超簡(jiǎn)單的 Web 爬蟲(chóng)程序，不過(guò)可以在他基礎(chǔ)之上改造一下，寫(xiě)出強(qiáng)大點(diǎn)的爬蟲(chóng)！
謝謝提供程序的 blog 友！
/**
* @author Jack.Wang
*
*/
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.URL;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.HashSet;
import java.util.LinkedHashSet;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
// 搜索Web爬行者
public class SearchCrawler implements Runnable {
/*
* disallowListCache緩存robot不允許搜索的URL。 Robot協(xié)議在Web站點(diǎn)的根目錄下設(shè)置一個(gè)robots.txt文件,
* 規(guī)定站點(diǎn)上的哪些頁(yè)面是限制搜索的。
* 搜索程序應(yīng)該在搜索過(guò)程中跳過(guò)這些區(qū)域,下面是robots.txt的一個(gè)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>();// 錯(cuò)誤信息
ArrayList<String> result = new ArrayList<String>(); // 搜索到的結(jié)果
String startUrl;// 開(kāi)始搜索的起點(diǎn)
int maxUrl;// 最大處理的url數(shù)
String searchString;// 要搜索的字符串(英文)
boolean caseSensitive = false;// 是否區(qū)分大小寫(xiě)
boolean limitHost = false;// 是否在限制的主機(jī)內(nèi)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() {// 啟動(dòng)搜索線程
crawl(startUrl, maxUrl, searchString, limitHost, caseSensitive);
}
// 檢測(cè)URL格式
private URL verifyUrl(String url) {
// 只處理HTTP URLs.
if (!url.toLowerCase().startsWith("http://"))
return null;
URL verifiedUrl = null;
try {
verifiedUrl = new URL(url);
} catch (Exception e) {
return null;
}
return verifiedUrl;
}
// 檢測(cè)robot是否允許訪問(wèn)給出的URL.
private boolean isRobotAllowed(URL urlToCheck) {
String host = urlToCheck.getHost().toLowerCase();// 獲取給出RUL的主機(jī)
// System.out.println("主機(jī)="+host);
// 獲取主機(jī)不允許搜索的URL緩存
ArrayList<String> disallowList = disallowListCache.get(host);
// 如果還沒(méi)有緩存,下載并緩存。
if (disallowList == null) {
disallowList = new ArrayList<String>();
try {
URL robotsFileUrl = new URL("http://" + host + "/robots.txt");
BufferedReader reader = new BufferedReader(
new InputStreamReader(robotsFileUrl.openStream()));
// 讀robot文件，創(chuàng)建不允許訪問(wèn)的路徑列表。
String line;
while ((line = reader.readLine()) != null) {
if (line.indexOf("Disallow:") == 0) {// 是否包含"Disallow:"
String disallowPath = line.substring("Disallow:"
.length());// 獲取不允許訪問(wèn)路徑
// 檢查是否有注釋。
int commentIndex = disallowPath.indexOf("#");
if (commentIndex != -1) {
disallowPath = disallowPath.substring(0,
commentIndex);// 去掉注釋
}
disallowPath = disallowPath.trim();
disallowList.add(disallowPath);
}
}
// 緩存此主機(jī)不允許訪問(wèn)的路徑。
disallowListCache.put(host, disallowList);
} catch (Exception e) {
return true; // web站點(diǎn)根目錄下沒(méi)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;
}
// 從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);
}
// 解析頁(yè)面并找出鏈接
private ArrayList<String> retrieveLinks(URL pageUrl, String pageContents,
HashSet crawledList, boolean limitHost) {
// 用正則表達(dá)式編譯鏈接的匹配模式。
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;
}
// 跳過(guò)鏈到本頁(yè)面內(nèi)鏈接。
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) == '/') {// 處理絕對(duì)地
link = "http://" + pageUrl.getHost() + ":"
+ pageUrl.getPort() + link;
} else {
String file = pageUrl.getFile();
if (file.indexOf('/') == -1) {// 處理相對(duì)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;
}
/* 如果限定主機(jī)，排除那些不合條件的URL */
if (limitHost
&& !pageUrl.getHost().toLowerCase().equals(
verifiedLink.getHost().toLowerCase())) {
continue;
}
// 跳過(guò)那些已經(jīng)處理的鏈接.
if (crawledList.contains(link)) {
continue;
}
linkList.add(link);
}
return (linkList);
}
// 搜索下載Web頁(yè)面的內(nèi)容，判斷在該頁(yè)面內(nèi)有沒(méi)有指定的搜索字符串
private boolean searchStringMatches(String pageContents,
String searchString, boolean caseSensitive) {
String searchContents = pageContents;
if (!caseSensitive) {// 如果不區(qū)分大小寫(xiě)
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;
}
// 執(zhí)行實(shí)際的搜索操作
public ArrayList<String> crawl(String startUrl, int maxUrls,
String searchString, boolean limithost, boolean caseSensitive) {
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;
}
// 從開(kāi)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;
}
// 增加已處理的URL到crawledList
crawledList.add(url);
String pageContents = downloadPage(verifiedUrl);
if (pageContents != null && pageContents.length() > 0) {
// 從頁(yè)面中獲取有效的鏈接
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;
}
// 主函數(shù)
public static void main(String[] args) {
SearchCrawler crawler = new SearchCrawler("http://www.tkk7.com/Jack2007/", 20,"jack");
Thread search = new Thread(crawler);
System.out.println("Start searching...");
System.out.println("result:");
search.start();
try {
search.join();
} catch (InterruptedException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
本博客為學(xué)習(xí)交流用，凡未注明引用的均為本人作品，轉(zhuǎn)載請(qǐng)注明出處，如有版權(quán)問(wèn)題請(qǐng)及時(shí)通知。由于博客時(shí)間倉(cāng)促，錯(cuò)誤之處敬請(qǐng)諒解，有任何意見(jiàn)可給我留言，愿共同學(xué)習(xí)進(jìn)步。