Merge pull request #43 from rss-translator/next_version

Next version

core/tasks.py

@@ -307,12 +307,12 @@ def content_translate(original_content: str, target_language: str, engine: Trans
         comments = soup.find_all(string=lambda text: isinstance(text, Comment))
         [comment.extract() for comment in comments]
 
-        for element in soup.get_text():
+        for element in soup:
             if text_handler.should_skip(element):
                 continue
             #TODO 如果文字长度大于最大长度，就分段翻译，需要用chunk_translate
 
-            text = str(element)
+            text = element.get_text()
             logging.info("Translate content: %s", text)
             cached = Translated_Content.is_translated(text, target_language)
 

templates/admin/base_site.html

@@ -4,7 +4,7 @@
 <div id="footer" style="text-align: center;">
     <a href="https://rsstranslator.com" title="RSS Translator">RSS Translator</a> ·
     <a href="https://afdian.net/a/versun" title="Donate">Donate</a> ·
-    Version: 2024.3.27
+    Version: 2024.3.30
 
     <!--    <div class="social">-->
 

utils/text_handler.py

@@ -56,23 +56,23 @@ def group_chunks(split_chunks: dict, min_size: int, max_size: int,
     return grouped_chunks
 
 def should_skip(element):
-    if element.find_parent('code'):
+    if element.name == 'code':
         return True
     # 去除两端的空白字符
-    element = element.strip()
-    if not element:
+    text = element.get_text()
+    text = text.strip()
+    if not text:
         return True
 
     # 使用正则表达式来检查元素是否为数字、URL、电子邮件或包含特定符号
     skip_patterns = [
         r'^http',  # URL
         r'^[^@]+@[^@]+\.[^@]+$',  # 电子邮件
         r'^[\d\W]+$'  # 纯数字或者数字和符号的组合
-        r'<code>.*</code>'  # <code>标签的内容
     ]
 
     for pattern in skip_patterns:
-        if re.match(pattern, element):
+        if re.match(pattern, text):
             return True
 
     return False