網(wǎng)絡(luò)爬蟲(chóng)是一個(gè)自動(dòng)提取網(wǎng)頁(yè)的程序，它為搜索引擎從萬(wàn)維網(wǎng)上下載網(wǎng)頁(yè)，是搜索引擎的重要組成。\x0d\x0a傳統(tǒng)爬蟲(chóng)從一個(gè)或若干初始網(wǎng)頁(yè)的URL開(kāi)始，獲得初始網(wǎng)頁(yè)上的URL，在抓取網(wǎng)頁(yè)的過(guò)程中，不斷從當(dāng)前頁(yè)面上抽取新的URL放入隊(duì)列，直到滿足系統(tǒng)的一定停止條件。對(duì)于垂直搜索來(lái)說(shuō)，聚焦爬蟲(chóng)，即有針對(duì)性地爬取特定主題網(wǎng)頁(yè)的爬蟲(chóng)，更為適合。\x0d\x0a\x0d\x0a以下是一個(gè)使用java實(shí)現(xiàn)的簡(jiǎn)單爬蟲(chóng)核心代碼：\x0d\x0apublic void crawl() throws Throwable { \x0d\x0a while (continueCrawling()) { \x0d\x0a CrawlerUrl url = getNextUrl(); //獲取待爬取隊(duì)列中的下一個(gè)URL \x0d\x0a if (url != null) { \x0d\x0a printCrawlInfo(); \x0d\x0a String content = getContent(url); //獲取URL的文本信息 \x0d\x0a \x0d\x0a //聚焦爬蟲(chóng)只爬取與主題內(nèi)容相關(guān)的網(wǎng)頁(yè)，這里采用正則匹配簡(jiǎn)單處理 \x0d\x0a if (isContentRelevant(content, this.regexpSearchPattern)) { \x0d\x0a saveContent(url, content); //保存網(wǎng)頁(yè)至本地 \x0d\x0a \x0d\x0a //獲取網(wǎng)頁(yè)內(nèi)容中的鏈接，并放入待爬取隊(duì)列中 \x0d\x0a Collection urlStrings = extractUrls(content, url); \x0d\x0a addUrlsToUrlQueue(url, urlStrings); \x0d\x0a } else { \x0d\x0a System.out.println(url + " is not relevant ignoring ..."); \x0d\x0a } \x0d\x0a \x0d\x0a //延時(shí)防止被對(duì)方屏蔽 \x0d\x0a Thread.sleep(this.delayBetweenUrls); \x0d\x0a } \x0d\x0a } \x0d\x0a closeOutputStream(); \x0d\x0a}\x0d\x0aprivate CrawlerUrl getNextUrl() throws Throwable { \x0d\x0a CrawlerUrl nextUrl = null; \x0d\x0a while ((nextUrl == null) (!urlQueue.isEmpty())) { \x0d\x0a CrawlerUrl crawlerUrl = this.urlQueue.remove(); \x0d\x0a //doWeHavePermissionToVisit：是否有權(quán)限訪問(wèn)該URL，友好的爬蟲(chóng)會(huì)根據(jù)網(wǎng)站提供的"Robot.txt"中配置的規(guī)則進(jìn)行爬取 \x0d\x0a //isUrlAlreadyVisited：URL是否訪問(wèn)過(guò)，大型的搜索引擎往往采用BloomFilter進(jìn)行排重，這里簡(jiǎn)單使用HashMap \x0d\x0a //isDepthAcceptable：是否達(dá)到指定的深度上限。爬蟲(chóng)一般采取廣度優(yōu)先的方式。一些網(wǎng)站會(huì)構(gòu)建爬蟲(chóng)陷阱（自動(dòng)生成一些無(wú)效鏈接使爬蟲(chóng)陷入死循環(huán)），采用深度限制加以避免 \x0d\x0a if (doWeHavePermissionToVisit(crawlerUrl) \x0d\x0a (!isUrlAlreadyVisited(crawlerUrl)) \x0d\x0a isDepthAcceptable(crawlerUrl)) { \x0d\x0a nextUrl = crawlerUrl; \x0d\x0a // System.out.println("Next url to be visited is " + nextUrl); \x0d\x0a } \x0d\x0a } \x0d\x0a return nextUrl; \x0d\x0a}\x0d\x0aprivate String getContent(CrawlerUrl url) throws Throwable { \x0d\x0a //HttpClient4.1的調(diào)用與之前的方式不同 \x0d\x0a HttpClient client = new DefaultHttpClient(); \x0d\x0a HttpGet httpGet = new HttpGet(url.getUrlString()); \x0d\x0a StringBuffer strBuf = new StringBuffer(); \x0d\x0a HttpResponse response = client.execute(httpGet); \x0d\x0a if (HttpStatus.SC_OK == response.getStatusLine().getStatusCode()) { \x0d\x0a HttpEntity entity = response.getEntity(); \x0d\x0a if (entity != null) { \x0d\x0a BufferedReader reader = new BufferedReader( \x0d\x0a new InputStreamReader(entity.getContent(), "UTF-8")); \x0d\x0a String line = null; \x0d\x0a if (entity.getContentLength() 0) { \x0d\x0a strBuf = new StringBuffer((int) entity.getContentLength()); \x0d\x0a while ((line = reader.readLine()) != null) { \x0d\x0a strBuf.append(line); \x0d\x0a } \x0d\x0a } \x0d\x0a } \x0d\x0a if (entity != null) { \x0d\x0a nsumeContent(); \x0d\x0a } \x0d\x0a } \x0d\x0a //將url標(biāo)記為已訪問(wèn) \x0d\x0a markUrlAsVisited(url); \x0d\x0a return strBuf.toString(); \x0d\x0a}\x0d\x0apublic static boolean isContentRelevant(String content, \x0d\x0aPattern regexpPattern) { \x0d\x0a boolean retValue = false; \x0d\x0a if (content != null) { \x0d\x0a //是否符合正則表達(dá)式的條件 \x0d\x0a Matcher m = regexpPattern.matcher(content.toLowerCase()); \x0d\x0a retValue = m.find(); \x0d\x0a } \x0d\x0a return retValue; \x0d\x0a}\x0d\x0apublic List extractUrls(String text, CrawlerUrl crawlerUrl) { \x0d\x0a Map urlMap = new HashMap(); \x0d\x0a extractHttpUrls(urlMap, text); \x0d\x0a extractRelativeUrls(urlMap, text, crawlerUrl); \x0d\x0a return new ArrayList(urlMap.keySet()); \x0d\x0a} \x0d\x0aprivate void extractHttpUrls(Map urlMap, String text) { \x0d\x0a Matcher m = (text); \x0d\x0a while (m.find()) { \x0d\x0a String url = m.group(); \x0d\x0a String[] terms = url.split("a href=\""); \x0d\x0a for (String term : terms) { \x0d\x0a // System.out.println("Term = " + term); \x0d\x0a if (term.startsWith("http")) { \x0d\x0a int index = term.indexOf("\""); \x0d\x0a if (index 0) { \x0d\x0a term = term.substring(0, index); \x0d\x0a } \x0d\x0a urlMap.put(term, term); \x0d\x0a System.out.println("Hyperlink: " + term); \x0d\x0a } \x0d\x0a } \x0d\x0a } \x0d\x0a} \x0d\x0aprivate void extractRelativeUrls(Map urlMap, String text, \x0d\x0a CrawlerUrl crawlerUrl) { \x0d\x0a Matcher m = relativeRegexp.matcher(text); \x0d\x0a URL textURL = crawlerUrl.getURL(); \x0d\x0a String host = textURL.getHost(); \x0d\x0a while (m.find()) { \x0d\x0a String url = m.group(); \x0d\x0a String[] terms = url.split("a href=\""); \x0d\x0a for (String term : terms) { \x0d\x0a if (term.startsWith("/")) { \x0d\x0a int index = term.indexOf("\""); \x0d\x0a if (index 0) { \x0d\x0a term = term.substring(0, index); \x0d\x0a } \x0d\x0a String s = //" + host + term; \x0d\x0a urlMap.put(s, s); \x0d\x0a System.out.println("Relative url: " + s); \x0d\x0a } \x0d\x0a } \x0d\x0a } \x0d\x0a \x0d\x0a}\x0d\x0apublic static void main(String[] args) { \x0d\x0a try { \x0d\x0a String url = ""; \x0d\x0a Queue urlQueue = new LinkedList(); \x0d\x0a String regexp = "java"; \x0d\x0a urlQueue.add(new CrawlerUrl(url, 0)); \x0d\x0a NaiveCrawler crawler = new NaiveCrawler(urlQueue, 100, 5, 1000L, \x0d\x0a regexp); \x0d\x0a // boolean allowCrawl = crawler.areWeAllowedToVisit(url); \x0d\x0a // System.out.println("Allowed to crawl: " + url + " " + \x0d\x0a // allowCrawl); \x0d\x0a crawler.crawl(); \x0d\x0a } catch (Throwable t) { \x0d\x0a System.out.println(t.toString()); \x0d\x0a t.printStackTrace(); \x0d\x0a } \x0d\x0a}
創(chuàng)新互聯(lián)主要從事網(wǎng)站設(shè)計(jì)、網(wǎng)站制作、網(wǎng)頁(yè)設(shè)計(jì)、企業(yè)做網(wǎng)站、公司建網(wǎng)站等業(yè)務(wù)。立足成都服務(wù)宣漢,10余年網(wǎng)站建設(shè)經(jīng)驗(yàn),價(jià)格優(yōu)惠、服務(wù)專業(yè),歡迎來(lái)電咨詢建站服務(wù):18980820575
import java.awt.*;
import java.awt.event.*;
import java.io.*;
import java.net.*;
import java.util.*;
import java.util.regex.*;
import javax.swing.*;
import javax.swing.table.*;//一個(gè)Web的爬行者(注：爬行在這里的意思與抓取，捕獲相同)
public class SearchCrawler extends JFrame{
//最大URL保存值
private static final String[] MAX_URLS={"50","100","500","1000"};
//緩存robot禁止爬行列表
private HashMap disallowListCache=new HashMap();
//搜索GUI控件
private JTextField startTextField;
private JComboBox maxComboBox;
private JCheckBox limitCheckBox;
private JTextField logTextField;
private JTextField searchTextField;
private JCheckBox caseCheckBox;
private JButton searchButton;
//搜索狀態(tài)GUI控件
private JLabel crawlingLabel2;
private JLabel crawledLabel2;
private JLabel toCrawlLabel2;
private JProgressBar progressBar;
private JLabel matchesLabel2;
//搜索匹配項(xiàng)表格列表
private JTable table;
//標(biāo)記爬行機(jī)器是否正在爬行
private boolean crawling;
//寫(xiě)日志匹配文件的引用
private PrintWriter logFileWriter;
//網(wǎng)絡(luò)爬行者的構(gòu)造函數(shù)
public SearchCrawler(){
//設(shè)置應(yīng)用程序標(biāo)題欄
setTitle("搜索爬行者");
//設(shè)置窗體大小
setSize(600,600);
//處理窗體關(guān)閉事件
addWindowListener(new WindowAdapter(){
public void windowClosing(WindowEvent e){
actionExit();
}
});
//設(shè)置文件菜單
JMenuBar menuBar=new JMenuBar();
JMenu fileMenu=new JMenu("文件");
fileMenu.setMnemonic(KeyEvent.VK_F);
JMenuItem fileExitMenuItem=new JMenuItem("退出",KeyEvent.VK_X);
fileExitMenuItem.addActionListener(new ActionListener(){
public void actionPerformed(ActionEvent e){
actionExit();
}
});
fileMenu.add(fileExitMenuItem);
menuBar.add(fileMenu);
setJMenuBar(menuBar);
網(wǎng)絡(luò)爬蟲(chóng)是一個(gè)自動(dòng)提取網(wǎng)頁(yè)的程序，它為搜索引擎從萬(wàn)維網(wǎng)上下載網(wǎng)頁(yè)，是搜索引擎的重要組成。
傳統(tǒng)爬蟲(chóng)從一個(gè)或若干初始網(wǎng)頁(yè)的URL開(kāi)始，獲得初始網(wǎng)頁(yè)上的URL，在抓取網(wǎng)頁(yè)的過(guò)程中，不斷從當(dāng)前頁(yè)面上抽取新的URL放入隊(duì)列，直到滿足系統(tǒng)的一定停止條件。對(duì)于垂直搜索來(lái)說(shuō)，聚焦爬蟲(chóng)，即有針對(duì)性地爬取特定主題網(wǎng)頁(yè)的爬蟲(chóng)，更為適合。
以下是一個(gè)使用java實(shí)現(xiàn)的簡(jiǎn)單爬蟲(chóng)核心代碼：
public void crawl() throws Throwable {
while (continueCrawling()) {
CrawlerUrl url = getNextUrl(); //獲取待爬取隊(duì)列中的下一個(gè)URL
if (url != null) {
printCrawlInfo();
String content = getContent(url); //獲取URL的文本信息
//聚焦爬蟲(chóng)只爬取與主題內(nèi)容相關(guān)的網(wǎng)頁(yè)，這里采用正則匹配簡(jiǎn)單處理
if (isContentRelevant(content, this.regexpSearchPattern)) {
saveContent(url, content); //保存網(wǎng)頁(yè)至本地
//獲取網(wǎng)頁(yè)內(nèi)容中的鏈接，并放入待爬取隊(duì)列中
Collection urlStrings = extractUrls(content, url);
addUrlsToUrlQueue(url, urlStrings);
} else {
System.out.println(url + " is not relevant ignoring ...");
}
//延時(shí)防止被對(duì)方屏蔽
Thread.sleep(this.delayBetweenUrls);
}
}
closeOutputStream();
}
private CrawlerUrl getNextUrl() throws Throwable {
CrawlerUrl nextUrl = null;
while ((nextUrl == null) (!urlQueue.isEmpty())) {
CrawlerUrl crawlerUrl = this.urlQueue.remove();
//doWeHavePermissionToVisit：是否有權(quán)限訪問(wèn)該URL，友好的爬蟲(chóng)會(huì)根據(jù)網(wǎng)站提供的"Robot.txt"中配置的規(guī)則進(jìn)行爬取
//isUrlAlreadyVisited：URL是否訪問(wèn)過(guò)，大型的搜索引擎往往采用BloomFilter進(jìn)行排重，這里簡(jiǎn)單使用HashMap
//isDepthAcceptable：是否達(dá)到指定的深度上限。爬蟲(chóng)一般采取廣度優(yōu)先的方式。一些網(wǎng)站會(huì)構(gòu)建爬蟲(chóng)陷阱（自動(dòng)生成一些無(wú)效鏈接使爬蟲(chóng)陷入死循環(huán)），采用深度限制加以避免
if (doWeHavePermissionToVisit(crawlerUrl)
(!isUrlAlreadyVisited(crawlerUrl))
isDepthAcceptable(crawlerUrl)) {
nextUrl = crawlerUrl;
// System.out.println("Next url to be visited is " + nextUrl);
}
}
return nextUrl;
}
private String getContent(CrawlerUrl url) throws Throwable {
//HttpClient4.1的調(diào)用與之前的方式不同
HttpClient client = new DefaultHttpClient();
HttpGet httpGet = new HttpGet(url.getUrlString());
StringBuffer strBuf = new StringBuffer();
HttpResponse response = client.execute(httpGet);
if (HttpStatus.SC_OK == response.getStatusLine().getStatusCode()) {
HttpEntity entity = response.getEntity();
if (entity != null) {
BufferedReader reader = new BufferedReader(
new InputStreamReader(entity.getContent(), "UTF-8"));
String line = null;
if (entity.getContentLength() 0) {
strBuf = new StringBuffer((int) entity.getContentLength());
while ((line = reader.readLine()) != null) {
strBuf.append(line);
}
}
}
if (entity != null) {
nsumeContent();
}
}
//將url標(biāo)記為已訪問(wèn)
markUrlAsVisited(url);
return strBuf.toString();
}
public static boolean isContentRelevant(String content,
Pattern regexpPattern) {
boolean retValue = false;
if (content != null) {
//是否符合正則表達(dá)式的條件
Matcher m = regexpPattern.matcher(content.toLowerCase());
retValue = m.find();
}
return retValue;
}
public List extractUrls(String text, CrawlerUrl crawlerUrl) {
Map urlMap = new HashMap();
extractHttpUrls(urlMap, text);
extractRelativeUrls(urlMap, text, crawlerUrl);
return new ArrayList(urlMap.keySet());
}
private void extractHttpUrls(Map urlMap, String text) {
Matcher m = (text);
while (m.find()) {
String url = m.group();
String[] terms = url.split("a href=\"");
for (String term : terms) {
// System.out.println("Term = " + term);
if (term.startsWith("http")) {
int index = term.indexOf("\"");
if (index 0) {
term = term.substring(0, index);
}
urlMap.put(term, term);
System.out.println("Hyperlink: " + term);
}
}
}
}
private void extractRelativeUrls(Map urlMap, String text,
CrawlerUrl crawlerUrl) {
Matcher m = relativeRegexp.matcher(text);
URL textURL = crawlerUrl.getURL();
String host = textURL.getHost();
while (m.find()) {
String url = m.group();
String[] terms = url.split("a href=\"");
for (String term : terms) {
if (term.startsWith("/")) {
int index = term.indexOf("\"");
if (index 0) {
term = term.substring(0, index);
}
String s = //" + host + term;
urlMap.put(s, s);
System.out.println("Relative url: " + s);
}
}
}
}
public static void main(String[] args) {
try {
String url = "";
Queue urlQueue = new LinkedList();
String regexp = "java";
urlQueue.add(new CrawlerUrl(url, 0));
NaiveCrawler crawler = new NaiveCrawler(urlQueue, 100, 5, 1000L,
regexp);
// boolean allowCrawl = crawler.areWeAllowedToVisit(url);
// System.out.println("Allowed to crawl: " + url + " " +
// allowCrawl);
crawler.crawl();
} catch (Throwable t) {
System.out.println(t.toString());
t.printStackTrace();
}
}
重慶分公司
重慶分公司
