自己写的Java抓图程序

公司里要写一个抓图的程序

其实和搜索引擎差不多的原理 下载分析网页遇到<a>标签继续模拟点击进去再分析该网页 遇到<img>就下载该图

难点:

1 URL去重 采用bloomfilter算法

2 序列化方式存储URL库

3 线程的合理切换

难度不大 大家看代码吧 没图形界面的 完全控制台 跨平台 呵呵

java -jar JavaCrawler.jar http://www.foxhq.com/ 900000000 boob C:/pic/ D:/url.tmp D:/img.tmp

序列化工具类:

package com.hengking.crawl.util; import java.io.*; public class UtilSeriz { /** *将对象序列化到磁盘文件中 *@param *@throwsException */ public static void writeObject(Object o,String strPath) throws Exception{ File f=new File(strPath); if(f.exists()){ f.delete(); } FileOutputStream os=new FileOutputStream(f); //ObjectOutputStream 核心类 ObjectOutputStream oos=new ObjectOutputStream(os); oos.writeObject(o); oos.close(); os.close(); } /** *反序列化,将磁盘文件转化为对象 *@paramf *@return *@throwsException */ public static Object readObject(String strPath) throws Exception{ File f=new File(strPath); if(!f.exists()) { return null; } InputStream is=new FileInputStream(f); //ObjectOutputStream 核心类 ObjectInputStream ois=new ObjectInputStream(is); return ois.readObject(); } }

BloomFilter去重算法类

package com.hengking.crawl; import java.io.Serializable; import java.util.BitSet; public class SimpleBloomFilter implements Serializable { private final int DEFAULT_SIZE = 2 << 24; private final int[] seeds = new int[] { 7, 11, 13, 31, 37, 61, }; private BitSet bits = new BitSet(DEFAULT_SIZE); private SimpleHash[] func = new SimpleHash[seeds.length]; // public void main(String[] args) { // String value = "stone2083@yahoo.cn"; // SimpleBloomFilter filter = new SimpleBloomFilter(); // System.out.println(filter.contains(value)); // filter.add(value); // System.out.println(filter.contains(value)); // } public SimpleBloomFilter() { for (int i = 0; i < seeds.length; i++) { func[i] = new SimpleHash(DEFAULT_SIZE, seeds[i]); } } public void add(String value) { for (SimpleHash f : func) { bits.set(f.hash(value), true); } } public boolean contains(String value) { if (value == null) { return false; } boolean ret = true; for (SimpleHash f : func) { ret = ret && bits.get(f.hash(value)); } return ret; } public class SimpleHash implements Serializable { private int cap; private int seed; public SimpleHash(int cap, int seed) { this.cap = cap; this.seed = seed; } public int hash(String value) { int result = 0; int len = value.length(); for (int i = 0; i < len; i++) { result = seed * result + value.charAt(i); } return (cap - 1) & result; } } @Override public String toString() { // TODO Auto-generated method stub return super.toString(); } }

核心类

package com.hengking.crawl; import java.text.SimpleDateFormat; import java.util.*; import java.net.*; import java.awt.image.BufferedImage; import java.io.*; import java.util.regex.*; import javax.imageio.ImageIO; import com.hengking.crawl.util.UtilSeriz; // 搜索Web爬行者 public class SearchCrawler implements Runnable{ /* disallowListCache缓存robot不允许搜索的URL。 Robot协议在Web站点的根目录下设置一个robots.txt文件, *规定站点上的哪些页面是限制搜索的。 搜索程序应该在搜索过程中跳过这些区域,下面是robots.txt的一个例子: # robots.txt for http://somehost.com/ User-agent: * Disallow: /cgi-bin/ Disallow: /registration # /Disallow robots on registration page Disallow: /login */ public static SimpleBloomFilter filterUrl; public static SimpleBloomFilter filterImg; private HashMap< String,ArrayList< String>> disallowListCache = new HashMap< String,ArrayList< String>>(); ArrayList< String> errorList= new ArrayList< String>();//错误信息 ArrayList< String> result=new ArrayList< String>(); //搜索到的结果 String startUrl;//开始搜索的起点 int maxUrl;//最大处理的url数 String searchString;//要搜索的字符串(英文) boolean caseSensitive=false;//是否区分大小写 boolean limitHost=false;//是否在限制的主机内搜索 private static String outdir; private static String seroutdir; private static String seroutdirimg; private boolean blnFlag=false; /*** * 构造函数 * @param startUrl * @param maxUrl * @param searchString */ public SearchCrawler(String startUrl,int maxUrl,String searchString) { this.startUrl=startUrl; this.maxUrl=maxUrl; this.searchString=searchString; } public ArrayList< String> getResult(){ return result; } public void run(){//启动搜索线程 new Thread(new TimeWrite2File()).start(); blnFlag=true; crawl(startUrl,maxUrl, searchString,limitHost,caseSensitive); } //检测URL格式 private URL verifyUrl(String url) { // 只处理HTTP URLs. if (!url.toLowerCase().startsWith("http://")) return null; URL verifiedUrl = null; try { verifiedUrl = new URL(url); } catch (Exception e) { return null; } return verifiedUrl; } // 检测robot是否允许访问给出的URL. private boolean isRobotAllowed(URL urlToCheck) { String host = urlToCheck.getHost().toLowerCase();//获取给出RUL的主机 //System.out.println("主机="+host); // 获取主机不允许搜索的URL缓存 ArrayList< String> disallowList =disallowListCache.get(host); // 如果还没有缓存,下载并缓存。 if (disallowList == null) { disallowList = new ArrayList< String>(); try { URL robotsFileUrl =new URL("http://" + host + "/robots.txt"); BufferedReader reader =new BufferedReader(new InputStreamReader(robotsFileUrl.openStream())); // 读robot文件，创建不允许访问的路径列表。 String line; while ((line = reader.readLine()) != null) { if (line.indexOf("Disallow:") == 0) {//是否包含"Disallow:" String disallowPath =line.substring("Disallow:".length());//获取不允许访问路径 // 检查是否有注释。 int commentIndex = disallowPath.indexOf("#"); if (commentIndex != - 1) { disallowPath =disallowPath.substring(0, commentIndex);//去掉注释 } disallowPath = disallowPath.trim(); disallowList.add(disallowPath); } } // 缓存此主机不允许访问的路径。 disallowListCache.put(host, disallowList); } catch (Exception e) { return true; //web站点根目录下没有robots.txt文件,返回真 } } String file = urlToCheck.getFile(); //System.out.println("文件getFile()="+file); for (int i = 0; i < disallowList.size(); i++) { String disallow = disallowList.get(i); if (file.startsWith(disallow)) { return false; } } return true; } private String downloadPage(URL pageUrl) { try { // Open connection to URL for reading. BufferedReader reader = new BufferedReader(new InputStreamReader(pageUrl.openStream())); // Read page into buffer. String line; StringBuffer pageBuffer = new StringBuffer(); while ((line = reader.readLine()) != null) { pageBuffer.append(line); } return pageBuffer.toString(); } catch (Exception e) { } return null; } // 从URL中去掉"www" private String removeWwwFromUrl(String url) { int index = url.indexOf("://www."); if (index != -1) { return url.substring(0, index + 3) + url.substring(index + 7); } return (url); } // 解析页面并找出链接 private ArrayList< String> retrieveLinks(URL pageUrl, String pageContents, boolean limitHost) { // 用正则表达式编译链接的匹配模式。 Pattern p =Pattern.compile("<a//s+href//s*=//s*/"?(.*?)[/"|>]",Pattern.CASE_INSENSITIVE); Matcher m = p.matcher(pageContents); ArrayList< String> linkList = new ArrayList< String>(); while (m.find()) { String link = m.group(1).trim(); if (link.length() < 1) { continue; } // 跳过链到本页面内链接。 if (link.charAt(0) == '#') { continue; } if (link.indexOf("mailto:") != -1) { continue; } if (link.toLowerCase().indexOf("javascript") != -1) { continue; } if (link.indexOf("://") == -1){ if (link.charAt(0) == '/') {//处理绝对地 link = "http://" + pageUrl.getHost()+":"+pageUrl.getPort()+ link; } else { String file = pageUrl.getFile(); if (file.indexOf('/') == -1) {//处理相对地址 link = "http://" + pageUrl.getHost()+":"+pageUrl.getPort() + "/" + link; } else { String path =file.substring(0, file.lastIndexOf('/') + 1); link = "http://" + pageUrl.getHost() +":"+pageUrl.getPort()+ path + link; } } } int index = link.indexOf('#'); if (index != -1) { link = link.substring(0, index); } link = removeWwwFromUrl(link); URL verifiedLink = verifyUrl(link); if (verifiedLink == null) { continue; } /* 如果限定主机，排除那些不合条件的URL*/ if (limitHost && !pageUrl.getHost().toLowerCase().equals( verifiedLink.getHost().toLowerCase())) { continue; } // 跳过那些已经处理的链接. // if (crawledList.contains(link)) { // continue; // } if(filterUrl.contains(link)) { continue; } else { filterUrl.add(link); } linkList.add(link); } return (linkList); } // 解析页面并找出链接 private ArrayList< String> retrieveImgLinks(URL pageUrl, String pageContents, boolean limitHost) { // 用正则表达式编译链接的匹配模式。 Pattern p =Pattern.compile("<img//s+src//s*=//s*/"?(.*?)[/"|>]",Pattern.CASE_INSENSITIVE); Matcher m = p.matcher(pageContents); ArrayList< String> linkList = new ArrayList< String>(); while (m.find()) { String link = m.group(1).trim(); if (link.length() < 1) { continue; } // 跳过链到本页面内链接。 if (link.charAt(0) == '#') { continue; } if (link.indexOf("mailto:") != -1) { continue; } if (link.toLowerCase().indexOf("javascript") != -1) { continue; } if (link.indexOf("://") == -1) { if (link.charAt(0) == '/') {//处理绝对地 link = "http://" + pageUrl.getHost()+":"+pageUrl.getPort()+ link; } else { String file = pageUrl.getFile(); if (file.indexOf('/') == -1) {//处理相对地址 link = "http://" + pageUrl.getHost()+":"+pageUrl.getPort() + "/" + link; } else { String path =file.substring(0, file.lastIndexOf('/') + 1); link = "http://" + pageUrl.getHost() +":"+pageUrl.getPort()+ path + link; } } } int index = link.indexOf('#'); if (index != -1) { link = link.substring(0, index); } link = removeWwwFromUrl(link); URL verifiedLink = verifyUrl(link); if (verifiedLink == null) { continue; } /* 如果限定主机，排除那些不合条件的URL*/ if (limitHost && !pageUrl.getHost().toLowerCase().equals( verifiedLink.getHost().toLowerCase())) { continue; } // 跳过那些已经处理的链接. // if (crawledList.contains(link)) { // continue; // } if(filterImg.contains(link)) { continue; } else { filterImg.add(link); } if(link.lastIndexOf(".gif")==-1) { linkList.add(link); } } return (linkList); } // 搜索下载Web页面的内容，判断在该页面内有没有指定的搜索字符串 private boolean searchStringMatches(String pageContents, String searchString, boolean caseSensitive){ String searchContents = pageContents; if (!caseSensitive) {//如果不区分大小写 searchContents = pageContents.toLowerCase(); } Pattern p = Pattern.compile("[//s]+"); String[] terms = p.split(searchString); for (int i = 0; i < terms.length; i++) { if (caseSensitive) { if (searchContents.indexOf(terms[i]) == -1) { return false; } } else { if (searchContents.indexOf(terms[i].toLowerCase()) == -1) { return false; } } } return true; } //执行实际的搜索操作 public ArrayList< String> crawl(String startUrl, int maxUrls, String searchString,boolean limithost,boolean caseSensitive ) { // System.out.println("searchString="+searchString); // HashSet< String> crawledList = new HashSet< String>(); LinkedHashSet<String> toCrawlList = new LinkedHashSet<String>(); // LinkedHashSet< String> toImgList = new LinkedHashSet< String>(); if (maxUrls < 1) { errorList.add("Invalid Max URLs value."); System.out.println("Invalid Max URLs value."); } if (searchString.length() < 1) { errorList.add("Missing Search String."); System.out.println("Missing search String"); } if (errorList.size() > 0) { System.out.println("err!!!"); return errorList; } // 从开始URL中移出www startUrl = removeWwwFromUrl(startUrl); toCrawlList.add(startUrl); boolean isStart=false; while (toCrawlList.size()>0) { // Get URL at bottom of the list. String url = toCrawlList.iterator().next(); // Remove URL from the to crawl list. toCrawlList.remove(url); // if(filterUrl.contains(url)) // { // // continue; // } // else // { // filterUrl.add(url); // } // Convert string url to URL object. URL verifiedUrl = verifyUrl(url); // Skip URL if robots are not allowed to access it. if (!isRobotAllowed(verifiedUrl)) { continue; } // 增加已处理的URL到crawledList // crawledList.add(url); String pageContents = downloadPage(verifiedUrl); if (pageContents != null && pageContents.length() > 0) { // 从页面中获取有效的链接 ArrayList< String> links =retrieveLinks(verifiedUrl, pageContents,limitHost); // 从页面中获取有效的链接 ArrayList< String> imglinks =retrieveImgLinks(verifiedUrl, pageContents,limitHost); //添加到图片下载队列 toCrawlList.addAll(links); int iCount=0; for(int i=0;i<imglinks.size();i++) { if(imglinks.get(i).indexOf("http:")!=-1) { // if(!filterImg.contains(imglinks.get(i))) // { iCount++; filterImg.add(imglinks.get(i)); new Thread(new ImgDownThread(imglinks.get(i))).start(); // } if((iCount!=1) && (iCount%10==1) ) { try { logEvent("图多休息1秒......"); Thread.sleep(1000); } catch (InterruptedException e) { // TODO Auto-generated catch block e.printStackTrace(); } } } } System.out.println("iCount:"+iCount); if(iCount>10) { System.out.println( new SimpleDateFormat("yyyy年MM月dd日HH时mm分ss秒").format(new Date(Calendar.getInstance().getTimeInMillis()))+"=====>"+"超过10张..."); try { Thread.sleep(2000); } catch (InterruptedException e) { // TODO Auto-generated catch block e.printStackTrace(); } } // if (searchStringMatches(pageContents, searchString,caseSensitive)) // { // result.add(url); // System.out.println(url); // } } } blnFlag=false; logEvent("抓图完成......"); return result; } public static void logEvent(String strLog) { System.out.println( new SimpleDateFormat("yyyy年MM月dd日HH时mm分ss秒").format(new Date(Calendar.getInstance().getTimeInMillis()))+"=====>"+strLog); } // 主函数 public static void main(String[] args) { if(args.length!=6) { System.out.println("Usage:java SearchCrawler startUrl maxUrl searchString"); return; } int max=Integer.parseInt(args[1]); SearchCrawler crawler = new SearchCrawler(args[0],max,args[2]); outdir=args[3]; seroutdir=args[4]; seroutdirimg=args[5]; try { if(UtilSeriz.readObject(seroutdir)!=null) { System.out.println(new SimpleDateFormat("yyyy年MM月dd日HH时mm分ss秒").format(new Date(Calendar.getInstance().getTimeInMillis()))+"=====>"+"反序列化URL..."); filterUrl=(SimpleBloomFilter)UtilSeriz.readObject(seroutdir); } else { filterUrl=new SimpleBloomFilter(); } if(UtilSeriz.readObject(seroutdir)!=null) { System.out.println(new SimpleDateFormat("yyyy年MM月dd日HH时mm分ss秒").format(new Date(Calendar.getInstance().getTimeInMillis()))+"=====>"+"反序列化图片..."); filterImg=(SimpleBloomFilter)UtilSeriz.readObject(seroutdirimg); } else { filterImg=new SimpleBloomFilter(); } } catch (Exception e) { e.printStackTrace(); } Thread search=new Thread(crawler); System.out.println( new SimpleDateFormat("yyyy年MM月dd日HH时mm分ss秒").format(new Date(Calendar.getInstance().getTimeInMillis()))+"=====>"+"开始爬图..."); System.out.println("下载了图:"); search.start(); } /** * 说明:下载图片的线程 * @author binbin0915 * */ public class ImgDownThread implements Runnable{ private String stru; private boolean isStart=true; public ImgDownThread(String strurl) { super(); this.stru = strurl; } @Override public void run() { try { // String stru=""; // while(isStart) // { // stru = toImgList.iterator().next(); URL url=new URL(stru); BufferedInputStream in = new BufferedInputStream(url.openStream()); BufferedImage bi=ImageIO.read(url.openStream()); if (bi.getWidth()<30 || bi.getHeight()<30 ) { in.close(); return; } String ss=new SimpleDateFormat("yyyyMMddHHmmss").format(new Date(Calendar.getInstance().getTimeInMillis()))+"_"+Math.round(Math.random()*89999999999999L+1000)+stru.substring(stru.lastIndexOf(".")); String s=outdir+ss; FileOutputStream file = new FileOutputStream(new File(s)); int t; while ((t = in.read()) != -1) { file.write(t); } file.close(); if(new File(s).length()<=1*1024) { in.close(); new File(s).delete(); return; } in.close(); System.out.println( new SimpleDateFormat("yyyy年MM月dd日HH时mm分ss秒").format(new Date(Calendar.getInstance().getTimeInMillis()))+"=====>"+"下载了图片"+stru); // } } catch (Exception e) { // e.printStackTrace(); } } public boolean isStart() { return isStart; } public void setStart(boolean isStart) { this.isStart = isStart; } } public class TimeWrite2File implements Runnable{ @Override public void run() { while(blnFlag) { try { System.out.println(new SimpleDateFormat("yyyy年MM月dd日HH时mm分ss秒").format(new Date(Calendar.getInstance().getTimeInMillis()))+"=====>"+"序列化URL..."); logEvent("开始序列化URL"); UtilSeriz.writeObject(filterUrl,seroutdir); logEvent("开始序列化图片"); UtilSeriz.writeObject(filterImg,seroutdirimg); Thread.sleep(120000); } catch (Exception e) { e.printStackTrace(); } } } } }