java简易爬虫Crawler

package com.xhs.crawler;

import java.util.Scanner;

/**
 * @author XHS_12302
 * @version  1.0
 * @date  2017_07_11
 * 
 * 
 * @description 这是我的第一个爬虫，比较简单，没有队列，广度优先算法等，用list集合代替了队列。
 *              而且只爬取一个网址上面的图片，并不是将网址中的链接<href>加入队列，然后下载一个网址一个网址下载其中的图片。
 *              不过，这是前期的，处于摸索阶段，后期学完队列和广算后，在涉及一点多线程，肯定会比想象中的更实用
 */
public class Start_Crawler {
	public static void main(String[] args) {
		System.out.println("请输入网址：");
		
		//获取用户要爬取的网址
		Scanner in=new Scanner(System.in);
		String url=in.next();
		
		//通过用户的输入建立一个Get_Html的一个g对象
		Get_Html g=new Get_Html(url);
		//调用g中的get()方法模拟请求网站服务器，返回回应的字符串
		String htmlstr=g.get();
		
		//建立一个Html_analyze对象ha用来分析服务器返回来的字符串
		Html_analyze ha=new Html_analyze(htmlstr);
		
		/*for (String href :ha.analyzeHtmlHref()) {
			System.out.println(href);
		}*/
		
		//调用ha.analyzeHtmlImage()方法将分析出来的图片地址放进list里面，传回来一个图片地址集合，
		//然后新建下载。
		new Download_pic().Download(ha.analyzeHtmlImage());
		
		System.out.println("program has done!");
		in.close();
	}
}

package com.xhs.crawler;

import java.io.BufferedReader;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.net.URLConnection;

public class Get_Html {
	private String url_path;
	private String htmlstr;
	StringBuffer contentBuffer = new StringBuffer();
	Get_Html(String url){
		this.url_path=url;
	}

	public String get(){
		   FileWriter fw=null;
		try {
			fw=new FileWriter("C:\\Users\\Administrator\\Desktop\\crawler.txt");
			URL url=new URL(url_path);
			URLConnection hc=url.openConnection();
			hc.setConnectTimeout(5000);
			hc.setDoInput(true);
			((HttpURLConnection) hc).setRequestMethod("GET");
			int returnCode=((HttpURLConnection) hc).getResponseCode();
			if(returnCode==200){
				InputStream input=hc.getInputStream();
				
				 InputStreamReader istreamReader = new InputStreamReader(input, "utf-8");  
		         BufferedReader buffStr = new BufferedReader(istreamReader);  
		  
		        String str = null;  
		       while ((str = buffStr.readLine()) != null) 
		          contentBuffer.append(str);
		          htmlstr=contentBuffer.toString();
                  fw.write(htmlstr);
			   input.close();
			   istreamReader.close();
			   buffStr.close();
			   fw.close();
			}
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		return htmlstr;
		
	}
	
	
}

package com.xhs.crawler;


import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Html_analyze {
	private String src;
	Html_analyze(String src){
		this.src=src;
	}
	public List<String> analyzeHtmlImage(){
		String regex="http[s]{0,1}://[^\\s]*\\.(jpg|bmp|png)";
		//String sr="http://img5.imgtn.bdimg.com/it/u=1380084653,2448555822&fm=26&gp=0.jpg";
		List<String> listImgUrl=new ArrayList<>();
		Pattern p=Pattern.compile(regex);
		Matcher m=p.matcher(src);
		while(m.find()){
			System.out.println(m.group());
			listImgUrl.add(m.group());
		}
		System.out.println("\n\n总共找到记录："+listImgUrl.size()+"\n");
		return listImgUrl;
	}
	public List<String>  analyzeHtmlHref(){
		//分析href标签   并且加入listHref
		String regex="<a.*?href=\"(.*?)\">";
		List<String> listHref=new ArrayList<>();
		Pattern p=Pattern.compile(regex);
		Matcher m=p.matcher(src);
		while(m.find()){
			listHref.add(m.group());
		}
		return listHref;
	}
}

package com.xhs.crawler;

import java.io.File;

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.URL;

import java.util.List;

public class Download_pic {
	public void Download(List<String> listImgSrc) {
		int count = 1;
		for (String url_path : listImgSrc) {
			InputStream in = null;
			FileOutputStream fo = null;
			String imageName = url_path.substring(
					url_path.lastIndexOf("/") + 1, url_path.length());
			try {
				byte[] data = new byte[500];// 1024
				File f = new File(
						"C:\\Users\\Administrator\\Desktop\\crawler\\");
				if (!f.exists()) {
					f.mkdir();
				}
				fo = new FileOutputStream(new File(f.getAbsolutePath() + "\\"
						+ imageName));
				URL url = new URL(url_path);
				HttpURLConnection con = (HttpURLConnection) url
						.openConnection();
				con.setConnectTimeout(5000);
				con.setDoInput(true);
				con.setRequestMethod("GET");
				// con.setRequestProperty("user-agent","Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1;SV1)");
				// 设置代理
				int numCode = con.getResponseCode();
				in = con.getInputStream();// int length
				int lengthZ = 0;
				if (numCode == 200) {
					while ((lengthZ = in.read(data)) != -1) {
						fo.write(data, 0, lengthZ); // write(data,0,length);
						fo.flush();
					}
					System.out.println("下载成功:\t" + imageName + "\t剩余:\t"
							+ (listImgSrc.size() - count));
				} else {
					System.out.println("访问失败，返回码不是200");
				}

			} catch (Exception e) {
				// TODO Auto-generated catch block
				e.printStackTrace();
				System.out.println(imageName + "下载失败");
			} finally {
				try {
					if (in != null)
						in.close();
					if (fo != null)
						fo.close();
					count++;
				} catch (IOException e) {
					// TODO Auto-generated catch block
					// e.printStackTrace();
					System.out.println("关闭流出现点问题··");
				}
			}

		}
	}

}