View Code
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;
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
{
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="#" */
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("
String signContent = content.substring(sign);
int start = signContent.indexOf(">");
int end = signContent.indexOf("
");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("
}
}
HrefOfPage.java 此类为获取页面的超链接
View Code
package com.sreach.spider;
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("
for (int i = 1; i
{
int endHref = contents[i].indexOf("\"");
String aHref = FunctionUtils.getHrefOfInOut(contents[i].substring(
, 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
View Code
package com.sreach.spider;
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
View Code
package com.sreach.spider;
import java.util.LinkedList;
public class UrlQueue
{
/**超链接队列*/
public static LinkedList urlQueue = new LinkedList();
/**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
View Code
package com.sreach.spider;
import java.util.HashSet;
/**
* 已访问url队列
* @author HHZ
*
*/
public class VisitedUrlQueue
{
public static HashSet visitedUrlQueue = new HashSet();
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
View Code
import java.sql.SQLException;
import com.sreach.spider.UrlDataHanding;
import com.sreach.spider.UrlQueue;
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
{
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。