fork download
  1. import java.util.*;
  2. import java.util.regex.*;
  3. import java.lang.*;
  4. import java.io.*;
  5.  
  6. class Ideone
  7. {
  8. public static void main (String[] args) throws java.lang.Exception
  9. {
  10. String html = "Cleaned!<!-- \nsome comment --><title> my title</title> style='OUR_STYLE'<meta ...>";
  11. Pattern p = Pattern.compile("<!--.*?-->|<title>.*?</title>|\\s+style='[^']+'|"
  12. + "<(meta|link|/?o:|/?style|/?div|/?std|/?head|/?html|/?body|/?span|!\\[)[^>]*>|"
  13. + "(<[^>]+>)+&nbsp;(</\\w+>)+", Pattern.CASE_INSENSITIVE|Pattern.DOTALL);
  14. Matcher m = p.matcher(html);
  15. String result = m.replaceAll("");
  16. System.out.println(result);
  17. }
  18. }
Success #stdin #stdout 0.08s 33900KB
stdin
Standard input is empty
stdout
Cleaned!