gx

@@ -29,6 +29,8 @@ class ProofreadingController extends BaseController
         $list = $proofreadingModel->list(['url'=>$this->param['url'],'language_id'=>$this->param['language_id'],'type'=>1],'text',['text','translate']);
         //获取当前URl的所有文本内容
         $new_list = $this->getUrlRead($this->param['url']);
+        var_dump($new_list);
+        die();
         if(empty($list)){
             $data = [];
             $translate_list = Translate::tran($new_list, $countryInfo['alias']);
@@ -50,10 +52,6 @@ class ProofreadingController extends BaseController
             ];
         }
         $arr2 = array_diff($new_list, $old_list);
-        var_dump($new_list);
-        var_dump($old_list);
-        var_dump($arr2);
-        die();
         if(!empty($arr2)){
             $translate_list = Translate::tran($arr2, $countryInfo['alias']);
             foreach ($arr2 as $k1=>$v1){
@@ -160,17 +158,21 @@ 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));
-        });
-        $textContentArray = array_values($textContentArray);
-        $uniqueArray = array_unique($textContentArray);
-        $textContentArray = array_values($uniqueArray);
-        return $textContentArray;
+//        $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;
     }
 
     /**