// Code from: code.calum.org // Quick and dirty. public static String stripHTML(String inputHTML){ String check1 = regexReplace(inputHTML, "<.*?>", " "); String check2 = regexReplace(check1, "\n", " "); String check3 = regexReplace(check2, " ", " "); String check4 = regexReplace(check3, """, " \" "); String check5 = regexReplace(check4, " +", " "); return check5; } public static String regexReplace(String INPUT, String REGEX, String REPLACE){ Pattern p = Pattern.compile(REGEX); Matcher m = p.matcher(INPUT); // get a matcher object StringBuffer sb = new StringBuffer(); while (m.find()) { m.appendReplacement(sb, REPLACE); } m.appendTail(sb); //System.out.println(sb.toString()); return new String(sb); }