久久久久久国产精品免费,插插插综合视频,免费看a级毛片

一個(gè)簡(jiǎn)單的java網(wǎng)絡(luò)爬蟲,由于時(shí)間原因,沒有進(jìn)一步解釋.

需要的htmlparser.jar包到官方網(wǎng)上去下.

---------------------------------------------Spider.java-----------------------------------------------------------------
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.Iterator;
import java.util.List;
import org.htmlparser.RemarkNode;
import org.htmlparser.StringNode;
import org.htmlparser.Node;
import org.htmlparser.tags.*;
import org.htmlparser.Parser;
import org.htmlparser.filters.StringFilter;
import org.htmlparser.util.NodeIterator;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
import java.util.Queue;
import java.util.LinkedList;
public class Spider implements Runnable {
boolean search_key_words = false;
int count = 0;
int limitsite = 10;
int countsite = 1;
String keyword = "中國(guó)";//搜索關(guān)鍵字
Parser parser = new Parser();
// List linklist = new ArrayList();
String startsite = "";//搜索的其實(shí)站點(diǎn)
SearchResultBean srb;//保存搜索結(jié)果
List resultlist = new ArrayList();//搜索到關(guān)鍵字鏈接列表
List searchedsite = new ArrayList();//已經(jīng)被搜索站點(diǎn)列表
Queue linklist = new LinkedList();//需解析的鏈接列表
HashMap<String, ArrayList<String>> disallowListCache = new HashMap<String, ArrayList<String>>();
public Spider(String keyword, String startsite) {
this.keyword = keyword;
this.startsite = startsite;
linklist.add(startsite);
srb = new SearchResultBean();
}
public void run() {
// TODO Auto-generated method stub
search(linklist);
}
public void search(Queue queue) {
String url = "";
while(!queue.isEmpty()){
url = queue.peek().toString();//查找列隊(duì)
try {
if (!isSearched(searchedsite, url)) {
if (isRobotAllowed(new URL(url)))//檢查該鏈接是否被允許搜索
processHtml(url);
else
System.out.println("this page is disallowed to search");
}
} catch (Exception ex) {
}
queue.remove();
}
}
/**
* 解析HTML
* @param url
* @throws ParserException
* @throws Exception
*/
public void processHtml(String url) throws ParserException, Exception {
searchedsite.add(url);
count = 0;
System.out.println("searching ... :" + url);
parser.setURL(url);
parser.setEncoding("GBK");
URLConnection uc = parser.getConnection();
uc.connect();
//uc.getLastModified();
NodeIterator nit = parser.elements();
while (nit.hasMoreNodes()) {
Node node = nit.nextNode();
parserNode(node);
}
srb.setKeywords(keyword);
srb.setUrl(url);
srb.setCount_key_words(count);
resultlist.add(srb);
System.out.println("count keywords is :" + count);
System.out.println("----------------------------------------------");
}
/**
* 處理HTML標(biāo)簽
* @param tag
* @throws Exception
*/
public void dealTag(Tag tag) throws Exception {
NodeList list = tag.getChildren();
if (list != null) {
NodeIterator it = list.elements();
while (it.hasMoreNodes()) {
Node node = it.nextNode();
parserNode(node);
}
}
}
/**
* 處理HTML標(biāo)簽結(jié)點(diǎn)
* @param node
* @throws Exception
*/
public void parserNode(Node node) throws Exception{
if (node instanceof StringNode) {//判斷是否是文本結(jié)點(diǎn)
StringNode sNode = (StringNode) node;
StringFilter sf = new StringFilter(keyword,false);
search_key_words = sf.accept(sNode);
if (search_key_words) {
count++;
}
// System.out.println("text is :"+sNode.getText().trim());
} else if (node instanceof Tag) {//判斷是否是標(biāo)簽庫(kù)結(jié)點(diǎn)
Tag atag = (Tag) node;
if (atag instanceof TitleTag) {//判斷是否是標(biāo)TITLE結(jié)點(diǎn)
srb.setTitle(atag.getText());
}
if (atag instanceof LinkTag) {//判斷是否是標(biāo)LINK結(jié)點(diǎn)
LinkTag linkatag = (LinkTag) atag;
checkLink(linkatag.getLink(), linklist);
// System.out.println("-----------------this is link --------------");
}
dealTag(atag);
} else if (node instanceof RemarkNode) {//判斷是否是注釋
// System.out.println("this is remark");
}
}
/*
* 檢查鏈接是否需要加入列隊(duì)
*/
public void checkLink(String link, Queue queue) {
if (link != null && !link.equals("") && link.indexOf("#") == -1) {
if (!link.startsWith("http://") && !link.startsWith("ftp://")
&& !link.startsWith("www.")) {
link = "file:///" + link;
} else if (link.startsWith("www.")) {
link = "http://" + link;
}
if (queue.isEmpty())
queue.add(link);
else {
String link_end_=link.endsWith("/")?link.substring(0,link.lastIndexOf("/")):(link+"/");
if (!queue.contains(link)&&!queue .contains(link_end_)) {
queue.add(link);
}
}
}
}
/**
* 檢查該鏈接是否已經(jīng)被掃描
* @param list
* @param url
* @return
*/
public boolean isSearched(List list, String url) {
String url_end_ = "";
if (url.endsWith("/")) {
url_end_ = url.substring(0, url.lastIndexOf("/"));
} else {
url_end_ = url + "/";
}
if (list.size() > 0) {
if (list.indexOf(url) != -1 || list.indexOf(url_end_) != -1) {
return true;
}
}
return false;
}
/**
* 檢查URL是否被允許搜索
* @param urlToCheck
* @return
*/
private boolean isRobotAllowed(URL urlToCheck) {
String host = urlToCheck.getHost().toLowerCase();// 獲取給出RUL的主機(jī)
// System.out.println("主機(jī)="+host);
// 獲取主機(jī)不允許搜索的URL緩存
ArrayList<String> disallowList = disallowListCache.get(host);
// 如果還沒有緩存,下載并緩存。
if (disallowList == null) {
disallowList = new ArrayList<String>();
try {
URL robotsFileUrl = new URL("http://" + host + "/robots.txt");
BufferedReader reader = new BufferedReader(
new InputStreamReader(robotsFileUrl.openStream()));
// 讀robot文件，創(chuàng)建不允許訪問的路徑列表。
String line;
while ((line = reader.readLine()) != null) {
if (line.indexOf("Disallow:") == 0) {// 是否包含"Disallow:"
String disallowPath = line.substring("Disallow:"
.length());// 獲取不允許訪問路徑
// 檢查是否有注釋。
int commentIndex = disallowPath.indexOf("#");
if (commentIndex != -1) {
disallowPath = disallowPath.substring(0,
commentIndex);// 去掉注釋
}
disallowPath = disallowPath.trim();
disallowList.add(disallowPath);
}
}
for (Iterator it = disallowList.iterator(); it.hasNext();) {
System.out.println("Disallow is :" + it.next());
}
// 緩存此主機(jī)不允許訪問的路徑。
disallowListCache.put(host, disallowList);
} catch (Exception e) {
return true; // web站點(diǎn)根目錄下沒有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;
}
public static void main(String[] args) {
Spider ph = new Spider("英超", "http://www.microsoft.com");
try {
// ph.processHtml();
Thread search = new Thread(ph);
search.start();//啟動(dòng)線程
} catch (Exception ex) {
}
}
}
--------------------------------------SearchResultBean.java---------------------------------------------------------
public class SearchResultBean {
String url = "";
String title = "";
String keywords = "";
int count_key_words = 0;
public int getCount_key_words() {
return count_key_words;
}
public void setCount_key_words(int count_key_words) {
this.count_key_words = count_key_words;
}
public String getKeywords() {
return keywords;
}
public void setKeywords(String keywords) {
this.keywords = keywords;
}
public String getTitle() {
return title;
}
public void setTitle(String title) {
this.title = title;
}
public String getUrl() {
return url;
}
public void setUrl(String url) {
this.url = url;
}
}

本站僅提供存儲(chǔ)服務(wù)，所有內(nèi)容均由用戶發(fā)布，如發(fā)現(xiàn)有害或侵權(quán)內(nèi)容，請(qǐng)點(diǎn)擊舉報(bào)。

免费视频淫片aa毛片_日韩高清在线亚洲专区vr_日韩大片免费观看视频播放_亚洲欧美国产精品完整版