簡單java爬蟲,java爬蟲程序

本文目錄一覽：

• 1、如何用Java寫一個爬蟲
• 2、Java網路爬蟲怎麼實現？
• 3、java適合寫爬蟲嗎？

如何用Java寫一個爬蟲

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++);

}

}

}

}

Java網路爬蟲怎麼實現？

網路爬蟲是一個自動提取網頁的程序，它為搜索引擎從萬維網上下載網頁，是搜索引擎的重要組成。

傳統爬蟲從一個或若干初始網頁的URL開始，獲得初始網頁上的URL，在抓取網頁的過程中，不斷從當前頁面上抽取新的URL放入隊列，直到滿足系統的一定停止條件。對於垂直搜索來說，聚焦爬蟲，即有針對性地爬取特定主題網頁的爬蟲，更為適合。

以下是一個使用java實現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容相關的網頁，這裡採用正則匹配簡單處理

if (isContentRelevant(content, this.regexpSearchPattern)) {

saveContent(url, content); //保存網頁至本地

//獲取網頁內容中的鏈接，並放入待爬取隊列中

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：是否有許可權訪問該URL，友好的爬蟲會根據網站提供的”Robot.txt”中配置的規則進行爬取

//isUrlAlreadyVisited：URL是否訪問過，大型的搜索引擎往往採用BloomFilter進行排重，這裡簡單使用HashMap

//isDepthAcceptable：是否達到指定的深度上限。爬蟲一般採取廣度優先的方式。一些網站會構建爬蟲陷阱（自動生成一些無效鏈接使爬蟲陷入死循環），採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適合寫爬蟲嗎？

JAVA也可以實現爬蟲，比如jsoup包，一個非常方便解析html的工具呢。

不過相對來說，java語言笨重，稍微有些麻煩。