Psst.. new poll here.
Psst.. new forums here.
Microsoft is blocking us again (TY IP Reputation!) so just use oauth login instead. :)
Paste
Pasted as Java by 911up ( 15 years ago )
/*
* To change this template, choose Tools | Templates
* and open the template in the editor.
*/
package up.ux.krakow.pl;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.Set;
import java.util.logging.Level;
import java.util.logging.Logger;
/**
*
* @author guest
*/
public class UrlTester {
protected String getURLData(String urlAddress) {
StringBuilder s = new StringBuilder();
try {
URL url = new URL(urlAddress);
InputStream is = url.openStream();
BufferedReader br = new BufferedReader(new InputStreamReader(is, "UTF-8"));
String ln;
while ((ln = br.readLine()) != null) {
// System.out.println(ln);
s.append(ln).append("\n");
}
} catch (MalformedURLException ex) {
return(null);//Logger.getLogger(UrlTester.class.getName()).log(Level.SEVERE, null, ex);
} catch (IOException ex) {
return(null);// Logger.getLogger(UrlTester.class.getName()).log(Level.SEVERE, null, ex);
}
return s.toString();
}
protected void splitTest(){
String s = "Ala ma kota";
String[] ts =s.split(" ");
for(int i=0;i<ts.length;++i){
System.out.println("String nr:" + 1 + "=" + ts[i]);
}
}
protected ArrayList<String> linkSearcher(String page){
ArrayList<String> links =new ArrayList<String>();
String[] t1 =page.split("<a.*?href=[\"']?");
for(int i = 1; i<t1.length;++i){
String[] t2=t1[i].split("[\"'\\s>]");
System.out.println("Link:" + i + "=" + t2[0]);
}return links;
}
public static void main(String[] args) {
UrlTester ut = new UrlTester();
String strona = ut.getURLData("http://www.up.krakow.pl/kmk/new/index.php");
// System.out.println("Zrodlo strony: \n" + s);
// System.out.println("END");
// ut.splitTest();
//ut.linkSearcher(strona);
ArrayList<String> linksToVisit=new ArrayList<String>();
Set<String> linksAllredyVisited= new HashSet<String>();
linksToVisit.add("http://www.up.krakow.pl/kmk/new/index.php");
while(! linksToVisit.isEmpty()){
String l=linksToVisit.get(0);
if(!linksAllredyVisited.contains(1)){
System.out.println("Aktualna strona"+ l
+ "do odwiedzenia " + linksToVisit.size()
+ " odwiedzonych: " + linksAllredyVisited.size()
);
String page=ut.getURLData(l);
if (page!=null){
ArrayList<String> newLink=ut.linkSearcher(page);
linksToVisit.addAll(newLink);}
linksAllredyVisited.add(1);
linksToVisit.remove(0);
}
}
}
Revise this Paste