Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance.
Project price only 1 $
You can buy this project and download/modify it how often you want.
lodsve.core.utils.HTMLUtils Maven / Gradle / Ivy
/*
* Copyright (C) 2018 Sun.Hao
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see [email protected] )
* @version V1.0
* @createTime 2012-4-30 下午08:41:54
*/
public class HTMLUtils {
private static final String[] DEFAULT_ATTRS_TO_REMOVE = {"id", "name"};
private static final String[] DEFAULT_TAGS_TO_REMOVE = {"script", "style"};
private static final String[] DEFAULT_TAGS_TO_NOT_REMOVE_TAG_NAME = {"object", "embed", "param"};
private static final Logger logger = LoggerFactory.getLogger(HTMLUtils.class);
private static final String DEFAULT_ENCODING = "utf-8";
private static DOMFragmentParser fragmentParser = new DOMFragmentParser();
private static final Pattern XML_PATTERN = Pattern.compile("(?s)(.*?) ", Pattern.CASE_INSENSITIVE);
private static final Pattern STYLE_PATTERN = Pattern.compile("(?s)]*>(.*?)", Pattern.CASE_INSENSITIVE);
private static final Pattern SCRIPT_PATTERN = Pattern.compile("(?s)]*>(.*?)", Pattern.CASE_INSENSITIVE);
private static final Pattern TAGS_PATTERN = Pattern.compile("(?s)<[^>]+>", Pattern.CASE_INSENSITIVE);
private static final Pattern HTML_CHAR_PATTERN = Pattern.compile("&[\\w]+;", Pattern.CASE_INSENSITIVE);
private static final Pattern SPACE_PATTERN = Pattern.compile("(?s)[\\s]{2,}");
private static final Pattern FIST_LETTER_PATTERN = Pattern.compile("^[\\s]+");
/**
* 私有化构造器
*/
private HTMLUtils() {
}
static {
try {
fragmentParser.setFeature("http://cyberneko.org/html/features/augmentations", true);
// balance tags
fragmentParser.setFeature("http://cyberneko.org/html/features/balance-tags", true);
fragmentParser.setFeature("http://cyberneko.org/html/features/balance-tags/ignore-outside-content", false);
// to lower case
fragmentParser.setProperty("http://cyberneko.org/html/properties/names/elems", "lower");
// fix the html
fragmentParser.setFeature("http://cyberneko.org/html/features/document-fragment", false);
// Specifies whether to ignore the character encoding specified within the 我只中国人
";
String result = HTMLUtils.cleanHtml(test, "utf-8");
System.out.println(getRawText(3, test));
}
public static String escape(String src) {
int i;
char j;
StringBuffer tmp = new StringBuffer();
tmp.ensureCapacity(src.length() * 6);
for (i = 0; i < src.length(); i++) {
j = src.charAt(i);
if (Character.isDigit(j) || Character.isLowerCase(j) || Character.isUpperCase(j)) {
tmp.append(j);
} else if (j < 256) {
tmp.append("%");
if (j < 16) {
tmp.append("0");
}
tmp.append(Integer.toString(j, 16));
} else {
tmp.append("%u");
tmp.append(Integer.toString(j, 16));
}
}
return tmp.toString();
}
public static String unescape(String src) {
StringBuffer tmp = new StringBuffer();
tmp.ensureCapacity(src.length());
int lastPos = 0, pos = 0;
char ch;
while (lastPos < src.length()) {
pos = src.indexOf("%", lastPos);
if (pos == lastPos) {
if (src.charAt(pos + 1) == 'u') {
ch = (char) Integer.parseInt(src.substring(pos + 2, pos + 6), 16);
tmp.append(ch);
lastPos = pos + 6;
} else {
ch = (char) Integer.parseInt(src.substring(pos + 1, pos + 3), 16);
tmp.append(ch);
lastPos = pos + 3;
}
} else {
if (pos == -1) {
tmp.append(src.substring(lastPos));
lastPos = src.length();
} else {
tmp.append(src.substring(lastPos, pos));
lastPos = pos;
}
}
}
return tmp.toString();
}
public static String replaceHtmlEntities(String htmlStr) {
return htmlStr.replaceAll("<", "<").replaceAll(">", ">").replaceAll(""", "\"");
}
/**
* 提取出content中img内容.
*
* @param content 内容
* @return 提取的图片src
*/
public static List getImageUrls(String content) {
if (StringUtils.isNotEmpty(content)) {
List resultList = new ArrayList<>();
String regxp = "src=\"([^\"]+)\"";
Pattern p = Pattern.compile(regxp);
Matcher m = p.matcher(content);
while (m.find()) {
if (!m.group(1).contains("fckeditor")) {
// 获取被匹配的部分,并且去除fck的表情图片.
resultList.add(m.group(1));
}
}
return resultList;
}
return Collections.EMPTY_LIST;
}
}
