Skip to content

Instantly share code, notes, and snippets.

@quoideneuf
Created December 9, 2015 15:59
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save quoideneuf/6d8ca958d423a4020e93 to your computer and use it in GitHub Desktop.
Save quoideneuf/6d8ca958d423a4020e93 to your computer and use it in GitHub Desktop.
import java.util.Properties;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.jsoup.nodes.Entities.EscapeMode;
import org.jsoup.safety.Whitelist;
import org.jsoup.safety.Cleaner;
public class BriansTest {
public static void main(String[] args) {
Properties props = System.getProperties();
props.list(System.out);
Document doc = Jsoup.parse("<h1>øøøøøøøøøø</h1>");
doc = new Cleaner(Whitelist.simpleText()).clean(doc);
doc.outputSettings().escapeMode(EscapeMode.base);
// test 1
String string1 = doc.body().html();
System.out.println(string1);
// test 2
doc.outputSettings().charset("ASCII");
String string2 = doc.body().html();
System.out.println(string2);
// test 3
doc.outputSettings().charset("UTF-8");
String string3 = doc.body().html();
System.out.println(string3);
}
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment