/**
* @author Jack.Wang
*
*/
import
java.io.Buffered
Reader;
import
java.io.InputStream
Reader;
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;
// 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
*/
private HashMap<Str
ing, ArrayList<Str
ing>> disallowListCache = new HashMap<Str
ing, ArrayList<Str
ing>>();
ArrayList<Str
ing>
errorList = new ArrayList<Str
ing>();// 错误信息
ArrayList<Str
ing> result = new ArrayList<Str
ing>(); // 搜索到的结果
Str
ing startUrl;// 开始搜索的起点
int maxUrl;// 最大
处理的url数
Str
ing searchStr
ing;// 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
public SearchCrawler(Str
ing startUrl, int maxUrl, Str
ing searchStr
ing) {
this.startUrl = startUrl;
this.maxUrl = maxUrl;
this.searchStr
ing = searchStr
ing;
}
public ArrayList<Str
ing> getResult() {
return result;
}
public void run() {// 启动搜索线程
crawl(startUrl, maxUrl, searchStr
ing, limitHost, caseSensitive);
}
// 检测URL格式
private URL verifyUrl(Str
ing 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) {
Str
ing 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<Str
ing> disallowList = disallowListCache.get(host);
// 如果还没有缓存,下载并缓存。
if (disallowList == null) {
disallowList = new ArrayList<Str
ing>();
try {
URL robots
FileUrl = new URL("http://" + host + "/robots.txt");
Buffered
Reader
reader = new Buffered
Reader(
new InputStream
Reader(robots
FileUrl.openStream()));
// 读robot文件，
创建不允许访问的路径列表。
Str
ing line;
while ((line =
reader.
readLine()) != null) {
if (line.
indexOf("Disallow:") == 0) {// 是否
包含"Disallow:"
Str
ing disallowPath = line.substr
ing("Disallow:"
.length());// 获取不允许访问路径
// 检查是否有注释。
int comment
Index = disallowPath.
indexOf("#");
if (comment
Index != -1) {
disallowPath = disallowPath.substr
ing(0,
comment
Index);// 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
}
}
Str
ing file = urlToCheck.get
File();
// System.out.println("文件get
File()="+
file);
for (int i = 0; i < disallowList.size(); i++) {
Str
ing disallow = disallowList.get(i);
if (
file.startsWith(disallow)) {
return false;
}
}
return true;
}
private Str
ing downloadPage(URL pageUrl) {
try {
// Open connection to URL for
reading.
Buffered
Reader
reader = new Buffered
Reader(new InputStream
Reader(
pageUrl.openStream()));
//
Read page into buffer.
Str
ing line;
Str
ingBuffer pageBuffer = new Str
ingBuffer();
while ((line =
reader.
readLine()) != null) {
pageBuffer.append(line);
}
return pageBuffer.toStr
ing();
} catch (Exception e) {
}
return null;
}
// 从URL中去掉"www"
private Str
ing removeWwwFromUrl(Str
ing url) {
int
index = url.
indexOf("://www.");
if (
index != -1) {
return url.substr
ing(0,
index + 3) + url.substr
ing(
index + 7);
}
return (url);
}
// 解析页面并找出链接
private ArrayList<Str
ing> retrieveLinks(URL pageUrl, Str
ing 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<Str
ing> linkList = new ArrayList<Str
ing>();
while (m.f
ind()) {
Str
ing 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 {
Str
ing file = pageUrl.get
File();
if (
file.
indexOf('/') == -1) {//
处理相对地址
link = "http://" + pageUrl.getHost() + ":"
+ pageUrl.getPort() + "/" + link;
} else {
Str
ing path =
file.substr
ing(0,
file.last
IndexOf('/') + 1);
link = "http://" + pageUrl.getHost() + ":"
+ pageUrl.getPort() + path + link;
}
}
}
int
index = link.
indexOf('#');
if (
index != -1) {
link = link.substr
ing(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);
}
// 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 searchStr
ingMatches(Str
ing pageContents,
Str
ing searchStr
ing, boolean caseSensitive) {
Str
ing searchContents = pageContents;
if (!caseSensitive) {// 如果不区分大小写
searchContents = pageContents.toLowerCase();
}
Pattern p = Pattern.compile("[\\s]+");
Str
ing[] terms = p.split(searchStr
ing);
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<Str
ing> crawl(Str
ing startUrl, int maxUrls,
Str
ing searchStr
ing, boolean limithost, boolean caseSensitive) {
HashSet<Str
ing> crawledList = new HashSet<Str
ing>();
LinkedHashSet<Str
ing> toCrawlList = new LinkedHashSet<Str
ing>();
if (maxUrls < 1) {
errorList.add("Invalid Max URLs value.");
System.out.println("Invalid Max URLs value.");
}
if (searchStr
ing.length() < 1) {
errorList.add("Miss
ing Search Str
ing.");
System.out.println("Miss
ing search Str
ing");
}
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;
}
}
// Get URL at bottom of the list.
Str
ing url = toCrawlList.itera
tor().next();
// Remove URL from the to crawl list.
toCrawlList.remove(url);
// Convert str
ing 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);
Str
ing pageContents = downloadPage(verifiedUrl);
if (pageContents != null && pageContents.length() > 0) {
// 从页面中获取有效的链接
ArrayList<Str
ing> links = retrieveLinks(verifiedUrl,
pageContents, crawledList, limitHost);
toCrawlList.addAll(links);
if (searchStr
ingMatches(pageContents, searchStr
ing,
caseSensitive)) {
result.add(url);
System.out.println(url);
}
}
}
return result;
}
// 主函数
public static void main(Str
ing[] args) {
SearchCrawler crawler = new SearchCrawler("http://www.blog
java.net/Jack2007/", 20,"jack");
Th
read search = new Th
read(crawler);
System.out.println("Start search
ing...");
System.out.println("result:");
search.start();
try {
search.join();
} catch (InterruptedException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
3万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
