Java Utililty Methods HTML to String

List of utility methods to do HTML to String

  1. HOME
  2. Java
  3. H
  4. HTML to String

Description

The list of methods to do HTML to String are organized into topic(s).

Method

Stringhtml2Plain(String text)
html Plain 
StringBuilder result = new StringBuilder();
for (int i = 0; i < text.length(); i++) {
    if (text.charAt(i) != '&' || i >= text.length() - 2) {
        result.append(text.charAt(i));
    } else {
        i++;
        if (text.charAt(i) != '#') {
            result.append('&');
...
Stringhtml2Text(String html)
Cuts all the html tags/comments/styles from the html-text and returns the only printable text. 
StringBuilder sb = new StringBuilder();
int state = 0;
int styleStart = html.toLowerCase().indexOf("<style");
int styleEnd = html.toLowerCase().indexOf("/style>");
while (styleStart != -1 && styleEnd > styleStart) {
    html = html.substring(0, styleStart) + html.substring(styleEnd + "/style>".length());
    styleStart = html.toLowerCase().indexOf("<style");
    styleEnd = html.toLowerCase().indexOf("/style>");
...
StringhtmlToStr(String htmlStr, int max_count)
html To Str 
String result = "";
boolean flag = true;
if (htmlStr == null) {
    return null;
char[] a = htmlStr.toCharArray();
int length = a.length;
for (int i = 0; i < length; i++) {
...
StringhtmlToString(String aS_Text)
html To String 
if (aS_Text == null) {
    return null;
StringBuffer l_StringBuffer = new StringBuffer();
int li_length = aS_Text.length();
for (int li_index = 0; li_index < li_length; li_index++) {
    char l_char = aS_Text.charAt(li_index);
    switch (l_char) {
...
StringhtmlToString(String s)
Unescape HTML escape characters in String. 
StringBuilder sb = new StringBuilder(s.length());
int len = s.length();
for (int i = 0; i < len; ++i) {
    char c = s.charAt(i);
    if (c != '&') {
        sb.append(c);
    } else {
        if (i + 2 < len && s.charAt(i + 1) == '#') { 
...
StringhtmlToString(String string)
html To String 
String ans = string.replaceAll("&quot;", "\"");
ans = ans.replaceAll("&amp;", "&");
ans = ans.replaceAll("&lt;", "<");
ans = ans.replaceAll("&gt;", ">");
ans = ans.replaceAll("<.+?>", "");
return ans;
StringhtmlToText(String html)
Simply removes the <...> tags. 
char ch = '\u0000';
int idx = 0;
int len = html.length();
StringBuffer sb = new StringBuffer();
for (int i = 0; i < len; i++) {
    ch = html.charAt(i);
    if (ch != '<') {
        sb.append(ch);
...
StringhtmlToText(String html)
html To Text 
if (html != null) {
    html = html.replace("&aring;", "\u00e5");
    html = html.replace("&auml;", "\u00e4");
    html = html.replace("&ouml;", "\u00f6");
    html = html.replace("&Aring;", "\u00c5");
    html = html.replace("&Auml;", "\u00c4");
    html = html.replace("&Ouml;", "\u00d6");
return html;
StringhtmlToText(String input)
Converts HTML to plain text, according to the following rules:
  • Replaces any newlines or carriage returns in the source text with single spaces. 
    if (input == null)
    input = "";
input = input.replaceAll("[\r\n]+", " ");
StringBuilder buf = new StringBuilder(input.trim());
int openIdx = 0;
while ((openIdx = buf.indexOf("<", openIdx)) >= 0) {
    int closeIdx = buf.indexOf(">", openIdx);
    if (closeIdx < 0) {
...
StringhtmlToText(String sHTML)
html To Text 
String sText = "";
if (sHTML != null) {
    int i = 0;
    while (i < sHTML.length()) {
        char c = sHTML.charAt(i);
        switch (c) {
        case '<':
            i++;
...