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 27 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

MySQL进阶五之自动读写分离mysql-proxy

自动读写分离目前,大量现网用户的业务场景中存在读多写少、业务负载无法预测等情况,在有大量读请求的应用场景下,单个实例可能无法承受读取压力,甚至会对业务产生影响。为了实现读取能力的弹性扩展,分担数据库压...

Postgres vs MySQL_vs2022连接mysql数据库

...

3分钟短文 | Laravel SQL筛选两个日期之间的记录,怎么写?

引言今天说一个细分的需求,在模型中,或者使用laravel提供的EloquentORM功能,构造查询语句时,返回位于两个指定的日期之间的条目。应该怎么写?本文通过几个例子,为大家梳理一下。学习时...

一文由浅入深带你完全掌握MySQL的锁机制原理与应用

本文将跟大家聊聊InnoDB的锁。本文比较长,包括一条SQL是如何加锁的,一些加锁规则、如何分析和解决死锁问题等内容,建议耐心读完,肯定对大家有帮助的。为什么需要加锁呢?...

验证Mysql中联合索引的最左匹配原则

后端面试中一定是必问mysql的,在以往的面试中好几个面试官都反馈我Mysql基础不行,今天来着重复习一下自己的弱点知识。在Mysql调优中索引优化又是非常重要的方法,不管公司的大小只要后端项目中用到...

MySQL索引解析(联合索引/最左前缀/覆盖索引/索引下推)

目录1.索引基础...

你会看 MySQL 的执行计划(EXPLAIN)吗?

SQL执行太慢怎么办?我们通常会使用EXPLAIN命令来查看SQL的执行计划,然后根据执行计划找出问题所在并进行优化。用法简介...

MySQL 从入门到精通(四)之索引结构

索引概述索引(index),是帮助MySQL高效获取数据的数据结构(有序),在数据之外,数据库系统还维护者满足特定查询算法的数据结构,这些数据结构以某种方式引用(指向)数据,这样就可以在这些数据结构...

mysql总结——面试中最常问到的知识点

mysql作为开源数据库中的榜一大哥,一直是面试官们考察的重中之重。今天,我们来总结一下mysql的知识点,供大家复习参照,看完这些知识点,再加上一些边角细节,基本上能够应付大多mysql相关面试了(...

mysql总结——面试中最常问到的知识点(2)

首先我们回顾一下上篇内容,主要复习了索引,事务,锁,以及SQL优化的工具。本篇文章接着写后面的内容。性能优化索引优化,SQL中索引的相关优化主要有以下几个方面:最好是全匹配。如果是联合索引的话,遵循最...

MySQL基础全知全解!超详细无废话!轻松上手~

本期内容提醒:全篇2300+字,篇幅较长,可搭配饭菜一同“食”用,全篇无废话(除了这句),干货满满,可收藏供后期反复观看。注:MySQL中语法不区分大小写,本篇中...

深入剖析 MySQL 中的锁机制原理_mysql 锁详解

在互联网软件开发领域,MySQL作为一款广泛应用的关系型数据库管理系统,其锁机制在保障数据一致性和实现并发控制方面扮演着举足轻重的角色。对于互联网软件开发人员而言,深入理解MySQL的锁机制原理...

Java 与 MySQL 性能优化:MySQL分区表设计与性能优化全解析

引言在数据库管理领域,随着数据量的不断增长,如何高效地管理和操作数据成为了一个关键问题。MySQL分区表作为一种有效的数据管理技术,能够将大型表划分为多个更小、更易管理的分区,从而提升数据库的性能和可...

MySQL基础篇:DQL数据查询操作_mysql 查

一、基础查询DQL基础查询语法SELECT字段列表FROM表名列表WHERE条件列表GROUPBY分组字段列表HAVING分组后条件列表ORDERBY排序字段列表LIMIT...

MySql:索引的基本使用_mysql索引的使用和原理

一、索引基础概念1.什么是索引?索引是数据库表的特殊数据结构(通常是B+树),用于...