fix: auto-fix code issues (cron)

- 修复重复导入/字段
- 修复异常处理
- 修复PEP8格式问题
- 添加类型注解
- 修复缺失的urllib.parse导入

backend/document_processor.py

@@ -7,6 +7,7 @@ Document Processor - Phase 3
 import io
 import os
 
+
 class DocumentProcessor:
     """文档处理器 - 提取 PDF/DOCX 文本"""
 
@@ -33,7 +34,9 @@ class DocumentProcessor:
         ext = os.path.splitext(filename.lower())[1]
 
         if ext not in self.supported_formats:
-            raise ValueError(f"Unsupported file format: {ext}. Supported: {list(self.supported_formats.keys())}")
+            raise ValueError(
+                f"Unsupported file format: {ext}. Supported: {list(self.supported_formats.keys())}"
+            )
 
         extractor = self.supported_formats[ext]
         text = extractor(content)
@@ -71,7 +74,9 @@ class DocumentProcessor:
                             text_parts.append(page_text)
                 return "\n\n".join(text_parts)
             except ImportError:
-                raise ImportError("PDF processing requires PyPDF2 or pdfplumber. Install with: pip install PyPDF2")
+                raise ImportError(
+                    "PDF processing requires PyPDF2 or pdfplumber. Install with: pip install PyPDF2"
+                )
         except Exception as e:
             raise ValueError(f"PDF extraction failed: {str(e)}")
 
@@ -100,7 +105,9 @@ class DocumentProcessor:
 
             return "\n\n".join(text_parts)
         except ImportError:
-            raise ImportError("DOCX processing requires python-docx. Install with: pip install python-docx")
+            raise ImportError(
+                "DOCX processing requires python-docx. Install with: pip install python-docx"
+            )
         except Exception as e:
             raise ValueError(f"DOCX extraction failed: {str(e)}")
 
@@ -149,6 +156,7 @@ class DocumentProcessor:
         ext = os.path.splitext(filename.lower())[1]
         return ext in self.supported_formats
 
+
 # 简单的文本提取器（不需要外部依赖）
 class SimpleTextExtractor:
     """简单的文本提取器，用于测试"""
@@ -165,6 +173,7 @@ class SimpleTextExtractor:
 
         return content.decode("latin-1", errors="ignore")
 
+
 if __name__ == "__main__":
     # 测试
     processor = DocumentProcessor()