求用JAVA編寫一個(gè)網(wǎng)絡(luò)爬蟲的程序

先根據(jù)一個(gè)鏈接，抓取該頁(yè)面；解析該頁(yè)面，搜取出該頁(yè)面中有用的鏈接，根據(jù)鏈接地址循環(huán)抓取就OK了；--簡(jiǎn)單爬行器原理 抓取完文件后還需要一個(gè)功能好點(diǎn)的文檔解析器來(lái)解析出文件中的內(nèi)容；--文件解析器 再根據(jù)關(guān)鍵字（分詞器）處理這些頁(yè)面，建立自己的搜索引擎；--分詞器不好解決 我也正在搞這方面 呵呵

創(chuàng)新互聯(lián)建站公司2013年成立，先為招遠(yuǎn)等服務(wù)建站，招遠(yuǎn)等地企業(yè)，進(jìn)行企業(yè)商務(wù)咨詢服務(wù)。為招遠(yuǎn)企業(yè)網(wǎng)站制作PC+手機(jī)+微官網(wǎng)三網(wǎng)同步一站式服務(wù)解決您的所有建站問(wèn)題。

Java源碼 實(shí)現(xiàn)網(wǎng)絡(luò)爬蟲?

//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(jié)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++);

}

}

}

}

Java網(wǎng)絡(luò)爬蟲怎么實(shí)現(xiàn)？

網(wǎng)絡(luò)爬蟲是一個(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)爬蟲從一個(gè)或若干初始網(wǎng)頁(yè)的URL開始，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，即有針對(duì)性地爬取特定主題網(wǎng)頁(yè)的爬蟲，更為適合。

以下是一個(gè)使用java實(shí)現(xiàn)的簡(jiǎn)單爬蟲核心代碼：

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。爬蟲一般采取廣度優(yōu)先的方式。一些網(wǎng)站會(huì)構(gòu)建爬蟲陷阱（自動(dòng)生成一些無(wú)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(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();

}

}