import java.awt.*;
創(chuàng)新互聯(lián)長期為上千多家客戶提供的網(wǎng)站建設服務，團隊從業(yè)經(jīng)驗10年，關注不同地域、不同群體，并針對不同對象提供差異化的產(chǎn)品和服務；打造開放共贏平臺，與合作伙伴共同營造健康的互聯(lián)網(wǎng)生態(tài)環(huán)境。為銅陵企業(yè)提供專業(yè)的網(wǎng)站設計、成都網(wǎng)站制作，銅陵網(wǎng)站改版等技術服務。擁有十年豐富建站經(jīng)驗和眾多成功案例,為您定制開發(fā)。
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;
//搜索匹配項表格列表
private JTable table;
//標記爬行機器是否正在爬行
private boolean crawling;
//寫日志匹配文件的引用
private PrintWriter logFileWriter;
//網(wǎng)絡爬行者的構造函數(shù)
public SearchCrawler(){
//設置應用程序標題欄
setTitle("搜索爬行者");
//設置窗體大小
setSize(600,600);
//處理窗體關閉事件
addWindowListener(new WindowAdapter(){
public void windowClosing(WindowEvent e){
actionExit();
}
});
//設置文件菜單
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);
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
import java.io.File;
import java.net.URL;
import java.net.URLConnection;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.Scanner;
import java.util.UUID;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class DownMM {
public static void main(String[] args) throws Exception {
//out為輸出的路徑,注意要以\\結尾
String out = "D:\\JSP\\pic\\java\\";
try{
File f = new File(out);
if(! f.exists()) {
f.mkdirs();
}
}catch(Exception e){
System.out.println("no");
}
String url = "-";
Pattern reg = Pattern.compile("img src=\"(.*?)\"");
for(int j=0, i=1; i=10; i++){
URL uu = new URL(url+i);
URLConnection conn = uu.openConnection();
conn.setRequestProperty("User-Agent", "Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko");
Scanner sc = new Scanner(conn.getInputStream());
Matcher m = reg.matcher(sc.useDelimiter("\\A").next());
while(m.find()){
Files.copy(new URL(m.group(1)).openStream(), Paths.get(out + UUID.randomUUID() + ".jpg"));
System.out.println("已下載:"+j++);
}
}
}
網(wǎng)絡爬蟲是一個自動提取網(wǎng)頁的程序，它為搜索引擎從萬維網(wǎng)上下載網(wǎng)頁，是搜索引擎的重要組成。
傳統(tǒng)爬蟲從一個或若干初始網(wǎng)頁的URL開始，獲得初始網(wǎng)頁上的URL，在抓取網(wǎng)頁的過程中，不斷從當前頁面上抽取新的URL放入隊列，直到滿足系統(tǒng)的一定停止條件。對于垂直搜索來說，聚焦爬蟲，即有針對性地爬取特定主題網(wǎng)頁的爬蟲，更為適合。
以下是一個使用java實現(xiàn)的簡單爬蟲核心代碼：
public void crawl() throws Throwable {
while (continueCrawling()) {
CrawlerUrl url = getNextUrl(); //獲取待爬取隊列中的下一個URL
if (url != null) {
printCrawlInfo();
String content = getContent(url); //獲取URL的文本信息
//聚焦爬蟲只爬取與主題內(nèi)容相關的網(wǎng)頁，這里采用正則匹配簡單處理
if (isContentRelevant(content, this.regexpSearchPattern)) {
saveContent(url, content); //保存網(wǎng)頁至本地
//獲取網(wǎng)頁內(nèi)容中的鏈接，并放入待爬取隊列中
Collection urlStrings = extractUrls(content, url);
addUrlsToUrlQueue(url, urlStrings);
} else {
System.out.println(url + " is not relevant ignoring ...");
}
//延時防止被對方屏蔽
Thread.sleep(this.delayBetweenUrls);
}
}
closeOutputStream();
}
private CrawlerUrl getNextUrl() throws Throwable {
CrawlerUrl nextUrl = null;
while ((nextUrl == null) (!urlQueue.isEmpty())) {
CrawlerUrl crawlerUrl = this.urlQueue.remove();
//doWeHavePermissionToVisit：是否有權限訪問該URL，友好的爬蟲會根據(jù)網(wǎng)站提供的"Robot.txt"中配置的規(guī)則進行爬取
//isUrlAlreadyVisited：URL是否訪問過，大型的搜索引擎往往采用BloomFilter進行排重，這里簡單使用HashMap
//isDepthAcceptable：是否達到指定的深度上限。爬蟲一般采取廣度優(yōu)先的方式。一些網(wǎng)站會構建爬蟲陷阱（自動生成一些無效鏈接使爬蟲陷入死循環(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標記為已訪問
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();
}
}
//Java爬蟲demo
import?java.io.File;
import?java.net.URL;
import?java.net.URLConnection;
import?java.nio.file.Files;
import?java.nio.file.Paths;
import?java.util.Scanner;
import?java.util.UUID;
import?java.util.regex.Matcher;
import?java.util.regex.Pattern;
public?class?DownMM?{
public?static?void?main(String[]?args)?throws?Exception?{
//out為輸出的路徑,注意要以\\結尾
String?out?=?"D:\\JSP\\pic\\java\\";?
try{
File?f?=?new?File(out);
if(!?f.exists())?{??
f.mkdirs();??
}??
}catch(Exception?e){
System.out.println("no");
}
String?url?=?"-";
Pattern?reg?=?Pattern.compile("img?src=\"(.*?)\"");
for(int?j=0,?i=1;?i=10;?i++){
URL?uu?=?new?URL(url+i);
URLConnection?conn?=?uu.openConnection();
conn.setRequestProperty("User-Agent",?"Mozilla/5.0?(Windows?NT?6.3;?WOW64;?Trident/7.0;?rv:11.0)?like?Gecko");
Scanner?sc?=?new?Scanner(conn.getInputStream());
Matcher?m?=?reg.matcher(sc.useDelimiter("\\A").next());
while(m.find()){
Files.copy(new?URL(m.group(1)).openStream(),?Paths.get(out?+?UUID.randomUUID()?+?".jpg"));
System.out.println("已下載:"+j++);
}
}
}
}
重慶分公司
重慶分公司
