自动同步: 2026-03-17 02:10

skills/kb-deep-analyzer/deep_analyzer.py

@@ -141,14 +141,26 @@ class DeepAnalyzer:
         
         # 标准化元数据
         metadata = self._normalize_metadata(metadata)
-        
+
         title = metadata.get('title', '未知')
         duration = metadata.get('duration', 0)
         author = metadata.get('author', '')
         pubtime = metadata.get('pubtime', '')
         url = metadata.get('url', '')
         bvid = metadata.get('bvid', '')
-        platform = metadata.get('platform', 'bilibili')
+
+        # 推断 platform：优先使用元数据中的值，否则根据 URL 或 content_type 推断
+        platform = metadata.get('platform', '')
+        if not platform:
+            if 'zhihu.com' in url or content_type in ('answer', 'zhuanlan', 'question'):
+                platform = 'zhihu'
+            elif 'bilibili.com' in url or bvid:
+                platform = 'bilibili'
+            else:
+                platform = 'bilibili'  # 默认值
+
+        # 清理 author 字段：移除零宽度空格和前后空白
+        author = self._clean_author(author)
         
         # 获取内容 - 支持多种字段名
         text = content.get('text', '') or content.get('subtitle', '') or content.get('subtitles', '') or content.get('description', '')
@@ -186,11 +198,11 @@ class DeepAnalyzer:
         
         return result
     
-    def _build_prompt(self, title: str, duration: int, duration_str: str, author: str, 
-                      pubtime: str, url: str, bvid: str, platform: str, text: str, 
+    def _build_prompt(self, title: str, duration: int, duration_str: str, author: str,
+                      pubtime: str, url: str, bvid: str, platform: str, text: str,
                       content_type: str = "video") -> str:
         """构建分析 prompt，根据内容类型选择不同模板"""
-        if content_type == "article":
+        if content_type in ("article", "answer", "zhuanlan"):
             return self._build_article_prompt(title, author, pubtime, url, platform, text)
         else:
             return self._build_video_prompt(title, duration, duration_str, author, pubtime, url, bvid, platform, text)
@@ -422,6 +434,22 @@ URL：{url}
             return f"{h}:{m:02d}:{s:02d}"
         return f"{m}:{s:02d}"
 
+    def _clean_author(self, author: str) -> str:
+        """清理 author 字段：移除零宽度空格和前后空白"""
+        if not author:
+            return ''
+        # 移除零宽度空格 (U+200B) 和其他不可见字符
+        invisible_chars = ['\u200b', '\u200c', '\u200d', '\ufeff', '\u00ad']
+        cleaned = author
+        for char in invisible_chars:
+            cleaned = cleaned.replace(char, '')
+        # 移除前后空白和换行
+        cleaned = cleaned.strip()
+        # 如果包含换行符，只取第一行
+        if '\n' in cleaned:
+            cleaned = cleaned.split('\n')[0].strip()
+        return cleaned
+
 
 # ============== 工具函数 ==============
 
@@ -437,19 +465,34 @@ def generate_frontmatter(metadata: Dict, result: AnalysisResult, content_type: s
     """生成 Markdown frontmatter"""
     # 提取标签
     tags = result.recommended_tags or []
-    
+
     # 格式化日期
     pubtime = metadata.get('pubtime', '')
     if pubtime:
         date_str = str(pubtime)[:10]
     else:
         date_str = datetime.now().strftime('%Y-%m-%d')
-    
-    fm = ["---", 
+
+    # 清理 author 字段
+    author = metadata.get('author', '未知')
+    author = _clean_string(author)
+
+    # 推断 platform
+    url = metadata.get('url', '')
+    platform = metadata.get('platform', '')
+    if not platform:
+        if 'zhihu.com' in url or content_type in ('answer', 'zhuanlan', 'question'):
+            platform = 'zhihu'
+        elif 'bilibili.com' in url or metadata.get('bvid'):
+            platform = 'bilibili'
+        else:
+            platform = 'bilibili'
+
+    fm = ["---",
           f"title: \"{metadata.get('title', '未命名')}\"",
           f"date: {date_str}",
-          f"author: {metadata.get('author', '未知')}",
-          f"platform: {metadata.get('platform', 'bilibili')}"]
+          f"author: {author}",
+          f"platform: {platform}"]
     
     # 视频类型添加 duration 和 bvid
     if content_type == "video":
@@ -470,6 +513,23 @@ def generate_frontmatter(metadata: Dict, result: AnalysisResult, content_type: s
     return '\n'.join(fm)
 
 
+def _clean_string(text: str) -> str:
+    """清理字符串：移除零宽度空格和前后空白"""
+    if not text:
+        return ''
+    # 移除零宽度空格 (U+200B) 和其他不可见字符
+    invisible_chars = ['\u200b', '\u200c', '\u200d', '\ufeff', '\u00ad']
+    cleaned = text
+    for char in invisible_chars:
+        cleaned = cleaned.replace(char, '')
+    # 移除前后空白和换行
+    cleaned = cleaned.strip()
+    # 如果包含换行符，只取第一行
+    if '\n' in cleaned:
+        cleaned = cleaned.split('\n')[0].strip()
+    return cleaned
+
+
 # ============== 主程序 ==============
 
 def main():