Get HTML Tags from HTML String in Java | Code Factory
1 min readApr 23, 2020
Reference Link : Link
Donate : Link
GetHTMLTags.java
package com.codeFactory;import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.regex.Matcher;
import java.util.regex.Pattern;public class GetHTMLTags {public static void main(String... args) throws IOException {
Pattern pattern = Pattern.compile("<([^\\s>/]+)");
Matcher matcher = pattern.matcher(getHTML());
while(matcher.find()) {
System.out.println(matcher.group(1));
}
}
private static String getHTML() throws IOException {
return new String(Files.readAllBytes(Paths.get("TestHTML.html")));
}
}
TestHTML.html
<!DOCTYPE html>
<html>
<head>
<title>Page Title</title>
</head>
<body><h1>This is a Heading</h1>
<p>This is a paragraph.</p></body>
</html>
Output :
!DOCTYPE
html
head
title
body
h1
p