一个简单的爬虫框架

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Get user-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";
}
}
}