分享一个简单的java爬虫框架

反复给网站编写不同的爬虫逻辑太麻烦了,自己实现了一个小框架

可以自定义的部分有:

请求方式(默认为getuser-agent为谷歌浏览器的设置),可以通过实现requestset接口来自定义请求方式

储存方式(默认储存在f盘的html文件夹下),可以通过saveutil接口来自定义保存方式

需要保存的资源(默认为整个html页面)

筛选方式(默认所有url都符合要求),通过实现resoursechooser接口来自定义需要保存的url和资源页面

实现的部分有:

html页面的下载方式,通过httpclient实现html页面的下载

html页面的解析部分,通过jsoup实现html页面的解析

htmldownloader类,用于根据一个url下载一个html页面

package downloadpackage;
import java.io.bufferedreader;
import java.io.ioexception;
import java.io.inputstreamreader;
import org.apache.http.httpentity;
import org.apache.http.httpresponse;
import org.apache.http.impl.client.closeablehttpclient;
import org.apache.http.impl.client.httpclients;
/*
 * 根据一个url下载一个html页面
 */
public class htmldownloader {
	requestset requestset = null;
	public htmldownloader(requestset requestset){
		this.requestset = requestset;
	}
	public string downloadhtml(string url){
		string html = null;
		//创建一个客户端
		//创建一个读取流从entity读取html
		bufferedreader reader = null;
		closeablehttpclient httpclient = httpclients.createdefault();
		httpresponse response = null;
		try {
			response = httpclient.execute(requestset.getmethod(url));
			httpentity entity = response.getentity();
			reader = new bufferedreader(new inputstreamreader(entity.getcontent()));
			stringbuilder sb = new stringbuilder();
			while((html = reader.readline()) != null){
				sb.append(html);
			}
			html = sb.tostring();
			system.out.println("一个html页面获取成功");
		}
		catch (ioexception e) {
			system.out.println(url+"连接失败");
		}
		finally{
			if(reader != null){
				try {
					reader.close();
					httpclient.close();
				}
				catch (ioexception e) {
					// todo auto-generated catch block
					e.printstacktrace();
				}
			}
		}
		return html;
	}
}

urlget类,用于根据一个html页面获得所有的url连接

package downloadpackage;
import java.util.linkedlist;
import org.jsoup.jsoup;
import org.jsoup.nodes.document;
import org.jsoup.nodes.element;
import org.jsoup.select.elements;
public class urlget {
	public linkedlist<string> geturls(string html){
		linkedlist<string> urls = new linkedlist<string>();
		document doc = jsoup.parse(html);
		elements links = doc.getelementsbytag("a");
		for (element link:links){
			string url = link.attr("href");
			urls.add(url);
		}
		return urls;
	}
}

资源选择接口,需要实现三个方法,第一是isneed方法,判断url是否为需要的,第二个是isresourse方法,判断url页面是不是需要的资源页面,第三个是process方法,

有时网页上的url是我们需要的但是格式不对,对url进行加工

package choosepackage;
public interface resoursechooser {
	public boolean isneed(string url);
	public boolean isresourse(string url);
	public string process(string url);
}

requsetset类,用于自定义请求方法的接口,实现getmethod方法获取请求方法

package downloadpackage;
import org.apache.http.client.methods.httpget;
/*
 * 一个用于获得request请求的接口
 * 实现getmethod方法获取get方法
 */
public interface requestset {
	public httpget getmethod(string url);
}
saveutil接口用于自定义保存方式,需要实现save方法
package saveutil;
/*
 * 数据储存的工具接口,必须实现保存方法
 */
public interface saveutil {
	public void save(string url,string html);
}

spider类,有五中构造方法,可以实现多种自定义操作,其中实现了上述自定义接口的默认实现类

package spider;
import java.io.bufferedwriter;
import java.io.file;
import java.io.filewriter;
import java.io.ioexception;
import java.util.hashset;
import java.util.iterator;
import java.util.linkedlist;
import org.apache.http.client.config.requestconfig;
import org.apache.http.client.methods.httpget;
import choosepackage.myresoursechooser;
import choosepackage.resoursechooser;
import downloadpackage.htmldownloader;
import downloadpackage.requestset;
import downloadpackage.urlget;
import saveutil.mysaveutil;
import saveutil.saveutil;
/*
 * 用于爬取资源的类
 */
public class spider{
	public static void main(string[] args) {
		new spider("http://www.bilibili.net").spiderstart();
	}
	//种子url
	string seed = null;
	//用于保存数据的类,需要自己实现
	private saveutil saveutil = null;
	//html下载类
	private htmldownloader downloader = null;
	//url下载类
	private urlget urldownloader = null;
	//资源选择工具
	private resoursechooser resoursechooser = null;
	//用于保存未下载的网页
	linkedlist<string> unvisited = new linkedlist<string>();
	//用于保存已下载的网页
	hashset<string> visited = new hashset<string>();
	//自定义储存方式,请求方式,资源筛选方式的构造方法
	public spider(saveutil saveutil,requestset request,resoursechooser resoursechooser,string seed){
		this.saveutil = saveutil;
		this.downloader = new htmldownloader(request);
		this.urldownloader = new urlget();
		this.resoursechooser = resoursechooser;
		this.seed = seed;
		unvisited.add(seed);
	}
	//自定义储存方式,资源筛选方式的构造方法
	public spider(saveutil saveutil,resoursechooser resoursechooser,string seed){
		this.resoursechooser = resoursechooser;
		this.downloader = new htmldownloader(new getrequest());
		this.saveutil = saveutil;
		this.urldownloader = new urlget();
		this.seed = seed;
		unvisited.add(seed);
	}
	//自定义储存方式,请求的构造方法
	public spider(saveutil saveutil,requestset requestset,string seed){
		this.saveutil = saveutil;
		this.downloader = new htmldownloader(requestset);
		this.resoursechooser = new myresoursechooser();
		this.urldownloader = new urlget();
		this.seed = seed;
		unvisited.add(seed);
	}
	//自定义储存方式的构造方法
	public spider(saveutil saveutil,string seed){
		this.saveutil = saveutil;
		this.downloader = new htmldownloader(new getrequest());
		this.resoursechooser = (new myresoursechooser());
		this.urldownloader = new urlget();
		this.seed = seed;
		unvisited.add(seed);
	}
	//默认的爬虫构造方法
	public spider(string seed){
		this.saveutil = new mysaveutil();
		this.downloader = new htmldownloader(new getrequest());
		this.resoursechooser = (new myresoursechooser());
		this.urldownloader = new urlget();
		this.seed = seed;
		unvisited.add(seed);
	}
	//开始爬取的方法
	private void spiderstart(){
		string html = null;
		while(!unvisited.isempty()){
			string url = unvisited.poll();
			system.out.println("开始获取"+url);
			if(resoursechooser.isneed(url)){
				try{
					html = downloader.downloadhtml(url);
				}
				catch(runtimeexception e){
					system.out.println(url+"连接获取失败");
					continue;
				}
				visited.add(url);
				linkedlist<string> urls = new linkedlist<string>();
				try{
					urls = urldownloader.geturls(html);
				}
				catch(runtimeexception e){
					system.out.println(url+"的html页面为空");
					continue;
				}
				iterator<string> it = urls.iterator();
				while(it.hasnext()){
					string newurl = it.next();
					if(resoursechooser.isneed(newurl)&&!visited.contains(newurl)&&!unvisited.contains(newurl)){
						newurl = resoursechooser.process(newurl);
						unvisited.add(newurl);
						system.out.println(newurl+"加入页面");
					}
				}
				system.out.println("获取了"+url+"上的所有url");
				if(resoursechooser.isresourse(url)){
					saveutil.save(url,html);
				}
			}
		}
	}
	//默认资源筛选类
	private class myresoursechooser implements resoursechooser{
		@override
		public boolean isneed(string url) {
			// todo auto-generated method stub
			if(!url.startswith("/")&&!url.startswith("http")){
				return false;
			}
			return true;
		}
		@override
		public boolean isresourse(string url) {
			// todo auto-generated method stub
			return true;
		}
		@override
		public string process(string url) {
			// todo auto-generated method stub
			if(!url.startswith("http")){
				url = seed+url;
			}
			return url;
		}
	}
	public class getrequest implements requestset{
		public httpget getmethod(string url) {
			// todo auto-generated method stub
			//创建一个get请求方法
			httpget getmethod = new httpget(url);
			//httphost proxy = new httphost("124.88.67.81",80);这里不设置代理ip
			//设置请求超时时间等 
			requestconfig responseconfig = requestconfig.custom().setconnectionrequesttimeout(10000).setconnecttimeout(10000).setsockettimeout(10000).build();
			//设置请求头,主要是user-agent
			getmethod.addheader("user-agent","mozilla/5.0 (windows nt 10.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/56.0.2924.87 safari/537.36");
			//设置请求参数
			getmethod.setconfig(responseconfig);
			return getmethod;
		}
	}
	//默认的存储类
	public class mysaveutil implements saveutil{
		@override
		public void save(string url, string html) {
			// todo auto-generated method stub
			string filename = getfilename(url);
			bufferedwriter writer = null;
			try{
				writer = new bufferedwriter(new filewriter(filename));
				writer.write(html);
				writer.flush();
				system.out.println("文件写入成功");
			}
			catch(ioexception e){
				system.out.println("文件写入失败");
			}
			finally{
				try {
					if(writer != null)
					writer.close();
				}
				catch (ioexception e) {
					// todo auto-generated catch block
					system.out.println("流关闭失败");
				}
			}
		}
		private string getfilename(string url){
			string fileparentpath = "f://html";
			file file = new file(fileparentpath);
			if(!file.exists()){
				file.mkdir();
			}
			int last = url.lastindexof(".");
			int first = url.indexof(".");
			url = url.substring(first,last);
			url = url.replaceall("\\.", "");
			url = url.replaceall("/", "");
			return fileparentpath+"/"+url+".txt";
		}
	}
}

总结

以上就是本文关于分享一个简单的java爬虫框架的全部内容，希望对大家有所帮助。感兴趣的朋友可以继续参阅本站：python爬虫实例爬取网站搞笑段子、java线程之锁对象lock-同步问题更完美的处理方式代码实例、java编程几个循环实例代码分享等，有什么问题可以随时留言，小编会及时回复大家的。感谢朋友们对本站的支持！