myagent-ai 1.15.90 → 1.15.92

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "myagent-ai",
-  "version": "1.15.90",
+  "version": "1.15.92",
   "description": "本地桌面端执行型AI助手 - Open Interpreter 风格 | Local Desktop Execution-Oriented AI Assistant",
   "main": "main.py",
   "bin": {

package/skills/search_skill.py

@@ -330,12 +330,19 @@ class WebReadSkill(Skill):
                 for tag in soup(["script", "style", "nav", "footer", "header", "aside"]):
                     tag.decompose()
                 # 移除所有 class 含特定关键词的元素
-                for tag in soup.find_all(True, class_=True):
-                    cls_str = " ".join(tag.get("class", []))
-                    if any(kw in cls_str.lower() for kw in
-                           ["sidebar", "footer", "nav", "header", "advertisement",
-                            "cookie", "popup", "modal", "banner", "social", "share"]):
-                        tag.decompose()
+                # 注意: decompose() 会连带销毁子元素，子元素的 attrs 变为 None，
+                # 必须同时检查 attrs 和 parent 来跳过已被销毁的标签
+                try:
+                    for tag in list(soup.find_all(True, class_=True)):
+                        if not getattr(tag, 'attrs', None):
+                            continue
+                        cls_str = " ".join(tag.get("class", []))
+                        if any(kw in cls_str.lower() for kw in
+                               ["sidebar", "footer", "nav", "header", "advertisement",
+                                "cookie", "popup", "modal", "banner", "social", "share"]):
+                            tag.decompose()
+                except Exception:
+                    pass  # 解析异常时跳过清理，不影响主要内容提取
 
                 text = soup.get_text(separator="\n", strip=True)
                 text = "\n".join(line for line in text.split("\n") if line.strip())