Skip to content

Instantly share code, notes, and snippets.

@franfj
Last active August 29, 2015 14:19
Show Gist options
  • Save franfj/eb5ce37ead2fd3d33f15 to your computer and use it in GitHub Desktop.
Save franfj/eb5ce37ead2fd3d33f15 to your computer and use it in GitHub Desktop.
Parsear nombres de usuario de StackOverflow
package parser;
import java.net.URL;
import java.net.URLConnection;
import java.util.List;
import java.util.Scanner;
public class Parser {
public static void main(String[] args) {
List<String> htmls = null;
for(int i=1; i<1000; ++i){
//-----------------------------------[Sólo para coger html de la web]
String content = null;
URLConnection connection = null;
try {
connection = new URL("http://stackoverflow.com/users/"+i).openConnection();
Scanner scanner = new Scanner(connection.getInputStream());
scanner.useDelimiter("\\Z");
content = scanner.next();
//-----------------------------------[/Sólo para coger html de la web]
String comUser = "<title>User";
String finUser = "- Stack Overflow";
Integer comienzo = content.indexOf(comUser);
Integer fin = content.indexOf(finUser);
if(comienzo != -1 && fin != -1)
System.out.println(content.subSequence(comienzo+comUser.length(), fin).toString().trim());
}catch ( Exception ex ) {
System.out.println("ERROR - "+ex.toString());
}
}
}
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment