Java写的爬虫的基本程序

这是一个web搜索的基本程序，从命令行输入搜索条件（起始的URL、处理url的最大数、要搜索的字符串),
它就会逐个对Internet上的URL进行实时搜索,查找并输出匹配搜索条件的页面。 这个程序的原型来自《java编程艺术》，
为了更好的分析，站长去掉了其中的GUI部分，并稍作修改以适用jdk1.5。以这个程序为基础，可以写出在互联网上搜索
诸如图像、邮件、网页下载之类的“爬虫”。
先请看程序运行的过程：

D:java>javac SearchCrawler.java（编译）

D:java>java SearchCrawler http://127.0.0.1:8080/zz3zcwbwebhome/index.jsp 20 java

Start searching...
result:
searchString=java
http://127.0.0.1:8080/zz3zcwbwebhome/index.jsp
http://127.0.0.1:8080/zz3zcwbwebhome/reply.jsp
http://127.0.0.1:8080/zz3zcwbwebhome/learn.jsp
http://127.0.0.1:8080/zz3zcwbwebhome/download.jsp
http://127.0.0.1:8080/zz3zcwbwebhome/article.jsp
http://127.0.0.1:8080/zz3zcwbwebhome/myexample/jlGUIOverview.htm
http://127.0.0.1:8080/zz3zcwbwebhome/myexample/Proxooldoc/index.html
http://127.0.0.1:8080/zz3zcwbwebhome/view.jsp?id=301
http://127.0.0.1:8080/zz3zcwbwebhome/view.jsp?id=297
http://127.0.0.1:8080/zz3zcwbwebhome/view.jsp?id=291
http://127.0.0.1:8080/zz3zcwbwebhome/view.jsp?id=286
http://127.0.0.1:8080/zz3zcwbwebhome/view.jsp?id=285
http://127.0.0.1:8080/zz3zcwbwebhome/view.jsp?id=284
http://127.0.0.1:8080/zz3zcwbwebhome/view.jsp?id=276
http://127.0.0.1:8080/zz3zcwbwebhome/view.jsp?id=272

又如：
D:java>java SearchCrawler http://www.sina.com 20 java
Start searching...
result:
searchString=java
http://sina.com
http://redirect.sina.com/WWW/sinaCN/www.sina.com.cn class="a2"
http://redirect.sina.com/WWW/sinaCN/www.sina.com.cn class="a8"
http://redirect.sina.com/WWW/sinaHK/www.sina.com.hk class="a2"
http://redirect.sina.com/WWW/sinaTW/www.sina.com.tw class="a8"
http://redirect.sina.com/WWW/sinaUS/home.sina.com class="a8"
http://redirect.sina.com/WWW/smsCN/sms.sina.com.cn/ class="a2"
http://redirect.sina.com/WWW/smsCN/sms.sina.com.cn/ class="a3"
http://redirect.sina.com/WWW/sinaNet/www.sina.net/ class="a3"

D:java>
下面是这个程序的源码

import java.util.*;
import java.net.*;
import java.io.*;
import java.util.regex.*;

// 搜索Web爬行者
public class SearchCrawler implements Runnable{

/* disallowListCache缓存robot不允许搜索的URL。 Robot协议在Web站点的根目录下设置一个robots.txt文件,
*规定站点上的哪些页面是限制搜索的。 搜索程序应该在搜索过程中跳过这些区域,下面是robots.txt的一个例子:
# robots.txt for http://somehost.com/
User-agent: *
Disallow: /cgi-bin/
Disallow: /registration # /Disallow robots on registration page
Disallow: /login
*/

private HashMap< String,ArrayList< String>> disallowListCache = new HashMap< String,ArrayList< String>>();
ArrayList< String> errorList= new ArrayList< String>();//错误信息
ArrayList< String> result=new ArrayList< String>(); //搜索到的结果
String startUrl;//开始搜索的起点
int maxUrl;//最大处理的url数
String searchString;//要搜索的字符串(英文)
boolean caseSensitive=false;//是否区分大小写
boolean limitHost=false;//是否在限制的主机内搜索

public SearchCrawler(String startUrl,int maxUrl,String searchString){
this.startUrl=startUrl;
this.maxUrl=maxUrl;
this.searchString=searchString;
}

public ArrayList< String> getResult(){
return result;
}

public void run(){//启动搜索线程

crawl(startUrl,maxUrl, searchString,limitHost,caseSensitive);
}

//检测URL格式
private URL verifyUrl(String url) {
// 只处理HTTP URLs.
if (!url.toLowerCase().startsWith("http://"))
return null;

URL verifiedUrl = null;
try {
verifiedUrl = new URL(url);
} catch (Exception e) {
return null;
}

return verifiedUrl;
}

// 检测robot是否允许访问给出的URL.
private boolean isRobotAllowed(URL urlToCheck) {
String host = urlToCheck.getHost().toLowerCase();//获取给出RUL的主机
//System.out.println("主机="+host);

// 获取主机不允许搜索的URL缓存
ArrayList< String> disallowList =disallowListCache.get(host);

// 如果还没有缓存,下载并缓存。
if (disallowList == null) {
disallowList = new ArrayList< String>();
try {
URL robotsFileUrl =new URL("http://" + host + "/robots.txt");
BufferedReader reader =new BufferedReader(new InputStreamReader(robotsFileUrl.openStream()));

// 读robot文件，创建不允许访问的路径列表。
String line;
while ((line = reader.readLine()) != null) {
if (line.indexOf("Disallow:") == 0) {//是否包含"Disallow:"
String disallowPath =line.substring("Disallow:".length());//获取不允许访问路径

// 检查是否有注释。
int commentIndex = disallowPath.indexOf("#");
if (commentIndex != - 1) {
disallowPath =disallowPath.substring(0, commentIndex);//去掉注释
}

disallowPath = disallowPath.trim();
disallowList.add(disallowPath);
}
}

// 缓存此主机不允许访问的路径。
disallowListCache.put(host, disallowList);
} catch (Exception e) {
return true; //web站点根目录下没有robots.txt文件,返回真
}
}

String file = urlToCheck.getFile();
//System.out.println("文件getFile()="+file);
for (int i = 0; i < disallowList.size(); i++) {
String disallow = disallowList.get(i);
if (file.startsWith(disallow)) {
return false;
}
}

return true;
}

private String downloadPage(URL pageUrl) {
try {
// Open connection to URL for reading.
BufferedReader reader =
new BufferedReader(new InputStreamReader(pageUrl.openStream()));

// Read page into buffer.
String line;
StringBuffer pageBuffer = new StringBuffer();
while ((line = reader.readLine()) != null) {
pageBuffer.append(line);
}

return pageBuffer.toString();
} catch (Exception e) {
}

return null;
}

// 从URL中去掉"www"
private String removeWwwFromUrl(String url) {
int index = url.indexOf("://www.");
if (index != -1) {
return url.substring(0, index + 3) +
url.substring(index + 7);
}

return (url);
}

// 解析页面并找出链接
private ArrayList< String> retrieveLinks(URL pageUrl, String pageContents, HashSet crawledList,
boolean limitHost)
{
// 用正则表达式编译链接的匹配模式。
Pattern p =Pattern.compile("<a\s+href\s*=\s*"?(.*?)["|>]",Pattern.CASE_INSENSITIVE);
Matcher m = p.matcher(pageContents);

ArrayList< String> linkList = new ArrayList< String>();
while (m.find()) {
String link = m.group(1).trim();

if (link.length() < 1) {
continue;
}

// 跳过链到本页面内链接。
if (link.charAt(0) == '#') {
continue;
}

if (link.indexOf("mailto:") != -1) {
continue;
}

if (link.toLowerCase().indexOf("javascript") != -1) {
continue;
}

if (link.indexOf("://") == -1){
if (link.charAt(0) == '/') {//处理绝对地
link = "http://" + pageUrl.getHost()+":"+pageUrl.getPort()+ link;
} else {
String file = pageUrl.getFile();
if (file.indexOf('/') == -1) {//处理相对地址
link = "http://" + pageUrl.getHost()+":"+pageUrl.getPort() + "/" + link;
} else {
String path =file.substring(0, file.lastIndexOf('/') + 1);
link = "http://" + pageUrl.getHost() +":"+pageUrl.getPort()+ path + link;
}
}
}

int index = link.indexOf('#');
if (index != -1) {
link = link.substring(0, index);
}

link = removeWwwFromUrl(link);

URL verifiedLink = verifyUrl(link);
if (verifiedLink == null) {
continue;
}

/* 如果限定主机，排除那些不合条件的URL*/
if (limitHost &&
!pageUrl.getHost().toLowerCase().equals(
verifiedLink.getHost().toLowerCase()))
{
continue;
}

// 跳过那些已经处理的链接.
if (crawledList.contains(link)) {
continue;
}

linkList.add(link);
}

return (linkList);
}

// 搜索下载Web页面的内容，判断在该页面内有没有指定的搜索字符串

private boolean searchStringMatches(String pageContents, String searchString, boolean caseSensitive){
String searchContents = pageContents;
if (!caseSensitive) {//如果不区分大小写
searchContents = pageContents.toLowerCase();
}

Pattern p = Pattern.compile("[\s]+");
String[] terms = p.split(searchString);
for (int i = 0; i < terms.length; i++) {
if (caseSensitive) {
if (searchContents.indexOf(terms[i]) == -1) {
return false;
}
} else {
if (searchContents.indexOf(terms[i].toLowerCase()) == -1) {
return false;
}
} }

return true;
}

//执行实际的搜索操作
public ArrayList< String> crawl(String startUrl, int maxUrls, String searchString,boolean limithost,boolean caseSensitive )
{

System.out.println("searchString="+searchString);
HashSet< String> crawledList = new HashSet< String>();
LinkedHashSet< String> toCrawlList = new LinkedHashSet< String>();

if (maxUrls < 1) {
errorList.add("Invalid Max URLs value.");
System.out.println("Invalid Max URLs value.");
}


if (searchString.length() < 1) {
errorList.add("Missing Search String.");
System.out.println("Missing search String");
}

if (errorList.size() > 0) {
System.out.println("err!!!");
return errorList;
}

// 从开始URL中移出www
startUrl = removeWwwFromUrl(startUrl);

toCrawlList.add(startUrl);
while (toCrawlList.size() > 0) {

if (maxUrls != -1) {
if (crawledList.size() == maxUrls) {
break;
}
}

// Get URL at bottom of the list.
String url = toCrawlList.iterator().next();

// Remove URL from the to crawl list.
toCrawlList.remove(url);

// Convert string url to URL object.
URL verifiedUrl = verifyUrl(url);

// Skip URL if robots are not allowed to access it.
if (!isRobotAllowed(verifiedUrl)) {
continue;
}

// 增加已处理的URL到crawledList
crawledList.add(url);
String pageContents = downloadPage(verifiedUrl);

if (pageContents != null && pageContents.length() > 0){
// 从页面中获取有效的链接
ArrayList< String> links =retrieveLinks(verifiedUrl, pageContents, crawledList,limitHost);

toCrawlList.addAll(links);

if (searchStringMatches(pageContents, searchString,caseSensitive))
{
result.add(url);
System.out.println(url);
}
}

}
return result;
}

// 主函数
public static void main(String[] args) {
if(args.length!=3){
System.out.println("Usage:java SearchCrawler startUrl maxUrl searchString");
return;
}
int max=Integer.parseInt(args[1]);
SearchCrawler crawler = new SearchCrawler(args[0],max,args[2]);
Thread search=new Thread(crawler);
System.out.println("Start searching...");
System.out.println("result:");
search.start();

}
}

注意 connection和inputstream都没有关闭的功能，变量也没有最后申明为null，导致内存消耗很大，也就是没有考虑到java的垃圾回收机制

ps: 这个爬虫我本人看了一次以后觉得很不错！