先根据一个链接，抓取该页面；解析该页面，搜取出该页面中有用的链接，根据链接地址循环抓取就OK了；--简单爬行器原理 抓取完文件后还需要一个功能好点的文档解析器来解析出文件中的内容；--文件解析器 再根据关键字（分词器）处理这些页面，建立自己的搜索引擎；--分词器不好解决 我也正在搞这方面 呵呵
创新互联建站公司2013年成立，先为招远等服务建站，招远等地企业，进行企业商务咨询服务。为招远企业网站制作PC+手机+微官网三网同步一站式服务解决您的所有建站问题。
//Java爬虫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为输出的路径,注意要以\\结尾
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("已下载:"+j++);
}
}
}
}
网络爬虫是一个自动提取网页的程序，它为搜索引擎从万维网上下载网页，是搜索引擎的重要组成。
传统爬虫从一个或若干初始网页的URL开始，获得初始网页上的URL，在抓取网页的过程中，不断从当前页面上抽取新的URL放入队列，直到满足系统的一定停止条件。对于垂直搜索来说，聚焦爬虫，即有针对性地爬取特定主题网页的爬虫，更为适合。
以下是一个使用java实现的简单爬虫核心代码：
public void crawl() throws Throwable {
while (continueCrawling()) {
CrawlerUrl url = getNextUrl(); //获取待爬取队列中的下一个URL
if (url != null) {
printCrawlInfo();
String content = getContent(url); //获取URL的文本信息
//聚焦爬虫只爬取与主题内容相关的网页，这里采用正则匹配简单处理
if (isContentRelevant(content, this.regexpSearchPattern)) {
saveContent(url, content); //保存网页至本地
//获取网页内容中的链接，并放入待爬取队列中
Collection urlStrings = extractUrls(content, url);
addUrlsToUrlQueue(url, urlStrings);
} else {
System.out.println(url + " is not relevant ignoring ...");
}
//延时防止被对方屏蔽
Thread.sleep(this.delayBetweenUrls);
}
}
closeOutputStream();
}
private CrawlerUrl getNextUrl() throws Throwable {
CrawlerUrl nextUrl = null;
while ((nextUrl == null) (!urlQueue.isEmpty())) {
CrawlerUrl crawlerUrl = this.urlQueue.remove();
//doWeHavePermissionToVisit：是否有权限访问该URL，友好的爬虫会根据网站提供的"Robot.txt"中配置的规则进行爬取
//isUrlAlreadyVisited：URL是否访问过，大型的搜索引擎往往采用BloomFilter进行排重，这里简单使用HashMap
//isDepthAcceptable：是否达到指定的深度上限。爬虫一般采取广度优先的方式。一些网站会构建爬虫陷阱（自动生成一些无效链接使爬虫陷入死循环），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的调用与之前的方式不同
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();
}
}
//将url标记为已访问
markUrlAsVisited(url);
return strBuf.toString();
}
public static boolean isContentRelevant(String content,
Pattern regexpPattern) {
boolean retValue = false;
if (content != null) {
//是否符合正则表达式的条件
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();
}
}
