refactor: 完善降级链的异常捕获机制

为所有 Reader 的 parser 循环添加 try-except 防护层，确保即使 parser 抛出意外异常，降级链也能继续尝试下一个 parser。主要变更： - 所有 Reader (DocxReader/PdfReader/XlsxReader/PptxReader/HtmlReader) 的 parse 方法中添加防护层，捕获意外异常并标记为 [意外异常] - cleaner.clean_html_content() 添加异常处理，返回 (content, error) 元组 - HtmlReader.parse() 更新 cleaner 调用方式，处理新的返回值格式 - BaseReader 添加详细的异常处理规范文档设计原则：双层异常保护 - Parser 层：捕获预期的解析失败（库未安装、格式不支持） - Reader 层：捕获意外的编程错误（NoneType、索引越界等）
2026-03-09 00:26:51 +08:00
parent 2b81dd49fe
commit b80c635f07
7 changed files with 141 additions and 80 deletions
--- a/scripts/readers/html/init.py
+++ b/scripts/readers/html/init.py
@@ -50,7 +50,11 @@ class HtmlReader(BaseReader):
                return None, [f"- {error}"]

        # 步骤 2: 清理 HTML 内容
-        html_content = cleaner.clean_html_content(html_content)
+        cleaned_html, error = cleaner.clean_html_content(html_content)
+        if error:
+            all_failures.append(f"- cleaner: {error}")
+            return None, all_failures
+        html_content = cleaned_html

        # 步骤 3: 对每个 Parser 创建独立的临时文件并尝试解析
        for parser_name, parser_func in PARSERS:
@@ -61,12 +65,15 @@ class HtmlReader(BaseReader):
                with os.fdopen(fd, 'w', encoding='utf-8') as f:
                    f.write(html_content)

-                # 调用 Parser 解析
-                content, error = parser_func(temp_file_path)
-                if content is not None:
-                    return content, all_failures
-                else:
-                    all_failures.append(f"- {parser_name}: {error}")
+                # 调用 Parser 解析（添加防护层）
+                try:
+                    content, error = parser_func(temp_file_path)
+                    if content is not None:
+                        return content, all_failures
+                    else:
+                        all_failures.append(f"- {parser_name}: {error}")
+                except Exception as e:
+                    all_failures.append(f"- {parser_name}: [意外异常] {type(e).__name__}: {str(e)}")
            finally:
                # 清理临时文件
                try:
--- a/scripts/readers/html/cleaner.py
+++ b/scripts/readers/html/cleaner.py
@@ -1,69 +1,87 @@
 """HTML 清理模块，用于清理 HTML 内容中的敏感信息。"""

 import re
+from typing import Optional, Tuple
+
 from bs4 import BeautifulSoup


-def clean_html_content(html_content: str) -> str:
-    """清理 HTML 内容，移除 script/style/link/svg 标签和 URL 属性。"""
-    soup = BeautifulSoup(html_content, "html.parser")
+def clean_html_content(html_content: str) -> Tuple[Optional[str], Optional[str]]:
+    """
+    清理 HTML 内容，移除 script/style/link/svg 标签和 URL 属性。

-    # Remove all script tags
-    for script in soup.find_all("script"):
-        script.decompose()
+    Returns:
+        (content, error): 成功时返回 (清理后的 HTML, None)，失败时返回 (None, 错误信息)
+    """
+    try:
+        from bs4 import BeautifulSoup
+    except ImportError:
+        return None, "beautifulsoup4 库未安装"

-    # Remove all style tags
-    for style in soup.find_all("style"):
-        style.decompose()
+    try:
+        soup = BeautifulSoup(html_content, "html.parser")

-    # Remove all svg tags
-    for svg in soup.find_all("svg"):
-        svg.decompose()
+        # Remove all script tags
+        for script in soup.find_all("script"):
+            script.decompose()

-    # Remove all link tags
-    for link in soup.find_all("link"):
-        link.decompose()
+        # Remove all style tags
+        for style in soup.find_all("style"):
+            style.decompose()

-    # Remove URLs from href and src attributes
-    for tag in soup.find_all(True):
-        if "href" in tag.attrs:
-            del tag["href"]
-        if "src" in tag.attrs:
-            del tag["src"]
-        if "srcset" in tag.attrs:
-            del tag["srcset"]
-        if "action" in tag.attrs:
-            del tag["action"]
-        data_attrs = [
-            attr
-            for attr in tag.attrs
-            if attr.startswith("data-") and "src" in attr.lower()
-        ]
-        for attr in data_attrs:
-            del tag[attr]
+        # Remove all svg tags
+        for svg in soup.find_all("svg"):
+            svg.decompose()

-    # Remove all style attributes from all tags
-    for tag in soup.find_all(True):
-        if "style" in tag.attrs:
-            del tag["style"]
+        # Remove all link tags
+        for link in soup.find_all("link"):
+            link.decompose()

-    # Remove data-href attributes
-    for tag in soup.find_all(True):
-        if "data-href" in tag.attrs:
-            del tag["data-href"]
+        # Remove URLs from href and src attributes
+        for tag in soup.find_all(True):
+            if "href" in tag.attrs:
+                del tag["href"]
+            if "src" in tag.attrs:
+                del tag["src"]
+            if "srcset" in tag.attrs:
+                del tag["srcset"]
+            if "action" in tag.attrs:
+                del tag["action"]
+            data_attrs = [
+                attr
+                for attr in tag.attrs
+                if attr.startswith("data-") and "src" in attr.lower()
+            ]
+            for attr in data_attrs:
+                del tag[attr]

-    # Remove URLs from title attributes
-    for tag in soup.find_all(True):
-        if "title" in tag.attrs:
-            title = tag["title"]
-            cleaned_title = re.sub(r"https?://\S+", "", title, flags=re.IGNORECASE)
-            tag["title"] = cleaned_title
+        # Remove all style attributes from all tags
+        for tag in soup.find_all(True):
+            if "style" in tag.attrs:
+                del tag["style"]

-    # Remove class attributes that contain URL-like patterns
-    for tag in soup.find_all(True):
-        if "class" in tag.attrs:
-            classes = tag["class"]
-            cleaned_classes = [c for c in classes if not c.startswith("url ") and not "hyperlink-href:" in c]
-            tag["class"] = cleaned_classes
+        # Remove data-href attributes
+        for tag in soup.find_all(True):
+            if "data-href" in tag.attrs:
+                del tag["data-href"]

-    return str(soup)
+        # Remove URLs from title attributes
+        for tag in soup.find_all(True):
+            if "title" in tag.attrs:
+                title = tag["title"]
+                cleaned_title = re.sub(r"https?://\S+", "", title, flags=re.IGNORECASE)
+                tag["title"] = cleaned_title
+
+        # Remove class attributes that contain URL-like patterns
+        for tag in soup.find_all(True):
+            if "class" in tag.attrs:
+                classes = tag["class"]
+                cleaned_classes = [c for c in classes if not c.startswith("url ") and not "hyperlink-href:" in c]
+                tag["class"] = cleaned_classes
+
+        content = str(soup)
+        if not content.strip():
+            return None, "清理后内容为空"
+        return content, None
+    except Exception as e:
+        return None, f"BeautifulSoup 解析失败: {str(e)}"