/* Daniel Shiffman */
/* Programming from A to Z */
/* Spring 2006 */
/* http://www.shiffman.net */
/* daniel.shiffman@nyu.edu */
/* Parsing HTML Example */
package basics;
import java.io.IOException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import a2z.A2ZUrlReader;
public class WeatherGrabberHTML {
public static void main(String[] args) throws IOException {
A2ZUrlReader urlreader = new A2ZUrlReader("http://weather.yahoo.com/forecast/USNY0996.html");
String html = urlreader.getContent();
// Yucky yucky HTML looks like this, we want to search for 37 & 25
// High: 37°
// Low: 25°
// Grab high temperature
String high = regexTextBetween(html,"High: ","°");
System.out.println("The high for today is: " + high + " degrees.");
// Grab low temperature
String low = regexTextBetween(html,"Low: ","°");
System.out.println("The low for today is: " + low + " degrees.");
}
public static String regexTextBetween(String s, String startRegex, String endRegex) {
String bigRegex = startRegex + "(.*?)" + endRegex;
Pattern p = Pattern.compile(bigRegex);
Matcher m = p.matcher(s);
if (m.find()) {
return m.group(1);
} else {
return "oops!";
}
}
}