gx

@@ -158,21 +158,17 @@ class ProofreadingController extends BaseController
         $strippedContent = preg_replace($pattern, '', $strippedContent); // 删除 `<link>` 标签
         $pattern = '/<footer\b[^>]*>(.*?)<\/footer>/s'; // 定义匹配`<script>`标签及其内容的正则表达式
         $strippedContent = preg_replace($pattern, '', $strippedContent); // 删除`<script>`标签及其内容
-//        $pattern = '/>([^<]+)</'; // 定义匹配中间内容不是标签的正则表达式
-//        $matches = array();
-//        preg_match_all($pattern, $strippedContent, $matches);
-//        $textContentArray = array_filter($matches[1], function($item) {
-//            $item = str_replace("\n", "", $item);
-//            return !empty(trim($item));
-//        });
-        $pattern = '/<(\w+)[^>]*>(.*?)<\/\1>/s'; // Define the regular expression pattern
-        preg_match_all($pattern, $strippedContent, $matches); // Match all tags and their content
-
-        $tagContentArray = $matches[2]; // Extract the content part from the matches array
-//        $textContentArray = array_values($textContentArray);
-//        $uniqueArray = array_unique($textContentArray);
-//        $textContentArray = array_values($uniqueArray);
-        return $tagContentArray;
+        $pattern = '/>([^<]+)</'; // 定义匹配中间内容不是标签的正则表达式
+        $matches = array();
+        preg_match_all($pattern, $strippedContent, $matches);
+        $textContentArray = array_filter($matches[1], function($item) {
+            $item = str_replace("\n", "", $item);
+            return !empty(trim($item));
+        });
+        $textContentArray = array_values($textContentArray);
+        $uniqueArray = array_unique($textContentArray);
+        $textContentArray = array_values($uniqueArray);
+        return $textContentArray;
     }
 
     /**