82 lines
3.3 KiB
Java
82 lines
3.3 KiB
Java
package com.gh.common.util;
|
|
|
|
import android.text.TextUtils;
|
|
|
|
import java.util.regex.Matcher;
|
|
import java.util.regex.Pattern;
|
|
|
|
/**
|
|
* Created by khy on 27/12/17.
|
|
*/
|
|
|
|
public class HtmlUtils {
|
|
|
|
public static String stripHtml(String htmlStr) {
|
|
if (TextUtils.isEmpty(htmlStr)) return "";
|
|
|
|
String regEx_script = "<script[^>]*?>[\\s\\S]*?<\\/script>"; //定义script的正则表达式
|
|
String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>"; //定义style的正则表达式
|
|
String regEx_html = "<[^>]+>"; //定义HTML标签的正则表达式
|
|
|
|
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
|
|
|
|
return htmlStr.trim(); //返回文本字符串
|
|
}
|
|
|
|
/**
|
|
* 去除html代码及文本
|
|
*/
|
|
public static String stripHtmlCode(String htmlStr) {
|
|
if (TextUtils.isEmpty(htmlStr)) return "";
|
|
|
|
String regEx_script = "<script[^>]*?>[\\s\\S]*?<\\/script>"; //定义script的正则表达式
|
|
String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>"; //定义style的正则表达式
|
|
String regEx_html = "<[^>]+>[\\s\\S]*?<\\/[^>]+>"; //定义HTML标签的正则表达式
|
|
String regEx_html_single = "<[^>]+>"; //定义HTML单标签的正则表达式
|
|
String regEx_blank = "\\s+"; //定义空白字符的正则表达式
|
|
|
|
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_html_single = Pattern.compile(regEx_html_single, Pattern.CASE_INSENSITIVE);
|
|
Matcher m_html_single = p_html_single.matcher(htmlStr);
|
|
htmlStr = m_html_single.replaceAll(""); //过滤html单标签
|
|
|
|
Pattern p_blank = Pattern.compile(regEx_blank, Pattern.CASE_INSENSITIVE);
|
|
Matcher m_blank = p_blank.matcher(htmlStr);
|
|
htmlStr = m_blank.replaceAll(" ");//过滤空白字符
|
|
|
|
return htmlStr.trim(); //返回文本字符串
|
|
}
|
|
|
|
/**
|
|
* 过滤掉标签，保留标签内容
|
|
*/
|
|
public static String filterHtmlLabel(String htmlStr) {
|
|
String regEx_html = "<[^>]+>([\\s\\S]*?)<\\/[^>]+>"; //定义HTML标签的正则表达式
|
|
Pattern p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
|
|
Matcher m_html = p_html.matcher(htmlStr);
|
|
htmlStr = m_html.replaceAll("$1"); //过滤html标签
|
|
return htmlStr.trim(); //返回文本字符串
|
|
}
|
|
}
|