亲宝软件园·资讯

展开

Java 实现网络爬虫框架

冰 河 人气:0

Java 实现网络爬虫框架

最近在做一个搜索相关的项目,需要爬取网络上的一些链接存储到索引库中,虽然有很多开源的强大的爬虫框架,但本着学习的态度,自己写了一个简单的网络爬虫,以便了解其中的原理。今天,就为小伙伴们分享下这个简单的爬虫程序!!

一、每个类的功能介绍

二、每个类的源代码

DownloadPage.java 此类要用到HttpClient组件。

package com.sreach.spider;

import java.io.IOException;
import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.util.EntityUtils;

/**
 * @author binghe
 */
public class DownloadPage {

 /**
  * 根据URL抓取网页内容
  * 
  * @param url
  * @return
  */
 public static String getContentFormUrl(String url) {
  /* 实例化一个HttpClient客户端 */
  HttpClient client = new DefaultHttpClient();
  HttpGet getHttp = new HttpGet(url);

  String content = null;

  HttpResponse response;
  try {
   /* 获得信息载体 */
   response = client.execute(getHttp);
   HttpEntity entity = response.getEntity();

   VisitedUrlQueue.addElem(url);

   if (entity != null) {
    /* 转化为文本信息 */
    content = EntityUtils.toString(entity);

    /* 判断是否符合下载网页源代码到本地的条件 */
    if (FunctionUtils.isCreateFile(url)
      && FunctionUtils.isHasGoalContent(content) != -1) {
     FunctionUtils.createFile(
       FunctionUtils.getGoalContent(content), url);
    }
   }

  } catch (ClientProtocolException e) {
   e.printStackTrace();
  } catch (IOException e) {
   e.printStackTrace();
  } finally {
   client.getConnectionManager().shutdown();
  }

  return content;
 }

}

 FunctionUtils.java 此类的方法均为static方法

package com.sreach.spider;

import java.io.BufferedWriter;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
 * @author binghe
 */
public class FunctionUtils {

 /**
  * 匹配超链接的正则表达式
  */
 private static String pat = "http://www\\.oschina\\.net/code/explore/.*/\\w+\\.[a-zA-Z]+";
 private static Pattern pattern = Pattern.compile(pat);

 private static BufferedWriter writer = null;

 /**
  * 爬虫搜索深度
  */
 public static int depth = 0;

 /**
  * 以"/"来分割URL,获得超链接的元素
  * 
  * @param url
  * @return
  */
 public static String[] divUrl(String url) {
  return url.split("/");
 }

 /**
  * 判断是否创建文件
  * 
  * @param url
  * @return
  */
 public static boolean isCreateFile(String url) {
  Matcher matcher = pattern.matcher(url);

  return matcher.matches();
 }

 /**
  * 创建对应文件
  * 
  * @param content
  * @param urlPath
  */
 public static void createFile(String content, String urlPath) {
  /* 分割url */
  String[] elems = divUrl(urlPath);
  StringBuffer path = new StringBuffer();

  File file = null;
  for (int i = 1; i < elems.length; i++) {
   if (i != elems.length - 1) {

    path.append(elems[i]);
    path.append(File.separator);
    file = new File("D:" + File.separator + path.toString());

   }

   if (i == elems.length - 1) {
    Pattern pattern = Pattern.compile("\\w+\\.[a-zA-Z]+");
    Matcher matcher = pattern.matcher(elems[i]);
    if ((matcher.matches())) {
     if (!file.exists()) {
      file.mkdirs();
     }
     String[] fileName = elems[i].split("\\.");
     file = new File("D:" + File.separator + path.toString()
       + File.separator + fileName[0] + ".txt");
     try {
      file.createNewFile();
      writer = new BufferedWriter(new OutputStreamWriter(
        new FileOutputStream(file)));
      writer.write(content);
      writer.flush();
      writer.close();
      System.out.println("创建文件成功");
     } catch (IOException e) {
      e.printStackTrace();
     }

    }
   }

  }
 }

 /**
  * 获取页面的超链接并将其转换为正式的A标签
  * 
  * @param href
  * @return
  */
 public static String getHrefOfInOut(String href) {
  /* 内外部链接最终转化为完整的链接格式 */
  String resultHref = null;

  /* 判断是否为外部链接 */
  if (href.startsWith("http://")) {
   resultHref = href;
  } else {
   /* 如果是内部链接,则补充完整的链接地址,其他的格式忽略不处理,如:a href="#" rel="external nofollow"  */
   if (href.startsWith("/")) {
    resultHref = "http://www.oschina.net" + href;
   }
  }

  return resultHref;
 }

 /**
  * 截取网页网页源文件的目标内容
  * 
  * @param content
  * @return
  */
 public static String getGoalContent(String content) {
  int sign = content.indexOf("<pre class=\"");
  String signContent = content.substring(sign);

  int start = signContent.indexOf(">");
  int end = signContent.indexOf("</pre>");

  return signContent.substring(start + 1, end);
 }

 /**
  * 检查网页源文件中是否有目标文件
  * 
  * @param content
  * @return
  */
 public static int isHasGoalContent(String content) {
  return content.indexOf("<pre class=\"");
 }

}

HrefOfPage.java 此类为获取页面的超链接

package com.sreach.spider;
/**
 * @author binghe
 *
 */
public class HrefOfPage {
 /**
  * 获得页面源代码中超链接
  */
 public static void getHrefOfContent(String content) {
  System.out.println("开始");
  String[] contents = content.split("<a href=\"");
  for (int i = 1; i < contents.length; i++) {
   int endHref = contents[i].indexOf("\"");

   String aHref = FunctionUtils.getHrefOfInOut(contents[i].substring(
     0, endHref));

   if (aHref != null) {
    String href = FunctionUtils.getHrefOfInOut(aHref);

    if (!UrlQueue.isContains(href)
      && href.indexOf("/code/explore") != -1
      && !VisitedUrlQueue.isContains(href)) {
     UrlQueue.addElem(href);
    }
   }
  }

  System.out.println(UrlQueue.size() + "--抓取到的连接数");
  System.out.println(VisitedUrlQueue.size() + "--已处理的页面数");

 }

}

UrlDataHanding.java 此类主要是从未访问队列中获取url,下载页面,分析url,保存已访问url等操作,实现Runnable接口

package com.sreach.spider;
/**
 * @author binghe
 *
 */
public class UrlDataHanding implements Runnable {
 /**
  * 下载对应页面并分析出页面对应的URL放在未访问队列中。
  * 
  * @param url
  */
 public void dataHanding(String url) {
  HrefOfPage.getHrefOfContent(DownloadPage.getContentFormUrl(url));
 }

 public void run() {
  while (!UrlQueue.isEmpty()) {
   dataHanding(UrlQueue.outElem());
  }
 }
}

UrlQueue.java 此类主要是用来存放未访问的URL队列

package com.sreach.spider;

import java.util.LinkedList;
/**
 * @author binghe
 *
 */
public class UrlQueue {
 /** 超链接队列 */
 public static LinkedList<String> urlQueue = new LinkedList<String>();

 /** 队列中对应最多的超链接数量 */
 public static final int MAX_SIZE = 10000;

 public synchronized static void addElem(String url) {
  urlQueue.add(url);
 }

 public synchronized static String outElem() {
  return urlQueue.removeFirst();
 }

 public synchronized static boolean isEmpty() {
  return urlQueue.isEmpty();
 }

 public static int size() {
  return urlQueue.size();
 }

 public static boolean isContains(String url) {
  return urlQueue.contains(url);
 }

}

VisitedUrlQueue.java 主要是保存已访问过的URL,使用HashSet来保存,主要是考虑到每个访问过的URL是不同。HashSet刚好符合这个要求

package com.sreach.spider;

import java.util.HashSet;

/**
 * 已访问url队列
 * @author binghe
 * 
 */
public class VisitedUrlQueue {
 public static HashSet<String> visitedUrlQueue = new HashSet<String>();

 public synchronized static void addElem(String url) {
  visitedUrlQueue.add(url);
 }

 public synchronized static boolean isContains(String url) {
  return visitedUrlQueue.contains(url);
 }

 public synchronized static int size() {
  return visitedUrlQueue.size();
 }
}

Test.java 此类为测试类

import java.sql.SQLException;

import com.sreach.spider.UrlDataHanding;
import com.sreach.spider.UrlQueue;
/**
 * @author binghe
 *
 */
public class Test {
 public static void main(String[] args) throws SQLException {
  String url = "http://www.oschina.net/code/explore/achartengine/client/AndroidManifest.xml";
  String url1 = "http://www.oschina.net/code/explore";
  String url2 = "http://www.oschina.net/code/explore/achartengine";
  String url3 = "http://www.oschina.net/code/explore/achartengine/client";

  UrlQueue.addElem(url);
  UrlQueue.addElem(url1);
  UrlQueue.addElem(url2);
  UrlQueue.addElem(url3);

  UrlDataHanding[] url_Handings = new UrlDataHanding[10];

  for (int i = 0; i < 10; i++) {
   url_Handings[i] = new UrlDataHanding();
   new Thread(url_Handings[i]).start();
  }

 }
}

说明一下:由于我抓取的是针对oschina的,所以里面的url正则表达式不适合其他网站,需要自己修改一下。你也可以写成xml来配置。

加载全部内容

相关教程
猜你喜欢
用户评论