Maven
Java爬虫第三篇:使用Jsoup 抓取文章
Java爬虫第三篇:使用Jsoup 抓取文章
113 0
|
数据采集 Java
Java爬虫:Jsoup解析HTML
Java爬虫:Jsoup解析HTML
119 0
|
数据采集 Python
Python爬虫:使用lxml解析网页内容
Python爬虫:使用lxml解析网页内容
112 0
|
数据采集 Python
Python爬虫:pyquery模块解析网页
Python爬虫:pyquery模块解析网页