爬虫程序代码,Java代码库,德仔网

代码语言
代码分类
【Java】爬虫程序
作者:文杰 / 发布于2015/11/16/ 676
网络爬虫，是一种自动获取网页内容的程序。是搜索引擎的重要组成部分，因此搜索引擎优化很大程度上就是针对爬虫而做出的优化。

	import java.io.BufferedReader;
	import java.io.InputStreamReader;
	import java.net.URL;
	import java.util.ArrayList;
	import java.util.HashMap;
	import java.util.HashSet;
	import java.util.LinkedHashSet;
	import java.util.regex.Matcher;
	import java.util.regex.Pattern;
	
	public class SearchCrawler implements Runnable {
	 // disallowListCache缓存robot不允许搜索的URL
	 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
	 boolean caseSensitive = false;// 是否区分大小写
	 boolean limitHost = false;// 是否在限制的主机内搜索
	
	 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
	 crawl(startUrl, maxUrl, searchString, limitHost, caseSensitive);
	 }
	
	 /**
	 * 检测URL格式返回URL 类型的连接
	 * @param url
	 * @return
	 */
	 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URL.在robot文件中是否被允许抓取
	 * @param urlToCheck
	 * @return
	 */
	 private boolean isRobotAllowed(URL urlToCheck) {
	 String host = urlToCheck.getHost().toLowerCase();// 获取给出RUL的主机
	 // 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robots.txt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();
	 //如果是robots.txt中不允许抓取的连接，返回false
	 for (int i = 0; i < disallowList.size(); i++) {
	 String disallow = disallowList.get(i);
	 if (file.startsWith(disallow)) {
	 return false;
	 }
	 }
	 return true;
	 }
	
	 /**
	 * 下载url内容
	 * @param pageUrl
	 * @return
	 */
	 private String downloadPage(URL pageUrl) {
	 try {
	 BufferedReader reader = new BufferedReader(new InputStreamReader(pageUrl.openStream(), "UTF-8"));
	 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"
	 * @param url
	 * @return
	 */
	 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
	 * @param pageUrl 连接地址
	 * @param pageContents 页面内容
	 * @param crawledList 已处理过的连接
	 * @param limitHost 是否在限制的主机内搜索
	 * @return
	 */
	 private ArrayList<String> retrieveLinks(URL pageUrl, String pageContents,HashSet crawledList, 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;
	 }
	
	 // 跳过邮件地址
	 if (link.indexOf("mailto:") != -1) {
	 continue;
	 }
	
	 //跳过javascript连接
	 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;
	 }
	 }
	 }
	
	 //去掉#后边的东西
	 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;
	 }
	 linkList.add(link);
	 }
	 return (linkList);
	 }
	
	 /**
	 * 判断在该页面内有没有指定的搜索字符串
	 * @param pageContents 页面内容
	 * @param searchString 搜索字符串
	 * @param caseSensitive 是否去区分大小写
	 * @return
	 */
	 private boolean searchStringMatches(String pageContents,String searchString, boolean caseSensitive) {
	 pageContents = Html2Text(pageContents);
	 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>();
	
	 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);
	 while (toCrawlList.size() > 0) {
	
	 if (maxUrls != -1) {
	 if (crawledList.size() == maxUrls) {
	 break;
	 }
	 }
	 String url = toCrawlList.iterator().next();
	 toCrawlList.remove(url);
	 URL verifiedUrl = verifyUrl(url);
	 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, crawledList, limitHost);
	 toCrawlList.addAll(links);
	 if (searchStringMatches(pageContents, searchString,caseSensitive)) {
	 result.add(url);
	 System.out.println(url);
	 }
	 }
	 }
	 return result;
	 }
	
	 /**
	 * 去掉html标签
	 */
	 public static String Html2Text(String inputString) {
	 String htmlStr = inputString; // 含html标签的字符串
	 String textStr = "";
	 java.util.regex.Pattern p_script;
	 java.util.regex.Matcher m_script;
	 java.util.regex.Pattern p_style;
	 java.util.regex.Matcher m_style;
	 java.util.regex.Pattern p_html;
	 java.util.regex.Matcher m_html;
	 java.util.regex.Pattern p_html1;
	 java.util.regex.Matcher m_html1;
	
	 try {
	 String regEx_script = "<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\s]*?>"; // 定义script的正则表达式{或<script[^>]*?>[\\s\\S]*?<\\/script>
	 String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>"; // 定义style的正则表达式{或<style[^>]*?>[\\s\\S]*?<\\/style>
	 String regEx_html = "<[^>]+>"; // 定义HTML标签的正则表达式
	 String regEx_html1 = "<[^>]+";
	 p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
	 m_script = p_script.matcher(htmlStr);
	 htmlStr = m_script.replaceAll(""); // 过滤script标签
	
	 p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
	 m_style = p_style.matcher(htmlStr);
	 htmlStr = m_style.replaceAll(""); // 过滤style标签
	
	 p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
	 m_html = p_html.matcher(htmlStr);
	 htmlStr = m_html.replaceAll(""); // 过滤html标签
	
	 p_html1 = Pattern.compile(regEx_html1, Pattern.CASE_INSENSITIVE);
	 m_html1 = p_html1.matcher(htmlStr);
	 htmlStr = m_html1.replaceAll(""); // 过滤html标签
	 textStr = htmlStr;
	
	 } catch (Exception e) {
	 System.err.println("Html2Text: " + e.getMessage());
	 }
	 return textStr;// 返回文本字符串
	 }
	
	 // 主函数
	 public static void main(String[] args) {
	 String url = "http://www.nontrace.com";
	 int max = 20;
	 String str = "无痕";
	 SearchCrawler crawler = new SearchCrawler(url, max, str);
	 Thread search = new Thread(crawler);
	 System.out.println("Start searching...");
	 System.out.println("result:");
	 search.start();
	
	 }
	
	}
试试其它关键字
　爬虫程序　
同语言下
可能有用的
文杰贡献的其它代码(20)