Fix #58

leanote · Jan 21, 2018 · 7903d83 · 7903d83
1 parent 09fd851
commit 7903d83
Showing 1 changed file with 17 additions and 14 deletions.
diff --git a/app/src/main/java/org/houxg/leamonax/utils/HtmlUtils.java b/app/src/main/java/org/houxg/leamonax/utils/HtmlUtils.java
@@ -195,22 +195,25 @@ public static String decodeHtml(String html) {
     }
 
     public static String delHTMLTag(String htmlStr){
-        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
+        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_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
+        Matcher m_html = p_html.matcher(htmlStr);
+        if (!m_html.find()) {
+            return 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_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_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
+        Matcher m_style = p_style.matcher(htmlStr);
+        htmlStr = m_style.replaceAll(""); //过滤style标签
 
+        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
     }
 }