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
创新互联专注于企业全网整合营销推广、网站重做改版、滁州网站定制设计、自适应品牌网站建设、H5页面制作、成都做商城网站、集团公司官网建设、成都外贸网站制作、高端网站制作、响应式网页设计等建站业务，价格优惠性价比高，为滁州等各大城市提供网站开发制作服务。
//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++);
}
}
}
}
下面是源代码,希望可以帮到你~~
package com.ly.mainprocess;
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.List;
import org.apache.http.Consts;
import org.apache.http.Header;
import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.NameValuePair;
import org.apache.http.StatusLine;
import org.apache.http.client.entity.UrlEncodedFormEntity;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.cookie.Cookie;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.message.BasicNameValuePair;
import org.apache.http.util.EntityUtils;
public class Test1 {
public static void main(String[] args){
Test1 test1 = new Test1();
System.out.println(test1.process("******","******"));
}
@SuppressWarnings("deprecation")
public boolean process(String username,String password) {
boolean ret=false;
DefaultHttpClient httpclient = new DefaultHttpClient();
try {
HttpGet httpget;
HttpResponse response;
HttpEntity entity;
ListCookie cookies;
//组建登录的post包
HttpPost httppost = new HttpPost(""); // 用户登录
ListNameValuePair nvps = new ArrayListNameValuePair();
nvps.add(new BasicNameValuePair("nickname", username));
nvps.add(new BasicNameValuePair("password", password));
nvps.add(new BasicNameValuePair("origURL", ""));
nvps.add(new BasicNameValuePair("loginregFrom", "index"));
nvps.add(new BasicNameValuePair("ss", "10101"));
httppost.setEntity(new UrlEncodedFormEntity(nvps, Consts.UTF_8));
httppost.addHeader("Referer", "");
httppost.addHeader("Connection", "keep-alive");
httppost.addHeader("Content-Type", "application/x-www-form-urlencoded");
httppost.addHeader("Accept-Language", "zh-CN,zh;q=0.8");
httppost.addHeader("Origin", "");
httppost.addHeader("User-Agent", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36");
response = httpclient.execute(httppost);
entity = response.getEntity();
// System.out.println("Login form get: " + response.getStatusLine());
EntityUtils.consume(entity);
// System.out.println("Post logon cookies:");
cookies = httpclient.getCookieStore().getCookies();
if (cookies.isEmpty()) {
// System.out.println("None");
} else {
for (int i = 0; i cookies.size(); i++) {
// System.out.println("- " + cookies.get(i).toString());
}
}
//进行页面跳转
String url = ""; // 页面跳转
Header locationHeader = response.getFirstHeader("Location");
// System.out.println(locationHeader.getValue());
if (locationHeader != null) {
url = locationHeader.getValue(); // 得到跳转href
HttpGet httpget1 = new HttpGet(url);
response = httpclient.execute(httpget1);
// 登陆成功。。。hoho
}
entity = response.getEntity();
// System.out.println(response.getStatusLine());
if (entity != null) {
// System.out.println("Response content length: " + entity.getContentLength());
}
// 显示结果
BufferedReader reader = new BufferedReader(new InputStreamReader(entity.getContent(), "UTF-8"));
String line = null;
while ((line = reader.readLine()) != null) {
// System.out.println(line);
}
//自动打卡
// 访问网站的子网页。
HttpPost httppost1 = new HttpPost(""); // 设置个人信息页面
httppost1.addHeader("Content-Type", "text/plain;charset=UTF-8");
httppost1.addHeader("Accept", "text/plain, */*");
httppost1.addHeader("X-Requested-With", "XMLHttpRequest");
httppost1.addHeader("Referer", "");
response = httpclient.execute(httppost1);
entity = response.getEntity();
// System.out.println(response.getStatusLine());
if(response.getStatusLine().toString().indexOf("HTTP/1.1 200 OK")=0){
ret = true;
}
if (entity != null) {
// System.out.println("Response content length: " + entity.getContentLength());
}
// 显示结果
reader = new BufferedReader(new InputStreamReader(entity.getContent(), "UTF-8"));
line = null;
while ((line = reader.readLine()) != null) {
System.out.println(line);
}
} catch (Exception e) {
} finally {
httpclient.getConnectionManager().shutdown();
}
return ret;
}
}
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。\x0d\x0a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。\x0d\x0a\x0d\x0a以下是一个使用java实现的简单爬虫核心代码：\x0d\x0apublic void crawl() throws Throwable { \x0d\x0a while (continueCrawling()) { \x0d\x0a CrawlerUrl url = getNextUrl(); //获取待爬取队列中的下一个URL \x0d\x0a if (url != null) { \x0d\x0a printCrawlInfo(); \x0d\x0a String content = getContent(url); //获取URL的文本信息 \x0d\x0a \x0d\x0a //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 \x0d\x0a if (isContentRelevant(content, this.regexpSearchPattern)) { \x0d\x0a saveContent(url, content); //保存网页至本地 \x0d\x0a \x0d\x0a //获取网页内容中的链接，并放入待爬取队列中 \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 //延时防止被对方屏蔽 \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 \x0d\x0a //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 \x0d\x0a //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 \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的调用与之前的方式不同 \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 //将url标记为已访问 \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 //是否符合正则表达式的条件 \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}
根据java网络编程相关的内容，使用jdk提供的相关类可以得到url对应网页的html页面代码。
针对得到的html代码，通过使用正则表达式即可得到我们想要的内容。
比如，我们如果想得到一个网页上所有包括“java”关键字的文本内容，就可以逐行对网页代码进行正则表达式的匹配。最后达到去除html标签和不相关的内容，只得到包括“java”这个关键字的内容的效果。
从网页上爬取图片的流程和爬取内容的流程基本相同，但是爬取图片的步骤会多一步。
需要先用img标签的正则表达式匹配获取到img标签，再用src属性的正则表达式获取这个img标签中的src属性的图片url，然后再通过缓冲输入流对象读取到这个图片url的图片信息，配合文件输出流将读到的图片信息写入到本地即可。
