import org.apache.commons.lang3.StringUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class HtmlUtil {
private static final String regEx_script = "<script[^>]*?>[\\s\\S]*?<\\/script>"; // 定义script的正则表达式
private static final String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>"; // 定义style的正则表达式
private static final String regEx_html = "<[^>]+>"; // 定义HTML标签的正则表达式
private static final String regEx_space = "\\s*|\t|\r|\n";//定义空格回车换行符
/**
* @param htmlStr
* @return
* 删除Html标签
*/
public static String delHTMLTag(String htmlStr) {
Pattern p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
Matcher m_script = p_script.matcher(htmlStr);
htmlStr = m_script.replaceAll(""); // 过滤script标签
Pattern p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
Matcher m_style = p_style.matcher(htmlStr);
htmlStr = m_style.replaceAll(""); // 过滤style标签
Pattern p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
Matcher m_html = p_html.matcher(htmlStr);
htmlStr = m_html.replaceAll(""); // 过滤html标签
Pattern p_space = Pattern.compile(regEx_space, Pattern.CASE_INSENSITIVE);
Matcher m_space = p_space.matcher(htmlStr);
htmlStr = m_space.replaceAll(""); // 过滤空格回车标签
return htmlStr.trim(); // 返回文本字符串
}
/**
* 修该公告文本中的a标签
* @param text 公告文本
*/
public static String modifyATagByAnno(String text) {
checkHtmlIsEmpty(text);
Document document = Jsoup.parse(text);
Elements es = document.getElementsByTag("a");
for(Element a : es){
if(!a.hasAttr("style")){
a.attr("style","cursor: default; color: black; text-decoration: none;");
}
a.attr("href","javascript:void(0)");
}
return document.body().html();
}
private static void checkHtmlIsEmpty(String html){
if(StringUtils.isBlank(html)){
throw new NullPointerException("announcement content is empty!");
}
}
public static String getTextFromHtml(String htmlStr){
htmlStr = delHTMLTag(htmlStr);
htmlStr = htmlStr.replaceAll(" ", "");
//htmlStr = htmlStr.substring(0, htmlStr.indexOf("。")+1);
return htmlStr;
}
public static void main(String strs[]){
System.err.print(getTextFromHtml("<p>东科教育</p><p>测试 www.dongkit.com</p>");
}
}